id
stringlengths 6
113
| author
stringlengths 2
36
| task_category
stringclasses 39
values | tags
sequencelengths 1
4.05k
| created_time
int64 1,646B
1,742B
| last_modified
timestamp[s]date 2020-05-14 13:13:12
2025-03-18 10:01:09
| downloads
int64 0
118M
| likes
int64 0
4.86k
| README
stringlengths 30
1.01M
| matched_task
sequencelengths 1
10
| is_bionlp
stringclasses 3
values |
|---|---|---|---|---|---|---|---|---|---|---|
Lots-of-LoRAs/Mistral-7B-Instruct-v0.2-4b-r16-task1275 | Lots-of-LoRAs | null | [
"pytorch",
"safetensors",
"en",
"arxiv:1910.09700",
"arxiv:2407.00066",
"license:mit",
"region:us"
] | 1,735,602,142,000 | 2024-12-30T23:42:30 | 0 | 0 | ---
language: en
library_name: pytorch
license: mit
---
# Model Card for Mistral-7B-Instruct-v0.2-4b-r16-task1275
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
LoRA trained on task1275_ted_translation_pt_ja
- **Developed by:** bruel
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** LoRA
- **Language(s) (NLP):** en
- **License:** mit
- **Finetuned from model [optional]:** mistralai/Mistral-7B-Instruct-v0.2
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** https://github.com/bruel-gabrielsson
- **Paper [optional]:** "Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead" (2024), Rickard Brüel Gabrielsson, Jiacheng Zhu, Onkar Bhardwaj, Leshem Choshen, Kristjan Greenewald, Mikhail Yurochkin and Justin Solomon
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
https://huggingface.co/datasets/Lots-of-LoRAs/task1275_ted_translation_pt_ja sourced from https://github.com/allenai/natural-instructions
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
@misc{brüelgabrielsson2024compressserveservingthousands,
title={Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead},
author={Rickard Brüel-Gabrielsson and Jiacheng Zhu and Onkar Bhardwaj and Leshem Choshen and Kristjan Greenewald and Mikhail Yurochkin and Justin Solomon},
year={2024},
eprint={2407.00066},
archivePrefix={arXiv},
primaryClass={cs.DC},
url={https://arxiv.org/abs/2407.00066},
}
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | [
"TRANSLATION"
] | Non_BioNLP |
Triangle104/Phi-4-QwQ-Q6_K-GGUF | Triangle104 | text-generation | [
"transformers",
"gguf",
"text-generation-inference",
"llama",
"phi3",
"phi",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"en",
"base_model:prithivMLmods/Phi-4-QwQ",
"base_model:quantized:prithivMLmods/Phi-4-QwQ",
"license:mit",
"endpoints_compatible",
"region:us",
"conversational"
] | 1,738,480,433,000 | 2025-02-02T07:15:38 | 6 | 0 | ---
base_model: prithivMLmods/Phi-4-QwQ
language:
- en
library_name: transformers
license: mit
pipeline_tag: text-generation
tags:
- text-generation-inference
- llama
- phi3
- phi
- llama-cpp
- gguf-my-repo
---
# Triangle104/Phi-4-QwQ-Q6_K-GGUF
This model was converted to GGUF format from [`prithivMLmods/Phi-4-QwQ`](https://huggingface.co/prithivMLmods/Phi-4-QwQ) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/prithivMLmods/Phi-4-QwQ) for more details on the model.
---
[Phi-4-QwQ finetuned] from Microsoft's Phi-4 is a state-of-the-art open model developed with a focus on responsible problem solving and advanced reasoning capabilities. Built upon a diverse blend of synthetic datasets, carefully filtered public domain websites, and high-quality academic books and Q&A datasets, Phi-4-QwQ ensures that small, capable models are trained with datasets of exceptional depth and precision.
Phi-4-QwQ adopts a robust safety post-training approach using open-source and in-house synthetic datasets. This involves a combination of SFT (Supervised Fine-Tuning) and iterative DPO (Direct Preference Optimization) techniques, ensuring helpful and harmless outputs across various safety categories.
Dataset Info
Phi-4-QwQ is fine-tuned on a carefully curated synthetic dataset generated using an advanced pipeline optimized for Chain of Thought (CoT) reasoning and Responsible Problem Breakdown (RPB) methodologies. This ensures that the model excels at:
Logical reasoning
Step-by-step problem-solving
Breaking down complex tasks into manageable parts
The dataset also emphasizes responsible decision-making and fairness in generating solutions.
Run with Transformers
# pip install accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
tokenizer = AutoTokenizer.from_pretrained("prithivMLmods/Phi-4-QwQ")
model = AutoModelForCausalLM.from_pretrained(
"prithivMLmods/Phi-4-QwQ",
device_map="auto",
torch_dtype=torch.bfloat16,
)
input_text = "Explain the concept of black holes."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=64)
print(tokenizer.decode(outputs[0]))
For chat-style interactions, use tokenizer.apply_chat_template:
messages = [
{"role": "user", "content": "Explain the concept of black holes."},
]
input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt", return_dict=True).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=256)
print(tokenizer.decode(outputs[0]))
Intended Use
Phi-4-QwQ is tailored for a wide range of applications, especially those involving advanced reasoning, multilingual capabilities, and responsible problem-solving. Its primary use cases include:
Responsible Problem Solving
Breaking down complex problems into logical, actionable steps.
Offering ethical, well-rounded solutions in academic and professional contexts.
Advanced Reasoning Tasks
Excelling in mathematics, logic, and scientific reasoning.
Providing detailed explanations and systematic answers.
Content Generation
Assisting in generating high-quality content for various domains, including creative writing and technical documentation.
Supporting marketers, writers, and educators with detailed and well-structured outputs.
Educational Support
Acting as a virtual tutor for students by generating practice questions, answers, and detailed explanations.
Helping educators design learning material that promotes critical thinking and step-by-step problem-solving.
Customer Support & Dialogue Systems
Enabling chatbots and virtual assistants to provide accurate, helpful, and responsible responses.
Enhancing customer service with reasoning-driven automation.
Multilingual Capabilities
Supporting multilingual communication and content generation while maintaining contextual accuracy.
Assisting in translations with a focus on retaining meaning and nuance.
Safety-Critical Applications
Ensuring safe and harmless outputs, making it suitable for sensitive domains.
Providing aligned interactions with human oversight for critical systems.
Limitations
Despite its strengths, Phi-4-QwQ has some limitations that users should be aware of:
Bias and Fairness
While great effort has been made to minimize biases, users should critically assess the model’s output in sensitive scenarios to avoid unintended bias.
Contextual Interpretation
The model may occasionally misinterpret highly nuanced prompts or ambiguous contexts, leading to suboptimal responses.
Knowledge Cutoff
Phi-4-QwQ’s knowledge is static and based on the data available at the time of training. It does not include real-time updates or information on recent developments.
Safety and Harmlessness
Despite post-training safety alignment, inappropriate or harmful outputs may still occur. Continuous monitoring and human oversight are advised when using the model in critical contexts.
Computational Requirements
Deploying Phi-4-QwQ efficiently may require substantial computational resources, particularly for large-scale deployments or real-time applications.
Ethical Considerations
Users are responsible for ensuring that the model is not employed for malicious purposes, such as spreading misinformation, generating harmful content, or facilitating unethical behavior.
Domain-Specific Expertise
While the model is versatile, it may not perform optimally in highly specialized domains (e.g., law, medicine, finance) without further domain-specific fine-tuning.
---
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo Triangle104/Phi-4-QwQ-Q6_K-GGUF --hf-file phi-4-qwq-q6_k.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo Triangle104/Phi-4-QwQ-Q6_K-GGUF --hf-file phi-4-qwq-q6_k.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo Triangle104/Phi-4-QwQ-Q6_K-GGUF --hf-file phi-4-qwq-q6_k.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo Triangle104/Phi-4-QwQ-Q6_K-GGUF --hf-file phi-4-qwq-q6_k.gguf -c 2048
```
| [
"TRANSLATION"
] | Non_BioNLP |
Agnuxo/Qwen2-1.5B-Instruct_MOE_Director-GGUF_4bit | Agnuxo | null | [
"transformers",
"gguf",
"qwen2",
"text-generation-inference",
"unsloth",
"en",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | 1,724,712,715,000 | 2024-08-28T10:45:17 | 25 | 0 | ---
base_model: unsloth/qwen2-1.5b-instruct-bnb-4bit
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- qwen2
- gguf
---
# Qwen2-1.5B-Instruct MOE Director (16-bit)
## Model Description
This is a 16-bit quantized version of the Qwen2-1.5B-Instruct model fine-tuned to act as a "director" within a Multi-Expert Question Answering System (MOE). It's designed to efficiently route incoming questions to specialized expert LLMs in different domains.
**Developed by:** Agnuxo
**License:** Apache-2.0
**Finetuned from model:** [unsloth/qwen2-1.5b-instruct-bnb-4bit](https://huggingface.co/unsloth/qwen2-1.5b-instruct-bnb-4bit)
This model was trained 2x faster using [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
## How the MOE System Works
This model is a core component of a larger Multi-Expert Question Answering System. Here's a breakdown of the system's functionality:
1. **Model Loading:** The system loads the "director" LLM and keeps other expert LLMs (e.g., for programming, biology, mathematics) ready for use.
2. **Expert Routing:** When a user asks a question, the system either:
- Uses keyword matching to identify the relevant domain.
- Consults the director LLM to classify the question's category.
3. **Dynamic Expert Loading:** The system loads the chosen expert LLM into memory, optimizing resource usage by releasing any previously active expert.
4. **Response Generation:** The selected expert LLM receives the question and generates a tailored answer.
5. **Chat Interface:** A user-friendly chat interface facilitates interaction with the MOE system.
This MOE approach enhances efficiency and accuracy compared to relying on a single, general-purpose LLM.
Repository and Additional Information
Full Code: https://huggingface.co/Agnuxo/Qwen2-1.5B-Instruct_MOE_Director_16bit/resolve/main/MOE-LLMs3.py
GitHub Repository: https://github.com/Agnuxo1/NEBULA
## Code Example
The following code demonstrates the implementation of the Multi-Expert Question Answering System:
```python
import os
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
MODEL_CONFIG = {
"director": {
"name": "Agnuxo/Qwen2-1.5B-Instruct_MOE_Director_16bit",
"task": "text-generation",
},
"programming": {
"name": "Qwen/Qwen2-1.5B-Instruct",
"task": "text-generation",
},
"biology": {
"name": "Agnuxo/Qwen2-1.5B-Instruct_MOE_BIOLOGY_assistant_16bit",
"task": "text-generation",
},
"mathematics": {
"name": "Qwen/Qwen2-Math-1.5B-Instruct",
"task": "text-generation",
}
}
KEYWORDS = {
"biology": ["cell", "DNA", "protein", "evolution", "genetics", "ecosystem", "organism", "metabolism", "photosynthesis", "microbiology", "célula", "ADN", "proteína", "evolución", "genética", "ecosistema", "organismo", "metabolismo", "fotosíntesis", "microbiología"],
"mathematics": ["Math" "mathematics", "equation", "integral", "derivative", "function", "geometry", "algebra", "statistics", "probability", "ecuación", "integral", "derivada", "función", "geometría", "álgebra", "estadística", "probabilidad"],
"programming": ["python", "java", "C++", "HTML", "scrip", "code", "Dataset", "API", "framework", "debugging", "algorithm", "compiler", "database", "CSS", "JSON", "XML", "encryption", "IDE", "repository", "Git", "version control", "front-end", "back-end", "API", "stack trace", "REST", "machine learning"]
}
class MOELLM:
def __init__(self):
self.current_expert = None
self.current_model = None
self.current_tokenizer = None
self.device = "cuda" if torch.cuda.is_available() else "cpu"
print(f"Using device: {self.device}")
self.load_director_model()
def load_director_model(self):
"""Loads the director model."""
print("Loading director model...")
model_name = MODEL_CONFIG["director"]["name"]
self.director_tokenizer = AutoTokenizer.from_pretrained(model_name)
self.director_model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16).to(self.device)
self.director_pipeline = pipeline(
MODEL_CONFIG["director"]["task"],
model=self.director_model,
tokenizer=self.director_tokenizer,
device=self.device
)
print("Director model loaded.")
def load_expert_model(self, expert):
"""Dynamically loads an expert model, releasing memory from the previous model."""
if expert not in MODEL_CONFIG:
raise ValueError(f"Unknown expert: {expert}")
if self.current_expert != expert:
print(f"Loading expert model: {expert}...")
# Free memory from the current model if it exists
if self.current_model:
del self.current_model
del self.current_tokenizer
torch.cuda.empty_cache()
model_config = MODEL_CONFIG[expert]
self.current_tokenizer = AutoTokenizer.from_pretrained(model_config["name"])
self.current_model = AutoModelForCausalLM.from_pretrained(model_config["name"], torch_dtype=torch.float16).to(self.device)
self.current_expert = expert
print(f"{expert.capitalize()} model loaded.")
return pipeline(
MODEL_CONFIG[expert]["task"],
model=self.current_model,
tokenizer=self.current_tokenizer,
device=self.device
)
def determine_expert_by_keywords(self, question):
"""Determines the expert based on keywords in the question."""
question_lower = question.lower()
for expert, keywords in KEYWORDS.items():
if any(keyword in question_lower for keyword in keywords):
return expert
return None
def determine_expert(self, question):
"""Determines which expert should answer the question."""
expert = self.determine_expert_by_keywords(question)
if expert:
print(f"Expert determined by keyword: {expert}")
return expert
prompt = f"Classify the following question into one of these categories: programming, biology, mathematics. Question: {question}\nCategory:"
response = self.director_pipeline(prompt, max_length=100, num_return_sequences=1)[0]['generated_text']
expert = response.split(":")[-1].strip().lower()
if expert not in MODEL_CONFIG:
expert = "director"
print(f"Redirecting question to: {expert}")
return expert
def generate_response(self, question, expert):
"""Generates a response using the appropriate model."""
try:
model = self.load_expert_model(expert)
prompt = f"Answer the following question as an expert in {expert}: {question}\nAnswer:"
response = model(prompt, max_length=200, num_return_sequences=1)[0]['generated_text']
return response.split("Answer:")[-1].strip()
except Exception as e:
print(f"Error generating response: {str(e)}")
return "Sorry, there was an error processing your request. Please try again."
def chat_interface(self):
"""Simple chat interface."""
print("Welcome to the MOE-LLM chat. Type 'exit' to quit.")
while True:
question = input("\nYou: ")
if question.lower() in ['exit', 'quit']:
break
try:
expert = self.determine_expert(question)
response = self.generate_response(question, expert)
print(f"\n{expert.capitalize()}: {response}")
except Exception as e:
print(f"Error in chat: {str(e)}")
print("Please try asking another question.")
if __name__ == "__main__":
moe_llm = MOELLM()
moe_llm.chat_interface()
| [
"QUESTION_ANSWERING"
] | Non_BioNLP |
tahrirchi/tahrirchi-bert-base | tahrirchi | fill-mask | [
"transformers",
"pytorch",
"safetensors",
"bert",
"fill-mask",
"uz",
"dataset:tahrirchi/uz-crawl",
"dataset:tahrirchi/uz-books",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 1,698,313,307,000 | 2023-11-20T14:41:42 | 267 | 9 | ---
datasets:
- tahrirchi/uz-crawl
- tahrirchi/uz-books
language:
- uz
library_name: transformers
license: apache-2.0
pipeline_tag: fill-mask
tags:
- bert
widget:
- text: Alisher Navoiy – ulug‘ o‘zbek va boshqa turkiy xalqlarning <mask>, mutafakkiri
va davlat arbobi bo‘lgan.
---
# TahrirchiBERT base model
The TahrirchiBERT-base is an encoder-only Transformer text model with 110 million parameters.
It is pretrained model on Uzbek language (latin script) using a masked language modeling (MLM) objective. This model is case-sensitive: it does make a difference between uzbek and Uzbek.
For full details of this model please read our paper (coming soon!) and [release blog post](https://tahrirchi.uz/grammatika-tekshiruvi).
## Model variations
This model is part of the family of **TahrirchiBERT models** trained with different number of parameters that will continuously expanded in the future.
| Model | Number of parameters | Language | Script
|------------------------|--------------------------------|-------|-------|
| [`tahrirchi-bert-small`](https://huggingface.co/tahrirchi/tahrirchi-bert-small) | 67M | Uzbek | Latin
| [`tahrirchi-bert-base`](https://huggingface.co/tahrirchi/tahrirchi-bert-base) | 110M | Uzbek | Latin
## Intended uses & limitations
This model is primarily aimed at being fine-tuned on tasks that use the whole sentence (potentially masked)
to make decisions, such as sequence classification, token classification or question answering.
### How to use
You can use this model directly with a pipeline for masked language modeling:
```python
>>> from transformers import pipeline
>>> unmasker = pipeline('fill-mask', model='tahrirchi/tahrirchi-bert-base')
>>> unmasker("Alisher Navoiy – ulug‘ o‘zbek va boshqa turkiy xalqlarning <mask>, mutafakkiri va davlat arbobi bo‘lgan.")
[{'score': 0.4616584777832031,
'token': 10879,
'token_str': ' shoiri',
'sequence': 'Alisher Navoiy – ulug‘ o‘zbek va boshqa turkiy xalqlarning shoiri, mutafakkiri va davlat arbobi bo‘lgan.'},
{'score': 0.19899587333202362,
'token': 10013,
'token_str': ' olimi',
'sequence': 'Alisher Navoiy – ulug‘ o‘zbek va boshqa turkiy xalqlarning olimi, mutafakkiri va davlat arbobi bo‘lgan.'},
{'score': 0.055418431758880615,
'token': 12224,
'token_str': ' asoschisi',
'sequence': 'Alisher Navoiy – ulug‘ o‘zbek va boshqa turkiy xalqlarning asoschisi, mutafakkiri va davlat arbobi bo‘lgan.'},
{'score': 0.037673842161893845,
'token': 24597,
'token_str': ' faylasufi',
'sequence': 'Alisher Navoiy – ulug‘ o‘zbek va boshqa turkiy xalqlarning faylasufi, mutafakkiri va davlat arbobi bo‘lgan.'},
{'score': 0.029616089537739754,
'token': 9543,
'token_str': ' farzandi',
'sequence': 'Alisher Navoiy – ulug‘ o‘zbek va boshqa turkiy xalqlarning farzandi, mutafakkiri va davlat arbobi bo‘lgan.'}]
>>> unmasker("Egiluvchan boʻgʻinlari va <mask>, yarim bukilgan tirnoqlari tik qiyaliklar hamda daraxtlarga oson chiqish imkonini beradi.")
[{'score': 0.1740381121635437,
'token': 12571,
'token_str': ' oyoqlari',
'sequence': 'Egiluvchan bo‘g‘inlari va oyoqlari, yarim bukilgan tirnoqlari tik qiyaliklar hamda daraxtlarga oson chiqish imkonini beradi.'},
{'score': 0.05455964431166649,
'token': 2073,
'token_str': ' uzun',
'sequence': 'Egiluvchan bo‘g‘inlari va uzun, yarim bukilgan tirnoqlari tik qiyaliklar hamda daraxtlarga oson chiqish imkonini beradi.'},
{'score': 0.050441522151231766,
'token': 19725,
'token_str': ' barmoqlari',
'sequence': 'Egiluvchan bo‘g‘inlari va barmoqlari, yarim bukilgan tirnoqlari tik qiyaliklar hamda daraxtlarga oson chiqish imkonini beradi.'},
{'score': 0.04490342736244202,
'token': 10424,
'token_str': ' tanasi',
'sequence': 'Egiluvchan bo‘g‘inlari va tanasi, yarim bukilgan tirnoqlari tik qiyaliklar hamda daraxtlarga oson chiqish imkonini beradi.'},
{'score': 0.03777358680963516,
'token': 27116,
'token_str': ' bukilgan',
'sequence': 'Egiluvchan bo‘g‘inlari va bukilgan, yarim bukilgan tirnoqlari tik qiyaliklar hamda daraxtlarga oson chiqish imkonini beradi.'}]
```
## Training data
TahrirchiBERT is pretrained using a standard Masked Language Modeling (MLM) objective: the model is given a sequence of text with some tokens hidden, and it has to predict these masked tokens. TahrirchiBERT is trained on the [Uzbek Crawl](https://huggingface.co/datasets/tahrirchi/uz-crawl) and all latin portion of [Uzbek Books](https://huggingface.co/datasets/tahrirchi/uz-books), which contains roughly 4000 preprocessd books, 1.2 million curated text documents scraped from the internet and Telegram blogs (equivalent to 5 billion tokens).
## Training procedure
### Preprocessing
The texts are tokenized using a byte version of Byte-Pair Encoding (BPE) and a vocabulary size of 30,528 to make fully use of rare words. The inputs of the model take pieces of 512 contiguous tokens that may span over documents. Also, we added number of regular expressions to avoid misrepresentation of different symbols that is used mostly incorrectly in practise.
### Pretraining
The model was trained for one million steps with a batch size of 512. The sequence length was limited to 512 tokens during all pre-training stage. The optimizer used is Adam with a learning rate of 5e-4, \\(\beta_{1} = 0.9\\) and \\(\beta_{2} = 0.98\\), a weight decay of 1e-5, learning rate warmup to the full LR for 6% of the training duration with linearly decay to 0.02x the full LR by the end of the training duration.
## Citation
Please cite this model using the following format:
```
@online{Mamasaidov2023TahrirchiBERT,
author = {Mukhammadsaid Mamasaidov and Abror Shopulatov},
title = {TahrirchiBERT base},
year = {2023},
url = {https://huggingface.co/tahrirchi/tahrirchi-bert-base},
note = {Accessed: 2023-10-27}, % change this date
urldate = {2023-10-27} % change this date
}
```
## Gratitude
We are thankfull for these awesome organizations and people for help to make it happen:
- [MosaicML team](https://mosaicml.com/): for their script for efficiently training BERT models
- [Ilya Gusev](https://github.com/IlyaGusev/): for advise throughout the process
- [David Dale](https://daviddale.ru): for advise throughout the process | [
"QUESTION_ANSWERING"
] | Non_BioNLP |
fathyshalab/reklambox2-2-15 | fathyshalab | text-classification | [
"sentence-transformers",
"pytorch",
"xlm-roberta",
"setfit",
"text-classification",
"arxiv:2209.11055",
"license:apache-2.0",
"region:us"
] | 1,677,763,868,000 | 2023-03-02T18:32:30 | 9 | 0 | ---
license: apache-2.0
pipeline_tag: text-classification
tags:
- setfit
- sentence-transformers
- text-classification
---
# fathyshalab/reklambox2-2-15
This is a [SetFit model](https://github.com/huggingface/setfit) that can be used for text classification. The model has been trained using an efficient few-shot learning technique that involves:
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.
## Usage
To use this model for inference, first install the SetFit library:
```bash
python -m pip install setfit
```
You can then run inference as follows:
```python
from setfit import SetFitModel
# Download from Hub and run inference
model = SetFitModel.from_pretrained("fathyshalab/reklambox2-2-15")
# Run inference
preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"])
```
## BibTeX entry and citation info
```bibtex
@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
| [
"TEXT_CLASSIFICATION"
] | Non_BioNLP |
cross-encoder-testing/reranker-bert-tiny-gooaq-bce-tanh-v3 | cross-encoder-testing | text-classification | [
"sentence-transformers",
"safetensors",
"bert",
"cross-encoder",
"text-classification",
"generated_from_trainer",
"dataset_size:578402",
"loss:BinaryCrossEntropyLoss",
"en",
"arxiv:1908.10084",
"base_model:prajjwal1/bert-tiny",
"base_model:finetune:prajjwal1/bert-tiny",
"license:apache-2.0",
"co2_eq_emissions",
"region:us"
] | 1,741,093,469,000 | 2025-03-04T13:04:55 | 397 | 0 | ---
base_model: prajjwal1/bert-tiny
language:
- en
library_name: sentence-transformers
license: apache-2.0
metrics:
- map
- mrr@10
- ndcg@10
pipeline_tag: text-classification
tags:
- sentence-transformers
- cross-encoder
- text-classification
- generated_from_trainer
- dataset_size:578402
- loss:BinaryCrossEntropyLoss
co2_eq_emissions:
emissions: 7.3866990525881215
energy_consumed: 0.019003501532248668
source: codecarbon
training_type: fine-tuning
on_cloud: false
cpu_model: 13th Gen Intel(R) Core(TM) i7-13700K
ram_total_size: 31.777088165283203
hours_used: 0.099
hardware_used: 1 x NVIDIA GeForce RTX 3090
model-index:
- name: BERT-tiny trained on GooAQ
results: []
---
# BERT-tiny trained on GooAQ
This is a [Cross Encoder](https://www.sbert.net/docs/cross_encoder/usage/usage.html) model finetuned from [prajjwal1/bert-tiny](https://huggingface.co/prajjwal1/bert-tiny) using the [sentence-transformers](https://www.SBERT.net) library. It computes scores for pairs of texts, which can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
This model was trained using [train_script.py](train_script.py).
## Model Details
### Model Description
- **Model Type:** Cross Encoder
- **Base model:** [prajjwal1/bert-tiny](https://huggingface.co/prajjwal1/bert-tiny) <!-- at revision 6f75de8b60a9f8a2fdf7b69cbd86d9e64bcb3837 -->
- **Maximum Sequence Length:** 512 tokens
- **Number of Output Labels:** 1 label
<!-- - **Training Dataset:** Unknown -->
- **Language:** en
- **License:** apache-2.0
### Model Sources
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
- **Documentation:** [Cross Encoder Documentation](https://www.sbert.net/docs/cross_encoder/usage/usage.html)
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
- **Hugging Face:** [Cross Encoders on Hugging Face](https://huggingface.co/models?library=sentence-transformers&other=cross-encoder)
## Usage
### Direct Usage (Sentence Transformers)
First install the Sentence Transformers library:
```bash
pip install -U sentence-transformers
```
Then you can load this model and run inference.
```python
from sentence_transformers import CrossEncoder
# Download from the 🤗 Hub
model = CrossEncoder("cross-encoder-testing/reranker-bert-tiny-gooaq-bce")
# Get scores for pairs of texts
pairs = [
['are javascript developers in demand?', "JavaScript is the skill that is most in-demand for IT in 2020, according to a report from developer skills tester DevSkiller. The report, “Top IT Skills report 2020: Demand and Hiring Trends,” has JavaScript switching places with Java when compared to last year's report, with Java in third place this year, behind SQL."],
['are javascript developers in demand?', 'In one line difference between the two is: JavaScript is the programming language where as AngularJS is a framework based on JavaScript. ... It is also the basic for all java script based technologies like jquery, angular JS, bootstrap JS and so on. Angular JS is a framework written in javascript and uses MVC architecture.'],
['are javascript developers in demand?', 'Java applications are run in a virtual machine or web browser while JavaScript is run on a web browser. Java code is compiled whereas while JavaScript code is in text and in a web page. JavaScript is an OOP scripting language, whereas Java is an OOP programming language.'],
['are javascript developers in demand?', 'Things in the body tag are the things that should be displayed: the actual content. Javascript in the body is executed as it is read and as the page is rendered. Javascript in the head is interpreted before anything is rendered.'],
['are javascript developers in demand?', 'Web apps tend to be built using JavaScript, CSS and HTML5. Unlike mobile apps, there is no standard software development kit for building web apps. However, developers do have access to templates. Compared to mobile apps, web apps are usually quicker and easier to build — but they are much simpler in terms of features.'],
]
scores = model.predict(pairs)
print(scores.shape)
# (5,)
# Or rank different texts based on similarity to a single text
ranks = model.rank(
'are javascript developers in demand?',
[
"JavaScript is the skill that is most in-demand for IT in 2020, according to a report from developer skills tester DevSkiller. The report, “Top IT Skills report 2020: Demand and Hiring Trends,” has JavaScript switching places with Java when compared to last year's report, with Java in third place this year, behind SQL.",
'In one line difference between the two is: JavaScript is the programming language where as AngularJS is a framework based on JavaScript. ... It is also the basic for all java script based technologies like jquery, angular JS, bootstrap JS and so on. Angular JS is a framework written in javascript and uses MVC architecture.',
'Java applications are run in a virtual machine or web browser while JavaScript is run on a web browser. Java code is compiled whereas while JavaScript code is in text and in a web page. JavaScript is an OOP scripting language, whereas Java is an OOP programming language.',
'Things in the body tag are the things that should be displayed: the actual content. Javascript in the body is executed as it is read and as the page is rendered. Javascript in the head is interpreted before anything is rendered.',
'Web apps tend to be built using JavaScript, CSS and HTML5. Unlike mobile apps, there is no standard software development kit for building web apps. However, developers do have access to templates. Compared to mobile apps, web apps are usually quicker and easier to build — but they are much simpler in terms of features.',
]
)
# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]
```
<!--
### Direct Usage (Transformers)
<details><summary>Click to see the direct usage in Transformers</summary>
</details>
-->
<!--
### Downstream Usage (Sentence Transformers)
You can finetune this model on your own dataset.
<details><summary>Click to expand</summary>
</details>
-->
<!--
### Out-of-Scope Use
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->
## Evaluation
### Metrics
#### Cross Encoder Reranking
* Datasets: `gooaq-dev`, `NanoMSMARCO`, `NanoNFCorpus` and `NanoNQ`
* Evaluated with [<code>CrossEncoderRerankingEvaluator</code>](https://sbert.net/docs/package_reference/cross_encoder/evaluation.html#sentence_transformers.cross_encoder.evaluation.CrossEncoderRerankingEvaluator)
| Metric | gooaq-dev | NanoMSMARCO | NanoNFCorpus | NanoNQ |
|:------------|:---------------------|:---------------------|:---------------------|:---------------------|
| map | 0.5677 (+0.0366) | 0.4280 (-0.0616) | 0.3397 (+0.0787) | 0.4149 (-0.0047) |
| mrr@10 | 0.5558 (+0.0318) | 0.4129 (-0.0646) | 0.5196 (+0.0198) | 0.4132 (-0.0135) |
| **ndcg@10** | **0.6157 (+0.0245)** | **0.4772 (-0.0632)** | **0.3308 (+0.0058)** | **0.4859 (-0.0147)** |
#### Cross Encoder Nano BEIR
* Dataset: `NanoBEIR_R100_mean`
* Evaluated with [<code>CrossEncoderNanoBEIREvaluator</code>](https://sbert.net/docs/package_reference/cross_encoder/evaluation.html#sentence_transformers.cross_encoder.evaluation.CrossEncoderNanoBEIREvaluator)
| Metric | Value |
|:------------|:---------------------|
| map | 0.3942 (+0.0041) |
| mrr@10 | 0.4486 (-0.0194) |
| **ndcg@10** | **0.4313 (-0.0241)** |
<!--
## Bias, Risks and Limitations
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
-->
<!--
### Recommendations
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
-->
## Training Details
### Training Dataset
#### Unnamed Dataset
* Size: 578,402 training samples
* Columns: <code>question</code>, <code>answer</code>, and <code>label</code>
* Approximate statistics based on the first 1000 samples:
| | question | answer | label |
|:--------|:-----------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------|:------------------------------------------------|
| type | string | string | int |
| details | <ul><li>min: 21 characters</li><li>mean: 43.81 characters</li><li>max: 96 characters</li></ul> | <ul><li>min: 51 characters</li><li>mean: 252.46 characters</li><li>max: 405 characters</li></ul> | <ul><li>0: ~82.90%</li><li>1: ~17.10%</li></ul> |
* Samples:
| question | answer | label |
|:--------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------|
| <code>are javascript developers in demand?</code> | <code>JavaScript is the skill that is most in-demand for IT in 2020, according to a report from developer skills tester DevSkiller. The report, “Top IT Skills report 2020: Demand and Hiring Trends,” has JavaScript switching places with Java when compared to last year's report, with Java in third place this year, behind SQL.</code> | <code>1</code> |
| <code>are javascript developers in demand?</code> | <code>In one line difference between the two is: JavaScript is the programming language where as AngularJS is a framework based on JavaScript. ... It is also the basic for all java script based technologies like jquery, angular JS, bootstrap JS and so on. Angular JS is a framework written in javascript and uses MVC architecture.</code> | <code>0</code> |
| <code>are javascript developers in demand?</code> | <code>Java applications are run in a virtual machine or web browser while JavaScript is run on a web browser. Java code is compiled whereas while JavaScript code is in text and in a web page. JavaScript is an OOP scripting language, whereas Java is an OOP programming language.</code> | <code>0</code> |
* Loss: [<code>BinaryCrossEntropyLoss</code>](https://sbert.net/docs/package_reference/cross_encoder/losses.html#binarycrossentropyloss) with these parameters:
```json
{
"activation_fct": "torch.nn.modules.linear.Identity",
"pos_weight": 5
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `eval_strategy`: steps
- `per_device_train_batch_size`: 2048
- `per_device_eval_batch_size`: 2048
- `learning_rate`: 0.0005
- `num_train_epochs`: 1
- `warmup_ratio`: 0.1
- `seed`: 12
- `bf16`: True
#### All Hyperparameters
<details><summary>Click to expand</summary>
- `overwrite_output_dir`: False
- `do_predict`: False
- `eval_strategy`: steps
- `prediction_loss_only`: True
- `per_device_train_batch_size`: 2048
- `per_device_eval_batch_size`: 2048
- `per_gpu_train_batch_size`: None
- `per_gpu_eval_batch_size`: None
- `gradient_accumulation_steps`: 1
- `eval_accumulation_steps`: None
- `torch_empty_cache_steps`: None
- `learning_rate`: 0.0005
- `weight_decay`: 0.0
- `adam_beta1`: 0.9
- `adam_beta2`: 0.999
- `adam_epsilon`: 1e-08
- `max_grad_norm`: 1.0
- `num_train_epochs`: 1
- `max_steps`: -1
- `lr_scheduler_type`: linear
- `lr_scheduler_kwargs`: {}
- `warmup_ratio`: 0.1
- `warmup_steps`: 0
- `log_level`: passive
- `log_level_replica`: warning
- `log_on_each_node`: True
- `logging_nan_inf_filter`: True
- `save_safetensors`: True
- `save_on_each_node`: False
- `save_only_model`: False
- `restore_callback_states_from_checkpoint`: False
- `no_cuda`: False
- `use_cpu`: False
- `use_mps_device`: False
- `seed`: 12
- `data_seed`: None
- `jit_mode_eval`: False
- `use_ipex`: False
- `bf16`: True
- `fp16`: False
- `fp16_opt_level`: O1
- `half_precision_backend`: auto
- `bf16_full_eval`: False
- `fp16_full_eval`: False
- `tf32`: None
- `local_rank`: 0
- `ddp_backend`: None
- `tpu_num_cores`: None
- `tpu_metrics_debug`: False
- `debug`: []
- `dataloader_drop_last`: False
- `dataloader_num_workers`: 0
- `dataloader_prefetch_factor`: None
- `past_index`: -1
- `disable_tqdm`: False
- `remove_unused_columns`: True
- `label_names`: None
- `load_best_model_at_end`: False
- `ignore_data_skip`: False
- `fsdp`: []
- `fsdp_min_num_params`: 0
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
- `fsdp_transformer_layer_cls_to_wrap`: None
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
- `deepspeed`: None
- `label_smoothing_factor`: 0.0
- `optim`: adamw_torch
- `optim_args`: None
- `adafactor`: False
- `group_by_length`: False
- `length_column_name`: length
- `ddp_find_unused_parameters`: None
- `ddp_bucket_cap_mb`: None
- `ddp_broadcast_buffers`: False
- `dataloader_pin_memory`: True
- `dataloader_persistent_workers`: False
- `skip_memory_metrics`: True
- `use_legacy_prediction_loop`: False
- `push_to_hub`: False
- `resume_from_checkpoint`: None
- `hub_model_id`: None
- `hub_strategy`: every_save
- `hub_private_repo`: None
- `hub_always_push`: False
- `gradient_checkpointing`: False
- `gradient_checkpointing_kwargs`: None
- `include_inputs_for_metrics`: False
- `include_for_metrics`: []
- `eval_do_concat_batches`: True
- `fp16_backend`: auto
- `push_to_hub_model_id`: None
- `push_to_hub_organization`: None
- `mp_parameters`:
- `auto_find_batch_size`: False
- `full_determinism`: False
- `torchdynamo`: None
- `ray_scope`: last
- `ddp_timeout`: 1800
- `torch_compile`: False
- `torch_compile_backend`: None
- `torch_compile_mode`: None
- `dispatch_batches`: None
- `split_batches`: None
- `include_tokens_per_second`: False
- `include_num_input_tokens_seen`: False
- `neftune_noise_alpha`: None
- `optim_target_modules`: None
- `batch_eval_metrics`: False
- `eval_on_start`: False
- `use_liger_kernel`: False
- `eval_use_gather_object`: False
- `average_tokens_across_devices`: False
- `prompts`: None
- `batch_sampler`: batch_sampler
- `multi_dataset_batch_sampler`: proportional
</details>
### Training Logs
| Epoch | Step | Training Loss | gooaq-dev_ndcg@10 | NanoMSMARCO_ndcg@10 | NanoNFCorpus_ndcg@10 | NanoNQ_ndcg@10 | NanoBEIR_R100_mean_ndcg@10 |
|:------:|:----:|:-------------:|:-----------------:|:-------------------:|:--------------------:|:----------------:|:--------------------------:|
| -1 | -1 | - | 0.0887 (-0.5025) | 0.0063 (-0.5341) | 0.3262 (+0.0012) | 0.0000 (-0.5006) | 0.1108 (-0.3445) |
| 0.0035 | 1 | 1.1945 | - | - | - | - | - |
| 0.0707 | 20 | 1.1664 | 0.4082 (-0.1830) | 0.1805 (-0.3600) | 0.3168 (-0.0083) | 0.2243 (-0.2763) | 0.2405 (-0.2149) |
| 0.1413 | 40 | 1.1107 | 0.5260 (-0.0652) | 0.3453 (-0.1951) | 0.3335 (+0.0085) | 0.3430 (-0.1576) | 0.3406 (-0.1147) |
| 0.2120 | 60 | 1.022 | 0.5623 (-0.0289) | 0.3929 (-0.1475) | 0.3512 (+0.0262) | 0.3472 (-0.1535) | 0.3638 (-0.0916) |
| 0.2827 | 80 | 0.973 | 0.5691 (-0.0221) | 0.4048 (-0.1356) | 0.3530 (+0.0280) | 0.3833 (-0.1174) | 0.3804 (-0.0750) |
| 0.3534 | 100 | 0.963 | 0.5814 (-0.0098) | 0.4385 (-0.1019) | 0.3471 (+0.0221) | 0.4227 (-0.0779) | 0.4028 (-0.0526) |
| 0.4240 | 120 | 0.9419 | 0.5963 (+0.0050) | 0.4106 (-0.1298) | 0.3540 (+0.0289) | 0.4843 (-0.0163) | 0.4163 (-0.0391) |
| 0.4947 | 140 | 0.9331 | 0.5953 (+0.0041) | 0.4310 (-0.1094) | 0.3367 (+0.0117) | 0.4163 (-0.0843) | 0.3947 (-0.0607) |
| 0.5654 | 160 | 0.9263 | 0.6070 (+0.0158) | 0.4626 (-0.0778) | 0.3443 (+0.0193) | 0.4823 (-0.0184) | 0.4297 (-0.0256) |
| 0.6360 | 180 | 0.9212 | 0.6069 (+0.0156) | 0.4602 (-0.0802) | 0.3391 (+0.0141) | 0.4782 (-0.0224) | 0.4258 (-0.0295) |
| 0.7067 | 200 | 0.901 | 0.6126 (+0.0214) | 0.4602 (-0.0803) | 0.3413 (+0.0162) | 0.4780 (-0.0227) | 0.4265 (-0.0289) |
| 0.7774 | 220 | 0.8997 | 0.6136 (+0.0224) | 0.4801 (-0.0604) | 0.3349 (+0.0098) | 0.4903 (-0.0103) | 0.4351 (-0.0203) |
| 0.8481 | 240 | 0.9021 | 0.6132 (+0.0220) | 0.4850 (-0.0554) | 0.3438 (+0.0188) | 0.4855 (-0.0151) | 0.4381 (-0.0173) |
| 0.9187 | 260 | 0.9013 | 0.6188 (+0.0276) | 0.4820 (-0.0584) | 0.3387 (+0.0137) | 0.4851 (-0.0156) | 0.4353 (-0.0201) |
| 0.9894 | 280 | 0.8996 | 0.6157 (+0.0245) | 0.4772 (-0.0632) | 0.3305 (+0.0054) | 0.4859 (-0.0147) | 0.4312 (-0.0242) |
| -1 | -1 | - | 0.6157 (+0.0245) | 0.4772 (-0.0632) | 0.3308 (+0.0058) | 0.4859 (-0.0147) | 0.4313 (-0.0241) |
### Environmental Impact
Carbon emissions were measured using [CodeCarbon](https://github.com/mlco2/codecarbon).
- **Energy Consumed**: 0.019 kWh
- **Carbon Emitted**: 0.007 kg of CO2
- **Hours Used**: 0.099 hours
### Training Hardware
- **On Cloud**: No
- **GPU Model**: 1 x NVIDIA GeForce RTX 3090
- **CPU Model**: 13th Gen Intel(R) Core(TM) i7-13700K
- **RAM Size**: 31.78 GB
### Framework Versions
- Python: 3.11.6
- Sentence Transformers: 3.5.0.dev0
- Transformers: 4.48.3
- PyTorch: 2.5.0+cu121
- Accelerate: 1.3.0
- Datasets: 2.20.0
- Tokenizers: 0.21.0
## Citation
### BibTeX
#### Sentence Transformers
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "https://arxiv.org/abs/1908.10084",
}
```
<!--
## Glossary
*Clearly define terms in order to be accessible across audiences.*
-->
<!--
## Model Card Authors
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->
<!--
## Model Card Contact
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
--> | [
"TEXT_CLASSIFICATION"
] | Non_BioNLP |
gokulsrinivasagan/bert_base_lda_5_sst2 | gokulsrinivasagan | text-classification | [
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"en",
"dataset:glue",
"base_model:gokulsrinivasagan/bert_base_lda_5",
"base_model:finetune:gokulsrinivasagan/bert_base_lda_5",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 1,732,274,540,000 | 2024-11-22T11:35:46 | 5 | 0 | ---
base_model: gokulsrinivasagan/bert_base_lda_5
datasets:
- glue
language:
- en
library_name: transformers
metrics:
- accuracy
tags:
- generated_from_trainer
model-index:
- name: bert_base_lda_5_sst2
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: GLUE SST2
type: glue
args: sst2
metrics:
- type: accuracy
value: 0.5091743119266054
name: Accuracy
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bert_base_lda_5_sst2
This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_5](https://huggingface.co/gokulsrinivasagan/bert_base_lda_5) on the GLUE SST2 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6957
- Accuracy: 0.5092
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.001
- train_batch_size: 256
- eval_batch_size: 256
- seed: 10
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 30
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.7066 | 1.0 | 264 | 0.6991 | 0.5092 |
| 0.6869 | 2.0 | 528 | 0.6957 | 0.5092 |
| 0.6868 | 3.0 | 792 | 0.6972 | 0.5092 |
| 0.6867 | 4.0 | 1056 | 0.6974 | 0.5092 |
| 0.687 | 5.0 | 1320 | 0.6972 | 0.5092 |
| 0.6873 | 6.0 | 1584 | 0.7022 | 0.5092 |
| 0.6864 | 7.0 | 1848 | 0.6988 | 0.5092 |
### Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3
| [
"TEXT_CLASSIFICATION"
] | Non_BioNLP |
google/t5-efficient-large-dm2000 | google | text2text-generation | [
"transformers",
"pytorch",
"tf",
"jax",
"t5",
"text2text-generation",
"deep-narrow",
"en",
"dataset:c4",
"arxiv:2109.10686",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | 1,646,263,745,000 | 2023-01-24T16:46:16 | 13 | 0 | ---
datasets:
- c4
language:
- en
license: apache-2.0
tags:
- deep-narrow
inference: false
---
# T5-Efficient-LARGE-DM2000 (Deep-Narrow version)
T5-Efficient-LARGE-DM2000 is a variation of [Google's original T5](https://ai.googleblog.com/2020/02/exploring-transfer-learning-with-t5.html) following the [T5 model architecture](https://huggingface.co/docs/transformers/model_doc/t5).
It is a *pretrained-only* checkpoint and was released with the
paper **[Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers](https://arxiv.org/abs/2109.10686)**
by *Yi Tay, Mostafa Dehghani, Jinfeng Rao, William Fedus, Samira Abnar, Hyung Won Chung, Sharan Narang, Dani Yogatama, Ashish Vaswani, Donald Metzler*.
In a nutshell, the paper indicates that a **Deep-Narrow** model architecture is favorable for **downstream** performance compared to other model architectures
of similar parameter count.
To quote the paper:
> We generally recommend a DeepNarrow strategy where the model’s depth is preferentially increased
> before considering any other forms of uniform scaling across other dimensions. This is largely due to
> how much depth influences the Pareto-frontier as shown in earlier sections of the paper. Specifically, a
> tall small (deep and narrow) model is generally more efficient compared to the base model. Likewise,
> a tall base model might also generally more efficient compared to a large model. We generally find
> that, regardless of size, even if absolute performance might increase as we continue to stack layers,
> the relative gain of Pareto-efficiency diminishes as we increase the layers, converging at 32 to 36
> layers. Finally, we note that our notion of efficiency here relates to any one compute dimension, i.e.,
> params, FLOPs or throughput (speed). We report all three key efficiency metrics (number of params,
> FLOPS and speed) and leave this decision to the practitioner to decide which compute dimension to
> consider.
To be more precise, *model depth* is defined as the number of transformer blocks that are stacked sequentially.
A sequence of word embeddings is therefore processed sequentially by each transformer block.
## Details model architecture
This model checkpoint - **t5-efficient-large-dm2000** - is of model type **Large** with the following variations:
- **dm** is **2000**
It has **1475.39** million parameters and thus requires *ca.* **5901.57 MB** of memory in full precision (*fp32*)
or **2950.78 MB** of memory in half precision (*fp16* or *bf16*).
A summary of the *original* T5 model architectures can be seen here:
| Model | nl (el/dl) | ff | dm | kv | nh | #Params|
| ----| ---- | ---- | ---- | ---- | ---- | ----|
| Tiny | 4/4 | 1024 | 256 | 32 | 4 | 16M|
| Mini | 4/4 | 1536 | 384 | 32 | 8 | 31M|
| Small | 6/6 | 2048 | 512 | 32 | 8 | 60M|
| Base | 12/12 | 3072 | 768 | 64 | 12 | 220M|
| Large | 24/24 | 4096 | 1024 | 64 | 16 | 738M|
| Xl | 24/24 | 16384 | 1024 | 128 | 32 | 3B|
| XXl | 24/24 | 65536 | 1024 | 128 | 128 | 11B|
whereas the following abbreviations are used:
| Abbreviation | Definition |
| ----| ---- |
| nl | Number of transformer blocks (depth) |
| dm | Dimension of embedding vector (output vector of transformers block) |
| kv | Dimension of key/value projection matrix |
| nh | Number of attention heads |
| ff | Dimension of intermediate vector within transformer block (size of feed-forward projection matrix) |
| el | Number of transformer blocks in the encoder (encoder depth) |
| dl | Number of transformer blocks in the decoder (decoder depth) |
| sh | Signifies that attention heads are shared |
| skv | Signifies that key-values projection matrices are tied |
If a model checkpoint has no specific, *el* or *dl* than both the number of encoder- and decoder layers correspond to *nl*.
## Pre-Training
The checkpoint was pretrained on the [Colossal, Cleaned version of Common Crawl (C4)](https://huggingface.co/datasets/c4) for 524288 steps using
the span-based masked language modeling (MLM) objective.
## Fine-Tuning
**Note**: This model is a **pretrained** checkpoint and has to be fine-tuned for practical usage.
The checkpoint was pretrained in English and is therefore only useful for English NLP tasks.
You can follow on of the following examples on how to fine-tune the model:
*PyTorch*:
- [Summarization](https://github.com/huggingface/transformers/tree/master/examples/pytorch/summarization)
- [Question Answering](https://github.com/huggingface/transformers/blob/master/examples/pytorch/question-answering/run_seq2seq_qa.py)
- [Text Classification](https://github.com/huggingface/transformers/tree/master/examples/pytorch/text-classification) - *Note*: You will have to slightly adapt the training example here to make it work with an encoder-decoder model.
*Tensorflow*:
- [Summarization](https://github.com/huggingface/transformers/tree/master/examples/tensorflow/summarization)
- [Text Classification](https://github.com/huggingface/transformers/tree/master/examples/tensorflow/text-classification) - *Note*: You will have to slightly adapt the training example here to make it work with an encoder-decoder model.
*JAX/Flax*:
- [Summarization](https://github.com/huggingface/transformers/tree/master/examples/flax/summarization)
- [Text Classification](https://github.com/huggingface/transformers/tree/master/examples/flax/text-classification) - *Note*: You will have to slightly adapt the training example here to make it work with an encoder-decoder model.
## Downstream Performance
TODO: Add table if available
## Computational Complexity
TODO: Add table if available
## More information
We strongly recommend the reader to go carefully through the original paper **[Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers](https://arxiv.org/abs/2109.10686)** to get a more nuanced understanding of this model checkpoint.
As explained in the following [issue](https://github.com/google-research/google-research/issues/986#issuecomment-1035051145), checkpoints including the *sh* or *skv*
model architecture variations have *not* been ported to Transformers as they are probably of limited practical usage and are lacking a more detailed description. Those checkpoints are kept [here](https://huggingface.co/NewT5SharedHeadsSharedKeyValues) as they might be ported potentially in the future. | [
"TEXT_CLASSIFICATION",
"QUESTION_ANSWERING",
"SUMMARIZATION"
] | Non_BioNLP |
jxm/cde-small-v2 | jxm | feature-extraction | [
"sentence-transformers",
"safetensors",
"feature-extraction",
"mteb",
"transformers",
"modernbert",
"custom_code",
"arxiv:2410.02525",
"base_model:answerdotai/ModernBERT-base",
"base_model:finetune:answerdotai/ModernBERT-base",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 1,736,791,454,000 | 2025-02-03T23:41:38 | 3,933 | 78 | ---
base_model: answerdotai/ModernBERT-base
tags:
- mteb
- transformers
- sentence-transformers
- modernbert
model-index:
- name: cde-small-v2
results:
- task:
type: Classification
dataset:
name: MTEB AmazonCounterfactualClassification (en)
type: mteb/amazon_counterfactual
config: en
split: test
revision: e8379541af4e31359cca9fbcf4b00f2671dba205
metrics:
- type: accuracy
value: 86.01490000000001
- type: f1
value: 80.938
- type: f1_weighted
value: 86.9232
- type: ap
value: 54.949099999999994
- type: ap_weighted
value: 54.949099999999994
- type: main_score
value: 86.01490000000001
- task:
type: Classification
dataset:
name: MTEB AmazonPolarityClassification (default)
type: mteb/amazon_polarity
config: default
split: test
revision: e2d317d38cd51312af73b3d32a06d1a08b442046
metrics:
- type: accuracy
value: 96.0223
- type: f1
value: 96.0206
- type: f1_weighted
value: 96.0206
- type: ap
value: 93.8301
- type: ap_weighted
value: 93.8301
- type: main_score
value: 96.0223
- task:
type: Classification
dataset:
name: MTEB AmazonReviewsClassification (en)
type: mteb/amazon_reviews_multi
config: en
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 55.096000000000004
- type: f1
value: 54.4353
- type: f1_weighted
value: 54.4353
- type: main_score
value: 55.096000000000004
- task:
type: Retrieval
dataset:
name: MTEB ArguAna (default)
type: mteb/arguana
config: default
split: test
revision: c22ab2a51041ffd869aaddef7af8d8215647e41a
metrics:
- type: ndcg_at_1
value: 54.125
- type: ndcg_at_3
value: 69.009
- type: ndcg_at_5
value: 72.722
- type: ndcg_at_10
value: 74.957
- type: ndcg_at_20
value: 75.801
- type: ndcg_at_100
value: 75.986
- type: ndcg_at_1000
value: 76.015
- type: map_at_1
value: 54.125
- type: map_at_3
value: 65.375
- type: map_at_5
value: 67.448
- type: map_at_10
value: 68.38499999999999
- type: map_at_20
value: 68.636
- type: map_at_100
value: 68.66600000000001
- type: map_at_1000
value: 68.66799999999999
- type: recall_at_1
value: 54.125
- type: recall_at_3
value: 79.51599999999999
- type: recall_at_5
value: 88.478
- type: recall_at_10
value: 95.306
- type: recall_at_20
value: 98.506
- type: recall_at_100
value: 99.431
- type: recall_at_1000
value: 99.644
- type: precision_at_1
value: 54.125
- type: precision_at_3
value: 26.505000000000003
- type: precision_at_5
value: 17.696
- type: precision_at_10
value: 9.531
- type: precision_at_20
value: 4.925
- type: precision_at_100
value: 0.9939999999999999
- type: precision_at_1000
value: 0.1
- type: mrr_at_1
value: 54.623
- type: mrr_at_3
value: 65.505
- type: mrr_at_5
value: 67.6174
- type: mrr_at_10
value: 68.5664
- type: mrr_at_20
value: 68.8173
- type: mrr_at_100
value: 68.8476
- type: mrr_at_1000
value: 68.8489
- type: nauc_ndcg_at_1_max
value: -14.4789
- type: nauc_ndcg_at_1_std
value: -25.5432
- type: nauc_ndcg_at_1_diff1
value: 23.7267
- type: nauc_ndcg_at_3_max
value: -8.1401
- type: nauc_ndcg_at_3_std
value: -22.9099
- type: nauc_ndcg_at_3_diff1
value: 21.069499999999998
- type: nauc_ndcg_at_5_max
value: -8.4301
- type: nauc_ndcg_at_5_std
value: -22.9185
- type: nauc_ndcg_at_5_diff1
value: 21.229100000000003
- type: nauc_ndcg_at_10_max
value: -8.6651
- type: nauc_ndcg_at_10_std
value: -23.5444
- type: nauc_ndcg_at_10_diff1
value: 21.9585
- type: nauc_ndcg_at_20_max
value: -9.285400000000001
- type: nauc_ndcg_at_20_std
value: -23.4297
- type: nauc_ndcg_at_20_diff1
value: 21.6731
- type: nauc_ndcg_at_100_max
value: -9.8693
- type: nauc_ndcg_at_100_std
value: -23.313
- type: nauc_ndcg_at_100_diff1
value: 21.5888
- type: nauc_ndcg_at_1000_max
value: -9.9675
- type: nauc_ndcg_at_1000_std
value: -23.3522
- type: nauc_ndcg_at_1000_diff1
value: 21.5714
- type: nauc_map_at_1_max
value: -14.4789
- type: nauc_map_at_1_std
value: -25.5432
- type: nauc_map_at_1_diff1
value: 23.7267
- type: nauc_map_at_3_max
value: -10.0484
- type: nauc_map_at_3_std
value: -23.3575
- type: nauc_map_at_3_diff1
value: 21.329
- type: nauc_map_at_5_max
value: -10.3514
- type: nauc_map_at_5_std
value: -23.3955
- type: nauc_map_at_5_diff1
value: 21.3531
- type: nauc_map_at_10_max
value: -10.484200000000001
- type: nauc_map_at_10_std
value: -23.6726
- type: nauc_map_at_10_diff1
value: 21.6458
- type: nauc_map_at_20_max
value: -10.638499999999999
- type: nauc_map_at_20_std
value: -23.6588
- type: nauc_map_at_20_diff1
value: 21.576600000000003
- type: nauc_map_at_100_max
value: -10.717400000000001
- type: nauc_map_at_100_std
value: -23.6559
- type: nauc_map_at_100_diff1
value: 21.5688
- type: nauc_map_at_1000_max
value: -10.7203
- type: nauc_map_at_1000_std
value: -23.6557
- type: nauc_map_at_1000_diff1
value: 21.5682
- type: nauc_recall_at_1_max
value: -14.4789
- type: nauc_recall_at_1_std
value: -25.5432
- type: nauc_recall_at_1_diff1
value: 23.7267
- type: nauc_recall_at_3_max
value: -0.2134
- type: nauc_recall_at_3_std
value: -21.251800000000003
- type: nauc_recall_at_3_diff1
value: 20.3069
- type: nauc_recall_at_5_max
value: 4.109100000000001
- type: nauc_recall_at_5_std
value: -20.1382
- type: nauc_recall_at_5_diff1
value: 21.1976
- type: nauc_recall_at_10_max
value: 18.3416
- type: nauc_recall_at_10_std
value: -22.9791
- type: nauc_recall_at_10_diff1
value: 29.4668
- type: nauc_recall_at_20_max
value: 45.3219
- type: nauc_recall_at_20_std
value: -14.8366
- type: nauc_recall_at_20_diff1
value: 31.829800000000002
- type: nauc_recall_at_100_max
value: 38.8075
- type: nauc_recall_at_100_std
value: 25.4176
- type: nauc_recall_at_100_diff1
value: 32.2733
- type: nauc_recall_at_1000_max
value: 28.1372
- type: nauc_recall_at_1000_std
value: 35.442
- type: nauc_recall_at_1000_diff1
value: 31.8247
- type: nauc_precision_at_1_max
value: -14.4789
- type: nauc_precision_at_1_std
value: -25.5432
- type: nauc_precision_at_1_diff1
value: 23.7267
- type: nauc_precision_at_3_max
value: -0.2134
- type: nauc_precision_at_3_std
value: -21.251800000000003
- type: nauc_precision_at_3_diff1
value: 20.3069
- type: nauc_precision_at_5_max
value: 4.109100000000001
- type: nauc_precision_at_5_std
value: -20.1382
- type: nauc_precision_at_5_diff1
value: 21.1976
- type: nauc_precision_at_10_max
value: 18.3416
- type: nauc_precision_at_10_std
value: -22.9791
- type: nauc_precision_at_10_diff1
value: 29.4668
- type: nauc_precision_at_20_max
value: 45.3219
- type: nauc_precision_at_20_std
value: -14.8366
- type: nauc_precision_at_20_diff1
value: 31.829800000000002
- type: nauc_precision_at_100_max
value: 38.8075
- type: nauc_precision_at_100_std
value: 25.4176
- type: nauc_precision_at_100_diff1
value: 32.2733
- type: nauc_precision_at_1000_max
value: 28.1372
- type: nauc_precision_at_1000_std
value: 35.442
- type: nauc_precision_at_1000_diff1
value: 31.8247
- type: nauc_mrr_at_1_max
value: -14.066600000000001
- type: nauc_mrr_at_1_std
value: -25.0145
- type: nauc_mrr_at_1_diff1
value: 22.361900000000002
- type: nauc_mrr_at_3_max
value: -10.6465
- type: nauc_mrr_at_3_std
value: -23.4323
- type: nauc_mrr_at_3_diff1
value: 19.758899999999997
- type: nauc_mrr_at_5_max
value: -10.7144
- type: nauc_mrr_at_5_std
value: -23.2823
- type: nauc_mrr_at_5_diff1
value: 19.8552
- type: nauc_mrr_at_10_max
value: -10.7815
- type: nauc_mrr_at_10_std
value: -23.51
- type: nauc_mrr_at_10_diff1
value: 20.157
- type: nauc_mrr_at_20_max
value: -10.9391
- type: nauc_mrr_at_20_std
value: -23.4946
- type: nauc_mrr_at_20_diff1
value: 20.072400000000002
- type: nauc_mrr_at_100_max
value: -11.018500000000001
- type: nauc_mrr_at_100_std
value: -23.491400000000002
- type: nauc_mrr_at_100_diff1
value: 20.0627
- type: nauc_mrr_at_1000_max
value: -11.0214
- type: nauc_mrr_at_1000_std
value: -23.491300000000003
- type: nauc_mrr_at_1000_diff1
value: 20.061999999999998
- type: main_score
value: 74.957
- task:
type: Clustering
dataset:
name: MTEB ArxivClusteringP2P (default)
type: mteb/arxiv-clustering-p2p
config: default
split: test
revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d
metrics:
- type: v_measure
value: 50.5269
- type: v_measure_std
value: 14.0094
- type: main_score
value: 50.5269
- task:
type: Clustering
dataset:
name: MTEB ArxivClusteringS2S (default)
type: mteb/arxiv-clustering-s2s
config: default
split: test
revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53
metrics:
- type: v_measure
value: 41.620200000000004
- type: v_measure_std
value: 14.4842
- type: main_score
value: 41.620200000000004
- task:
type: Reranking
dataset:
name: MTEB AskUbuntuDupQuestions (default)
type: mteb/askubuntudupquestions-reranking
config: default
split: test
revision: 2000358ca161889fa9c082cb41daa8dcfb161a54
metrics:
- type: map
value: 61.790299999999995
- type: mrr
value: 75.8156
- type: nAUC_map_max
value: 26.151200000000003
- type: nAUC_map_std
value: 15.8953
- type: nAUC_map_diff1
value: 5.0684
- type: nAUC_mrr_max
value: 36.9643
- type: nAUC_mrr_std
value: 19.0749
- type: nAUC_mrr_diff1
value: 15.549399999999999
- type: main_score
value: 61.790299999999995
- task:
type: STS
dataset:
name: MTEB BIOSSES (default)
type: mteb/biosses-sts
config: default
split: test
revision: d3fb88f8f02e40887cd149695127462bbcf29b4a
metrics:
- type: pearson
value: 88.41590000000001
- type: spearman
value: 86.7116
- type: cosine_pearson
value: 88.41590000000001
- type: cosine_spearman
value: 86.7116
- type: manhattan_pearson
value: 86.2045
- type: manhattan_spearman
value: 85.7248
- type: euclidean_pearson
value: 86.2336
- type: euclidean_spearman
value: 85.861
- type: main_score
value: 86.7116
- task:
type: Classification
dataset:
name: MTEB Banking77Classification (default)
type: mteb/banking77
config: default
split: test
revision: 0fd18e25b25c072e09e0d92ab615fda904d66300
metrics:
- type: accuracy
value: 88.3052
- type: f1
value: 88.2617
- type: f1_weighted
value: 88.2617
- type: main_score
value: 88.3052
- task:
type: Clustering
dataset:
name: MTEB BiorxivClusteringP2P (default)
type: mteb/biorxiv-clustering-p2p
config: default
split: test
revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40
metrics:
- type: v_measure
value: 45.4377
- type: v_measure_std
value: 0.8543000000000001
- type: main_score
value: 45.4377
- task:
type: Clustering
dataset:
name: MTEB BiorxivClusteringS2S (default)
type: mteb/biorxiv-clustering-s2s
config: default
split: test
revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908
metrics:
- type: v_measure
value: 39.6472
- type: v_measure_std
value: 0.7081999999999999
- type: main_score
value: 39.6472
- task:
type: Retrieval
dataset:
name: MTEB CQADupstackAndroidRetrieval (default)
type: mteb/cqadupstack-android
config: default
split: test
revision: f46a197baaae43b4f621051089b82a364682dfeb
metrics:
- type: ndcg_at_1
value: 39.342
- type: ndcg_at_3
value: 44.718999999999994
- type: ndcg_at_5
value: 47.449999999999996
- type: ndcg_at_10
value: 50.17
- type: ndcg_at_20
value: 52.366
- type: ndcg_at_100
value: 55.400000000000006
- type: ndcg_at_1000
value: 57.13399999999999
- type: map_at_1
value: 32.300000000000004
- type: map_at_3
value: 39.937
- type: map_at_5
value: 42.141
- type: map_at_10
value: 43.681
- type: map_at_20
value: 44.516
- type: map_at_100
value: 45.14
- type: map_at_1000
value: 45.25
- type: recall_at_1
value: 32.300000000000004
- type: recall_at_3
value: 47.12
- type: recall_at_5
value: 54.581
- type: recall_at_10
value: 62.873000000000005
- type: recall_at_20
value: 70.604
- type: recall_at_100
value: 84.465
- type: recall_at_1000
value: 95.299
- type: precision_at_1
value: 39.342
- type: precision_at_3
value: 21.459
- type: precision_at_5
value: 15.622
- type: precision_at_10
value: 9.514
- type: precision_at_20
value: 5.665
- type: precision_at_100
value: 1.5150000000000001
- type: precision_at_1000
value: 0.19499999999999998
- type: mrr_at_1
value: 39.3419
- type: mrr_at_3
value: 46.805
- type: mrr_at_5
value: 48.5861
- type: mrr_at_10
value: 49.6697
- type: mrr_at_20
value: 50.131
- type: mrr_at_100
value: 50.373599999999996
- type: mrr_at_1000
value: 50.4106
- type: nauc_ndcg_at_1_max
value: 40.0004
- type: nauc_ndcg_at_1_std
value: -1.8753
- type: nauc_ndcg_at_1_diff1
value: 45.9146
- type: nauc_ndcg_at_3_max
value: 41.3777
- type: nauc_ndcg_at_3_std
value: -1.2817
- type: nauc_ndcg_at_3_diff1
value: 42.710100000000004
- type: nauc_ndcg_at_5_max
value: 42.4211
- type: nauc_ndcg_at_5_std
value: -0.6910999999999999
- type: nauc_ndcg_at_5_diff1
value: 42.9048
- type: nauc_ndcg_at_10_max
value: 42.609399999999994
- type: nauc_ndcg_at_10_std
value: 0.4398
- type: nauc_ndcg_at_10_diff1
value: 42.4967
- type: nauc_ndcg_at_20_max
value: 42.7921
- type: nauc_ndcg_at_20_std
value: 0.9266
- type: nauc_ndcg_at_20_diff1
value: 42.701899999999995
- type: nauc_ndcg_at_100_max
value: 43.4878
- type: nauc_ndcg_at_100_std
value: 2.2893
- type: nauc_ndcg_at_100_diff1
value: 42.735
- type: nauc_ndcg_at_1000_max
value: 43.3776
- type: nauc_ndcg_at_1000_std
value: 2.1375
- type: nauc_ndcg_at_1000_diff1
value: 42.6437
- type: nauc_map_at_1_max
value: 37.573499999999996
- type: nauc_map_at_1_std
value: -1.4611
- type: nauc_map_at_1_diff1
value: 50.0479
- type: nauc_map_at_3_max
value: 40.5952
- type: nauc_map_at_3_std
value: -1.7034
- type: nauc_map_at_3_diff1
value: 45.7247
- type: nauc_map_at_5_max
value: 41.3854
- type: nauc_map_at_5_std
value: -1.5435
- type: nauc_map_at_5_diff1
value: 45.278400000000005
- type: nauc_map_at_10_max
value: 41.7269
- type: nauc_map_at_10_std
value: -1.0763
- type: nauc_map_at_10_diff1
value: 45.0862
- type: nauc_map_at_20_max
value: 42.0241
- type: nauc_map_at_20_std
value: -0.8463999999999999
- type: nauc_map_at_20_diff1
value: 45.1365
- type: nauc_map_at_100_max
value: 42.248200000000004
- type: nauc_map_at_100_std
value: -0.6139
- type: nauc_map_at_100_diff1
value: 45.0658
- type: nauc_map_at_1000_max
value: 42.2442
- type: nauc_map_at_1000_std
value: -0.6187
- type: nauc_map_at_1000_diff1
value: 45.0382
- type: nauc_recall_at_1_max
value: 37.573499999999996
- type: nauc_recall_at_1_std
value: -1.4611
- type: nauc_recall_at_1_diff1
value: 50.0479
- type: nauc_recall_at_3_max
value: 39.9536
- type: nauc_recall_at_3_std
value: -0.132
- type: nauc_recall_at_3_diff1
value: 39.6892
- type: nauc_recall_at_5_max
value: 41.428799999999995
- type: nauc_recall_at_5_std
value: 1.2703
- type: nauc_recall_at_5_diff1
value: 38.2213
- type: nauc_recall_at_10_max
value: 41.3254
- type: nauc_recall_at_10_std
value: 4.9163
- type: nauc_recall_at_10_diff1
value: 35.1215
- type: nauc_recall_at_20_max
value: 41.3807
- type: nauc_recall_at_20_std
value: 7.3897
- type: nauc_recall_at_20_diff1
value: 33.7864
- type: nauc_recall_at_100_max
value: 49.6612
- type: nauc_recall_at_100_std
value: 25.1511
- type: nauc_recall_at_100_diff1
value: 33.968199999999996
- type: nauc_recall_at_1000_max
value: 71.2452
- type: nauc_recall_at_1000_std
value: 68.7065
- type: nauc_recall_at_1000_diff1
value: 33.0124
- type: nauc_precision_at_1_max
value: 40.0004
- type: nauc_precision_at_1_std
value: -1.8753
- type: nauc_precision_at_1_diff1
value: 45.9146
- type: nauc_precision_at_3_max
value: 36.741800000000005
- type: nauc_precision_at_3_std
value: -1.2777
- type: nauc_precision_at_3_diff1
value: 23.3539
- type: nauc_precision_at_5_max
value: 32.9756
- type: nauc_precision_at_5_std
value: -0.1613
- type: nauc_precision_at_5_diff1
value: 15.866
- type: nauc_precision_at_10_max
value: 25.7284
- type: nauc_precision_at_10_std
value: 2.7586
- type: nauc_precision_at_10_diff1
value: 6.579899999999999
- type: nauc_precision_at_20_max
value: 18.8213
- type: nauc_precision_at_20_std
value: 3.6470000000000002
- type: nauc_precision_at_20_diff1
value: -0.45690000000000003
- type: nauc_precision_at_100_max
value: 5.7518
- type: nauc_precision_at_100_std
value: 3.4711
- type: nauc_precision_at_100_diff1
value: -12.380700000000001
- type: nauc_precision_at_1000_max
value: -8.6862
- type: nauc_precision_at_1000_std
value: -4.5796
- type: nauc_precision_at_1000_diff1
value: -19.9355
- type: nauc_mrr_at_1_max
value: 40.0004
- type: nauc_mrr_at_1_std
value: -1.8753
- type: nauc_mrr_at_1_diff1
value: 45.9146
- type: nauc_mrr_at_3_max
value: 40.686
- type: nauc_mrr_at_3_std
value: -0.8626999999999999
- type: nauc_mrr_at_3_diff1
value: 41.4552
- type: nauc_mrr_at_5_max
value: 41.2445
- type: nauc_mrr_at_5_std
value: -0.7058
- type: nauc_mrr_at_5_diff1
value: 41.7244
- type: nauc_mrr_at_10_max
value: 41.1575
- type: nauc_mrr_at_10_std
value: -0.44489999999999996
- type: nauc_mrr_at_10_diff1
value: 41.355199999999996
- type: nauc_mrr_at_20_max
value: 41.1548
- type: nauc_mrr_at_20_std
value: -0.33
- type: nauc_mrr_at_20_diff1
value: 41.444199999999995
- type: nauc_mrr_at_100_max
value: 41.1908
- type: nauc_mrr_at_100_std
value: -0.3263
- type: nauc_mrr_at_100_diff1
value: 41.505900000000004
- type: nauc_mrr_at_1000_max
value: 41.1935
- type: nauc_mrr_at_1000_std
value: -0.3216
- type: nauc_mrr_at_1000_diff1
value: 41.5128
- type: main_score
value: 50.17
- task:
type: Retrieval
dataset:
name: MTEB CQADupstackEnglishRetrieval (default)
type: mteb/cqadupstack-english
config: default
split: test
revision: ad9991cb51e31e31e430383c75ffb2885547b5f0
metrics:
- type: ndcg_at_1
value: 42.102000000000004
- type: ndcg_at_3
value: 45.741
- type: ndcg_at_5
value: 47.734
- type: ndcg_at_10
value: 49.732
- type: ndcg_at_20
value: 51.295
- type: ndcg_at_100
value: 53.935
- type: ndcg_at_1000
value: 55.765
- type: map_at_1
value: 33.306999999999995
- type: map_at_3
value: 40.953
- type: map_at_5
value: 42.731
- type: map_at_10
value: 44.022
- type: map_at_20
value: 44.693
- type: map_at_100
value: 45.259
- type: map_at_1000
value: 45.383
- type: recall_at_1
value: 33.306999999999995
- type: recall_at_3
value: 47.127
- type: recall_at_5
value: 52.89
- type: recall_at_10
value: 59.16400000000001
- type: recall_at_20
value: 64.85
- type: recall_at_100
value: 77.206
- type: recall_at_1000
value: 88.701
- type: precision_at_1
value: 42.102000000000004
- type: precision_at_3
value: 21.975
- type: precision_at_5
value: 15.465000000000002
- type: precision_at_10
value: 9.229
- type: precision_at_20
value: 5.404
- type: precision_at_100
value: 1.461
- type: precision_at_1000
value: 0.192
- type: mrr_at_1
value: 42.1019
- type: mrr_at_3
value: 48.322700000000005
- type: mrr_at_5
value: 49.593399999999995
- type: mrr_at_10
value: 50.364399999999996
- type: mrr_at_20
value: 50.7215
- type: mrr_at_100
value: 50.962300000000006
- type: mrr_at_1000
value: 50.9999
- type: nauc_ndcg_at_1_max
value: 40.6054
- type: nauc_ndcg_at_1_std
value: -3.4602
- type: nauc_ndcg_at_1_diff1
value: 54.0346
- type: nauc_ndcg_at_3_max
value: 40.0946
- type: nauc_ndcg_at_3_std
value: -3.7981000000000003
- type: nauc_ndcg_at_3_diff1
value: 49.2481
- type: nauc_ndcg_at_5_max
value: 40.198699999999995
- type: nauc_ndcg_at_5_std
value: -3.2983
- type: nauc_ndcg_at_5_diff1
value: 48.7252
- type: nauc_ndcg_at_10_max
value: 40.6072
- type: nauc_ndcg_at_10_std
value: -3.472
- type: nauc_ndcg_at_10_diff1
value: 48.7302
- type: nauc_ndcg_at_20_max
value: 41.0897
- type: nauc_ndcg_at_20_std
value: -2.8645
- type: nauc_ndcg_at_20_diff1
value: 48.8834
- type: nauc_ndcg_at_100_max
value: 41.450900000000004
- type: nauc_ndcg_at_100_std
value: -1.3305
- type: nauc_ndcg_at_100_diff1
value: 48.2699
- type: nauc_ndcg_at_1000_max
value: 41.4853
- type: nauc_ndcg_at_1000_std
value: -0.7634
- type: nauc_ndcg_at_1000_diff1
value: 48.28
- type: nauc_map_at_1_max
value: 31.776100000000003
- type: nauc_map_at_1_std
value: -12.5085
- type: nauc_map_at_1_diff1
value: 56.84630000000001
- type: nauc_map_at_3_max
value: 36.3131
- type: nauc_map_at_3_std
value: -9.3976
- type: nauc_map_at_3_diff1
value: 52.4471
- type: nauc_map_at_5_max
value: 37.330799999999996
- type: nauc_map_at_5_std
value: -8.0619
- type: nauc_map_at_5_diff1
value: 51.692800000000005
- type: nauc_map_at_10_max
value: 38.406400000000005
- type: nauc_map_at_10_std
value: -7.1754
- type: nauc_map_at_10_diff1
value: 51.46849999999999
- type: nauc_map_at_20_max
value: 38.940000000000005
- type: nauc_map_at_20_std
value: -6.4747
- type: nauc_map_at_20_diff1
value: 51.34570000000001
- type: nauc_map_at_100_max
value: 39.3424
- type: nauc_map_at_100_std
value: -5.7301
- type: nauc_map_at_100_diff1
value: 51.0633
- type: nauc_map_at_1000_max
value: 39.3905
- type: nauc_map_at_1000_std
value: -5.5938
- type: nauc_map_at_1000_diff1
value: 51.04109999999999
- type: nauc_recall_at_1_max
value: 31.776100000000003
- type: nauc_recall_at_1_std
value: -12.5085
- type: nauc_recall_at_1_diff1
value: 56.84630000000001
- type: nauc_recall_at_3_max
value: 35.702
- type: nauc_recall_at_3_std
value: -7.3138
- type: nauc_recall_at_3_diff1
value: 46.3454
- type: nauc_recall_at_5_max
value: 36.459399999999995
- type: nauc_recall_at_5_std
value: -4.678100000000001
- type: nauc_recall_at_5_diff1
value: 43.6423
- type: nauc_recall_at_10_max
value: 37.3534
- type: nauc_recall_at_10_std
value: -4.0492
- type: nauc_recall_at_10_diff1
value: 41.7513
- type: nauc_recall_at_20_max
value: 39.379999999999995
- type: nauc_recall_at_20_std
value: -1.0078
- type: nauc_recall_at_20_diff1
value: 41.638
- type: nauc_recall_at_100_max
value: 40.705799999999996
- type: nauc_recall_at_100_std
value: 8.9477
- type: nauc_recall_at_100_diff1
value: 35.7987
- type: nauc_recall_at_1000_max
value: 41.560399999999994
- type: nauc_recall_at_1000_std
value: 19.6108
- type: nauc_recall_at_1000_diff1
value: 30.694399999999998
- type: nauc_precision_at_1_max
value: 40.6054
- type: nauc_precision_at_1_std
value: -3.4602
- type: nauc_precision_at_1_diff1
value: 54.0346
- type: nauc_precision_at_3_max
value: 42.0217
- type: nauc_precision_at_3_std
value: 10.3896
- type: nauc_precision_at_3_diff1
value: 26.7498
- type: nauc_precision_at_5_max
value: 40.4414
- type: nauc_precision_at_5_std
value: 18.177599999999998
- type: nauc_precision_at_5_diff1
value: 16.9455
- type: nauc_precision_at_10_max
value: 38.921
- type: nauc_precision_at_10_std
value: 24.1093
- type: nauc_precision_at_10_diff1
value: 8.4258
- type: nauc_precision_at_20_max
value: 34.620200000000004
- type: nauc_precision_at_20_std
value: 29.351399999999998
- type: nauc_precision_at_20_diff1
value: 0.15360000000000001
- type: nauc_precision_at_100_max
value: 25.230000000000004
- type: nauc_precision_at_100_std
value: 36.8424
- type: nauc_precision_at_100_diff1
value: -12.225900000000001
- type: nauc_precision_at_1000_max
value: 13.1715
- type: nauc_precision_at_1000_std
value: 34.7096
- type: nauc_precision_at_1000_diff1
value: -16.5331
- type: nauc_mrr_at_1_max
value: 40.6054
- type: nauc_mrr_at_1_std
value: -3.4602
- type: nauc_mrr_at_1_diff1
value: 54.0346
- type: nauc_mrr_at_3_max
value: 42.2127
- type: nauc_mrr_at_3_std
value: -1.0392000000000001
- type: nauc_mrr_at_3_diff1
value: 49.748
- type: nauc_mrr_at_5_max
value: 42.2638
- type: nauc_mrr_at_5_std
value: -0.40049999999999997
- type: nauc_mrr_at_5_diff1
value: 49.3009
- type: nauc_mrr_at_10_max
value: 42.0477
- type: nauc_mrr_at_10_std
value: -0.6505000000000001
- type: nauc_mrr_at_10_diff1
value: 49.0978
- type: nauc_mrr_at_20_max
value: 42.0895
- type: nauc_mrr_at_20_std
value: -0.5649000000000001
- type: nauc_mrr_at_20_diff1
value: 49.1893
- type: nauc_mrr_at_100_max
value: 42.0951
- type: nauc_mrr_at_100_std
value: -0.5555
- type: nauc_mrr_at_100_diff1
value: 49.2047
- type: nauc_mrr_at_1000_max
value: 42.0946
- type: nauc_mrr_at_1000_std
value: -0.5584
- type: nauc_mrr_at_1000_diff1
value: 49.207699999999996
- type: main_score
value: 49.732
- task:
type: Retrieval
dataset:
name: MTEB CQADupstackGamingRetrieval (default)
type: mteb/cqadupstack-gaming
config: default
split: test
revision: 4885aa143210c98657558c04aaf3dc47cfb54340
metrics:
- type: ndcg_at_1
value: 48.276
- type: ndcg_at_3
value: 53.727000000000004
- type: ndcg_at_5
value: 56.511
- type: ndcg_at_10
value: 59.023
- type: ndcg_at_20
value: 60.802
- type: ndcg_at_100
value: 62.980999999999995
- type: ndcg_at_1000
value: 64.13600000000001
- type: map_at_1
value: 42.347
- type: map_at_3
value: 50.349999999999994
- type: map_at_5
value: 52.276999999999994
- type: map_at_10
value: 53.6
- type: map_at_20
value: 54.217000000000006
- type: map_at_100
value: 54.605000000000004
- type: map_at_1000
value: 54.663
- type: recall_at_1
value: 42.347
- type: recall_at_3
value: 57.499
- type: recall_at_5
value: 64.269
- type: recall_at_10
value: 71.568
- type: recall_at_20
value: 78.125
- type: recall_at_100
value: 88.699
- type: recall_at_1000
value: 96.887
- type: precision_at_1
value: 48.276
- type: precision_at_3
value: 23.49
- type: precision_at_5
value: 16.262999999999998
- type: precision_at_10
value: 9.322999999999999
- type: precision_at_20
value: 5.21
- type: precision_at_100
value: 1.22
- type: precision_at_1000
value: 0.136
- type: mrr_at_1
value: 48.2759
- type: mrr_at_3
value: 54.5246
- type: mrr_at_5
value: 56.0982
- type: mrr_at_10
value: 56.961
- type: mrr_at_20
value: 57.391400000000004
- type: mrr_at_100
value: 57.6295
- type: mrr_at_1000
value: 57.66139999999999
- type: nauc_ndcg_at_1_max
value: 43.5037
- type: nauc_ndcg_at_1_std
value: -7.6921
- type: nauc_ndcg_at_1_diff1
value: 58.544700000000006
- type: nauc_ndcg_at_3_max
value: 44.630900000000004
- type: nauc_ndcg_at_3_std
value: -6.260300000000001
- type: nauc_ndcg_at_3_diff1
value: 56.120999999999995
- type: nauc_ndcg_at_5_max
value: 45.1267
- type: nauc_ndcg_at_5_std
value: -5.5512
- type: nauc_ndcg_at_5_diff1
value: 54.8272
- type: nauc_ndcg_at_10_max
value: 45.691199999999995
- type: nauc_ndcg_at_10_std
value: -4.1767
- type: nauc_ndcg_at_10_diff1
value: 53.8565
- type: nauc_ndcg_at_20_max
value: 46.0581
- type: nauc_ndcg_at_20_std
value: -2.4019
- type: nauc_ndcg_at_20_diff1
value: 53.67150000000001
- type: nauc_ndcg_at_100_max
value: 46.3071
- type: nauc_ndcg_at_100_std
value: -1.856
- type: nauc_ndcg_at_100_diff1
value: 54.2616
- type: nauc_ndcg_at_1000_max
value: 46.3054
- type: nauc_ndcg_at_1000_std
value: -2.4795000000000003
- type: nauc_ndcg_at_1000_diff1
value: 54.6332
- type: nauc_map_at_1_max
value: 37.3915
- type: nauc_map_at_1_std
value: -9.6709
- type: nauc_map_at_1_diff1
value: 59.0807
- type: nauc_map_at_3_max
value: 42.3532
- type: nauc_map_at_3_std
value: -8.4634
- type: nauc_map_at_3_diff1
value: 57.342400000000005
- type: nauc_map_at_5_max
value: 43.065799999999996
- type: nauc_map_at_5_std
value: -7.430000000000001
- type: nauc_map_at_5_diff1
value: 56.5453
- type: nauc_map_at_10_max
value: 43.4845
- type: nauc_map_at_10_std
value: -6.5406
- type: nauc_map_at_10_diff1
value: 55.959199999999996
- type: nauc_map_at_20_max
value: 43.8265
- type: nauc_map_at_20_std
value: -5.8393
- type: nauc_map_at_20_diff1
value: 55.8438
- type: nauc_map_at_100_max
value: 44.014399999999995
- type: nauc_map_at_100_std
value: -5.6227
- type: nauc_map_at_100_diff1
value: 55.8762
- type: nauc_map_at_1000_max
value: 44.0386
- type: nauc_map_at_1000_std
value: -5.6262
- type: nauc_map_at_1000_diff1
value: 55.888099999999994
- type: nauc_recall_at_1_max
value: 37.3915
- type: nauc_recall_at_1_std
value: -9.6709
- type: nauc_recall_at_1_diff1
value: 59.0807
- type: nauc_recall_at_3_max
value: 43.8264
- type: nauc_recall_at_3_std
value: -6.309099999999999
- type: nauc_recall_at_3_diff1
value: 53.4872
- type: nauc_recall_at_5_max
value: 44.237300000000005
- type: nauc_recall_at_5_std
value: -4.1856
- type: nauc_recall_at_5_diff1
value: 49.3654
- type: nauc_recall_at_10_max
value: 46.7914
- type: nauc_recall_at_10_std
value: 1.3229
- type: nauc_recall_at_10_diff1
value: 45.1973
- type: nauc_recall_at_20_max
value: 49.560500000000005
- type: nauc_recall_at_20_std
value: 11.9406
- type: nauc_recall_at_20_diff1
value: 42.821999999999996
- type: nauc_recall_at_100_max
value: 53.3482
- type: nauc_recall_at_100_std
value: 27.375
- type: nauc_recall_at_100_diff1
value: 44.0535
- type: nauc_recall_at_1000_max
value: 64.18
- type: nauc_recall_at_1000_std
value: 53.603699999999996
- type: nauc_recall_at_1000_diff1
value: 50.1113
- type: nauc_precision_at_1_max
value: 43.5037
- type: nauc_precision_at_1_std
value: -7.6921
- type: nauc_precision_at_1_diff1
value: 58.544700000000006
- type: nauc_precision_at_3_max
value: 41.9145
- type: nauc_precision_at_3_std
value: 0.6891999999999999
- type: nauc_precision_at_3_diff1
value: 35.0689
- type: nauc_precision_at_5_max
value: 38.553399999999996
- type: nauc_precision_at_5_std
value: 6.1493
- type: nauc_precision_at_5_diff1
value: 23.127
- type: nauc_precision_at_10_max
value: 34.076699999999995
- type: nauc_precision_at_10_std
value: 12.673300000000001
- type: nauc_precision_at_10_diff1
value: 10.7967
- type: nauc_precision_at_20_max
value: 31.9315
- type: nauc_precision_at_20_std
value: 21.0503
- type: nauc_precision_at_20_diff1
value: 1.9767
- type: nauc_precision_at_100_max
value: 24.287300000000002
- type: nauc_precision_at_100_std
value: 24.5746
- type: nauc_precision_at_100_diff1
value: -9.751700000000001
- type: nauc_precision_at_1000_max
value: 19.252
- type: nauc_precision_at_1000_std
value: 21.0394
- type: nauc_precision_at_1000_diff1
value: -16.8851
- type: nauc_mrr_at_1_max
value: 43.5037
- type: nauc_mrr_at_1_std
value: -7.6921
- type: nauc_mrr_at_1_diff1
value: 58.544700000000006
- type: nauc_mrr_at_3_max
value: 45.9732
- type: nauc_mrr_at_3_std
value: -5.3982
- type: nauc_mrr_at_3_diff1
value: 56.1002
- type: nauc_mrr_at_5_max
value: 45.9223
- type: nauc_mrr_at_5_std
value: -5.3386000000000005
- type: nauc_mrr_at_5_diff1
value: 55.196
- type: nauc_mrr_at_10_max
value: 46.1619
- type: nauc_mrr_at_10_std
value: -4.965
- type: nauc_mrr_at_10_diff1
value: 55.081199999999995
- type: nauc_mrr_at_20_max
value: 46.238600000000005
- type: nauc_mrr_at_20_std
value: -4.5938
- type: nauc_mrr_at_20_diff1
value: 55.0906
- type: nauc_mrr_at_100_max
value: 46.2087
- type: nauc_mrr_at_100_std
value: -4.6099
- type: nauc_mrr_at_100_diff1
value: 55.1922
- type: nauc_mrr_at_1000_max
value: 46.2022
- type: nauc_mrr_at_1000_std
value: -4.6231
- type: nauc_mrr_at_1000_diff1
value: 55.209399999999995
- type: main_score
value: 59.023
- task:
type: Retrieval
dataset:
name: MTEB CQADupstackGisRetrieval (default)
type: mteb/cqadupstack-gis
config: default
split: test
revision: 5003b3064772da1887988e05400cf3806fe491f2
metrics:
- type: ndcg_at_1
value: 27.797
- type: ndcg_at_3
value: 34.787
- type: ndcg_at_5
value: 37.326
- type: ndcg_at_10
value: 39.583
- type: ndcg_at_20
value: 41.677
- type: ndcg_at_100
value: 44.932
- type: ndcg_at_1000
value: 46.893
- type: map_at_1
value: 26.209
- type: map_at_3
value: 32.365
- type: map_at_5
value: 33.819
- type: map_at_10
value: 34.827999999999996
- type: map_at_20
value: 35.447
- type: map_at_100
value: 35.93
- type: map_at_1000
value: 36.007
- type: recall_at_1
value: 26.209
- type: recall_at_3
value: 39.562999999999995
- type: recall_at_5
value: 45.594
- type: recall_at_10
value: 52.236000000000004
- type: recall_at_20
value: 60.019
- type: recall_at_100
value: 76.6
- type: recall_at_1000
value: 91.389
- type: precision_at_1
value: 27.797
- type: precision_at_3
value: 14.539
- type: precision_at_5
value: 10.215
- type: precision_at_10
value: 5.944
- type: precision_at_20
value: 3.469
- type: precision_at_100
value: 0.907
- type: precision_at_1000
value: 0.11100000000000002
- type: mrr_at_1
value: 27.796599999999998
- type: mrr_at_3
value: 34.2373
- type: mrr_at_5
value: 35.762699999999995
- type: mrr_at_10
value: 36.6849
- type: mrr_at_20
value: 37.257600000000004
- type: mrr_at_100
value: 37.6676
- type: mrr_at_1000
value: 37.723800000000004
- type: nauc_ndcg_at_1_max
value: 27.845599999999997
- type: nauc_ndcg_at_1_std
value: -8.0177
- type: nauc_ndcg_at_1_diff1
value: 44.9034
- type: nauc_ndcg_at_3_max
value: 28.7984
- type: nauc_ndcg_at_3_std
value: -6.7625
- type: nauc_ndcg_at_3_diff1
value: 38.344
- type: nauc_ndcg_at_5_max
value: 29.8333
- type: nauc_ndcg_at_5_std
value: -5.305
- type: nauc_ndcg_at_5_diff1
value: 37.8077
- type: nauc_ndcg_at_10_max
value: 30.0319
- type: nauc_ndcg_at_10_std
value: -3.7874
- type: nauc_ndcg_at_10_diff1
value: 36.7867
- type: nauc_ndcg_at_20_max
value: 29.768499999999996
- type: nauc_ndcg_at_20_std
value: -4.4994
- type: nauc_ndcg_at_20_diff1
value: 36.2424
- type: nauc_ndcg_at_100_max
value: 29.6882
- type: nauc_ndcg_at_100_std
value: -3.0686999999999998
- type: nauc_ndcg_at_100_diff1
value: 35.5097
- type: nauc_ndcg_at_1000_max
value: 30.0696
- type: nauc_ndcg_at_1000_std
value: -3.0852
- type: nauc_ndcg_at_1000_diff1
value: 36.168
- type: nauc_map_at_1_max
value: 26.105800000000002
- type: nauc_map_at_1_std
value: -9.0379
- type: nauc_map_at_1_diff1
value: 46.5148
- type: nauc_map_at_3_max
value: 27.851100000000002
- type: nauc_map_at_3_std
value: -7.6508
- type: nauc_map_at_3_diff1
value: 40.441
- type: nauc_map_at_5_max
value: 28.498600000000003
- type: nauc_map_at_5_std
value: -6.8919
- type: nauc_map_at_5_diff1
value: 40.2012
- type: nauc_map_at_10_max
value: 28.754
- type: nauc_map_at_10_std
value: -6.1987
- type: nauc_map_at_10_diff1
value: 39.7856
- type: nauc_map_at_20_max
value: 28.7468
- type: nauc_map_at_20_std
value: -6.372999999999999
- type: nauc_map_at_20_diff1
value: 39.7445
- type: nauc_map_at_100_max
value: 28.762999999999998
- type: nauc_map_at_100_std
value: -6.1504
- type: nauc_map_at_100_diff1
value: 39.643699999999995
- type: nauc_map_at_1000_max
value: 28.7886
- type: nauc_map_at_1000_std
value: -6.1426
- type: nauc_map_at_1000_diff1
value: 39.6637
- type: nauc_recall_at_1_max
value: 26.105800000000002
- type: nauc_recall_at_1_std
value: -9.0379
- type: nauc_recall_at_1_diff1
value: 46.5148
- type: nauc_recall_at_3_max
value: 28.845399999999998
- type: nauc_recall_at_3_std
value: -4.6356
- type: nauc_recall_at_3_diff1
value: 32.9931
- type: nauc_recall_at_5_max
value: 31.3996
- type: nauc_recall_at_5_std
value: -1.7656
- type: nauc_recall_at_5_diff1
value: 31.254199999999997
- type: nauc_recall_at_10_max
value: 31.406
- type: nauc_recall_at_10_std
value: 2.6767
- type: nauc_recall_at_10_diff1
value: 27.5627
- type: nauc_recall_at_20_max
value: 29.6752
- type: nauc_recall_at_20_std
value: 0.0991
- type: nauc_recall_at_20_diff1
value: 24.0771
- type: nauc_recall_at_100_max
value: 28.4217
- type: nauc_recall_at_100_std
value: 12.0071
- type: nauc_recall_at_100_diff1
value: 13.231100000000001
- type: nauc_recall_at_1000_max
value: 35.8245
- type: nauc_recall_at_1000_std
value: 30.705
- type: nauc_recall_at_1000_diff1
value: 2.7809
- type: nauc_precision_at_1_max
value: 27.845599999999997
- type: nauc_precision_at_1_std
value: -8.0177
- type: nauc_precision_at_1_diff1
value: 44.9034
- type: nauc_precision_at_3_max
value: 32.706
- type: nauc_precision_at_3_std
value: -3.9037
- type: nauc_precision_at_3_diff1
value: 29.921599999999998
- type: nauc_precision_at_5_max
value: 34.192
- type: nauc_precision_at_5_std
value: -0.5177
- type: nauc_precision_at_5_diff1
value: 28.4206
- type: nauc_precision_at_10_max
value: 33.6132
- type: nauc_precision_at_10_std
value: 4.372
- type: nauc_precision_at_10_diff1
value: 23.5257
- type: nauc_precision_at_20_max
value: 31.1237
- type: nauc_precision_at_20_std
value: 1.9191
- type: nauc_precision_at_20_diff1
value: 18.445700000000002
- type: nauc_precision_at_100_max
value: 22.5504
- type: nauc_precision_at_100_std
value: 11.1776
- type: nauc_precision_at_100_diff1
value: 3.3670999999999998
- type: nauc_precision_at_1000_max
value: 13.5905
- type: nauc_precision_at_1000_std
value: 12.9311
- type: nauc_precision_at_1000_diff1
value: -8.054699999999999
- type: nauc_mrr_at_1_max
value: 27.845599999999997
- type: nauc_mrr_at_1_std
value: -8.0177
- type: nauc_mrr_at_1_diff1
value: 44.9034
- type: nauc_mrr_at_3_max
value: 29.1589
- type: nauc_mrr_at_3_std
value: -6.4891000000000005
- type: nauc_mrr_at_3_diff1
value: 39.088699999999996
- type: nauc_mrr_at_5_max
value: 29.9228
- type: nauc_mrr_at_5_std
value: -5.6324
- type: nauc_mrr_at_5_diff1
value: 38.862
- type: nauc_mrr_at_10_max
value: 29.907600000000002
- type: nauc_mrr_at_10_std
value: -5.148
- type: nauc_mrr_at_10_diff1
value: 38.4778
- type: nauc_mrr_at_20_max
value: 29.8398
- type: nauc_mrr_at_20_std
value: -5.3067
- type: nauc_mrr_at_20_diff1
value: 38.275999999999996
- type: nauc_mrr_at_100_max
value: 29.828100000000003
- type: nauc_mrr_at_100_std
value: -5.1385
- type: nauc_mrr_at_100_diff1
value: 38.2314
- type: nauc_mrr_at_1000_max
value: 29.8443
- type: nauc_mrr_at_1000_std
value: -5.146
- type: nauc_mrr_at_1000_diff1
value: 38.2581
- type: main_score
value: 39.583
- task:
type: Retrieval
dataset:
name: MTEB CQADupstackMathematicaRetrieval (default)
type: mteb/cqadupstack-mathematica
config: default
split: test
revision: 90fceea13679c63fe563ded68f3b6f06e50061de
metrics:
- type: ndcg_at_1
value: 22.015
- type: ndcg_at_3
value: 25.941
- type: ndcg_at_5
value: 28.469
- type: ndcg_at_10
value: 31.391000000000002
- type: ndcg_at_20
value: 33.485
- type: ndcg_at_100
value: 37.145
- type: ndcg_at_1000
value: 39.909
- type: map_at_1
value: 17.580000000000002
- type: map_at_3
value: 22.900000000000002
- type: map_at_5
value: 24.498
- type: map_at_10
value: 25.823
- type: map_at_20
value: 26.429000000000002
- type: map_at_100
value: 27.029999999999998
- type: map_at_1000
value: 27.147
- type: recall_at_1
value: 17.580000000000002
- type: recall_at_3
value: 29.355999999999998
- type: recall_at_5
value: 35.634
- type: recall_at_10
value: 44.336
- type: recall_at_20
value: 51.661
- type: recall_at_100
value: 68.766
- type: recall_at_1000
value: 88.429
- type: precision_at_1
value: 22.015
- type: precision_at_3
value: 12.520999999999999
- type: precision_at_5
value: 9.254
- type: precision_at_10
value: 5.784000000000001
- type: precision_at_20
value: 3.514
- type: precision_at_100
value: 1.019
- type: precision_at_1000
value: 0.13899999999999998
- type: mrr_at_1
value: 22.0149
- type: mrr_at_3
value: 27.5705
- type: mrr_at_5
value: 29.168699999999998
- type: mrr_at_10
value: 30.352
- type: mrr_at_20
value: 30.968200000000003
- type: mrr_at_100
value: 31.3807
- type: mrr_at_1000
value: 31.4469
- type: nauc_ndcg_at_1_max
value: 21.2985
- type: nauc_ndcg_at_1_std
value: -4.6632
- type: nauc_ndcg_at_1_diff1
value: 36.1703
- type: nauc_ndcg_at_3_max
value: 23.2761
- type: nauc_ndcg_at_3_std
value: -2.9883
- type: nauc_ndcg_at_3_diff1
value: 31.11
- type: nauc_ndcg_at_5_max
value: 22.697400000000002
- type: nauc_ndcg_at_5_std
value: -2.6858
- type: nauc_ndcg_at_5_diff1
value: 29.1155
- type: nauc_ndcg_at_10_max
value: 21.745
- type: nauc_ndcg_at_10_std
value: -2.1321
- type: nauc_ndcg_at_10_diff1
value: 27.6691
- type: nauc_ndcg_at_20_max
value: 22.368
- type: nauc_ndcg_at_20_std
value: -1.1924000000000001
- type: nauc_ndcg_at_20_diff1
value: 27.453100000000003
- type: nauc_ndcg_at_100_max
value: 23.1279
- type: nauc_ndcg_at_100_std
value: 0.1931
- type: nauc_ndcg_at_100_diff1
value: 27.2613
- type: nauc_ndcg_at_1000_max
value: 23.5609
- type: nauc_ndcg_at_1000_std
value: 0.4277
- type: nauc_ndcg_at_1000_diff1
value: 27.898
- type: nauc_map_at_1_max
value: 22.1777
- type: nauc_map_at_1_std
value: -3.6511
- type: nauc_map_at_1_diff1
value: 35.193799999999996
- type: nauc_map_at_3_max
value: 22.6711
- type: nauc_map_at_3_std
value: -3.2921
- type: nauc_map_at_3_diff1
value: 31.647199999999998
- type: nauc_map_at_5_max
value: 22.3125
- type: nauc_map_at_5_std
value: -3.3684
- type: nauc_map_at_5_diff1
value: 30.6346
- type: nauc_map_at_10_max
value: 22.1293
- type: nauc_map_at_10_std
value: -3.0963000000000003
- type: nauc_map_at_10_diff1
value: 29.9676
- type: nauc_map_at_20_max
value: 22.345599999999997
- type: nauc_map_at_20_std
value: -2.7918
- type: nauc_map_at_20_diff1
value: 29.873300000000004
- type: nauc_map_at_100_max
value: 22.547600000000003
- type: nauc_map_at_100_std
value: -2.5456
- type: nauc_map_at_100_diff1
value: 29.8869
- type: nauc_map_at_1000_max
value: 22.5777
- type: nauc_map_at_1000_std
value: -2.5162
- type: nauc_map_at_1000_diff1
value: 29.9082
- type: nauc_recall_at_1_max
value: 22.1777
- type: nauc_recall_at_1_std
value: -3.6511
- type: nauc_recall_at_1_diff1
value: 35.193799999999996
- type: nauc_recall_at_3_max
value: 22.8589
- type: nauc_recall_at_3_std
value: -1.541
- type: nauc_recall_at_3_diff1
value: 26.8307
- type: nauc_recall_at_5_max
value: 21.2508
- type: nauc_recall_at_5_std
value: -1.6594000000000002
- type: nauc_recall_at_5_diff1
value: 23.0152
- type: nauc_recall_at_10_max
value: 18.4227
- type: nauc_recall_at_10_std
value: -0.29610000000000003
- type: nauc_recall_at_10_diff1
value: 19.0389
- type: nauc_recall_at_20_max
value: 20.0064
- type: nauc_recall_at_20_std
value: 2.6574
- type: nauc_recall_at_20_diff1
value: 18.1572
- type: nauc_recall_at_100_max
value: 22.8024
- type: nauc_recall_at_100_std
value: 11.629100000000001
- type: nauc_recall_at_100_diff1
value: 13.7353
- type: nauc_recall_at_1000_max
value: 33.8158
- type: nauc_recall_at_1000_std
value: 28.807
- type: nauc_recall_at_1000_diff1
value: 10.385900000000001
- type: nauc_precision_at_1_max
value: 21.2985
- type: nauc_precision_at_1_std
value: -4.6632
- type: nauc_precision_at_1_diff1
value: 36.1703
- type: nauc_precision_at_3_max
value: 23.8607
- type: nauc_precision_at_3_std
value: -1.2343
- type: nauc_precision_at_3_diff1
value: 26.056600000000003
- type: nauc_precision_at_5_max
value: 22.3303
- type: nauc_precision_at_5_std
value: -0.6769
- type: nauc_precision_at_5_diff1
value: 21.1393
- type: nauc_precision_at_10_max
value: 18.9603
- type: nauc_precision_at_10_std
value: 0.9261
- type: nauc_precision_at_10_diff1
value: 15.4373
- type: nauc_precision_at_20_max
value: 18.1666
- type: nauc_precision_at_20_std
value: 3.9616
- type: nauc_precision_at_20_diff1
value: 11.2774
- type: nauc_precision_at_100_max
value: 13.095399999999998
- type: nauc_precision_at_100_std
value: 7.7341999999999995
- type: nauc_precision_at_100_diff1
value: 3.3591999999999995
- type: nauc_precision_at_1000_max
value: 3.0223
- type: nauc_precision_at_1000_std
value: 4.3308
- type: nauc_precision_at_1000_diff1
value: -1.0134
- type: nauc_mrr_at_1_max
value: 21.2985
- type: nauc_mrr_at_1_std
value: -4.6632
- type: nauc_mrr_at_1_diff1
value: 36.1703
- type: nauc_mrr_at_3_max
value: 23.1376
- type: nauc_mrr_at_3_std
value: -3.228
- type: nauc_mrr_at_3_diff1
value: 33.150800000000004
- type: nauc_mrr_at_5_max
value: 22.7773
- type: nauc_mrr_at_5_std
value: -2.9971
- type: nauc_mrr_at_5_diff1
value: 31.8828
- type: nauc_mrr_at_10_max
value: 22.15
- type: nauc_mrr_at_10_std
value: -2.8863
- type: nauc_mrr_at_10_diff1
value: 31.465799999999998
- type: nauc_mrr_at_20_max
value: 22.3119
- type: nauc_mrr_at_20_std
value: -2.6858
- type: nauc_mrr_at_20_diff1
value: 31.446600000000004
- type: nauc_mrr_at_100_max
value: 22.3597
- type: nauc_mrr_at_100_std
value: -2.6425
- type: nauc_mrr_at_100_diff1
value: 31.4728
- type: nauc_mrr_at_1000_max
value: 22.3731
- type: nauc_mrr_at_1000_std
value: -2.6344
- type: nauc_mrr_at_1000_diff1
value: 31.489299999999997
- type: main_score
value: 31.391000000000002
- task:
type: Retrieval
dataset:
name: MTEB CQADupstackPhysicsRetrieval (default)
type: mteb/cqadupstack-physics
config: default
split: test
revision: 79531abbd1fb92d06c6d6315a0cbbbf5bb247ea4
metrics:
- type: ndcg_at_1
value: 38.690999999999995
- type: ndcg_at_3
value: 43.519000000000005
- type: ndcg_at_5
value: 45.862
- type: ndcg_at_10
value: 48.542
- type: ndcg_at_20
value: 50.40599999999999
- type: ndcg_at_100
value: 53.766000000000005
- type: ndcg_at_1000
value: 55.657000000000004
- type: map_at_1
value: 31.696
- type: map_at_3
value: 39.228
- type: map_at_5
value: 41.046
- type: map_at_10
value: 42.539
- type: map_at_20
value: 43.199
- type: map_at_100
value: 43.799
- type: map_at_1000
value: 43.902
- type: recall_at_1
value: 31.696
- type: recall_at_3
value: 46.482
- type: recall_at_5
value: 52.800999999999995
- type: recall_at_10
value: 60.650999999999996
- type: recall_at_20
value: 67.007
- type: recall_at_100
value: 82.669
- type: recall_at_1000
value: 95.02199999999999
- type: precision_at_1
value: 38.690999999999995
- type: precision_at_3
value: 20.404
- type: precision_at_5
value: 14.321
- type: precision_at_10
value: 8.709999999999999
- type: precision_at_20
value: 5.01
- type: precision_at_100
value: 1.315
- type: precision_at_1000
value: 0.165
- type: mrr_at_1
value: 38.690999999999995
- type: mrr_at_3
value: 45.684999999999995
- type: mrr_at_5
value: 47.1575
- type: mrr_at_10
value: 48.1562
- type: mrr_at_20
value: 48.582
- type: mrr_at_100
value: 48.9294
- type: mrr_at_1000
value: 48.968
- type: nauc_ndcg_at_1_max
value: 38.6678
- type: nauc_ndcg_at_1_std
value: -0.7451
- type: nauc_ndcg_at_1_diff1
value: 54.51089999999999
- type: nauc_ndcg_at_3_max
value: 38.5936
- type: nauc_ndcg_at_3_std
value: -1.185
- type: nauc_ndcg_at_3_diff1
value: 50.5312
- type: nauc_ndcg_at_5_max
value: 38.0602
- type: nauc_ndcg_at_5_std
value: -1.8034999999999999
- type: nauc_ndcg_at_5_diff1
value: 49.2837
- type: nauc_ndcg_at_10_max
value: 38.342
- type: nauc_ndcg_at_10_std
value: -0.9533
- type: nauc_ndcg_at_10_diff1
value: 49.0239
- type: nauc_ndcg_at_20_max
value: 39.2226
- type: nauc_ndcg_at_20_std
value: 0.6093999999999999
- type: nauc_ndcg_at_20_diff1
value: 48.7193
- type: nauc_ndcg_at_100_max
value: 39.3235
- type: nauc_ndcg_at_100_std
value: 2.3982
- type: nauc_ndcg_at_100_diff1
value: 48.5831
- type: nauc_ndcg_at_1000_max
value: 39.8333
- type: nauc_ndcg_at_1000_std
value: 2.4336
- type: nauc_ndcg_at_1000_diff1
value: 48.802099999999996
- type: nauc_map_at_1_max
value: 33.9405
- type: nauc_map_at_1_std
value: -3.9303999999999997
- type: nauc_map_at_1_diff1
value: 55.7491
- type: nauc_map_at_3_max
value: 36.550399999999996
- type: nauc_map_at_3_std
value: -2.7818
- type: nauc_map_at_3_diff1
value: 51.7018
- type: nauc_map_at_5_max
value: 36.999500000000005
- type: nauc_map_at_5_std
value: -2.7546999999999997
- type: nauc_map_at_5_diff1
value: 51.011300000000006
- type: nauc_map_at_10_max
value: 37.4157
- type: nauc_map_at_10_std
value: -1.9426999999999999
- type: nauc_map_at_10_diff1
value: 50.8876
- type: nauc_map_at_20_max
value: 37.729
- type: nauc_map_at_20_std
value: -1.3641999999999999
- type: nauc_map_at_20_diff1
value: 50.6926
- type: nauc_map_at_100_max
value: 37.7894
- type: nauc_map_at_100_std
value: -1.0082
- type: nauc_map_at_100_diff1
value: 50.6244
- type: nauc_map_at_1000_max
value: 37.8313
- type: nauc_map_at_1000_std
value: -0.9648
- type: nauc_map_at_1000_diff1
value: 50.6292
- type: nauc_recall_at_1_max
value: 33.9405
- type: nauc_recall_at_1_std
value: -3.9303999999999997
- type: nauc_recall_at_1_diff1
value: 55.7491
- type: nauc_recall_at_3_max
value: 35.6518
- type: nauc_recall_at_3_std
value: -3.166
- type: nauc_recall_at_3_diff1
value: 47.0684
- type: nauc_recall_at_5_max
value: 34.9043
- type: nauc_recall_at_5_std
value: -3.3676
- type: nauc_recall_at_5_diff1
value: 43.152499999999996
- type: nauc_recall_at_10_max
value: 35.2134
- type: nauc_recall_at_10_std
value: -1.0841
- type: nauc_recall_at_10_diff1
value: 41.1852
- type: nauc_recall_at_20_max
value: 37.417699999999996
- type: nauc_recall_at_20_std
value: 4.1923
- type: nauc_recall_at_20_diff1
value: 39.1819
- type: nauc_recall_at_100_max
value: 36.471900000000005
- type: nauc_recall_at_100_std
value: 19.8322
- type: nauc_recall_at_100_diff1
value: 34.0503
- type: nauc_recall_at_1000_max
value: 51.3256
- type: nauc_recall_at_1000_std
value: 46.2018
- type: nauc_recall_at_1000_diff1
value: 25.4702
- type: nauc_precision_at_1_max
value: 38.6678
- type: nauc_precision_at_1_std
value: -0.7451
- type: nauc_precision_at_1_diff1
value: 54.51089999999999
- type: nauc_precision_at_3_max
value: 39.763
- type: nauc_precision_at_3_std
value: 5.3316
- type: nauc_precision_at_3_diff1
value: 34.5965
- type: nauc_precision_at_5_max
value: 35.8709
- type: nauc_precision_at_5_std
value: 5.8021
- type: nauc_precision_at_5_diff1
value: 25.3427
- type: nauc_precision_at_10_max
value: 30.9008
- type: nauc_precision_at_10_std
value: 11.5405
- type: nauc_precision_at_10_diff1
value: 15.775
- type: nauc_precision_at_20_max
value: 28.403200000000002
- type: nauc_precision_at_20_std
value: 18.1899
- type: nauc_precision_at_20_diff1
value: 6.8557999999999995
- type: nauc_precision_at_100_max
value: 15.776499999999999
- type: nauc_precision_at_100_std
value: 21.5746
- type: nauc_precision_at_100_diff1
value: -7.0051000000000005
- type: nauc_precision_at_1000_max
value: 6.2587
- type: nauc_precision_at_1000_std
value: 18.0076
- type: nauc_precision_at_1000_diff1
value: -17.366400000000002
- type: nauc_mrr_at_1_max
value: 38.6678
- type: nauc_mrr_at_1_std
value: -0.7451
- type: nauc_mrr_at_1_diff1
value: 54.51089999999999
- type: nauc_mrr_at_3_max
value: 40.489399999999996
- type: nauc_mrr_at_3_std
value: -0.3225
- type: nauc_mrr_at_3_diff1
value: 51.41480000000001
- type: nauc_mrr_at_5_max
value: 40.1627
- type: nauc_mrr_at_5_std
value: -0.16219999999999998
- type: nauc_mrr_at_5_diff1
value: 50.560300000000005
- type: nauc_mrr_at_10_max
value: 40.125899999999994
- type: nauc_mrr_at_10_std
value: 0.0545
- type: nauc_mrr_at_10_diff1
value: 50.3771
- type: nauc_mrr_at_20_max
value: 40.2183
- type: nauc_mrr_at_20_std
value: 0.2818
- type: nauc_mrr_at_20_diff1
value: 50.387
- type: nauc_mrr_at_100_max
value: 40.201100000000004
- type: nauc_mrr_at_100_std
value: 0.43350000000000005
- type: nauc_mrr_at_100_diff1
value: 50.395100000000006
- type: nauc_mrr_at_1000_max
value: 40.2026
- type: nauc_mrr_at_1000_std
value: 0.42129999999999995
- type: nauc_mrr_at_1000_diff1
value: 50.405199999999994
- type: main_score
value: 48.542
- task:
type: Retrieval
dataset:
name: MTEB CQADupstackProgrammersRetrieval (default)
type: mteb/cqadupstack-programmers
config: default
split: test
revision: 6184bc1440d2dbc7612be22b50686b8826d22b32
metrics:
- type: ndcg_at_1
value: 33.333
- type: ndcg_at_3
value: 39.431
- type: ndcg_at_5
value: 42.120000000000005
- type: ndcg_at_10
value: 44.968
- type: ndcg_at_20
value: 47.099000000000004
- type: ndcg_at_100
value: 50.288
- type: ndcg_at_1000
value: 52.371
- type: map_at_1
value: 27.087
- type: map_at_3
value: 35.203
- type: map_at_5
value: 37.230999999999995
- type: map_at_10
value: 38.693
- type: map_at_20
value: 39.425
- type: map_at_100
value: 40.001
- type: map_at_1000
value: 40.119
- type: recall_at_1
value: 27.087
- type: recall_at_3
value: 42.846000000000004
- type: recall_at_5
value: 49.846000000000004
- type: recall_at_10
value: 58.083
- type: recall_at_20
value: 65.615
- type: recall_at_100
value: 80.831
- type: recall_at_1000
value: 94.474
- type: precision_at_1
value: 33.333
- type: precision_at_3
value: 19.139999999999997
- type: precision_at_5
value: 13.858
- type: precision_at_10
value: 8.413
- type: precision_at_20
value: 4.926
- type: precision_at_100
value: 1.275
- type: precision_at_1000
value: 0.165
- type: mrr_at_1
value: 33.3333
- type: mrr_at_3
value: 41.0959
- type: mrr_at_5
value: 42.6826
- type: mrr_at_10
value: 43.819900000000004
- type: mrr_at_20
value: 44.3087
- type: mrr_at_100
value: 44.6693
- type: mrr_at_1000
value: 44.7164
- type: nauc_ndcg_at_1_max
value: 36.037
- type: nauc_ndcg_at_1_std
value: -0.2425
- type: nauc_ndcg_at_1_diff1
value: 46.9443
- type: nauc_ndcg_at_3_max
value: 33.5311
- type: nauc_ndcg_at_3_std
value: 1.2205000000000001
- type: nauc_ndcg_at_3_diff1
value: 38.8166
- type: nauc_ndcg_at_5_max
value: 34.3091
- type: nauc_ndcg_at_5_std
value: 2.8846
- type: nauc_ndcg_at_5_diff1
value: 38.222899999999996
- type: nauc_ndcg_at_10_max
value: 34.443400000000004
- type: nauc_ndcg_at_10_std
value: 3.5393
- type: nauc_ndcg_at_10_diff1
value: 37.9537
- type: nauc_ndcg_at_20_max
value: 34.929500000000004
- type: nauc_ndcg_at_20_std
value: 4.4444
- type: nauc_ndcg_at_20_diff1
value: 37.811099999999996
- type: nauc_ndcg_at_100_max
value: 35.6285
- type: nauc_ndcg_at_100_std
value: 6.356199999999999
- type: nauc_ndcg_at_100_diff1
value: 37.4749
- type: nauc_ndcg_at_1000_max
value: 35.8451
- type: nauc_ndcg_at_1000_std
value: 6.1044
- type: nauc_ndcg_at_1000_diff1
value: 38.5065
- type: nauc_map_at_1_max
value: 30.017100000000003
- type: nauc_map_at_1_std
value: -5.056299999999999
- type: nauc_map_at_1_diff1
value: 46.4338
- type: nauc_map_at_3_max
value: 31.936999999999998
- type: nauc_map_at_3_std
value: -1.0591
- type: nauc_map_at_3_diff1
value: 39.8778
- type: nauc_map_at_5_max
value: 32.859100000000005
- type: nauc_map_at_5_std
value: 0.42050000000000004
- type: nauc_map_at_5_diff1
value: 39.7368
- type: nauc_map_at_10_max
value: 33.042899999999996
- type: nauc_map_at_10_std
value: 0.8545
- type: nauc_map_at_10_diff1
value: 39.5713
- type: nauc_map_at_20_max
value: 33.3227
- type: nauc_map_at_20_std
value: 1.3109000000000002
- type: nauc_map_at_20_diff1
value: 39.5833
- type: nauc_map_at_100_max
value: 33.537
- type: nauc_map_at_100_std
value: 1.7505
- type: nauc_map_at_100_diff1
value: 39.6109
- type: nauc_map_at_1000_max
value: 33.578
- type: nauc_map_at_1000_std
value: 1.7679
- type: nauc_map_at_1000_diff1
value: 39.677299999999995
- type: nauc_recall_at_1_max
value: 30.017100000000003
- type: nauc_recall_at_1_std
value: -5.056299999999999
- type: nauc_recall_at_1_diff1
value: 46.4338
- type: nauc_recall_at_3_max
value: 31.3062
- type: nauc_recall_at_3_std
value: 1.6736
- type: nauc_recall_at_3_diff1
value: 32.743
- type: nauc_recall_at_5_max
value: 32.7338
- type: nauc_recall_at_5_std
value: 5.9388000000000005
- type: nauc_recall_at_5_diff1
value: 30.8784
- type: nauc_recall_at_10_max
value: 32.9312
- type: nauc_recall_at_10_std
value: 8.1993
- type: nauc_recall_at_10_diff1
value: 29.4248
- type: nauc_recall_at_20_max
value: 33.9206
- type: nauc_recall_at_20_std
value: 10.673
- type: nauc_recall_at_20_diff1
value: 27.377200000000002
- type: nauc_recall_at_100_max
value: 37.119
- type: nauc_recall_at_100_std
value: 24.6249
- type: nauc_recall_at_100_diff1
value: 19.403699999999997
- type: nauc_recall_at_1000_max
value: 52.2307
- type: nauc_recall_at_1000_std
value: 53.405199999999994
- type: nauc_recall_at_1000_diff1
value: 24.122799999999998
- type: nauc_precision_at_1_max
value: 36.037
- type: nauc_precision_at_1_std
value: -0.2425
- type: nauc_precision_at_1_diff1
value: 46.9443
- type: nauc_precision_at_3_max
value: 34.110600000000005
- type: nauc_precision_at_3_std
value: 8.7398
- type: nauc_precision_at_3_diff1
value: 27.441
- type: nauc_precision_at_5_max
value: 33.0042
- type: nauc_precision_at_5_std
value: 13.7932
- type: nauc_precision_at_5_diff1
value: 23.011300000000002
- type: nauc_precision_at_10_max
value: 28.8408
- type: nauc_precision_at_10_std
value: 14.4897
- type: nauc_precision_at_10_diff1
value: 18.0244
- type: nauc_precision_at_20_max
value: 25.5054
- type: nauc_precision_at_20_std
value: 16.5918
- type: nauc_precision_at_20_diff1
value: 14.665500000000002
- type: nauc_precision_at_100_max
value: 18.084400000000002
- type: nauc_precision_at_100_std
value: 20.7595
- type: nauc_precision_at_100_diff1
value: 6.2877
- type: nauc_precision_at_1000_max
value: 6.778099999999999
- type: nauc_precision_at_1000_std
value: 9.0734
- type: nauc_precision_at_1000_diff1
value: 5.6030999999999995
- type: nauc_mrr_at_1_max
value: 36.037
- type: nauc_mrr_at_1_std
value: -0.2425
- type: nauc_mrr_at_1_diff1
value: 46.9443
- type: nauc_mrr_at_3_max
value: 36.0423
- type: nauc_mrr_at_3_std
value: 3.0699
- type: nauc_mrr_at_3_diff1
value: 40.6527
- type: nauc_mrr_at_5_max
value: 36.3279
- type: nauc_mrr_at_5_std
value: 4.0948
- type: nauc_mrr_at_5_diff1
value: 40.1667
- type: nauc_mrr_at_10_max
value: 36.3884
- type: nauc_mrr_at_10_std
value: 4.5214
- type: nauc_mrr_at_10_diff1
value: 40.3499
- type: nauc_mrr_at_20_max
value: 36.3977
- type: nauc_mrr_at_20_std
value: 4.4357
- type: nauc_mrr_at_20_diff1
value: 40.342800000000004
- type: nauc_mrr_at_100_max
value: 36.422900000000006
- type: nauc_mrr_at_100_std
value: 4.501200000000001
- type: nauc_mrr_at_100_diff1
value: 40.3487
- type: nauc_mrr_at_1000_max
value: 36.4317
- type: nauc_mrr_at_1000_std
value: 4.4942
- type: nauc_mrr_at_1000_diff1
value: 40.3843
- type: main_score
value: 44.968
- task:
type: Retrieval
dataset:
name: MTEB CQADupstackRetrieval (default)
type: CQADupstackRetrieval_is_a_combined_dataset
config: default
split: test
revision: CQADupstackRetrieval_is_a_combined_dataset
metrics:
- type: main_score
value: 42.51058333333334
- type: ndcg_at_10
value: 42.51058333333334
- task:
type: Retrieval
dataset:
name: MTEB CQADupstackStatsRetrieval (default)
type: mteb/cqadupstack-stats
config: default
split: test
revision: 65ac3a16b8e91f9cee4c9828cc7c335575432a2a
metrics:
- type: ndcg_at_1
value: 28.066999999999997
- type: ndcg_at_3
value: 33.326
- type: ndcg_at_5
value: 35.432
- type: ndcg_at_10
value: 37.711
- type: ndcg_at_20
value: 39.377
- type: ndcg_at_100
value: 42.437999999999995
- type: ndcg_at_1000
value: 44.653999999999996
- type: map_at_1
value: 24.91
- type: map_at_3
value: 30.641000000000002
- type: map_at_5
value: 32.003
- type: map_at_10
value: 33.027
- type: map_at_20
value: 33.52
- type: map_at_100
value: 33.958
- type: map_at_1000
value: 34.048
- type: recall_at_1
value: 24.91
- type: recall_at_3
value: 36.931000000000004
- type: recall_at_5
value: 42.257
- type: recall_at_10
value: 49.248
- type: recall_at_20
value: 55.504
- type: recall_at_100
value: 71.086
- type: recall_at_1000
value: 87.209
- type: precision_at_1
value: 28.066999999999997
- type: precision_at_3
value: 14.571000000000002
- type: precision_at_5
value: 10.152999999999999
- type: precision_at_10
value: 5.982
- type: precision_at_20
value: 3.405
- type: precision_at_100
value: 0.903
- type: precision_at_1000
value: 0.11800000000000001
- type: mrr_at_1
value: 28.067500000000003
- type: mrr_at_3
value: 33.8957
- type: mrr_at_5
value: 35.0997
- type: mrr_at_10
value: 36.0272
- type: mrr_at_20
value: 36.4454
- type: mrr_at_100
value: 36.8325
- type: mrr_at_1000
value: 36.8906
- type: nauc_ndcg_at_1_max
value: 41.64
- type: nauc_ndcg_at_1_std
value: -3.0991999999999997
- type: nauc_ndcg_at_1_diff1
value: 52.059
- type: nauc_ndcg_at_3_max
value: 38.3407
- type: nauc_ndcg_at_3_std
value: -2.0187
- type: nauc_ndcg_at_3_diff1
value: 44.6053
- type: nauc_ndcg_at_5_max
value: 39.5482
- type: nauc_ndcg_at_5_std
value: 0.6605
- type: nauc_ndcg_at_5_diff1
value: 44.1187
- type: nauc_ndcg_at_10_max
value: 40.2625
- type: nauc_ndcg_at_10_std
value: 1.6514999999999997
- type: nauc_ndcg_at_10_diff1
value: 43.170500000000004
- type: nauc_ndcg_at_20_max
value: 40.067
- type: nauc_ndcg_at_20_std
value: 2.1887
- type: nauc_ndcg_at_20_diff1
value: 42.8359
- type: nauc_ndcg_at_100_max
value: 41.749900000000004
- type: nauc_ndcg_at_100_std
value: 4.3462
- type: nauc_ndcg_at_100_diff1
value: 42.1422
- type: nauc_ndcg_at_1000_max
value: 41.4899
- type: nauc_ndcg_at_1000_std
value: 3.9956
- type: nauc_ndcg_at_1000_diff1
value: 42.4235
- type: nauc_map_at_1_max
value: 39.1049
- type: nauc_map_at_1_std
value: -7.072000000000001
- type: nauc_map_at_1_diff1
value: 53.76840000000001
- type: nauc_map_at_3_max
value: 38.3832
- type: nauc_map_at_3_std
value: -4.0869
- type: nauc_map_at_3_diff1
value: 46.848600000000005
- type: nauc_map_at_5_max
value: 39.4646
- type: nauc_map_at_5_std
value: -2.0288
- type: nauc_map_at_5_diff1
value: 46.3888
- type: nauc_map_at_10_max
value: 39.8593
- type: nauc_map_at_10_std
value: -1.4203000000000001
- type: nauc_map_at_10_diff1
value: 45.9306
- type: nauc_map_at_20_max
value: 39.835300000000004
- type: nauc_map_at_20_std
value: -1.2231
- type: nauc_map_at_20_diff1
value: 45.8283
- type: nauc_map_at_100_max
value: 40.1343
- type: nauc_map_at_100_std
value: -0.9245
- type: nauc_map_at_100_diff1
value: 45.7762
- type: nauc_map_at_1000_max
value: 40.1356
- type: nauc_map_at_1000_std
value: -0.9329000000000001
- type: nauc_map_at_1000_diff1
value: 45.785
- type: nauc_recall_at_1_max
value: 39.1049
- type: nauc_recall_at_1_std
value: -7.072000000000001
- type: nauc_recall_at_1_diff1
value: 53.76840000000001
- type: nauc_recall_at_3_max
value: 34.5115
- type: nauc_recall_at_3_std
value: -1.5186
- type: nauc_recall_at_3_diff1
value: 39.2881
- type: nauc_recall_at_5_max
value: 36.8705
- type: nauc_recall_at_5_std
value: 5.2115
- type: nauc_recall_at_5_diff1
value: 37.2112
- type: nauc_recall_at_10_max
value: 38.9486
- type: nauc_recall_at_10_std
value: 8.558
- type: nauc_recall_at_10_diff1
value: 34.027499999999996
- type: nauc_recall_at_20_max
value: 37.4174
- type: nauc_recall_at_20_std
value: 10.7121
- type: nauc_recall_at_20_diff1
value: 31.6372
- type: nauc_recall_at_100_max
value: 45.7135
- type: nauc_recall_at_100_std
value: 26.958900000000003
- type: nauc_recall_at_100_diff1
value: 22.6293
- type: nauc_recall_at_1000_max
value: 45.8455
- type: nauc_recall_at_1000_std
value: 41.8128
- type: nauc_recall_at_1000_diff1
value: 11.1735
- type: nauc_precision_at_1_max
value: 41.64
- type: nauc_precision_at_1_std
value: -3.0991999999999997
- type: nauc_precision_at_1_diff1
value: 52.059
- type: nauc_precision_at_3_max
value: 37.5109
- type: nauc_precision_at_3_std
value: 4.5869
- type: nauc_precision_at_3_diff1
value: 35.604200000000006
- type: nauc_precision_at_5_max
value: 39.441500000000005
- type: nauc_precision_at_5_std
value: 12.413499999999999
- type: nauc_precision_at_5_diff1
value: 31.566699999999997
- type: nauc_precision_at_10_max
value: 39.3943
- type: nauc_precision_at_10_std
value: 14.4375
- type: nauc_precision_at_10_diff1
value: 26.4044
- type: nauc_precision_at_20_max
value: 34.6082
- type: nauc_precision_at_20_std
value: 15.573899999999998
- type: nauc_precision_at_20_diff1
value: 21.3312
- type: nauc_precision_at_100_max
value: 33.6787
- type: nauc_precision_at_100_std
value: 24.4628
- type: nauc_precision_at_100_diff1
value: 9.238399999999999
- type: nauc_precision_at_1000_max
value: 15.7002
- type: nauc_precision_at_1000_std
value: 17.6244
- type: nauc_precision_at_1000_diff1
value: -2.8333
- type: nauc_mrr_at_1_max
value: 41.64
- type: nauc_mrr_at_1_std
value: -3.0991999999999997
- type: nauc_mrr_at_1_diff1
value: 52.059
- type: nauc_mrr_at_3_max
value: 40.2887
- type: nauc_mrr_at_3_std
value: -0.48650000000000004
- type: nauc_mrr_at_3_diff1
value: 46.2812
- type: nauc_mrr_at_5_max
value: 40.792899999999996
- type: nauc_mrr_at_5_std
value: 0.7635000000000001
- type: nauc_mrr_at_5_diff1
value: 45.8179
- type: nauc_mrr_at_10_max
value: 40.970099999999995
- type: nauc_mrr_at_10_std
value: 0.9508000000000001
- type: nauc_mrr_at_10_diff1
value: 45.4065
- type: nauc_mrr_at_20_max
value: 40.9322
- type: nauc_mrr_at_20_std
value: 1.0284
- type: nauc_mrr_at_20_diff1
value: 45.440999999999995
- type: nauc_mrr_at_100_max
value: 41.1209
- type: nauc_mrr_at_100_std
value: 1.2597
- type: nauc_mrr_at_100_diff1
value: 45.3654
- type: nauc_mrr_at_1000_max
value: 41.1143
- type: nauc_mrr_at_1000_std
value: 1.2467000000000001
- type: nauc_mrr_at_1000_diff1
value: 45.3792
- type: main_score
value: 37.711
- task:
type: Retrieval
dataset:
name: MTEB CQADupstackTexRetrieval (default)
type: mteb/cqadupstack-tex
config: default
split: test
revision: 46989137a86843e03a6195de44b09deda022eec7
metrics:
- type: ndcg_at_1
value: 21.37
- type: ndcg_at_3
value: 25.308000000000003
- type: ndcg_at_5
value: 27.211999999999996
- type: ndcg_at_10
value: 29.759999999999998
- type: ndcg_at_20
value: 31.806
- type: ndcg_at_100
value: 35.148
- type: ndcg_at_1000
value: 38.115
- type: map_at_1
value: 17.635
- type: map_at_3
value: 22.537
- type: map_at_5
value: 23.834
- type: map_at_10
value: 24.984
- type: map_at_20
value: 25.613999999999997
- type: map_at_100
value: 26.125
- type: map_at_1000
value: 26.256
- type: recall_at_1
value: 17.635
- type: recall_at_3
value: 27.759
- type: recall_at_5
value: 32.688
- type: recall_at_10
value: 40.326
- type: recall_at_20
value: 47.865
- type: recall_at_100
value: 64.43799999999999
- type: recall_at_1000
value: 85.589
- type: precision_at_1
value: 21.37
- type: precision_at_3
value: 11.928999999999998
- type: precision_at_5
value: 8.679
- type: precision_at_10
value: 5.502
- type: precision_at_20
value: 3.345
- type: precision_at_100
value: 0.962
- type: precision_at_1000
value: 0.13899999999999998
- type: mrr_at_1
value: 21.3696
- type: mrr_at_3
value: 26.4854
- type: mrr_at_5
value: 27.726
- type: mrr_at_10
value: 28.842499999999998
- type: mrr_at_20
value: 29.3902
- type: mrr_at_100
value: 29.7846
- type: mrr_at_1000
value: 29.860799999999998
- type: nauc_ndcg_at_1_max
value: 31.770300000000002
- type: nauc_ndcg_at_1_std
value: -4.784999999999999
- type: nauc_ndcg_at_1_diff1
value: 42.290499999999994
- type: nauc_ndcg_at_3_max
value: 31.1434
- type: nauc_ndcg_at_3_std
value: -2.8424
- type: nauc_ndcg_at_3_diff1
value: 36.7329
- type: nauc_ndcg_at_5_max
value: 31.1525
- type: nauc_ndcg_at_5_std
value: -2.2824
- type: nauc_ndcg_at_5_diff1
value: 35.517199999999995
- type: nauc_ndcg_at_10_max
value: 31.3549
- type: nauc_ndcg_at_10_std
value: -1.089
- type: nauc_ndcg_at_10_diff1
value: 34.9647
- type: nauc_ndcg_at_20_max
value: 31.3283
- type: nauc_ndcg_at_20_std
value: -0.5032
- type: nauc_ndcg_at_20_diff1
value: 34.73
- type: nauc_ndcg_at_100_max
value: 31.3324
- type: nauc_ndcg_at_100_std
value: 0.8308
- type: nauc_ndcg_at_100_diff1
value: 34.0739
- type: nauc_ndcg_at_1000_max
value: 31.563799999999997
- type: nauc_ndcg_at_1000_std
value: 1.0345
- type: nauc_ndcg_at_1000_diff1
value: 34.321400000000004
- type: nauc_map_at_1_max
value: 29.935299999999998
- type: nauc_map_at_1_std
value: -4.6685
- type: nauc_map_at_1_diff1
value: 43.6434
- type: nauc_map_at_3_max
value: 30.476
- type: nauc_map_at_3_std
value: -3.3331
- type: nauc_map_at_3_diff1
value: 38.6884
- type: nauc_map_at_5_max
value: 30.625200000000003
- type: nauc_map_at_5_std
value: -3.0722
- type: nauc_map_at_5_diff1
value: 37.845
- type: nauc_map_at_10_max
value: 30.8581
- type: nauc_map_at_10_std
value: -2.5201000000000002
- type: nauc_map_at_10_diff1
value: 37.5217
- type: nauc_map_at_20_max
value: 30.9267
- type: nauc_map_at_20_std
value: -2.3167
- type: nauc_map_at_20_diff1
value: 37.4216
- type: nauc_map_at_100_max
value: 31.0064
- type: nauc_map_at_100_std
value: -2.0629999999999997
- type: nauc_map_at_100_diff1
value: 37.3075
- type: nauc_map_at_1000_max
value: 31.0478
- type: nauc_map_at_1000_std
value: -2.0301
- type: nauc_map_at_1000_diff1
value: 37.3077
- type: nauc_recall_at_1_max
value: 29.935299999999998
- type: nauc_recall_at_1_std
value: -4.6685
- type: nauc_recall_at_1_diff1
value: 43.6434
- type: nauc_recall_at_3_max
value: 29.2327
- type: nauc_recall_at_3_std
value: -1.8466
- type: nauc_recall_at_3_diff1
value: 32.5214
- type: nauc_recall_at_5_max
value: 28.8576
- type: nauc_recall_at_5_std
value: -0.8358000000000001
- type: nauc_recall_at_5_diff1
value: 29.329499999999996
- type: nauc_recall_at_10_max
value: 28.8851
- type: nauc_recall_at_10_std
value: 2.3084000000000002
- type: nauc_recall_at_10_diff1
value: 27.3001
- type: nauc_recall_at_20_max
value: 28.0772
- type: nauc_recall_at_20_std
value: 4.2632
- type: nauc_recall_at_20_diff1
value: 25.6873
- type: nauc_recall_at_100_max
value: 27.4461
- type: nauc_recall_at_100_std
value: 11.9175
- type: nauc_recall_at_100_diff1
value: 20.7784
- type: nauc_recall_at_1000_max
value: 27.1262
- type: nauc_recall_at_1000_std
value: 24.4024
- type: nauc_recall_at_1000_diff1
value: 14.5445
- type: nauc_precision_at_1_max
value: 31.770300000000002
- type: nauc_precision_at_1_std
value: -4.784999999999999
- type: nauc_precision_at_1_diff1
value: 42.290499999999994
- type: nauc_precision_at_3_max
value: 32.5608
- type: nauc_precision_at_3_std
value: -1.3823999999999999
- type: nauc_precision_at_3_diff1
value: 30.9278
- type: nauc_precision_at_5_max
value: 32.0685
- type: nauc_precision_at_5_std
value: -0.2231
- type: nauc_precision_at_5_diff1
value: 26.8139
- type: nauc_precision_at_10_max
value: 31.8615
- type: nauc_precision_at_10_std
value: 3.3291
- type: nauc_precision_at_10_diff1
value: 22.608800000000002
- type: nauc_precision_at_20_max
value: 30.250799999999998
- type: nauc_precision_at_20_std
value: 5.242
- type: nauc_precision_at_20_diff1
value: 19.532
- type: nauc_precision_at_100_max
value: 25.2481
- type: nauc_precision_at_100_std
value: 9.711599999999999
- type: nauc_precision_at_100_diff1
value: 9.5108
- type: nauc_precision_at_1000_max
value: 19.072
- type: nauc_precision_at_1000_std
value: 9.0718
- type: nauc_precision_at_1000_diff1
value: -0.21090000000000003
- type: nauc_mrr_at_1_max
value: 31.770300000000002
- type: nauc_mrr_at_1_std
value: -4.784999999999999
- type: nauc_mrr_at_1_diff1
value: 42.290499999999994
- type: nauc_mrr_at_3_max
value: 31.5869
- type: nauc_mrr_at_3_std
value: -3.2058999999999997
- type: nauc_mrr_at_3_diff1
value: 37.3799
- type: nauc_mrr_at_5_max
value: 31.675199999999997
- type: nauc_mrr_at_5_std
value: -2.7127
- type: nauc_mrr_at_5_diff1
value: 36.5429
- type: nauc_mrr_at_10_max
value: 31.7662
- type: nauc_mrr_at_10_std
value: -2.314
- type: nauc_mrr_at_10_diff1
value: 36.3532
- type: nauc_mrr_at_20_max
value: 31.771300000000004
- type: nauc_mrr_at_20_std
value: -2.1448
- type: nauc_mrr_at_20_diff1
value: 36.3367
- type: nauc_mrr_at_100_max
value: 31.767899999999997
- type: nauc_mrr_at_100_std
value: -2.0333
- type: nauc_mrr_at_100_diff1
value: 36.2815
- type: nauc_mrr_at_1000_max
value: 31.7795
- type: nauc_mrr_at_1000_std
value: -2.0261
- type: nauc_mrr_at_1000_diff1
value: 36.2999
- type: main_score
value: 29.759999999999998
- task:
type: Retrieval
dataset:
name: MTEB CQADupstackUnixRetrieval (default)
type: mteb/cqadupstack-unix
config: default
split: test
revision: 6c6430d3a6d36f8d2a829195bc5dc94d7e063e53
metrics:
- type: ndcg_at_1
value: 33.302
- type: ndcg_at_3
value: 38.403
- type: ndcg_at_5
value: 40.319
- type: ndcg_at_10
value: 42.834
- type: ndcg_at_20
value: 44.932
- type: ndcg_at_100
value: 47.833
- type: ndcg_at_1000
value: 50.157
- type: map_at_1
value: 28.457
- type: map_at_3
value: 35.184
- type: map_at_5
value: 36.532
- type: map_at_10
value: 37.714
- type: map_at_20
value: 38.340999999999994
- type: map_at_100
value: 38.797
- type: map_at_1000
value: 38.903999999999996
- type: recall_at_1
value: 28.457
- type: recall_at_3
value: 41.937999999999995
- type: recall_at_5
value: 46.911
- type: recall_at_10
value: 54.303000000000004
- type: recall_at_20
value: 61.906000000000006
- type: recall_at_100
value: 76.074
- type: recall_at_1000
value: 92.191
- type: precision_at_1
value: 33.302
- type: precision_at_3
value: 17.382
- type: precision_at_5
value: 11.922
- type: precision_at_10
value: 7.08
- type: precision_at_20
value: 4.137
- type: precision_at_100
value: 1.064
- type: precision_at_1000
value: 0.13799999999999998
- type: mrr_at_1
value: 33.3022
- type: mrr_at_3
value: 39.5056
- type: mrr_at_5
value: 40.7276
- type: mrr_at_10
value: 41.7227
- type: mrr_at_20
value: 42.270799999999994
- type: mrr_at_100
value: 42.5991
- type: mrr_at_1000
value: 42.653999999999996
- type: nauc_ndcg_at_1_max
value: 41.5343
- type: nauc_ndcg_at_1_std
value: -2.8242
- type: nauc_ndcg_at_1_diff1
value: 55.388099999999994
- type: nauc_ndcg_at_3_max
value: 41.531800000000004
- type: nauc_ndcg_at_3_std
value: -0.0958
- type: nauc_ndcg_at_3_diff1
value: 50.5951
- type: nauc_ndcg_at_5_max
value: 41.0756
- type: nauc_ndcg_at_5_std
value: 0.7116
- type: nauc_ndcg_at_5_diff1
value: 49.0397
- type: nauc_ndcg_at_10_max
value: 40.5656
- type: nauc_ndcg_at_10_std
value: 1.2275
- type: nauc_ndcg_at_10_diff1
value: 48.1935
- type: nauc_ndcg_at_20_max
value: 39.967000000000006
- type: nauc_ndcg_at_20_std
value: 1.2213
- type: nauc_ndcg_at_20_diff1
value: 47.5459
- type: nauc_ndcg_at_100_max
value: 40.2487
- type: nauc_ndcg_at_100_std
value: 2.6310000000000002
- type: nauc_ndcg_at_100_diff1
value: 47.3499
- type: nauc_ndcg_at_1000_max
value: 40.802
- type: nauc_ndcg_at_1000_std
value: 2.9029
- type: nauc_ndcg_at_1000_diff1
value: 47.893299999999996
- type: nauc_map_at_1_max
value: 40.0689
- type: nauc_map_at_1_std
value: -3.2761
- type: nauc_map_at_1_diff1
value: 56.685399999999994
- type: nauc_map_at_3_max
value: 41.350500000000004
- type: nauc_map_at_3_std
value: -0.6871999999999999
- type: nauc_map_at_3_diff1
value: 52.737100000000005
- type: nauc_map_at_5_max
value: 41.1119
- type: nauc_map_at_5_std
value: -0.23340000000000002
- type: nauc_map_at_5_diff1
value: 51.5269
- type: nauc_map_at_10_max
value: 40.860400000000006
- type: nauc_map_at_10_std
value: -0.08760000000000001
- type: nauc_map_at_10_diff1
value: 51.01369999999999
- type: nauc_map_at_20_max
value: 40.5859
- type: nauc_map_at_20_std
value: -0.154
- type: nauc_map_at_20_diff1
value: 50.744699999999995
- type: nauc_map_at_100_max
value: 40.646300000000004
- type: nauc_map_at_100_std
value: 0.10189999999999999
- type: nauc_map_at_100_diff1
value: 50.7085
- type: nauc_map_at_1000_max
value: 40.6731
- type: nauc_map_at_1000_std
value: 0.1394
- type: nauc_map_at_1000_diff1
value: 50.708
- type: nauc_recall_at_1_max
value: 40.0689
- type: nauc_recall_at_1_std
value: -3.2761
- type: nauc_recall_at_1_diff1
value: 56.685399999999994
- type: nauc_recall_at_3_max
value: 40.5338
- type: nauc_recall_at_3_std
value: 1.4996
- type: nauc_recall_at_3_diff1
value: 46.9882
- type: nauc_recall_at_5_max
value: 39.745999999999995
- type: nauc_recall_at_5_std
value: 3.7415
- type: nauc_recall_at_5_diff1
value: 42.7628
- type: nauc_recall_at_10_max
value: 37.6122
- type: nauc_recall_at_10_std
value: 5.1345
- type: nauc_recall_at_10_diff1
value: 39.2683
- type: nauc_recall_at_20_max
value: 34.9745
- type: nauc_recall_at_20_std
value: 5.7971
- type: nauc_recall_at_20_diff1
value: 35.6486
- type: nauc_recall_at_100_max
value: 35.1278
- type: nauc_recall_at_100_std
value: 16.569
- type: nauc_recall_at_100_diff1
value: 30.4082
- type: nauc_recall_at_1000_max
value: 48.1561
- type: nauc_recall_at_1000_std
value: 46.2123
- type: nauc_recall_at_1000_diff1
value: 28.9314
- type: nauc_precision_at_1_max
value: 41.5343
- type: nauc_precision_at_1_std
value: -2.8242
- type: nauc_precision_at_1_diff1
value: 55.388099999999994
- type: nauc_precision_at_3_max
value: 37.9897
- type: nauc_precision_at_3_std
value: 2.563
- type: nauc_precision_at_3_diff1
value: 37.253
- type: nauc_precision_at_5_max
value: 33.9735
- type: nauc_precision_at_5_std
value: 3.5601000000000003
- type: nauc_precision_at_5_diff1
value: 29.017300000000002
- type: nauc_precision_at_10_max
value: 27.8221
- type: nauc_precision_at_10_std
value: 4.3591999999999995
- type: nauc_precision_at_10_diff1
value: 20.7948
- type: nauc_precision_at_20_max
value: 21.0119
- type: nauc_precision_at_20_std
value: 4.4604
- type: nauc_precision_at_20_diff1
value: 12.5115
- type: nauc_precision_at_100_max
value: 11.1615
- type: nauc_precision_at_100_std
value: 10.1361
- type: nauc_precision_at_100_diff1
value: -2.5748
- type: nauc_precision_at_1000_max
value: -3.5173
- type: nauc_precision_at_1000_std
value: 6.248
- type: nauc_precision_at_1000_diff1
value: -17.6147
- type: nauc_mrr_at_1_max
value: 41.5343
- type: nauc_mrr_at_1_std
value: -2.8242
- type: nauc_mrr_at_1_diff1
value: 55.388099999999994
- type: nauc_mrr_at_3_max
value: 41.599199999999996
- type: nauc_mrr_at_3_std
value: -0.5716
- type: nauc_mrr_at_3_diff1
value: 50.932100000000005
- type: nauc_mrr_at_5_max
value: 41.2312
- type: nauc_mrr_at_5_std
value: -0.2443
- type: nauc_mrr_at_5_diff1
value: 49.9174
- type: nauc_mrr_at_10_max
value: 41.0053
- type: nauc_mrr_at_10_std
value: 0.0628
- type: nauc_mrr_at_10_diff1
value: 49.6375
- type: nauc_mrr_at_20_max
value: 40.930499999999995
- type: nauc_mrr_at_20_std
value: -0.063
- type: nauc_mrr_at_20_diff1
value: 49.6391
- type: nauc_mrr_at_100_max
value: 40.9473
- type: nauc_mrr_at_100_std
value: 0.0646
- type: nauc_mrr_at_100_diff1
value: 49.6701
- type: nauc_mrr_at_1000_max
value: 40.9676
- type: nauc_mrr_at_1000_std
value: 0.0838
- type: nauc_mrr_at_1000_diff1
value: 49.695299999999996
- type: main_score
value: 42.834
- task:
type: Retrieval
dataset:
name: MTEB CQADupstackWebmastersRetrieval (default)
type: mteb/cqadupstack-webmasters
config: default
split: test
revision: 160c094312a0e1facb97e55eeddb698c0abe3571
metrics:
- type: ndcg_at_1
value: 32.411
- type: ndcg_at_3
value: 37.911
- type: ndcg_at_5
value: 39.983000000000004
- type: ndcg_at_10
value: 42.321999999999996
- type: ndcg_at_20
value: 44.855000000000004
- type: ndcg_at_100
value: 48.515
- type: ndcg_at_1000
value: 50.845
- type: map_at_1
value: 27.062
- type: map_at_3
value: 33.689
- type: map_at_5
value: 35.161
- type: map_at_10
value: 36.492000000000004
- type: map_at_20
value: 37.486999999999995
- type: map_at_100
value: 38.235
- type: map_at_1000
value: 38.421
- type: recall_at_1
value: 27.062
- type: recall_at_3
value: 40.459
- type: recall_at_5
value: 46.221000000000004
- type: recall_at_10
value: 53.348
- type: recall_at_20
value: 62.852
- type: recall_at_100
value: 80.582
- type: recall_at_1000
value: 95.14099999999999
- type: precision_at_1
value: 32.411
- type: precision_at_3
value: 17.984
- type: precision_at_5
value: 12.767000000000001
- type: precision_at_10
value: 7.945
- type: precision_at_20
value: 5.0
- type: precision_at_100
value: 1.534
- type: precision_at_1000
value: 0.234
- type: mrr_at_1
value: 32.4111
- type: mrr_at_3
value: 38.8011
- type: mrr_at_5
value: 40.2437
- type: mrr_at_10
value: 41.1494
- type: mrr_at_20
value: 41.8962
- type: mrr_at_100
value: 42.275800000000004
- type: mrr_at_1000
value: 42.3273
- type: nauc_ndcg_at_1_max
value: 27.961799999999997
- type: nauc_ndcg_at_1_std
value: 1.9207999999999998
- type: nauc_ndcg_at_1_diff1
value: 47.9837
- type: nauc_ndcg_at_3_max
value: 28.009099999999997
- type: nauc_ndcg_at_3_std
value: 1.212
- type: nauc_ndcg_at_3_diff1
value: 42.1361
- type: nauc_ndcg_at_5_max
value: 27.304299999999998
- type: nauc_ndcg_at_5_std
value: 1.4559
- type: nauc_ndcg_at_5_diff1
value: 40.8799
- type: nauc_ndcg_at_10_max
value: 26.0726
- type: nauc_ndcg_at_10_std
value: 1.5731
- type: nauc_ndcg_at_10_diff1
value: 38.9119
- type: nauc_ndcg_at_20_max
value: 28.139799999999997
- type: nauc_ndcg_at_20_std
value: 3.0962
- type: nauc_ndcg_at_20_diff1
value: 39.0918
- type: nauc_ndcg_at_100_max
value: 29.0945
- type: nauc_ndcg_at_100_std
value: 5.6239
- type: nauc_ndcg_at_100_diff1
value: 39.4526
- type: nauc_ndcg_at_1000_max
value: 28.7139
- type: nauc_ndcg_at_1000_std
value: 4.3576
- type: nauc_ndcg_at_1000_diff1
value: 40.1353
- type: nauc_map_at_1_max
value: 26.4001
- type: nauc_map_at_1_std
value: -2.4035
- type: nauc_map_at_1_diff1
value: 50.6355
- type: nauc_map_at_3_max
value: 27.6775
- type: nauc_map_at_3_std
value: -1.2323
- type: nauc_map_at_3_diff1
value: 45.1028
- type: nauc_map_at_5_max
value: 27.7501
- type: nauc_map_at_5_std
value: -1.0206
- type: nauc_map_at_5_diff1
value: 44.137100000000004
- type: nauc_map_at_10_max
value: 27.3169
- type: nauc_map_at_10_std
value: -0.6242
- type: nauc_map_at_10_diff1
value: 42.992799999999995
- type: nauc_map_at_20_max
value: 27.9088
- type: nauc_map_at_20_std
value: 0.369
- type: nauc_map_at_20_diff1
value: 42.7076
- type: nauc_map_at_100_max
value: 28.0018
- type: nauc_map_at_100_std
value: 1.0477999999999998
- type: nauc_map_at_100_diff1
value: 42.663000000000004
- type: nauc_map_at_1000_max
value: 27.8892
- type: nauc_map_at_1000_std
value: 1.0114
- type: nauc_map_at_1000_diff1
value: 42.6802
- type: nauc_recall_at_1_max
value: 26.4001
- type: nauc_recall_at_1_std
value: -2.4035
- type: nauc_recall_at_1_diff1
value: 50.6355
- type: nauc_recall_at_3_max
value: 26.4415
- type: nauc_recall_at_3_std
value: 0.6093000000000001
- type: nauc_recall_at_3_diff1
value: 38.3001
- type: nauc_recall_at_5_max
value: 25.5757
- type: nauc_recall_at_5_std
value: 1.7046999999999999
- type: nauc_recall_at_5_diff1
value: 33.9953
- type: nauc_recall_at_10_max
value: 21.9077
- type: nauc_recall_at_10_std
value: 2.4832
- type: nauc_recall_at_10_diff1
value: 27.6569
- type: nauc_recall_at_20_max
value: 27.9785
- type: nauc_recall_at_20_std
value: 8.717
- type: nauc_recall_at_20_diff1
value: 26.076
- type: nauc_recall_at_100_max
value: 32.8372
- type: nauc_recall_at_100_std
value: 28.644799999999996
- type: nauc_recall_at_100_diff1
value: 22.3344
- type: nauc_recall_at_1000_max
value: 43.087199999999996
- type: nauc_recall_at_1000_std
value: 38.6013
- type: nauc_recall_at_1000_diff1
value: 19.057399999999998
- type: nauc_precision_at_1_max
value: 27.961799999999997
- type: nauc_precision_at_1_std
value: 1.9207999999999998
- type: nauc_precision_at_1_diff1
value: 47.9837
- type: nauc_precision_at_3_max
value: 26.680999999999997
- type: nauc_precision_at_3_std
value: 6.4623
- type: nauc_precision_at_3_diff1
value: 26.0754
- type: nauc_precision_at_5_max
value: 23.0766
- type: nauc_precision_at_5_std
value: 8.0635
- type: nauc_precision_at_5_diff1
value: 18.249399999999998
- type: nauc_precision_at_10_max
value: 14.0187
- type: nauc_precision_at_10_std
value: 10.793999999999999
- type: nauc_precision_at_10_diff1
value: 5.7888
- type: nauc_precision_at_20_max
value: 12.065
- type: nauc_precision_at_20_std
value: 15.728800000000001
- type: nauc_precision_at_20_diff1
value: -0.7351
- type: nauc_precision_at_100_max
value: -0.4148
- type: nauc_precision_at_100_std
value: 17.0201
- type: nauc_precision_at_100_diff1
value: -8.088099999999999
- type: nauc_precision_at_1000_max
value: -18.342
- type: nauc_precision_at_1000_std
value: 5.6757
- type: nauc_precision_at_1000_diff1
value: -13.869200000000001
- type: nauc_mrr_at_1_max
value: 27.961799999999997
- type: nauc_mrr_at_1_std
value: 1.9207999999999998
- type: nauc_mrr_at_1_diff1
value: 47.9837
- type: nauc_mrr_at_3_max
value: 27.7754
- type: nauc_mrr_at_3_std
value: 2.2727
- type: nauc_mrr_at_3_diff1
value: 42.864999999999995
- type: nauc_mrr_at_5_max
value: 27.7453
- type: nauc_mrr_at_5_std
value: 2.7718
- type: nauc_mrr_at_5_diff1
value: 41.9633
- type: nauc_mrr_at_10_max
value: 27.308300000000003
- type: nauc_mrr_at_10_std
value: 3.089
- type: nauc_mrr_at_10_diff1
value: 41.3641
- type: nauc_mrr_at_20_max
value: 27.814299999999996
- type: nauc_mrr_at_20_std
value: 3.2985
- type: nauc_mrr_at_20_diff1
value: 41.6228
- type: nauc_mrr_at_100_max
value: 27.8378
- type: nauc_mrr_at_100_std
value: 3.517
- type: nauc_mrr_at_100_diff1
value: 41.7328
- type: nauc_mrr_at_1000_max
value: 27.8277
- type: nauc_mrr_at_1000_std
value: 3.4743000000000004
- type: nauc_mrr_at_1000_diff1
value: 41.7584
- type: main_score
value: 42.321999999999996
- task:
type: Retrieval
dataset:
name: MTEB CQADupstackWordpressRetrieval (default)
type: mteb/cqadupstack-wordpress
config: default
split: test
revision: 4ffe81d471b1924886b33c7567bfb200e9eec5c4
metrics:
- type: ndcg_at_1
value: 23.105
- type: ndcg_at_3
value: 28.781000000000002
- type: ndcg_at_5
value: 31.338
- type: ndcg_at_10
value: 34.091
- type: ndcg_at_20
value: 36.046
- type: ndcg_at_100
value: 39.556999999999995
- type: ndcg_at_1000
value: 41.647
- type: map_at_1
value: 21.448
- type: map_at_3
value: 26.527
- type: map_at_5
value: 28.02
- type: map_at_10
value: 29.204
- type: map_at_20
value: 29.774
- type: map_at_100
value: 30.278
- type: map_at_1000
value: 30.364
- type: recall_at_1
value: 21.448
- type: recall_at_3
value: 33.167
- type: recall_at_5
value: 39.156
- type: recall_at_10
value: 47.277
- type: recall_at_20
value: 54.639
- type: recall_at_100
value: 72.809
- type: recall_at_1000
value: 88.099
- type: precision_at_1
value: 23.105
- type: precision_at_3
value: 12.138
- type: precision_at_5
value: 8.834999999999999
- type: precision_at_10
value: 5.434
- type: precision_at_20
value: 3.189
- type: precision_at_100
value: 0.8710000000000001
- type: precision_at_1000
value: 0.11499999999999999
- type: mrr_at_1
value: 23.1054
- type: mrr_at_3
value: 28.5582
- type: mrr_at_5
value: 30.0462
- type: mrr_at_10
value: 31.1854
- type: mrr_at_20
value: 31.6775
- type: mrr_at_100
value: 32.1183
- type: mrr_at_1000
value: 32.1723
- type: nauc_ndcg_at_1_max
value: 30.894
- type: nauc_ndcg_at_1_std
value: 0.8228
- type: nauc_ndcg_at_1_diff1
value: 50.571600000000004
- type: nauc_ndcg_at_3_max
value: 24.9603
- type: nauc_ndcg_at_3_std
value: -0.3032
- type: nauc_ndcg_at_3_diff1
value: 43.803799999999995
- type: nauc_ndcg_at_5_max
value: 26.1479
- type: nauc_ndcg_at_5_std
value: 0.3038
- type: nauc_ndcg_at_5_diff1
value: 42.5296
- type: nauc_ndcg_at_10_max
value: 26.0992
- type: nauc_ndcg_at_10_std
value: 1.2644
- type: nauc_ndcg_at_10_diff1
value: 41.943000000000005
- type: nauc_ndcg_at_20_max
value: 26.132300000000004
- type: nauc_ndcg_at_20_std
value: 1.798
- type: nauc_ndcg_at_20_diff1
value: 41.1586
- type: nauc_ndcg_at_100_max
value: 26.4048
- type: nauc_ndcg_at_100_std
value: 3.7023
- type: nauc_ndcg_at_100_diff1
value: 41.3297
- type: nauc_ndcg_at_1000_max
value: 26.889200000000002
- type: nauc_ndcg_at_1000_std
value: 3.7087000000000003
- type: nauc_ndcg_at_1000_diff1
value: 41.716300000000004
- type: nauc_map_at_1_max
value: 27.5981
- type: nauc_map_at_1_std
value: 0.387
- type: nauc_map_at_1_diff1
value: 48.6362
- type: nauc_map_at_3_max
value: 24.8521
- type: nauc_map_at_3_std
value: -0.414
- type: nauc_map_at_3_diff1
value: 44.766600000000004
- type: nauc_map_at_5_max
value: 25.937900000000003
- type: nauc_map_at_5_std
value: -0.054900000000000004
- type: nauc_map_at_5_diff1
value: 44.0302
- type: nauc_map_at_10_max
value: 26.018
- type: nauc_map_at_10_std
value: 0.3584
- type: nauc_map_at_10_diff1
value: 43.7009
- type: nauc_map_at_20_max
value: 26.0129
- type: nauc_map_at_20_std
value: 0.5091
- type: nauc_map_at_20_diff1
value: 43.4823
- type: nauc_map_at_100_max
value: 26.1059
- type: nauc_map_at_100_std
value: 0.7867999999999999
- type: nauc_map_at_100_diff1
value: 43.4867
- type: nauc_map_at_1000_max
value: 26.131500000000003
- type: nauc_map_at_1000_std
value: 0.8026
- type: nauc_map_at_1000_diff1
value: 43.5097
- type: nauc_recall_at_1_max
value: 27.5981
- type: nauc_recall_at_1_std
value: 0.387
- type: nauc_recall_at_1_diff1
value: 48.6362
- type: nauc_recall_at_3_max
value: 21.7315
- type: nauc_recall_at_3_std
value: -1.0671
- type: nauc_recall_at_3_diff1
value: 39.4999
- type: nauc_recall_at_5_max
value: 23.994699999999998
- type: nauc_recall_at_5_std
value: 0.0779
- type: nauc_recall_at_5_diff1
value: 36.9505
- type: nauc_recall_at_10_max
value: 23.2468
- type: nauc_recall_at_10_std
value: 2.654
- type: nauc_recall_at_10_diff1
value: 35.158899999999996
- type: nauc_recall_at_20_max
value: 23.28
- type: nauc_recall_at_20_std
value: 4.8041
- type: nauc_recall_at_20_diff1
value: 31.547399999999996
- type: nauc_recall_at_100_max
value: 21.7186
- type: nauc_recall_at_100_std
value: 17.083000000000002
- type: nauc_recall_at_100_diff1
value: 29.229899999999997
- type: nauc_recall_at_1000_max
value: 28.9168
- type: nauc_recall_at_1000_std
value: 29.9591
- type: nauc_recall_at_1000_diff1
value: 27.0436
- type: nauc_precision_at_1_max
value: 30.894
- type: nauc_precision_at_1_std
value: 0.8228
- type: nauc_precision_at_1_diff1
value: 50.571600000000004
- type: nauc_precision_at_3_max
value: 25.076999999999998
- type: nauc_precision_at_3_std
value: 0.39890000000000003
- type: nauc_precision_at_3_diff1
value: 40.618300000000005
- type: nauc_precision_at_5_max
value: 29.274299999999997
- type: nauc_precision_at_5_std
value: 3.02
- type: nauc_precision_at_5_diff1
value: 35.3233
- type: nauc_precision_at_10_max
value: 28.1411
- type: nauc_precision_at_10_std
value: 6.628100000000001
- type: nauc_precision_at_10_diff1
value: 30.949700000000004
- type: nauc_precision_at_20_max
value: 25.974999999999998
- type: nauc_precision_at_20_std
value: 8.3134
- type: nauc_precision_at_20_diff1
value: 25.324799999999996
- type: nauc_precision_at_100_max
value: 22.682
- type: nauc_precision_at_100_std
value: 20.4648
- type: nauc_precision_at_100_diff1
value: 13.2139
- type: nauc_precision_at_1000_max
value: 2.8796
- type: nauc_precision_at_1000_std
value: 10.6158
- type: nauc_precision_at_1000_diff1
value: -11.8614
- type: nauc_mrr_at_1_max
value: 30.894
- type: nauc_mrr_at_1_std
value: 0.8228
- type: nauc_mrr_at_1_diff1
value: 50.571600000000004
- type: nauc_mrr_at_3_max
value: 27.8993
- type: nauc_mrr_at_3_std
value: 0.5541
- type: nauc_mrr_at_3_diff1
value: 46.307900000000004
- type: nauc_mrr_at_5_max
value: 28.4404
- type: nauc_mrr_at_5_std
value: 0.8992
- type: nauc_mrr_at_5_diff1
value: 45.405699999999996
- type: nauc_mrr_at_10_max
value: 28.492099999999997
- type: nauc_mrr_at_10_std
value: 1.3769
- type: nauc_mrr_at_10_diff1
value: 45.163
- type: nauc_mrr_at_20_max
value: 28.4509
- type: nauc_mrr_at_20_std
value: 1.4745
- type: nauc_mrr_at_20_diff1
value: 44.9459
- type: nauc_mrr_at_100_max
value: 28.533199999999997
- type: nauc_mrr_at_100_std
value: 1.7016
- type: nauc_mrr_at_100_diff1
value: 45.0053
- type: nauc_mrr_at_1000_max
value: 28.5364
- type: nauc_mrr_at_1000_std
value: 1.6894
- type: nauc_mrr_at_1000_diff1
value: 45.0407
- type: main_score
value: 34.091
- task:
type: Retrieval
dataset:
name: MTEB ClimateFEVER (default)
type: mteb/climate-fever
config: default
split: test
revision: 47f2ac6acb640fc46020b02a5b59fdda04d39380
metrics:
- type: ndcg_at_1
value: 32.964
- type: ndcg_at_3
value: 28.116000000000003
- type: ndcg_at_5
value: 29.932
- type: ndcg_at_10
value: 33.207
- type: ndcg_at_20
value: 35.730000000000004
- type: ndcg_at_100
value: 40.251999999999995
- type: ndcg_at_1000
value: 43.463
- type: map_at_1
value: 14.846
- type: map_at_3
value: 20.683
- type: map_at_5
value: 22.753999999999998
- type: map_at_10
value: 24.413
- type: map_at_20
value: 25.355
- type: map_at_100
value: 26.243
- type: map_at_1000
value: 26.43
- type: recall_at_1
value: 14.846
- type: recall_at_3
value: 25.368000000000002
- type: recall_at_5
value: 31.159
- type: recall_at_10
value: 38.391
- type: recall_at_20
value: 45.366
- type: recall_at_100
value: 62.597
- type: recall_at_1000
value: 80.448
- type: precision_at_1
value: 32.964
- type: precision_at_3
value: 20.782
- type: precision_at_5
value: 15.595999999999998
- type: precision_at_10
value: 9.98
- type: precision_at_20
value: 6.091
- type: precision_at_100
value: 1.7760000000000002
- type: precision_at_1000
value: 0.23700000000000002
- type: mrr_at_1
value: 32.9642
- type: mrr_at_3
value: 41.9001
- type: mrr_at_5
value: 43.4701
- type: mrr_at_10
value: 44.6392
- type: mrr_at_20
value: 45.129999999999995
- type: mrr_at_100
value: 45.4343
- type: mrr_at_1000
value: 45.4726
- type: nauc_ndcg_at_1_max
value: 31.2733
- type: nauc_ndcg_at_1_std
value: 17.8778
- type: nauc_ndcg_at_1_diff1
value: 30.7939
- type: nauc_ndcg_at_3_max
value: 35.7233
- type: nauc_ndcg_at_3_std
value: 20.499200000000002
- type: nauc_ndcg_at_3_diff1
value: 26.6175
- type: nauc_ndcg_at_5_max
value: 36.5593
- type: nauc_ndcg_at_5_std
value: 20.5487
- type: nauc_ndcg_at_5_diff1
value: 24.8006
- type: nauc_ndcg_at_10_max
value: 38.1663
- type: nauc_ndcg_at_10_std
value: 23.8688
- type: nauc_ndcg_at_10_diff1
value: 23.7262
- type: nauc_ndcg_at_20_max
value: 38.719
- type: nauc_ndcg_at_20_std
value: 26.4556
- type: nauc_ndcg_at_20_diff1
value: 22.7078
- type: nauc_ndcg_at_100_max
value: 40.396100000000004
- type: nauc_ndcg_at_100_std
value: 29.325200000000002
- type: nauc_ndcg_at_100_diff1
value: 22.7562
- type: nauc_ndcg_at_1000_max
value: 40.4082
- type: nauc_ndcg_at_1000_std
value: 29.595
- type: nauc_ndcg_at_1000_diff1
value: 22.8439
- type: nauc_map_at_1_max
value: 33.0891
- type: nauc_map_at_1_std
value: 13.3677
- type: nauc_map_at_1_diff1
value: 34.1515
- type: nauc_map_at_3_max
value: 35.384
- type: nauc_map_at_3_std
value: 17.637
- type: nauc_map_at_3_diff1
value: 28.4007
- type: nauc_map_at_5_max
value: 36.0659
- type: nauc_map_at_5_std
value: 18.5628
- type: nauc_map_at_5_diff1
value: 26.5464
- type: nauc_map_at_10_max
value: 37.2578
- type: nauc_map_at_10_std
value: 20.617
- type: nauc_map_at_10_diff1
value: 25.926199999999998
- type: nauc_map_at_20_max
value: 37.500299999999996
- type: nauc_map_at_20_std
value: 21.851300000000002
- type: nauc_map_at_20_diff1
value: 25.3292
- type: nauc_map_at_100_max
value: 37.933299999999996
- type: nauc_map_at_100_std
value: 22.6615
- type: nauc_map_at_100_diff1
value: 25.259500000000003
- type: nauc_map_at_1000_max
value: 37.9165
- type: nauc_map_at_1000_std
value: 22.7028
- type: nauc_map_at_1000_diff1
value: 25.239299999999997
- type: nauc_recall_at_1_max
value: 33.0891
- type: nauc_recall_at_1_std
value: 13.3677
- type: nauc_recall_at_1_diff1
value: 34.1515
- type: nauc_recall_at_3_max
value: 35.282000000000004
- type: nauc_recall_at_3_std
value: 18.8367
- type: nauc_recall_at_3_diff1
value: 24.2501
- type: nauc_recall_at_5_max
value: 34.3122
- type: nauc_recall_at_5_std
value: 18.5093
- type: nauc_recall_at_5_diff1
value: 18.8749
- type: nauc_recall_at_10_max
value: 36.2395
- type: nauc_recall_at_10_std
value: 24.2952
- type: nauc_recall_at_10_diff1
value: 16.3158
- type: nauc_recall_at_20_max
value: 35.6255
- type: nauc_recall_at_20_std
value: 29.56
- type: nauc_recall_at_20_diff1
value: 12.856699999999998
- type: nauc_recall_at_100_max
value: 39.016600000000004
- type: nauc_recall_at_100_std
value: 37.9984
- type: nauc_recall_at_100_diff1
value: 10.807
- type: nauc_recall_at_1000_max
value: 42.7582
- type: nauc_recall_at_1000_std
value: 46.9593
- type: nauc_recall_at_1000_diff1
value: 8.1464
- type: nauc_precision_at_1_max
value: 31.2733
- type: nauc_precision_at_1_std
value: 17.8778
- type: nauc_precision_at_1_diff1
value: 30.7939
- type: nauc_precision_at_3_max
value: 35.2819
- type: nauc_precision_at_3_std
value: 25.9018
- type: nauc_precision_at_3_diff1
value: 18.4633
- type: nauc_precision_at_5_max
value: 32.7525
- type: nauc_precision_at_5_std
value: 25.5596
- type: nauc_precision_at_5_diff1
value: 11.241
- type: nauc_precision_at_10_max
value: 32.4574
- type: nauc_precision_at_10_std
value: 31.1815
- type: nauc_precision_at_10_diff1
value: 6.3983
- type: nauc_precision_at_20_max
value: 29.522100000000002
- type: nauc_precision_at_20_std
value: 34.4644
- type: nauc_precision_at_20_diff1
value: 1.9328
- type: nauc_precision_at_100_max
value: 25.594299999999997
- type: nauc_precision_at_100_std
value: 36.7783
- type: nauc_precision_at_100_diff1
value: -1.9514
- type: nauc_precision_at_1000_max
value: 14.3931
- type: nauc_precision_at_1000_std
value: 28.8585
- type: nauc_precision_at_1000_diff1
value: -7.264600000000001
- type: nauc_mrr_at_1_max
value: 31.2733
- type: nauc_mrr_at_1_std
value: 17.8778
- type: nauc_mrr_at_1_diff1
value: 30.7939
- type: nauc_mrr_at_3_max
value: 34.4613
- type: nauc_mrr_at_3_std
value: 21.529
- type: nauc_mrr_at_3_diff1
value: 27.369
- type: nauc_mrr_at_5_max
value: 34.5965
- type: nauc_mrr_at_5_std
value: 21.7303
- type: nauc_mrr_at_5_diff1
value: 26.521800000000002
- type: nauc_mrr_at_10_max
value: 34.6792
- type: nauc_mrr_at_10_std
value: 22.4157
- type: nauc_mrr_at_10_diff1
value: 26.2542
- type: nauc_mrr_at_20_max
value: 34.746
- type: nauc_mrr_at_20_std
value: 22.586000000000002
- type: nauc_mrr_at_20_diff1
value: 26.305600000000002
- type: nauc_mrr_at_100_max
value: 34.7901
- type: nauc_mrr_at_100_std
value: 22.5625
- type: nauc_mrr_at_100_diff1
value: 26.429599999999997
- type: nauc_mrr_at_1000_max
value: 34.779700000000005
- type: nauc_mrr_at_1000_std
value: 22.5434
- type: nauc_mrr_at_1000_diff1
value: 26.437300000000004
- type: main_score
value: 33.207
- task:
type: Retrieval
dataset:
name: MTEB DBPedia (default)
type: mteb/dbpedia
config: default
split: test
revision: c0f706b76e590d620bd6618b3ca8efdd34e2d659
metrics:
- type: ndcg_at_1
value: 51.87500000000001
- type: ndcg_at_3
value: 42.552
- type: ndcg_at_5
value: 39.946
- type: ndcg_at_10
value: 37.897999999999996
- type: ndcg_at_20
value: 37.153000000000006
- type: ndcg_at_100
value: 42.012
- type: ndcg_at_1000
value: 49.202
- type: map_at_1
value: 7.869
- type: map_at_3
value: 12.307
- type: map_at_5
value: 14.394000000000002
- type: map_at_10
value: 17.175
- type: map_at_20
value: 19.689
- type: map_at_100
value: 23.857999999999997
- type: map_at_1000
value: 25.417
- type: recall_at_1
value: 7.869
- type: recall_at_3
value: 13.566
- type: recall_at_5
value: 17.403
- type: recall_at_10
value: 22.811999999999998
- type: recall_at_20
value: 29.378999999999998
- type: recall_at_100
value: 48.353
- type: recall_at_1000
value: 70.801
- type: precision_at_1
value: 62.5
- type: precision_at_3
value: 45.417
- type: precision_at_5
value: 38.15
- type: precision_at_10
value: 29.95
- type: precision_at_20
value: 22.462
- type: precision_at_100
value: 9.703000000000001
- type: precision_at_1000
value: 2.027
- type: mrr_at_1
value: 62.5
- type: mrr_at_3
value: 68.625
- type: mrr_at_5
value: 70.0625
- type: mrr_at_10
value: 70.60549999999999
- type: mrr_at_20
value: 70.934
- type: mrr_at_100
value: 71.0742
- type: mrr_at_1000
value: 71.0797
- type: nauc_ndcg_at_1_max
value: 41.436499999999995
- type: nauc_ndcg_at_1_std
value: 26.6537
- type: nauc_ndcg_at_1_diff1
value: 41.362500000000004
- type: nauc_ndcg_at_3_max
value: 38.2075
- type: nauc_ndcg_at_3_std
value: 28.1899
- type: nauc_ndcg_at_3_diff1
value: 29.353299999999997
- type: nauc_ndcg_at_5_max
value: 36.592
- type: nauc_ndcg_at_5_std
value: 27.9763
- type: nauc_ndcg_at_5_diff1
value: 30.2168
- type: nauc_ndcg_at_10_max
value: 36.2032
- type: nauc_ndcg_at_10_std
value: 26.7501
- type: nauc_ndcg_at_10_diff1
value: 33.409499999999994
- type: nauc_ndcg_at_20_max
value: 33.981
- type: nauc_ndcg_at_20_std
value: 25.5934
- type: nauc_ndcg_at_20_diff1
value: 33.3985
- type: nauc_ndcg_at_100_max
value: 36.448
- type: nauc_ndcg_at_100_std
value: 32.3459
- type: nauc_ndcg_at_100_diff1
value: 33.2002
- type: nauc_ndcg_at_1000_max
value: 40.2408
- type: nauc_ndcg_at_1000_std
value: 38.6683
- type: nauc_ndcg_at_1000_diff1
value: 31.9563
- type: nauc_map_at_1_max
value: 8.8384
- type: nauc_map_at_1_std
value: -12.18
- type: nauc_map_at_1_diff1
value: 42.5949
- type: nauc_map_at_3_max
value: 10.4264
- type: nauc_map_at_3_std
value: -6.4437
- type: nauc_map_at_3_diff1
value: 31.555
- type: nauc_map_at_5_max
value: 12.4445
- type: nauc_map_at_5_std
value: -3.5782000000000003
- type: nauc_map_at_5_diff1
value: 29.8594
- type: nauc_map_at_10_max
value: 16.9699
- type: nauc_map_at_10_std
value: 2.0362999999999998
- type: nauc_map_at_10_diff1
value: 29.737599999999997
- type: nauc_map_at_20_max
value: 21.4809
- type: nauc_map_at_20_std
value: 9.0494
- type: nauc_map_at_20_diff1
value: 30.0806
- type: nauc_map_at_100_max
value: 29.0583
- type: nauc_map_at_100_std
value: 22.3292
- type: nauc_map_at_100_diff1
value: 29.9971
- type: nauc_map_at_1000_max
value: 30.4654
- type: nauc_map_at_1000_std
value: 25.208799999999997
- type: nauc_map_at_1000_diff1
value: 29.3623
- type: nauc_recall_at_1_max
value: 8.8384
- type: nauc_recall_at_1_std
value: -12.18
- type: nauc_recall_at_1_diff1
value: 42.5949
- type: nauc_recall_at_3_max
value: 7.692400000000001
- type: nauc_recall_at_3_std
value: -7.5964
- type: nauc_recall_at_3_diff1
value: 27.5878
- type: nauc_recall_at_5_max
value: 7.3506
- type: nauc_recall_at_5_std
value: -7.152799999999999
- type: nauc_recall_at_5_diff1
value: 25.565199999999997
- type: nauc_recall_at_10_max
value: 13.009
- type: nauc_recall_at_10_std
value: -0.6829
- type: nauc_recall_at_10_diff1
value: 25.8442
- type: nauc_recall_at_20_max
value: 15.329
- type: nauc_recall_at_20_std
value: 5.9502
- type: nauc_recall_at_20_diff1
value: 24.584400000000002
- type: nauc_recall_at_100_max
value: 26.1527
- type: nauc_recall_at_100_std
value: 28.8597
- type: nauc_recall_at_100_diff1
value: 23.5886
- type: nauc_recall_at_1000_max
value: 32.736
- type: nauc_recall_at_1000_std
value: 41.5612
- type: nauc_recall_at_1000_diff1
value: 21.8267
- type: nauc_precision_at_1_max
value: 56.4401
- type: nauc_precision_at_1_std
value: 39.5242
- type: nauc_precision_at_1_diff1
value: 44.307
- type: nauc_precision_at_3_max
value: 44.521100000000004
- type: nauc_precision_at_3_std
value: 42.4366
- type: nauc_precision_at_3_diff1
value: 13.569899999999999
- type: nauc_precision_at_5_max
value: 42.3594
- type: nauc_precision_at_5_std
value: 44.4758
- type: nauc_precision_at_5_diff1
value: 10.2733
- type: nauc_precision_at_10_max
value: 41.260000000000005
- type: nauc_precision_at_10_std
value: 47.2496
- type: nauc_precision_at_10_diff1
value: 9.393799999999999
- type: nauc_precision_at_20_max
value: 39.8169
- type: nauc_precision_at_20_std
value: 49.8068
- type: nauc_precision_at_20_diff1
value: 8.7204
- type: nauc_precision_at_100_max
value: 30.9015
- type: nauc_precision_at_100_std
value: 46.853899999999996
- type: nauc_precision_at_100_diff1
value: 2.0425
- type: nauc_precision_at_1000_max
value: 5.3395
- type: nauc_precision_at_1000_std
value: 17.8995
- type: nauc_precision_at_1000_diff1
value: -13.3583
- type: nauc_mrr_at_1_max
value: 56.4401
- type: nauc_mrr_at_1_std
value: 39.5242
- type: nauc_mrr_at_1_diff1
value: 44.307
- type: nauc_mrr_at_3_max
value: 56.97990000000001
- type: nauc_mrr_at_3_std
value: 42.138
- type: nauc_mrr_at_3_diff1
value: 41.5078
- type: nauc_mrr_at_5_max
value: 56.234399999999994
- type: nauc_mrr_at_5_std
value: 41.3617
- type: nauc_mrr_at_5_diff1
value: 41.227599999999995
- type: nauc_mrr_at_10_max
value: 56.6701
- type: nauc_mrr_at_10_std
value: 41.6424
- type: nauc_mrr_at_10_diff1
value: 41.814800000000005
- type: nauc_mrr_at_20_max
value: 56.6094
- type: nauc_mrr_at_20_std
value: 41.7269
- type: nauc_mrr_at_20_diff1
value: 41.8099
- type: nauc_mrr_at_100_max
value: 56.623900000000006
- type: nauc_mrr_at_100_std
value: 41.6436
- type: nauc_mrr_at_100_diff1
value: 41.7734
- type: nauc_mrr_at_1000_max
value: 56.6269
- type: nauc_mrr_at_1000_std
value: 41.6455
- type: nauc_mrr_at_1000_diff1
value: 41.7701
- type: main_score
value: 37.897999999999996
- task:
type: Classification
dataset:
name: MTEB EmotionClassification (default)
type: mteb/emotion
config: default
split: test
revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37
metrics:
- type: accuracy
value: 63.235
- type: f1
value: 59.071799999999996
- type: f1_weighted
value: 64.6776
- type: main_score
value: 63.235
- task:
type: Retrieval
dataset:
name: MTEB FEVER (default)
type: mteb/fever
config: default
split: test
revision: bea83ef9e8fb933d90a2f1d5515737465d613e12
metrics:
- type: ndcg_at_1
value: 83.498
- type: ndcg_at_3
value: 86.69200000000001
- type: ndcg_at_5
value: 87.787
- type: ndcg_at_10
value: 88.31
- type: ndcg_at_20
value: 88.595
- type: ndcg_at_100
value: 88.905
- type: ndcg_at_1000
value: 89.09700000000001
- type: map_at_1
value: 77.41
- type: map_at_3
value: 83.673
- type: map_at_5
value: 84.464
- type: map_at_10
value: 84.748
- type: map_at_20
value: 84.863
- type: map_at_100
value: 84.929
- type: map_at_1000
value: 84.941
- type: recall_at_1
value: 77.41
- type: recall_at_3
value: 90.027
- type: recall_at_5
value: 92.804
- type: recall_at_10
value: 94.377
- type: recall_at_20
value: 95.321
- type: recall_at_100
value: 96.646
- type: recall_at_1000
value: 97.77900000000001
- type: precision_at_1
value: 83.498
- type: precision_at_3
value: 32.728
- type: precision_at_5
value: 20.375
- type: precision_at_10
value: 10.424999999999999
- type: precision_at_20
value: 5.305
- type: precision_at_100
value: 1.0919999999999999
- type: precision_at_1000
value: 0.11299999999999999
- type: mrr_at_1
value: 83.4983
- type: mrr_at_3
value: 89.1189
- type: mrr_at_5
value: 89.6395
- type: mrr_at_10
value: 89.79899999999999
- type: mrr_at_20
value: 89.8266
- type: mrr_at_100
value: 89.8373
- type: mrr_at_1000
value: 89.8376
- type: nauc_ndcg_at_1_max
value: 31.5238
- type: nauc_ndcg_at_1_std
value: -2.2584
- type: nauc_ndcg_at_1_diff1
value: 74.5023
- type: nauc_ndcg_at_3_max
value: 24.1127
- type: nauc_ndcg_at_3_std
value: -2.6446
- type: nauc_ndcg_at_3_diff1
value: 49.2508
- type: nauc_ndcg_at_5_max
value: 23.6616
- type: nauc_ndcg_at_5_std
value: -1.3849
- type: nauc_ndcg_at_5_diff1
value: 47.106300000000005
- type: nauc_ndcg_at_10_max
value: 24.0605
- type: nauc_ndcg_at_10_std
value: -0.4336
- type: nauc_ndcg_at_10_diff1
value: 46.9328
- type: nauc_ndcg_at_20_max
value: 24.7393
- type: nauc_ndcg_at_20_std
value: 0.2855
- type: nauc_ndcg_at_20_diff1
value: 47.6414
- type: nauc_ndcg_at_100_max
value: 25.228099999999998
- type: nauc_ndcg_at_100_std
value: 0.5433
- type: nauc_ndcg_at_100_diff1
value: 48.7128
- type: nauc_ndcg_at_1000_max
value: 25.7762
- type: nauc_ndcg_at_1000_std
value: 0.7018
- type: nauc_ndcg_at_1000_diff1
value: 49.6639
- type: nauc_map_at_1_max
value: 22.7408
- type: nauc_map_at_1_std
value: -1.3189
- type: nauc_map_at_1_diff1
value: 54.049400000000006
- type: nauc_map_at_3_max
value: 22.6962
- type: nauc_map_at_3_std
value: -1.9411
- type: nauc_map_at_3_diff1
value: 47.3787
- type: nauc_map_at_5_max
value: 22.8472
- type: nauc_map_at_5_std
value: -1.2210999999999999
- type: nauc_map_at_5_diff1
value: 46.8099
- type: nauc_map_at_10_max
value: 23.1253
- type: nauc_map_at_10_std
value: -0.8166
- type: nauc_map_at_10_diff1
value: 46.961000000000006
- type: nauc_map_at_20_max
value: 23.336299999999998
- type: nauc_map_at_20_std
value: -0.6204000000000001
- type: nauc_map_at_20_diff1
value: 47.2216
- type: nauc_map_at_100_max
value: 23.4294
- type: nauc_map_at_100_std
value: -0.5717
- type: nauc_map_at_100_diff1
value: 47.3991
- type: nauc_map_at_1000_max
value: 23.4583
- type: nauc_map_at_1000_std
value: -0.5559999999999999
- type: nauc_map_at_1000_diff1
value: 47.4426
- type: nauc_recall_at_1_max
value: 22.7408
- type: nauc_recall_at_1_std
value: -1.3189
- type: nauc_recall_at_1_diff1
value: 54.049400000000006
- type: nauc_recall_at_3_max
value: 17.4806
- type: nauc_recall_at_3_std
value: -3.1338
- type: nauc_recall_at_3_diff1
value: 26.4903
- type: nauc_recall_at_5_max
value: 13.660400000000001
- type: nauc_recall_at_5_std
value: 1.3013000000000001
- type: nauc_recall_at_5_diff1
value: 12.3123
- type: nauc_recall_at_10_max
value: 13.4502
- type: nauc_recall_at_10_std
value: 7.7186
- type: nauc_recall_at_10_diff1
value: 2.9850000000000003
- type: nauc_recall_at_20_max
value: 16.927400000000002
- type: nauc_recall_at_20_std
value: 15.0728
- type: nauc_recall_at_20_diff1
value: 0.3826
- type: nauc_recall_at_100_max
value: 19.942899999999998
- type: nauc_recall_at_100_std
value: 23.5429
- type: nauc_recall_at_100_diff1
value: -3.4923
- type: nauc_recall_at_1000_max
value: 31.8901
- type: nauc_recall_at_1000_std
value: 37.6917
- type: nauc_recall_at_1000_diff1
value: -3.8215
- type: nauc_precision_at_1_max
value: 31.5238
- type: nauc_precision_at_1_std
value: -2.2584
- type: nauc_precision_at_1_diff1
value: 74.5023
- type: nauc_precision_at_3_max
value: 21.2432
- type: nauc_precision_at_3_std
value: -4.3431
- type: nauc_precision_at_3_diff1
value: 27.9237
- type: nauc_precision_at_5_max
value: 12.6046
- type: nauc_precision_at_5_std
value: 1.9817
- type: nauc_precision_at_5_diff1
value: 4.920100000000001
- type: nauc_precision_at_10_max
value: 11.452900000000001
- type: nauc_precision_at_10_std
value: 7.691199999999999
- type: nauc_precision_at_10_diff1
value: -2.363
- type: nauc_precision_at_20_max
value: 10.7846
- type: nauc_precision_at_20_std
value: 9.517100000000001
- type: nauc_precision_at_20_diff1
value: -3.3125
- type: nauc_precision_at_100_max
value: 9.1886
- type: nauc_precision_at_100_std
value: 9.5228
- type: nauc_precision_at_100_diff1
value: -1.9271
- type: nauc_precision_at_1000_max
value: 8.9731
- type: nauc_precision_at_1000_std
value: 8.952200000000001
- type: nauc_precision_at_1000_diff1
value: 1.226
- type: nauc_mrr_at_1_max
value: 31.5238
- type: nauc_mrr_at_1_std
value: -2.2584
- type: nauc_mrr_at_1_diff1
value: 74.5023
- type: nauc_mrr_at_3_max
value: 32.1889
- type: nauc_mrr_at_3_std
value: -4.9427
- type: nauc_mrr_at_3_diff1
value: 72.74080000000001
- type: nauc_mrr_at_5_max
value: 32.0768
- type: nauc_mrr_at_5_std
value: -4.4333
- type: nauc_mrr_at_5_diff1
value: 72.8939
- type: nauc_mrr_at_10_max
value: 32.1312
- type: nauc_mrr_at_10_std
value: -4.1756
- type: nauc_mrr_at_10_diff1
value: 73.0284
- type: nauc_mrr_at_20_max
value: 32.163199999999996
- type: nauc_mrr_at_20_std
value: -4.0634999999999994
- type: nauc_mrr_at_20_diff1
value: 73.0685
- type: nauc_mrr_at_100_max
value: 32.118
- type: nauc_mrr_at_100_std
value: -4.0852
- type: nauc_mrr_at_100_diff1
value: 73.0722
- type: nauc_mrr_at_1000_max
value: 32.1164
- type: nauc_mrr_at_1000_std
value: -4.0867
- type: nauc_mrr_at_1000_diff1
value: 73.0722
- type: main_score
value: 88.31
- task:
type: Retrieval
dataset:
name: MTEB FiQA2018 (default)
type: mteb/fiqa
config: default
split: test
revision: 27a168819829fe9bcd655c2df245fb19452e8e06
metrics:
- type: ndcg_at_1
value: 48.302
- type: ndcg_at_3
value: 44.882
- type: ndcg_at_5
value: 45.898
- type: ndcg_at_10
value: 48.28
- type: ndcg_at_20
value: 51.536
- type: ndcg_at_100
value: 55.461000000000006
- type: ndcg_at_1000
value: 57.938
- type: map_at_1
value: 24.324
- type: map_at_3
value: 35.225
- type: map_at_5
value: 37.962
- type: map_at_10
value: 40.054
- type: map_at_20
value: 41.399
- type: map_at_100
value: 42.321
- type: map_at_1000
value: 42.476
- type: recall_at_1
value: 24.324
- type: recall_at_3
value: 41.036
- type: recall_at_5
value: 46.844
- type: recall_at_10
value: 54.75
- type: recall_at_20
value: 64.86800000000001
- type: recall_at_100
value: 80.413
- type: recall_at_1000
value: 95.242
- type: precision_at_1
value: 48.302
- type: precision_at_3
value: 29.835
- type: precision_at_5
value: 21.852
- type: precision_at_10
value: 13.333
- type: precision_at_20
value: 8.017000000000001
- type: precision_at_100
value: 2.068
- type: precision_at_1000
value: 0.25
- type: mrr_at_1
value: 48.302499999999995
- type: mrr_at_3
value: 55.0669
- type: mrr_at_5
value: 56.208800000000004
- type: mrr_at_10
value: 57.128299999999996
- type: mrr_at_20
value: 57.6631
- type: mrr_at_100
value: 57.897
- type: mrr_at_1000
value: 57.9236
- type: nauc_ndcg_at_1_max
value: 35.3012
- type: nauc_ndcg_at_1_std
value: -10.4163
- type: nauc_ndcg_at_1_diff1
value: 49.8902
- type: nauc_ndcg_at_3_max
value: 33.3967
- type: nauc_ndcg_at_3_std
value: -6.623900000000001
- type: nauc_ndcg_at_3_diff1
value: 39.811600000000006
- type: nauc_ndcg_at_5_max
value: 32.1592
- type: nauc_ndcg_at_5_std
value: -7.155799999999999
- type: nauc_ndcg_at_5_diff1
value: 39.4895
- type: nauc_ndcg_at_10_max
value: 32.6943
- type: nauc_ndcg_at_10_std
value: -5.543
- type: nauc_ndcg_at_10_diff1
value: 39.4015
- type: nauc_ndcg_at_20_max
value: 33.247
- type: nauc_ndcg_at_20_std
value: -3.5911
- type: nauc_ndcg_at_20_diff1
value: 40.1093
- type: nauc_ndcg_at_100_max
value: 35.8738
- type: nauc_ndcg_at_100_std
value: -0.0625
- type: nauc_ndcg_at_100_diff1
value: 40.1993
- type: nauc_ndcg_at_1000_max
value: 36.105
- type: nauc_ndcg_at_1000_std
value: -1.2023000000000001
- type: nauc_ndcg_at_1000_diff1
value: 40.9404
- type: nauc_map_at_1_max
value: 15.893099999999999
- type: nauc_map_at_1_std
value: -10.817400000000001
- type: nauc_map_at_1_diff1
value: 42.2743
- type: nauc_map_at_3_max
value: 24.8811
- type: nauc_map_at_3_std
value: -8.8756
- type: nauc_map_at_3_diff1
value: 40.2234
- type: nauc_map_at_5_max
value: 28.198
- type: nauc_map_at_5_std
value: -8.2681
- type: nauc_map_at_5_diff1
value: 39.8233
- type: nauc_map_at_10_max
value: 29.8969
- type: nauc_map_at_10_std
value: -7.2732
- type: nauc_map_at_10_diff1
value: 39.056200000000004
- type: nauc_map_at_20_max
value: 30.438900000000004
- type: nauc_map_at_20_std
value: -6.2997
- type: nauc_map_at_20_diff1
value: 39.2282
- type: nauc_map_at_100_max
value: 31.2085
- type: nauc_map_at_100_std
value: -5.4389
- type: nauc_map_at_100_diff1
value: 39.2156
- type: nauc_map_at_1000_max
value: 31.2581
- type: nauc_map_at_1000_std
value: -5.4575
- type: nauc_map_at_1000_diff1
value: 39.256099999999996
- type: nauc_recall_at_1_max
value: 15.893099999999999
- type: nauc_recall_at_1_std
value: -10.817400000000001
- type: nauc_recall_at_1_diff1
value: 42.2743
- type: nauc_recall_at_3_max
value: 20.7605
- type: nauc_recall_at_3_std
value: -7.9595
- type: nauc_recall_at_3_diff1
value: 33.0679
- type: nauc_recall_at_5_max
value: 24.532899999999998
- type: nauc_recall_at_5_std
value: -7.535
- type: nauc_recall_at_5_diff1
value: 32.5104
- type: nauc_recall_at_10_max
value: 26.8851
- type: nauc_recall_at_10_std
value: -2.7628
- type: nauc_recall_at_10_diff1
value: 28.9325
- type: nauc_recall_at_20_max
value: 25.8328
- type: nauc_recall_at_20_std
value: 3.2887
- type: nauc_recall_at_20_diff1
value: 28.417399999999997
- type: nauc_recall_at_100_max
value: 36.079699999999995
- type: nauc_recall_at_100_std
value: 27.093099999999996
- type: nauc_recall_at_100_diff1
value: 26.377299999999998
- type: nauc_recall_at_1000_max
value: 47.7952
- type: nauc_recall_at_1000_std
value: 53.0751
- type: nauc_recall_at_1000_diff1
value: 32.7248
- type: nauc_precision_at_1_max
value: 35.3012
- type: nauc_precision_at_1_std
value: -10.4163
- type: nauc_precision_at_1_diff1
value: 49.8902
- type: nauc_precision_at_3_max
value: 39.9322
- type: nauc_precision_at_3_std
value: 0.2644
- type: nauc_precision_at_3_diff1
value: 26.600600000000004
- type: nauc_precision_at_5_max
value: 40.3902
- type: nauc_precision_at_5_std
value: 2.3505000000000003
- type: nauc_precision_at_5_diff1
value: 19.7771
- type: nauc_precision_at_10_max
value: 39.415299999999995
- type: nauc_precision_at_10_std
value: 6.5885
- type: nauc_precision_at_10_diff1
value: 13.7527
- type: nauc_precision_at_20_max
value: 37.2422
- type: nauc_precision_at_20_std
value: 12.9599
- type: nauc_precision_at_20_diff1
value: 9.6751
- type: nauc_precision_at_100_max
value: 35.6967
- type: nauc_precision_at_100_std
value: 19.8202
- type: nauc_precision_at_100_diff1
value: 1.6320999999999999
- type: nauc_precision_at_1000_max
value: 28.9716
- type: nauc_precision_at_1000_std
value: 15.8223
- type: nauc_precision_at_1000_diff1
value: -3.3576
- type: nauc_mrr_at_1_max
value: 35.3012
- type: nauc_mrr_at_1_std
value: -10.4163
- type: nauc_mrr_at_1_diff1
value: 49.8902
- type: nauc_mrr_at_3_max
value: 36.6979
- type: nauc_mrr_at_3_std
value: -7.6057
- type: nauc_mrr_at_3_diff1
value: 48.1421
- type: nauc_mrr_at_5_max
value: 37.0712
- type: nauc_mrr_at_5_std
value: -7.4076
- type: nauc_mrr_at_5_diff1
value: 47.7326
- type: nauc_mrr_at_10_max
value: 37.4375
- type: nauc_mrr_at_10_std
value: -6.875299999999999
- type: nauc_mrr_at_10_diff1
value: 47.7446
- type: nauc_mrr_at_20_max
value: 37.473
- type: nauc_mrr_at_20_std
value: -6.694799999999999
- type: nauc_mrr_at_20_diff1
value: 47.8238
- type: nauc_mrr_at_100_max
value: 37.453599999999994
- type: nauc_mrr_at_100_std
value: -6.612500000000001
- type: nauc_mrr_at_100_diff1
value: 47.8186
- type: nauc_mrr_at_1000_max
value: 37.4367
- type: nauc_mrr_at_1000_std
value: -6.6572000000000005
- type: nauc_mrr_at_1000_diff1
value: 47.8333
- type: main_score
value: 48.28
- task:
type: Retrieval
dataset:
name: MTEB HotpotQA (default)
type: mteb/hotpotqa
config: default
split: test
revision: ab518f4d6fcca38d87c25209f94beba119d02014
metrics:
- type: ndcg_at_1
value: 82.836
- type: ndcg_at_3
value: 60.80799999999999
- type: ndcg_at_5
value: 62.719
- type: ndcg_at_10
value: 64.464
- type: ndcg_at_20
value: 65.613
- type: ndcg_at_100
value: 67.244
- type: ndcg_at_1000
value: 68.633
- type: map_at_1
value: 41.418
- type: map_at_3
value: 51.913
- type: map_at_5
value: 53.45100000000001
- type: map_at_10
value: 54.50899999999999
- type: map_at_20
value: 54.981
- type: map_at_100
value: 55.315000000000005
- type: map_at_1000
value: 55.387
- type: recall_at_1
value: 41.418
- type: recall_at_3
value: 55.206
- type: recall_at_5
value: 58.987
- type: recall_at_10
value: 63.369
- type: recall_at_20
value: 67.07
- type: recall_at_100
value: 74.29400000000001
- type: recall_at_1000
value: 83.504
- type: precision_at_1
value: 82.836
- type: precision_at_3
value: 36.803999999999995
- type: precision_at_5
value: 23.595
- type: precision_at_10
value: 12.674
- type: precision_at_20
value: 6.707000000000001
- type: precision_at_100
value: 1.486
- type: precision_at_1000
value: 0.167
- type: mrr_at_1
value: 82.8359
- type: mrr_at_3
value: 86.7207
- type: mrr_at_5
value: 87.1062
- type: mrr_at_10
value: 87.3533
- type: mrr_at_20
value: 87.4411
- type: mrr_at_100
value: 87.4944
- type: mrr_at_1000
value: 87.5012
- type: nauc_ndcg_at_1_max
value: 55.378400000000006
- type: nauc_ndcg_at_1_std
value: -8.999799999999999
- type: nauc_ndcg_at_1_diff1
value: 81.65289999999999
- type: nauc_ndcg_at_3_max
value: 27.530900000000003
- type: nauc_ndcg_at_3_std
value: -1.4845000000000002
- type: nauc_ndcg_at_3_diff1
value: 28.8078
- type: nauc_ndcg_at_5_max
value: 24.8019
- type: nauc_ndcg_at_5_std
value: -0.6705
- type: nauc_ndcg_at_5_diff1
value: 25.1054
- type: nauc_ndcg_at_10_max
value: 22.6678
- type: nauc_ndcg_at_10_std
value: 0.8309000000000001
- type: nauc_ndcg_at_10_diff1
value: 22.1137
- type: nauc_ndcg_at_20_max
value: 21.601200000000002
- type: nauc_ndcg_at_20_std
value: 1.6587
- type: nauc_ndcg_at_20_diff1
value: 20.9774
- type: nauc_ndcg_at_100_max
value: 20.258499999999998
- type: nauc_ndcg_at_100_std
value: 2.4681
- type: nauc_ndcg_at_100_diff1
value: 19.4499
- type: nauc_ndcg_at_1000_max
value: 20.4564
- type: nauc_ndcg_at_1000_std
value: 2.8757
- type: nauc_ndcg_at_1000_diff1
value: 19.674500000000002
- type: nauc_map_at_1_max
value: 55.378400000000006
- type: nauc_map_at_1_std
value: -8.999799999999999
- type: nauc_map_at_1_diff1
value: 81.65289999999999
- type: nauc_map_at_3_max
value: 22.8016
- type: nauc_map_at_3_std
value: -1.3432
- type: nauc_map_at_3_diff1
value: 21.9107
- type: nauc_map_at_5_max
value: 21.0041
- type: nauc_map_at_5_std
value: -0.8455
- type: nauc_map_at_5_diff1
value: 19.5463
- type: nauc_map_at_10_max
value: 19.9533
- type: nauc_map_at_10_std
value: -0.058
- type: nauc_map_at_10_diff1
value: 18.075
- type: nauc_map_at_20_max
value: 19.5951
- type: nauc_map_at_20_std
value: 0.2562
- type: nauc_map_at_20_diff1
value: 17.71
- type: nauc_map_at_100_max
value: 19.3598
- type: nauc_map_at_100_std
value: 0.42960000000000004
- type: nauc_map_at_100_diff1
value: 17.461299999999998
- type: nauc_map_at_1000_max
value: 19.359
- type: nauc_map_at_1000_std
value: 0.451
- type: nauc_map_at_1000_diff1
value: 17.4648
- type: nauc_recall_at_1_max
value: 55.378400000000006
- type: nauc_recall_at_1_std
value: -8.999799999999999
- type: nauc_recall_at_1_diff1
value: 81.65289999999999
- type: nauc_recall_at_3_max
value: 18.226
- type: nauc_recall_at_3_std
value: 0.7939999999999999
- type: nauc_recall_at_3_diff1
value: 12.2289
- type: nauc_recall_at_5_max
value: 12.998999999999999
- type: nauc_recall_at_5_std
value: 2.1354
- type: nauc_recall_at_5_diff1
value: 5.6548
- type: nauc_recall_at_10_max
value: 7.985200000000001
- type: nauc_recall_at_10_std
value: 5.3194
- type: nauc_recall_at_10_diff1
value: -0.9107000000000001
- type: nauc_recall_at_20_max
value: 4.3701
- type: nauc_recall_at_20_std
value: 7.6056
- type: nauc_recall_at_20_diff1
value: -4.7479000000000005
- type: nauc_recall_at_100_max
value: -2.7925
- type: nauc_recall_at_100_std
value: 11.228200000000001
- type: nauc_recall_at_100_diff1
value: -13.4144
- type: nauc_recall_at_1000_max
value: -7.6068
- type: nauc_recall_at_1000_std
value: 17.0487
- type: nauc_recall_at_1000_diff1
value: -21.2775
- type: nauc_precision_at_1_max
value: 55.378400000000006
- type: nauc_precision_at_1_std
value: -8.999799999999999
- type: nauc_precision_at_1_diff1
value: 81.65289999999999
- type: nauc_precision_at_3_max
value: 18.226
- type: nauc_precision_at_3_std
value: 0.7939999999999999
- type: nauc_precision_at_3_diff1
value: 12.2289
- type: nauc_precision_at_5_max
value: 12.998999999999999
- type: nauc_precision_at_5_std
value: 2.1354
- type: nauc_precision_at_5_diff1
value: 5.6548
- type: nauc_precision_at_10_max
value: 7.985200000000001
- type: nauc_precision_at_10_std
value: 5.3194
- type: nauc_precision_at_10_diff1
value: -0.9107000000000001
- type: nauc_precision_at_20_max
value: 4.3701
- type: nauc_precision_at_20_std
value: 7.6056
- type: nauc_precision_at_20_diff1
value: -4.7479000000000005
- type: nauc_precision_at_100_max
value: -2.7925
- type: nauc_precision_at_100_std
value: 11.228200000000001
- type: nauc_precision_at_100_diff1
value: -13.4144
- type: nauc_precision_at_1000_max
value: -7.6068
- type: nauc_precision_at_1000_std
value: 17.0487
- type: nauc_precision_at_1000_diff1
value: -21.2775
- type: nauc_mrr_at_1_max
value: 55.378400000000006
- type: nauc_mrr_at_1_std
value: -8.999799999999999
- type: nauc_mrr_at_1_diff1
value: 81.65289999999999
- type: nauc_mrr_at_3_max
value: 58.457
- type: nauc_mrr_at_3_std
value: -6.3487
- type: nauc_mrr_at_3_diff1
value: 80.559
- type: nauc_mrr_at_5_max
value: 58.4461
- type: nauc_mrr_at_5_std
value: -5.9587
- type: nauc_mrr_at_5_diff1
value: 80.6051
- type: nauc_mrr_at_10_max
value: 58.42659999999999
- type: nauc_mrr_at_10_std
value: -5.6473
- type: nauc_mrr_at_10_diff1
value: 80.6628
- type: nauc_mrr_at_20_max
value: 58.3928
- type: nauc_mrr_at_20_std
value: -5.6386
- type: nauc_mrr_at_20_diff1
value: 80.7154
- type: nauc_mrr_at_100_max
value: 58.341699999999996
- type: nauc_mrr_at_100_std
value: -5.6933
- type: nauc_mrr_at_100_diff1
value: 80.7071
- type: nauc_mrr_at_1000_max
value: 58.3298
- type: nauc_mrr_at_1000_std
value: -5.7103
- type: nauc_mrr_at_1000_diff1
value: 80.7062
- type: main_score
value: 64.464
- task:
type: Classification
dataset:
name: MTEB ImdbClassification (default)
type: mteb/imdb
config: default
split: test
revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7
metrics:
- type: accuracy
value: 94.9352
- type: f1
value: 94.9327
- type: f1_weighted
value: 94.9327
- type: ap
value: 92.00789999999999
- type: ap_weighted
value: 92.00789999999999
- type: main_score
value: 94.9352
- task:
type: Retrieval
dataset:
name: MTEB MSMARCO (default)
type: mteb/msmarco
config: default
split: dev
revision: c5a29a104738b98a9e76336939199e264163d4a0
metrics:
- type: ndcg_at_1
value: 21.504
- type: ndcg_at_3
value: 32.328
- type: ndcg_at_5
value: 36.452
- type: ndcg_at_10
value: 40.325
- type: ndcg_at_20
value: 43.07
- type: ndcg_at_100
value: 46.23
- type: ndcg_at_1000
value: 47.369
- type: map_at_1
value: 20.909
- type: map_at_3
value: 29.353
- type: map_at_5
value: 31.661
- type: map_at_10
value: 33.28
- type: map_at_20
value: 34.06
- type: map_at_100
value: 34.52
- type: map_at_1000
value: 34.567
- type: recall_at_1
value: 20.909
- type: recall_at_3
value: 40.339000000000006
- type: recall_at_5
value: 50.259
- type: recall_at_10
value: 62.059
- type: recall_at_20
value: 72.693
- type: recall_at_100
value: 89.269
- type: recall_at_1000
value: 97.933
- type: precision_at_1
value: 21.504
- type: precision_at_3
value: 13.944999999999999
- type: precision_at_5
value: 10.461
- type: precision_at_10
value: 6.491
- type: precision_at_20
value: 3.818
- type: precision_at_100
value: 0.943
- type: precision_at_1000
value: 0.104
- type: mrr_at_1
value: 21.5043
- type: mrr_at_3
value: 29.978500000000004
- type: mrr_at_5
value: 32.251400000000004
- type: mrr_at_10
value: 33.8389
- type: mrr_at_20
value: 34.5788
- type: mrr_at_100
value: 35.010200000000005
- type: mrr_at_1000
value: 35.051100000000005
- type: nauc_ndcg_at_1_max
value: -1.0808
- type: nauc_ndcg_at_1_std
value: -22.361900000000002
- type: nauc_ndcg_at_1_diff1
value: 36.9204
- type: nauc_ndcg_at_3_max
value: -2.0822
- type: nauc_ndcg_at_3_std
value: -25.852999999999998
- type: nauc_ndcg_at_3_diff1
value: 30.8521
- type: nauc_ndcg_at_5_max
value: -2.0332
- type: nauc_ndcg_at_5_std
value: -26.375
- type: nauc_ndcg_at_5_diff1
value: 30.1887
- type: nauc_ndcg_at_10_max
value: -2.2974
- type: nauc_ndcg_at_10_std
value: -26.712000000000003
- type: nauc_ndcg_at_10_diff1
value: 30.1484
- type: nauc_ndcg_at_20_max
value: -1.825
- type: nauc_ndcg_at_20_std
value: -25.4078
- type: nauc_ndcg_at_20_diff1
value: 30.1416
- type: nauc_ndcg_at_100_max
value: -1.2328000000000001
- type: nauc_ndcg_at_100_std
value: -23.2039
- type: nauc_ndcg_at_100_diff1
value: 30.348399999999998
- type: nauc_ndcg_at_1000_max
value: -1.2148
- type: nauc_ndcg_at_1000_std
value: -23.8282
- type: nauc_ndcg_at_1000_diff1
value: 30.704900000000002
- type: nauc_map_at_1_max
value: -1.3643
- type: nauc_map_at_1_std
value: -22.5875
- type: nauc_map_at_1_diff1
value: 36.7618
- type: nauc_map_at_3_max
value: -2.0389999999999997
- type: nauc_map_at_3_std
value: -25.2612
- type: nauc_map_at_3_diff1
value: 32.171499999999995
- type: nauc_map_at_5_max
value: -2.0125
- type: nauc_map_at_5_std
value: -25.605800000000002
- type: nauc_map_at_5_diff1
value: 31.8081
- type: nauc_map_at_10_max
value: -2.1288
- type: nauc_map_at_10_std
value: -25.7592
- type: nauc_map_at_10_diff1
value: 31.8241
- type: nauc_map_at_20_max
value: -2.0061
- type: nauc_map_at_20_std
value: -25.4037
- type: nauc_map_at_20_diff1
value: 31.836799999999997
- type: nauc_map_at_100_max
value: -1.9212
- type: nauc_map_at_100_std
value: -25.0965
- type: nauc_map_at_100_diff1
value: 31.8741
- type: nauc_map_at_1000_max
value: -1.9189
- type: nauc_map_at_1000_std
value: -25.111800000000002
- type: nauc_map_at_1000_diff1
value: 31.8865
- type: nauc_recall_at_1_max
value: -1.3643
- type: nauc_recall_at_1_std
value: -22.5875
- type: nauc_recall_at_1_diff1
value: 36.7618
- type: nauc_recall_at_3_max
value: -2.4667000000000003
- type: nauc_recall_at_3_std
value: -27.6077
- type: nauc_recall_at_3_diff1
value: 27.2784
- type: nauc_recall_at_5_max
value: -2.3782
- type: nauc_recall_at_5_std
value: -28.6853
- type: nauc_recall_at_5_diff1
value: 25.5971
- type: nauc_recall_at_10_max
value: -3.2792000000000003
- type: nauc_recall_at_10_std
value: -29.9584
- type: nauc_recall_at_10_diff1
value: 24.7197
- type: nauc_recall_at_20_max
value: -1.2229999999999999
- type: nauc_recall_at_20_std
value: -24.479799999999997
- type: nauc_recall_at_20_diff1
value: 23.377100000000002
- type: nauc_recall_at_100_max
value: 6.815
- type: nauc_recall_at_100_std
value: 5.1981
- type: nauc_recall_at_100_diff1
value: 18.5723
- type: nauc_recall_at_1000_max
value: 38.1041
- type: nauc_recall_at_1000_std
value: 54.1207
- type: nauc_recall_at_1000_diff1
value: 6.8622000000000005
- type: nauc_precision_at_1_max
value: -1.0808
- type: nauc_precision_at_1_std
value: -22.361900000000002
- type: nauc_precision_at_1_diff1
value: 36.9204
- type: nauc_precision_at_3_max
value: -2.2124
- type: nauc_precision_at_3_std
value: -27.3546
- type: nauc_precision_at_3_diff1
value: 27.108700000000002
- type: nauc_precision_at_5_max
value: -1.8263000000000003
- type: nauc_precision_at_5_std
value: -27.977899999999998
- type: nauc_precision_at_5_diff1
value: 24.8638
- type: nauc_precision_at_10_max
value: -2.2207
- type: nauc_precision_at_10_std
value: -27.9458
- type: nauc_precision_at_10_diff1
value: 22.851
- type: nauc_precision_at_20_max
value: 0.5773999999999999
- type: nauc_precision_at_20_std
value: -20.118
- type: nauc_precision_at_20_diff1
value: 19.5377
- type: nauc_precision_at_100_max
value: 9.327399999999999
- type: nauc_precision_at_100_std
value: 8.4253
- type: nauc_precision_at_100_diff1
value: 8.33
- type: nauc_precision_at_1000_max
value: 15.6001
- type: nauc_precision_at_1000_std
value: 18.066
- type: nauc_precision_at_1000_diff1
value: -4.5068
- type: nauc_mrr_at_1_max
value: -1.0808
- type: nauc_mrr_at_1_std
value: -22.361900000000002
- type: nauc_mrr_at_1_diff1
value: 36.9204
- type: nauc_mrr_at_3_max
value: -1.6818
- type: nauc_mrr_at_3_std
value: -24.8193
- type: nauc_mrr_at_3_diff1
value: 32.159
- type: nauc_mrr_at_5_max
value: -1.6575
- type: nauc_mrr_at_5_std
value: -25.0817
- type: nauc_mrr_at_5_diff1
value: 31.800800000000002
- type: nauc_mrr_at_10_max
value: -1.7668
- type: nauc_mrr_at_10_std
value: -25.196800000000003
- type: nauc_mrr_at_10_diff1
value: 31.8144
- type: nauc_mrr_at_20_max
value: -1.6674000000000002
- type: nauc_mrr_at_20_std
value: -24.8741
- type: nauc_mrr_at_20_diff1
value: 31.8324
- type: nauc_mrr_at_100_max
value: -1.6053000000000002
- type: nauc_mrr_at_100_std
value: -24.6091
- type: nauc_mrr_at_100_diff1
value: 31.883
- type: nauc_mrr_at_1000_max
value: -1.6053000000000002
- type: nauc_mrr_at_1000_std
value: -24.627
- type: nauc_mrr_at_1000_diff1
value: 31.896200000000004
- type: main_score
value: 40.325
- task:
type: Classification
dataset:
name: MTEB MTOPDomainClassification (en)
type: mteb/mtop_domain
config: en
split: test
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
metrics:
- type: accuracy
value: 96.311
- type: f1
value: 96.0432
- type: f1_weighted
value: 96.3129
- type: main_score
value: 96.311
- task:
type: Classification
dataset:
name: MTEB MTOPIntentClassification (en)
type: mteb/mtop_intent
config: en
split: test
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
metrics:
- type: accuracy
value: 86.5048
- type: f1
value: 67.3883
- type: f1_weighted
value: 88.2687
- type: main_score
value: 86.5048
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (en)
type: mteb/amazon_massive_intent
config: en
split: test
revision: 4672e20407010da34463acc759c162ca9734bca6
metrics:
- type: accuracy
value: 75.7902
- type: f1
value: 73.2351
- type: f1_weighted
value: 75.5894
- type: main_score
value: 75.7902
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (en)
type: mteb/amazon_massive_scenario
config: en
split: test
revision: fad2c6e8459f9e1c45d9315f4953d921437d70f8
metrics:
- type: accuracy
value: 77.3571
- type: f1
value: 77.3086
- type: f1_weighted
value: 77.235
- type: main_score
value: 77.3571
- task:
type: Clustering
dataset:
name: MTEB MedrxivClusteringP2P (default)
type: mteb/medrxiv-clustering-p2p
config: default
split: test
revision: e7a26af6f3ae46b30dde8737f02c07b1505bcc73
metrics:
- type: v_measure
value: 39.4623
- type: v_measure_std
value: 1.3405
- type: main_score
value: 39.4623
- task:
type: Clustering
dataset:
name: MTEB MedrxivClusteringS2S (default)
type: mteb/medrxiv-clustering-s2s
config: default
split: test
revision: 35191c8c0dca72d8ff3efcd72aa802307d469663
metrics:
- type: v_measure
value: 37.5047
- type: v_measure_std
value: 1.2052
- type: main_score
value: 37.5047
- task:
type: Reranking
dataset:
name: MTEB MindSmallReranking (default)
type: mteb/mind_small
config: default
split: test
revision: 59042f120c80e8afa9cdbb224f67076cec0fc9a7
metrics:
- type: map
value: 28.9125
- type: mrr
value: 29.656900000000004
- type: nAUC_map_max
value: -21.7929
- type: nAUC_map_std
value: -4.2712
- type: nAUC_map_diff1
value: 11.698500000000001
- type: nAUC_mrr_max
value: -16.4251
- type: nAUC_mrr_std
value: -2.1364
- type: nAUC_mrr_diff1
value: 11.3017
- type: main_score
value: 28.9125
- task:
type: Retrieval
dataset:
name: MTEB NFCorpus (default)
type: mteb/nfcorpus
config: default
split: test
revision: ec0fa4fe99da2ff19ca1214b7966684033a58814
metrics:
- type: ndcg_at_1
value: 44.737
- type: ndcg_at_3
value: 40.943000000000005
- type: ndcg_at_5
value: 38.914
- type: ndcg_at_10
value: 35.762
- type: ndcg_at_20
value: 33.274
- type: ndcg_at_100
value: 32.861000000000004
- type: ndcg_at_1000
value: 41.509
- type: map_at_1
value: 5.792
- type: map_at_3
value: 9.506
- type: map_at_5
value: 11.213
- type: map_at_10
value: 13.165
- type: map_at_20
value: 14.663
- type: map_at_100
value: 16.885
- type: map_at_1000
value: 18.368000000000002
- type: recall_at_1
value: 5.792
- type: recall_at_3
value: 10.517
- type: recall_at_5
value: 13.296
- type: recall_at_10
value: 17.37
- type: recall_at_20
value: 21.22
- type: recall_at_100
value: 33.953
- type: recall_at_1000
value: 65.462
- type: precision_at_1
value: 46.749
- type: precision_at_3
value: 38.596000000000004
- type: precision_at_5
value: 34.303
- type: precision_at_10
value: 26.779999999999998
- type: precision_at_20
value: 19.830000000000002
- type: precision_at_100
value: 8.466999999999999
- type: precision_at_1000
value: 2.12
- type: mrr_at_1
value: 46.7492
- type: mrr_at_3
value: 54.02479999999999
- type: mrr_at_5
value: 55.031
- type: mrr_at_10
value: 55.8081
- type: mrr_at_20
value: 56.143699999999995
- type: mrr_at_100
value: 56.4018
- type: mrr_at_1000
value: 56.4497
- type: nauc_ndcg_at_1_max
value: 54.4799
- type: nauc_ndcg_at_1_std
value: 19.8188
- type: nauc_ndcg_at_1_diff1
value: 35.095
- type: nauc_ndcg_at_3_max
value: 49.5282
- type: nauc_ndcg_at_3_std
value: 19.1444
- type: nauc_ndcg_at_3_diff1
value: 25.074800000000003
- type: nauc_ndcg_at_5_max
value: 50.437200000000004
- type: nauc_ndcg_at_5_std
value: 21.5019
- type: nauc_ndcg_at_5_diff1
value: 21.414
- type: nauc_ndcg_at_10_max
value: 46.907199999999996
- type: nauc_ndcg_at_10_std
value: 22.5521
- type: nauc_ndcg_at_10_diff1
value: 19.0604
- type: nauc_ndcg_at_20_max
value: 47.216
- type: nauc_ndcg_at_20_std
value: 24.535
- type: nauc_ndcg_at_20_diff1
value: 18.3393
- type: nauc_ndcg_at_100_max
value: 47.647
- type: nauc_ndcg_at_100_std
value: 25.7305
- type: nauc_ndcg_at_100_diff1
value: 20.5066
- type: nauc_ndcg_at_1000_max
value: 53.0034
- type: nauc_ndcg_at_1000_std
value: 32.229600000000005
- type: nauc_ndcg_at_1000_diff1
value: 21.729799999999997
- type: nauc_map_at_1_max
value: 18.8513
- type: nauc_map_at_1_std
value: -13.5714
- type: nauc_map_at_1_diff1
value: 42.4674
- type: nauc_map_at_3_max
value: 19.8798
- type: nauc_map_at_3_std
value: -12.600700000000002
- type: nauc_map_at_3_diff1
value: 34.545700000000004
- type: nauc_map_at_5_max
value: 24.756800000000002
- type: nauc_map_at_5_std
value: -7.959099999999999
- type: nauc_map_at_5_diff1
value: 29.1707
- type: nauc_map_at_10_max
value: 28.1916
- type: nauc_map_at_10_std
value: -3.1498
- type: nauc_map_at_10_diff1
value: 25.1522
- type: nauc_map_at_20_max
value: 31.9354
- type: nauc_map_at_20_std
value: 2.319
- type: nauc_map_at_20_diff1
value: 22.778100000000002
- type: nauc_map_at_100_max
value: 35.938700000000004
- type: nauc_map_at_100_std
value: 9.3661
- type: nauc_map_at_100_diff1
value: 21.2726
- type: nauc_map_at_1000_max
value: 36.8531
- type: nauc_map_at_1000_std
value: 12.0615
- type: nauc_map_at_1000_diff1
value: 19.761699999999998
- type: nauc_recall_at_1_max
value: 18.8513
- type: nauc_recall_at_1_std
value: -13.5714
- type: nauc_recall_at_1_diff1
value: 42.4674
- type: nauc_recall_at_3_max
value: 17.405
- type: nauc_recall_at_3_std
value: -11.779399999999999
- type: nauc_recall_at_3_diff1
value: 31.8655
- type: nauc_recall_at_5_max
value: 22.8368
- type: nauc_recall_at_5_std
value: -4.7815
- type: nauc_recall_at_5_diff1
value: 23.4258
- type: nauc_recall_at_10_max
value: 23.6849
- type: nauc_recall_at_10_std
value: 0.1013
- type: nauc_recall_at_10_diff1
value: 18.4986
- type: nauc_recall_at_20_max
value: 27.289400000000004
- type: nauc_recall_at_20_std
value: 7.126200000000001
- type: nauc_recall_at_20_diff1
value: 14.6343
- type: nauc_recall_at_100_max
value: 26.9683
- type: nauc_recall_at_100_std
value: 16.145899999999997
- type: nauc_recall_at_100_diff1
value: 9.705
- type: nauc_recall_at_1000_max
value: 18.4336
- type: nauc_recall_at_1000_std
value: 18.2245
- type: nauc_recall_at_1000_diff1
value: 2.3923
- type: nauc_precision_at_1_max
value: 56.8886
- type: nauc_precision_at_1_std
value: 22.122
- type: nauc_precision_at_1_diff1
value: 33.3152
- type: nauc_precision_at_3_max
value: 47.759299999999996
- type: nauc_precision_at_3_std
value: 23.3157
- type: nauc_precision_at_3_diff1
value: 14.015
- type: nauc_precision_at_5_max
value: 48.8089
- type: nauc_precision_at_5_std
value: 28.7149
- type: nauc_precision_at_5_diff1
value: 6.0146999999999995
- type: nauc_precision_at_10_max
value: 41.620200000000004
- type: nauc_precision_at_10_std
value: 32.275999999999996
- type: nauc_precision_at_10_diff1
value: -0.6839
- type: nauc_precision_at_20_max
value: 39.6123
- type: nauc_precision_at_20_std
value: 37.4586
- type: nauc_precision_at_20_diff1
value: -4.5309
- type: nauc_precision_at_100_max
value: 25.199700000000004
- type: nauc_precision_at_100_std
value: 34.449400000000004
- type: nauc_precision_at_100_diff1
value: -9.290700000000001
- type: nauc_precision_at_1000_max
value: 8.876000000000001
- type: nauc_precision_at_1000_std
value: 20.748
- type: nauc_precision_at_1000_diff1
value: -12.327399999999999
- type: nauc_mrr_at_1_max
value: 56.717600000000004
- type: nauc_mrr_at_1_std
value: 20.7515
- type: nauc_mrr_at_1_diff1
value: 33.3152
- type: nauc_mrr_at_3_max
value: 57.90689999999999
- type: nauc_mrr_at_3_std
value: 25.1369
- type: nauc_mrr_at_3_diff1
value: 31.157
- type: nauc_mrr_at_5_max
value: 59.2569
- type: nauc_mrr_at_5_std
value: 27.054000000000002
- type: nauc_mrr_at_5_diff1
value: 30.840400000000002
- type: nauc_mrr_at_10_max
value: 59.44819999999999
- type: nauc_mrr_at_10_std
value: 27.903299999999998
- type: nauc_mrr_at_10_diff1
value: 31.4959
- type: nauc_mrr_at_20_max
value: 59.7104
- type: nauc_mrr_at_20_std
value: 28.2328
- type: nauc_mrr_at_20_diff1
value: 31.330099999999998
- type: nauc_mrr_at_100_max
value: 59.573600000000006
- type: nauc_mrr_at_100_std
value: 28.044900000000002
- type: nauc_mrr_at_100_diff1
value: 31.305100000000003
- type: nauc_mrr_at_1000_max
value: 59.5608
- type: nauc_mrr_at_1000_std
value: 28.0034
- type: nauc_mrr_at_1000_diff1
value: 31.314199999999996
- type: main_score
value: 35.762
- task:
type: Retrieval
dataset:
name: MTEB NQ (default)
type: mteb/nq
config: default
split: test
revision: b774495ed302d8c44a3a7ea25c90dbce03968f31
metrics:
- type: ndcg_at_1
value: 39.89
- type: ndcg_at_3
value: 51.121
- type: ndcg_at_5
value: 55.184
- type: ndcg_at_10
value: 58.63699999999999
- type: ndcg_at_20
value: 60.659
- type: ndcg_at_100
value: 62.429
- type: ndcg_at_1000
value: 62.965
- type: map_at_1
value: 35.361
- type: map_at_3
value: 47.071000000000005
- type: map_at_5
value: 49.571
- type: map_at_10
value: 51.178999999999995
- type: map_at_20
value: 51.827999999999996
- type: map_at_100
value: 52.117000000000004
- type: map_at_1000
value: 52.141000000000005
- type: recall_at_1
value: 35.361
- type: recall_at_3
value: 59.40299999999999
- type: recall_at_5
value: 68.721
- type: recall_at_10
value: 78.64
- type: recall_at_20
value: 86.066
- type: recall_at_100
value: 94.865
- type: recall_at_1000
value: 98.79299999999999
- type: precision_at_1
value: 39.89
- type: precision_at_3
value: 23.078000000000003
- type: precision_at_5
value: 16.182
- type: precision_at_10
value: 9.363000000000001
- type: precision_at_20
value: 5.165
- type: precision_at_100
value: 1.15
- type: precision_at_1000
value: 0.12
- type: mrr_at_1
value: 39.8899
- type: mrr_at_3
value: 50.507000000000005
- type: mrr_at_5
value: 52.4899
- type: mrr_at_10
value: 53.761700000000005
- type: mrr_at_20
value: 54.223600000000005
- type: mrr_at_100
value: 54.427800000000005
- type: mrr_at_1000
value: 54.443299999999994
- type: nauc_ndcg_at_1_max
value: 19.524
- type: nauc_ndcg_at_1_std
value: -5.1782
- type: nauc_ndcg_at_1_diff1
value: 35.5793
- type: nauc_ndcg_at_3_max
value: 24.2974
- type: nauc_ndcg_at_3_std
value: -5.2507
- type: nauc_ndcg_at_3_diff1
value: 29.9937
- type: nauc_ndcg_at_5_max
value: 26.502100000000002
- type: nauc_ndcg_at_5_std
value: -3.6393
- type: nauc_ndcg_at_5_diff1
value: 30.0319
- type: nauc_ndcg_at_10_max
value: 26.66
- type: nauc_ndcg_at_10_std
value: -2.3816
- type: nauc_ndcg_at_10_diff1
value: 30.678100000000004
- type: nauc_ndcg_at_20_max
value: 26.9991
- type: nauc_ndcg_at_20_std
value: -1.5933
- type: nauc_ndcg_at_20_diff1
value: 30.824
- type: nauc_ndcg_at_100_max
value: 26.879199999999997
- type: nauc_ndcg_at_100_std
value: -0.8982
- type: nauc_ndcg_at_100_diff1
value: 31.338
- type: nauc_ndcg_at_1000_max
value: 26.2157
- type: nauc_ndcg_at_1000_std
value: -1.6907999999999999
- type: nauc_ndcg_at_1000_diff1
value: 31.428099999999997
- type: nauc_map_at_1_max
value: 17.2868
- type: nauc_map_at_1_std
value: -7.0931
- type: nauc_map_at_1_diff1
value: 35.9826
- type: nauc_map_at_3_max
value: 23.0406
- type: nauc_map_at_3_std
value: -5.973599999999999
- type: nauc_map_at_3_diff1
value: 31.9658
- type: nauc_map_at_5_max
value: 24.3828
- type: nauc_map_at_5_std
value: -4.8592
- type: nauc_map_at_5_diff1
value: 31.9392
- type: nauc_map_at_10_max
value: 24.4782
- type: nauc_map_at_10_std
value: -4.2431
- type: nauc_map_at_10_diff1
value: 32.130399999999995
- type: nauc_map_at_20_max
value: 24.5589
- type: nauc_map_at_20_std
value: -3.9991
- type: nauc_map_at_20_diff1
value: 32.201299999999996
- type: nauc_map_at_100_max
value: 24.5696
- type: nauc_map_at_100_std
value: -3.8531999999999997
- type: nauc_map_at_100_diff1
value: 32.284
- type: nauc_map_at_1000_max
value: 24.546599999999998
- type: nauc_map_at_1000_std
value: -3.8784
- type: nauc_map_at_1000_diff1
value: 32.2879
- type: nauc_recall_at_1_max
value: 17.2868
- type: nauc_recall_at_1_std
value: -7.0931
- type: nauc_recall_at_1_diff1
value: 35.9826
- type: nauc_recall_at_3_max
value: 26.753300000000003
- type: nauc_recall_at_3_std
value: -5.1822
- type: nauc_recall_at_3_diff1
value: 24.4274
- type: nauc_recall_at_5_max
value: 32.697900000000004
- type: nauc_recall_at_5_std
value: -1.4673
- type: nauc_recall_at_5_diff1
value: 23.5655
- type: nauc_recall_at_10_max
value: 35.22
- type: nauc_recall_at_10_std
value: 3.6904
- type: nauc_recall_at_10_diff1
value: 24.5926
- type: nauc_recall_at_20_max
value: 42.0975
- type: nauc_recall_at_20_std
value: 11.574
- type: nauc_recall_at_20_diff1
value: 23.5964
- type: nauc_recall_at_100_max
value: 62.5657
- type: nauc_recall_at_100_std
value: 45.2673
- type: nauc_recall_at_100_diff1
value: 26.6811
- type: nauc_recall_at_1000_max
value: 78.6598
- type: nauc_recall_at_1000_std
value: 70.7318
- type: nauc_recall_at_1000_diff1
value: 29.530099999999997
- type: nauc_precision_at_1_max
value: 19.524
- type: nauc_precision_at_1_std
value: -5.1782
- type: nauc_precision_at_1_diff1
value: 35.5793
- type: nauc_precision_at_3_max
value: 27.230999999999998
- type: nauc_precision_at_3_std
value: 0.13649999999999998
- type: nauc_precision_at_3_diff1
value: 18.817500000000003
- type: nauc_precision_at_5_max
value: 28.734700000000004
- type: nauc_precision_at_5_std
value: 5.1929
- type: nauc_precision_at_5_diff1
value: 14.3006
- type: nauc_precision_at_10_max
value: 25.3071
- type: nauc_precision_at_10_std
value: 11.0166
- type: nauc_precision_at_10_diff1
value: 9.481
- type: nauc_precision_at_20_max
value: 22.5098
- type: nauc_precision_at_20_std
value: 15.695400000000001
- type: nauc_precision_at_20_diff1
value: 4.5483
- type: nauc_precision_at_100_max
value: 15.834999999999999
- type: nauc_precision_at_100_std
value: 21.391099999999998
- type: nauc_precision_at_100_diff1
value: -2.3594
- type: nauc_precision_at_1000_max
value: 7.2892
- type: nauc_precision_at_1000_std
value: 16.1876
- type: nauc_precision_at_1000_diff1
value: -6.698900000000001
- type: nauc_mrr_at_1_max
value: 19.524
- type: nauc_mrr_at_1_std
value: -5.1782
- type: nauc_mrr_at_1_diff1
value: 35.5793
- type: nauc_mrr_at_3_max
value: 23.3415
- type: nauc_mrr_at_3_std
value: -3.7981000000000003
- type: nauc_mrr_at_3_diff1
value: 30.531799999999997
- type: nauc_mrr_at_5_max
value: 24.2743
- type: nauc_mrr_at_5_std
value: -3.1985
- type: nauc_mrr_at_5_diff1
value: 30.7564
- type: nauc_mrr_at_10_max
value: 24.1952
- type: nauc_mrr_at_10_std
value: -2.9042
- type: nauc_mrr_at_10_diff1
value: 31.2183
- type: nauc_mrr_at_20_max
value: 24.2339
- type: nauc_mrr_at_20_std
value: -2.8143000000000002
- type: nauc_mrr_at_20_diff1
value: 31.252999999999997
- type: nauc_mrr_at_100_max
value: 24.1954
- type: nauc_mrr_at_100_std
value: -2.7797
- type: nauc_mrr_at_100_diff1
value: 31.3283
- type: nauc_mrr_at_1000_max
value: 24.1793
- type: nauc_mrr_at_1000_std
value: -2.7987
- type: nauc_mrr_at_1000_diff1
value: 31.330099999999998
- type: main_score
value: 58.63699999999999
- task:
type: Retrieval
dataset:
name: MTEB QuoraRetrieval (default)
type: mteb/quora
config: default
split: test
revision: e4e08e0b7dbe3c8700f0daef558ff32256715259
metrics:
- type: ndcg_at_1
value: 83.33
- type: ndcg_at_3
value: 87.21900000000001
- type: ndcg_at_5
value: 88.725
- type: ndcg_at_10
value: 89.848
- type: ndcg_at_20
value: 90.426
- type: ndcg_at_100
value: 90.881
- type: ndcg_at_1000
value: 90.947
- type: map_at_1
value: 72.354
- type: map_at_3
value: 83.447
- type: map_at_5
value: 85.3
- type: map_at_10
value: 86.33800000000001
- type: map_at_20
value: 86.752
- type: map_at_100
value: 86.952
- type: map_at_1000
value: 86.965
- type: recall_at_1
value: 72.354
- type: recall_at_3
value: 88.726
- type: recall_at_5
value: 93.07900000000001
- type: recall_at_10
value: 96.392
- type: recall_at_20
value: 98.185
- type: recall_at_100
value: 99.737
- type: recall_at_1000
value: 99.994
- type: precision_at_1
value: 83.33
- type: precision_at_3
value: 38.163000000000004
- type: precision_at_5
value: 25.054
- type: precision_at_10
value: 13.600000000000001
- type: precision_at_20
value: 7.199999999999999
- type: precision_at_100
value: 1.539
- type: precision_at_1000
value: 0.157
- type: mrr_at_1
value: 83.33
- type: mrr_at_3
value: 88.2583
- type: mrr_at_5
value: 88.8703
- type: mrr_at_10
value: 89.1146
- type: mrr_at_20
value: 89.1631
- type: mrr_at_100
value: 89.1825
- type: mrr_at_1000
value: 89.1829
- type: nauc_ndcg_at_1_max
value: 35.1345
- type: nauc_ndcg_at_1_std
value: -51.2196
- type: nauc_ndcg_at_1_diff1
value: 78.4909
- type: nauc_ndcg_at_3_max
value: 32.547399999999996
- type: nauc_ndcg_at_3_std
value: -59.377500000000005
- type: nauc_ndcg_at_3_diff1
value: 76.46300000000001
- type: nauc_ndcg_at_5_max
value: 33.5504
- type: nauc_ndcg_at_5_std
value: -60.3836
- type: nauc_ndcg_at_5_diff1
value: 76.9467
- type: nauc_ndcg_at_10_max
value: 34.1371
- type: nauc_ndcg_at_10_std
value: -59.3526
- type: nauc_ndcg_at_10_diff1
value: 77.1373
- type: nauc_ndcg_at_20_max
value: 34.5537
- type: nauc_ndcg_at_20_std
value: -57.8514
- type: nauc_ndcg_at_20_diff1
value: 77.2059
- type: nauc_ndcg_at_100_max
value: 34.8817
- type: nauc_ndcg_at_100_std
value: -55.6778
- type: nauc_ndcg_at_100_diff1
value: 77.08080000000001
- type: nauc_ndcg_at_1000_max
value: 35.0003
- type: nauc_ndcg_at_1000_std
value: -55.292699999999996
- type: nauc_ndcg_at_1000_diff1
value: 77.078
- type: nauc_map_at_1_max
value: 24.889400000000002
- type: nauc_map_at_1_std
value: -50.5244
- type: nauc_map_at_1_diff1
value: 80.9461
- type: nauc_map_at_3_max
value: 30.461899999999996
- type: nauc_map_at_3_std
value: -61.017999999999994
- type: nauc_map_at_3_diff1
value: 77.8986
- type: nauc_map_at_5_max
value: 31.995800000000003
- type: nauc_map_at_5_std
value: -61.0579
- type: nauc_map_at_5_diff1
value: 77.6265
- type: nauc_map_at_10_max
value: 32.9371
- type: nauc_map_at_10_std
value: -59.662099999999995
- type: nauc_map_at_10_diff1
value: 77.3695
- type: nauc_map_at_20_max
value: 33.3268
- type: nauc_map_at_20_std
value: -58.4642
- type: nauc_map_at_20_diff1
value: 77.2616
- type: nauc_map_at_100_max
value: 33.481300000000005
- type: nauc_map_at_100_std
value: -57.51349999999999
- type: nauc_map_at_100_diff1
value: 77.1762
- type: nauc_map_at_1000_max
value: 33.51
- type: nauc_map_at_1000_std
value: -57.4361
- type: nauc_map_at_1000_diff1
value: 77.173
- type: nauc_recall_at_1_max
value: 24.889400000000002
- type: nauc_recall_at_1_std
value: -50.5244
- type: nauc_recall_at_1_diff1
value: 80.9461
- type: nauc_recall_at_3_max
value: 26.490399999999998
- type: nauc_recall_at_3_std
value: -70.6466
- type: nauc_recall_at_3_diff1
value: 74.3857
- type: nauc_recall_at_5_max
value: 28.3327
- type: nauc_recall_at_5_std
value: -77.8455
- type: nauc_recall_at_5_diff1
value: 73.348
- type: nauc_recall_at_10_max
value: 30.476999999999997
- type: nauc_recall_at_10_std
value: -84.933
- type: nauc_recall_at_10_diff1
value: 73.7724
- type: nauc_recall_at_20_max
value: 31.954700000000003
- type: nauc_recall_at_20_std
value: -88.4871
- type: nauc_recall_at_20_diff1
value: 75.3748
- type: nauc_recall_at_100_max
value: 26.290799999999997
- type: nauc_recall_at_100_std
value: -86.7429
- type: nauc_recall_at_100_diff1
value: 71.1186
- type: nauc_recall_at_1000_max
value: -46.823100000000004
- type: nauc_recall_at_1000_std
value: -34.474
- type: nauc_recall_at_1000_diff1
value: 43.9622
- type: nauc_precision_at_1_max
value: 35.1345
- type: nauc_precision_at_1_std
value: -51.2196
- type: nauc_precision_at_1_diff1
value: 78.4909
- type: nauc_precision_at_3_max
value: 5.0033
- type: nauc_precision_at_3_std
value: 6.1183000000000005
- type: nauc_precision_at_3_diff1
value: -23.093
- type: nauc_precision_at_5_max
value: 0.8462000000000001
- type: nauc_precision_at_5_std
value: 19.284599999999998
- type: nauc_precision_at_5_diff1
value: -34.740700000000004
- type: nauc_precision_at_10_max
value: -2.476
- type: nauc_precision_at_10_std
value: 30.449900000000003
- type: nauc_precision_at_10_diff1
value: -41.373
- type: nauc_precision_at_20_max
value: -4.067
- type: nauc_precision_at_20_std
value: 37.2089
- type: nauc_precision_at_20_diff1
value: -43.4846
- type: nauc_precision_at_100_max
value: -5.4187
- type: nauc_precision_at_100_std
value: 44.7639
- type: nauc_precision_at_100_diff1
value: -44.9325
- type: nauc_precision_at_1000_max
value: -5.309
- type: nauc_precision_at_1000_std
value: 46.4094
- type: nauc_precision_at_1000_diff1
value: -45.0127
- type: nauc_mrr_at_1_max
value: 35.1345
- type: nauc_mrr_at_1_std
value: -51.2196
- type: nauc_mrr_at_1_diff1
value: 78.4909
- type: nauc_mrr_at_3_max
value: 35.5355
- type: nauc_mrr_at_3_std
value: -54.636399999999995
- type: nauc_mrr_at_3_diff1
value: 77.537
- type: nauc_mrr_at_5_max
value: 35.8853
- type: nauc_mrr_at_5_std
value: -54.1871
- type: nauc_mrr_at_5_diff1
value: 77.6977
- type: nauc_mrr_at_10_max
value: 35.8488
- type: nauc_mrr_at_10_std
value: -53.825599999999994
- type: nauc_mrr_at_10_diff1
value: 77.7459
- type: nauc_mrr_at_20_max
value: 35.7887
- type: nauc_mrr_at_20_std
value: -53.778800000000004
- type: nauc_mrr_at_20_diff1
value: 77.7606
- type: nauc_mrr_at_100_max
value: 35.7656
- type: nauc_mrr_at_100_std
value: -53.74640000000001
- type: nauc_mrr_at_100_diff1
value: 77.7597
- type: nauc_mrr_at_1000_max
value: 35.7642
- type: nauc_mrr_at_1000_std
value: -53.744899999999994
- type: nauc_mrr_at_1000_diff1
value: 77.7598
- type: main_score
value: 89.848
- task:
type: Clustering
dataset:
name: MTEB RedditClustering (default)
type: mteb/reddit-clustering
config: default
split: test
revision: 24640382cdbf8abc73003fb0fa6d111a705499eb
metrics:
- type: v_measure
value: 58.794599999999996
- type: v_measure_std
value: 3.7606
- type: main_score
value: 58.794599999999996
- task:
type: Clustering
dataset:
name: MTEB RedditClusteringP2P (default)
type: mteb/reddit-clustering-p2p
config: default
split: test
revision: 385e3cb46b4cfa89021f56c4380204149d0efe33
metrics:
- type: v_measure
value: 65.4871
- type: v_measure_std
value: 13.1853
- type: main_score
value: 65.4871
- task:
type: Retrieval
dataset:
name: MTEB SCIDOCS (default)
type: mteb/scidocs
config: default
split: test
revision: f8c2fcf00f625baaa80f62ec5bd9e1fff3b8ae88
metrics:
- type: ndcg_at_1
value: 26.0
- type: ndcg_at_3
value: 21.369
- type: ndcg_at_5
value: 18.865000000000002
- type: ndcg_at_10
value: 22.847
- type: ndcg_at_20
value: 25.817
- type: ndcg_at_100
value: 31.824
- type: ndcg_at_1000
value: 37.997
- type: map_at_1
value: 5.268
- type: map_at_3
value: 9.604
- type: map_at_5
value: 11.797
- type: map_at_10
value: 13.891
- type: map_at_20
value: 15.062000000000001
- type: map_at_100
value: 16.323
- type: map_at_1000
value: 16.71
- type: recall_at_1
value: 5.268
- type: recall_at_3
value: 12.203
- type: recall_at_5
value: 16.963
- type: recall_at_10
value: 24.29
- type: recall_at_20
value: 31.267
- type: recall_at_100
value: 50.727
- type: recall_at_1000
value: 80.67800000000001
- type: precision_at_1
value: 26.0
- type: precision_at_3
value: 20.067
- type: precision_at_5
value: 16.74
- type: precision_at_10
value: 11.97
- type: precision_at_20
value: 7.7
- type: precision_at_100
value: 2.4979999999999998
- type: precision_at_1000
value: 0.398
- type: mrr_at_1
value: 26.0
- type: mrr_at_3
value: 34.2833
- type: mrr_at_5
value: 35.9333
- type: mrr_at_10
value: 37.5791
- type: mrr_at_20
value: 38.1301
- type: mrr_at_100
value: 38.556200000000004
- type: mrr_at_1000
value: 38.606899999999996
- type: nauc_ndcg_at_1_max
value: 21.9327
- type: nauc_ndcg_at_1_std
value: 8.761800000000001
- type: nauc_ndcg_at_1_diff1
value: 22.0695
- type: nauc_ndcg_at_3_max
value: 27.475300000000004
- type: nauc_ndcg_at_3_std
value: 11.126
- type: nauc_ndcg_at_3_diff1
value: 17.1458
- type: nauc_ndcg_at_5_max
value: 28.116200000000003
- type: nauc_ndcg_at_5_std
value: 13.919799999999999
- type: nauc_ndcg_at_5_diff1
value: 15.894400000000001
- type: nauc_ndcg_at_10_max
value: 30.3757
- type: nauc_ndcg_at_10_std
value: 17.2527
- type: nauc_ndcg_at_10_diff1
value: 14.1508
- type: nauc_ndcg_at_20_max
value: 31.451600000000003
- type: nauc_ndcg_at_20_std
value: 19.9009
- type: nauc_ndcg_at_20_diff1
value: 13.5029
- type: nauc_ndcg_at_100_max
value: 33.9342
- type: nauc_ndcg_at_100_std
value: 25.7798
- type: nauc_ndcg_at_100_diff1
value: 14.335500000000001
- type: nauc_ndcg_at_1000_max
value: 33.5581
- type: nauc_ndcg_at_1000_std
value: 25.082300000000004
- type: nauc_ndcg_at_1000_diff1
value: 14.223099999999999
- type: nauc_map_at_1_max
value: 22.0412
- type: nauc_map_at_1_std
value: 8.932
- type: nauc_map_at_1_diff1
value: 22.2384
- type: nauc_map_at_3_max
value: 26.761400000000002
- type: nauc_map_at_3_std
value: 9.1566
- type: nauc_map_at_3_diff1
value: 17.2375
- type: nauc_map_at_5_max
value: 27.7594
- type: nauc_map_at_5_std
value: 12.6506
- type: nauc_map_at_5_diff1
value: 15.739600000000001
- type: nauc_map_at_10_max
value: 29.6498
- type: nauc_map_at_10_std
value: 15.2716
- type: nauc_map_at_10_diff1
value: 14.638000000000002
- type: nauc_map_at_20_max
value: 30.1827
- type: nauc_map_at_20_std
value: 16.7742
- type: nauc_map_at_20_diff1
value: 14.0863
- type: nauc_map_at_100_max
value: 31.3787
- type: nauc_map_at_100_std
value: 19.3168
- type: nauc_map_at_100_diff1
value: 14.3807
- type: nauc_map_at_1000_max
value: 31.3749
- type: nauc_map_at_1000_std
value: 19.4008
- type: nauc_map_at_1000_diff1
value: 14.3151
- type: nauc_recall_at_1_max
value: 22.0412
- type: nauc_recall_at_1_std
value: 8.932
- type: nauc_recall_at_1_diff1
value: 22.2384
- type: nauc_recall_at_3_max
value: 29.4548
- type: nauc_recall_at_3_std
value: 12.4116
- type: nauc_recall_at_3_diff1
value: 14.9834
- type: nauc_recall_at_5_max
value: 28.7014
- type: nauc_recall_at_5_std
value: 16.1355
- type: nauc_recall_at_5_diff1
value: 12.4951
- type: nauc_recall_at_10_max
value: 31.2425
- type: nauc_recall_at_10_std
value: 21.3563
- type: nauc_recall_at_10_diff1
value: 9.0205
- type: nauc_recall_at_20_max
value: 31.478
- type: nauc_recall_at_20_std
value: 25.4813
- type: nauc_recall_at_20_diff1
value: 7.3628
- type: nauc_recall_at_100_max
value: 33.596199999999996
- type: nauc_recall_at_100_std
value: 37.5122
- type: nauc_recall_at_100_diff1
value: 8.3252
- type: nauc_recall_at_1000_max
value: 30.4869
- type: nauc_recall_at_1000_std
value: 38.8306
- type: nauc_recall_at_1000_diff1
value: 4.6079
- type: nauc_precision_at_1_max
value: 21.9327
- type: nauc_precision_at_1_std
value: 8.761800000000001
- type: nauc_precision_at_1_diff1
value: 22.0695
- type: nauc_precision_at_3_max
value: 29.608600000000003
- type: nauc_precision_at_3_std
value: 12.3347
- type: nauc_precision_at_3_diff1
value: 14.810200000000002
- type: nauc_precision_at_5_max
value: 28.8061
- type: nauc_precision_at_5_std
value: 16.0502
- type: nauc_precision_at_5_diff1
value: 12.251900000000001
- type: nauc_precision_at_10_max
value: 31.3513
- type: nauc_precision_at_10_std
value: 21.226300000000002
- type: nauc_precision_at_10_diff1
value: 8.772499999999999
- type: nauc_precision_at_20_max
value: 31.692999999999998
- type: nauc_precision_at_20_std
value: 25.4628
- type: nauc_precision_at_20_diff1
value: 7.1315
- type: nauc_precision_at_100_max
value: 33.3115
- type: nauc_precision_at_100_std
value: 36.888799999999996
- type: nauc_precision_at_100_diff1
value: 7.820100000000001
- type: nauc_precision_at_1000_max
value: 29.1927
- type: nauc_precision_at_1000_std
value: 36.2523
- type: nauc_precision_at_1000_diff1
value: 3.5833999999999997
- type: nauc_mrr_at_1_max
value: 21.9327
- type: nauc_mrr_at_1_std
value: 8.761800000000001
- type: nauc_mrr_at_1_diff1
value: 22.0695
- type: nauc_mrr_at_3_max
value: 26.1187
- type: nauc_mrr_at_3_std
value: 12.5639
- type: nauc_mrr_at_3_diff1
value: 19.642599999999998
- type: nauc_mrr_at_5_max
value: 25.8562
- type: nauc_mrr_at_5_std
value: 12.495000000000001
- type: nauc_mrr_at_5_diff1
value: 19.3465
- type: nauc_mrr_at_10_max
value: 26.218200000000003
- type: nauc_mrr_at_10_std
value: 13.1243
- type: nauc_mrr_at_10_diff1
value: 18.9542
- type: nauc_mrr_at_20_max
value: 26.422099999999997
- type: nauc_mrr_at_20_std
value: 13.4214
- type: nauc_mrr_at_20_diff1
value: 19.0105
- type: nauc_mrr_at_100_max
value: 26.338
- type: nauc_mrr_at_100_std
value: 13.4264
- type: nauc_mrr_at_100_diff1
value: 18.9729
- type: nauc_mrr_at_1000_max
value: 26.3327
- type: nauc_mrr_at_1000_std
value: 13.3904
- type: nauc_mrr_at_1000_diff1
value: 19.004199999999997
- type: main_score
value: 22.847
- task:
type: STS
dataset:
name: MTEB SICK-R (default)
type: mteb/sickr-sts
config: default
split: test
revision: 20a6d6f312dd54037fe07a32d58e5e168867909d
metrics:
- type: pearson
value: 81.13050000000001
- type: spearman
value: 79.01310000000001
- type: cosine_pearson
value: 81.13050000000001
- type: cosine_spearman
value: 79.01310000000001
- type: manhattan_pearson
value: 79.03999999999999
- type: manhattan_spearman
value: 79.1744
- type: euclidean_pearson
value: 79.0977
- type: euclidean_spearman
value: 79.2268
- type: main_score
value: 79.01310000000001
- task:
type: STS
dataset:
name: MTEB STS12 (default)
type: mteb/sts12-sts
config: default
split: test
revision: a0d554a64d88156834ff5ae9920b964011b16384
metrics:
- type: pearson
value: 86.9675
- type: spearman
value: 80.3531
- type: cosine_pearson
value: 86.9675
- type: cosine_spearman
value: 80.3531
- type: manhattan_pearson
value: 82.2315
- type: manhattan_spearman
value: 79.7004
- type: euclidean_pearson
value: 82.3305
- type: euclidean_spearman
value: 79.8601
- type: main_score
value: 80.3531
- task:
type: STS
dataset:
name: MTEB STS13 (default)
type: mteb/sts13-sts
config: default
split: test
revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca
metrics:
- type: pearson
value: 85.6041
- type: spearman
value: 86.0453
- type: cosine_pearson
value: 85.6041
- type: cosine_spearman
value: 86.0453
- type: manhattan_pearson
value: 85.2548
- type: manhattan_spearman
value: 85.8908
- type: euclidean_pearson
value: 85.253
- type: euclidean_spearman
value: 85.9181
- type: main_score
value: 86.0453
- task:
type: STS
dataset:
name: MTEB STS14 (default)
type: mteb/sts14-sts
config: default
split: test
revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375
metrics:
- type: pearson
value: 82.8792
- type: spearman
value: 82.9681
- type: cosine_pearson
value: 82.8792
- type: cosine_spearman
value: 82.9681
- type: manhattan_pearson
value: 81.4789
- type: manhattan_spearman
value: 82.4797
- type: euclidean_pearson
value: 81.4674
- type: euclidean_spearman
value: 82.4547
- type: main_score
value: 82.9681
- task:
type: STS
dataset:
name: MTEB STS15 (default)
type: mteb/sts15-sts
config: default
split: test
revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3
metrics:
- type: pearson
value: 87.5356
- type: spearman
value: 88.06540000000001
- type: cosine_pearson
value: 87.5356
- type: cosine_spearman
value: 88.06540000000001
- type: manhattan_pearson
value: 87.10759999999999
- type: manhattan_spearman
value: 87.75309999999999
- type: euclidean_pearson
value: 87.1489
- type: euclidean_spearman
value: 87.7857
- type: main_score
value: 88.06540000000001
- task:
type: STS
dataset:
name: MTEB STS16 (default)
type: mteb/sts16-sts
config: default
split: test
revision: 4d8694f8f0e0100860b497b999b3dbed754a0513
metrics:
- type: pearson
value: 85.0208
- type: spearman
value: 86.0136
- type: cosine_pearson
value: 85.0208
- type: cosine_spearman
value: 86.0136
- type: manhattan_pearson
value: 85.22
- type: manhattan_spearman
value: 86.1101
- type: euclidean_pearson
value: 85.2043
- type: euclidean_spearman
value: 86.113
- type: main_score
value: 86.0136
- task:
type: STS
dataset:
name: MTEB STS17 (en-en)
type: mteb/sts17-crosslingual-sts
config: en-en
split: test
revision: faeb762787bd10488a50c8b5be4a3b82e411949c
metrics:
- type: pearson
value: 89.4083
- type: spearman
value: 88.9498
- type: cosine_pearson
value: 89.4083
- type: cosine_spearman
value: 88.9498
- type: manhattan_pearson
value: 89.46539999999999
- type: manhattan_spearman
value: 88.8754
- type: euclidean_pearson
value: 89.4326
- type: euclidean_spearman
value: 88.8148
- type: main_score
value: 88.9498
- task:
type: STS
dataset:
name: MTEB STS22 (en)
type: mteb/sts22-crosslingual-sts
config: en
split: test
revision: de9d86b3b84231dc21f76c7b7af1f28e2f57f6e3
metrics:
- type: pearson
value: 66.60770000000001
- type: spearman
value: 67.1515
- type: cosine_pearson
value: 66.60770000000001
- type: cosine_spearman
value: 67.1515
- type: manhattan_pearson
value: 66.5604
- type: manhattan_spearman
value: 66.4621
- type: euclidean_pearson
value: 66.4628
- type: euclidean_spearman
value: 66.2979
- type: main_score
value: 67.1515
- task:
type: STS
dataset:
name: MTEB STSBenchmark (default)
type: mteb/stsbenchmark-sts
config: default
split: test
revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831
metrics:
- type: pearson
value: 86.86399999999999
- type: spearman
value: 87.7139
- type: cosine_pearson
value: 86.86399999999999
- type: cosine_spearman
value: 87.7139
- type: manhattan_pearson
value: 86.6602
- type: manhattan_spearman
value: 87.2606
- type: euclidean_pearson
value: 86.5924
- type: euclidean_spearman
value: 87.241
- type: main_score
value: 87.7139
- task:
type: Reranking
dataset:
name: MTEB SciDocsRR (default)
type: mteb/scidocs-reranking
config: default
split: test
revision: d3c5e1fc0b855ab6097bf1cda04dd73947d7caab
metrics:
- type: map
value: 84.37360000000001
- type: mrr
value: 95.6275
- type: nAUC_map_max
value: 52.991699999999994
- type: nAUC_map_std
value: 66.8168
- type: nAUC_map_diff1
value: -3.2009999999999996
- type: nAUC_mrr_max
value: 85.7492
- type: nAUC_mrr_std
value: 77.3543
- type: nAUC_mrr_diff1
value: 38.014700000000005
- type: main_score
value: 84.37360000000001
- task:
type: Retrieval
dataset:
name: MTEB SciFact (default)
type: mteb/scifact
config: default
split: test
revision: 0228b52cf27578f30900b9e5271d331663a030d7
metrics:
- type: ndcg_at_1
value: 60.667
- type: ndcg_at_3
value: 68.209
- type: ndcg_at_5
value: 71.409
- type: ndcg_at_10
value: 73.476
- type: ndcg_at_20
value: 74.339
- type: ndcg_at_100
value: 75.57000000000001
- type: ndcg_at_1000
value: 75.955
- type: map_at_1
value: 58.178
- type: map_at_3
value: 65.71900000000001
- type: map_at_5
value: 67.73
- type: map_at_10
value: 68.821
- type: map_at_20
value: 69.07600000000001
- type: map_at_100
value: 69.245
- type: map_at_1000
value: 69.258
- type: recall_at_1
value: 58.178
- type: recall_at_3
value: 73.172
- type: recall_at_5
value: 81.0
- type: recall_at_10
value: 86.867
- type: recall_at_20
value: 90.267
- type: recall_at_100
value: 96.933
- type: recall_at_1000
value: 100.0
- type: precision_at_1
value: 60.667
- type: precision_at_3
value: 26.444000000000003
- type: precision_at_5
value: 18.0
- type: precision_at_10
value: 9.866999999999999
- type: precision_at_20
value: 5.133
- type: precision_at_100
value: 1.097
- type: precision_at_1000
value: 0.11299999999999999
- type: mrr_at_1
value: 60.6667
- type: mrr_at_3
value: 67.1667
- type: mrr_at_5
value: 68.85
- type: mrr_at_10
value: 69.4799
- type: mrr_at_20
value: 69.6658
- type: mrr_at_100
value: 69.8134
- type: mrr_at_1000
value: 69.8257
- type: nauc_ndcg_at_1_max
value: 49.3608
- type: nauc_ndcg_at_1_std
value: 12.742400000000002
- type: nauc_ndcg_at_1_diff1
value: 74.5012
- type: nauc_ndcg_at_3_max
value: 49.524499999999996
- type: nauc_ndcg_at_3_std
value: 7.7241
- type: nauc_ndcg_at_3_diff1
value: 72.0127
- type: nauc_ndcg_at_5_max
value: 51.897099999999995
- type: nauc_ndcg_at_5_std
value: 12.8641
- type: nauc_ndcg_at_5_diff1
value: 69.7789
- type: nauc_ndcg_at_10_max
value: 55.1141
- type: nauc_ndcg_at_10_std
value: 17.136499999999998
- type: nauc_ndcg_at_10_diff1
value: 68.8711
- type: nauc_ndcg_at_20_max
value: 54.74719999999999
- type: nauc_ndcg_at_20_std
value: 17.0485
- type: nauc_ndcg_at_20_diff1
value: 69.4701
- type: nauc_ndcg_at_100_max
value: 53.7619
- type: nauc_ndcg_at_100_std
value: 15.335299999999998
- type: nauc_ndcg_at_100_diff1
value: 70.34479999999999
- type: nauc_ndcg_at_1000_max
value: 53.4516
- type: nauc_ndcg_at_1000_std
value: 14.7843
- type: nauc_ndcg_at_1000_diff1
value: 70.6041
- type: nauc_map_at_1_max
value: 44.9654
- type: nauc_map_at_1_std
value: 5.9821
- type: nauc_map_at_1_diff1
value: 76.2581
- type: nauc_map_at_3_max
value: 47.515299999999996
- type: nauc_map_at_3_std
value: 6.2703
- type: nauc_map_at_3_diff1
value: 73.5279
- type: nauc_map_at_5_max
value: 49.805899999999994
- type: nauc_map_at_5_std
value: 10.1001
- type: nauc_map_at_5_diff1
value: 72.1812
- type: nauc_map_at_10_max
value: 51.9276
- type: nauc_map_at_10_std
value: 12.698200000000002
- type: nauc_map_at_10_diff1
value: 71.6343
- type: nauc_map_at_20_max
value: 51.8856
- type: nauc_map_at_20_std
value: 12.814800000000002
- type: nauc_map_at_20_diff1
value: 71.78179999999999
- type: nauc_map_at_100_max
value: 51.7504
- type: nauc_map_at_100_std
value: 12.5353
- type: nauc_map_at_100_diff1
value: 71.8854
- type: nauc_map_at_1000_max
value: 51.739900000000006
- type: nauc_map_at_1000_std
value: 12.519
- type: nauc_map_at_1000_diff1
value: 71.8964
- type: nauc_recall_at_1_max
value: 44.9654
- type: nauc_recall_at_1_std
value: 5.9821
- type: nauc_recall_at_1_diff1
value: 76.2581
- type: nauc_recall_at_3_max
value: 47.9306
- type: nauc_recall_at_3_std
value: 3.5374000000000003
- type: nauc_recall_at_3_diff1
value: 68.4552
- type: nauc_recall_at_5_max
value: 54.374
- type: nauc_recall_at_5_std
value: 17.646700000000003
- type: nauc_recall_at_5_diff1
value: 60.5644
- type: nauc_recall_at_10_max
value: 69.6484
- type: nauc_recall_at_10_std
value: 38.3671
- type: nauc_recall_at_10_diff1
value: 54.39580000000001
- type: nauc_recall_at_20_max
value: 70.0061
- type: nauc_recall_at_20_std
value: 42.403999999999996
- type: nauc_recall_at_20_diff1
value: 55.3831
- type: nauc_recall_at_100_max
value: 69.02629999999999
- type: nauc_recall_at_100_std
value: 43.850699999999996
- type: nauc_recall_at_100_diff1
value: 57.837
- type: nauc_recall_at_1000_max
value: .nan
- type: nauc_recall_at_1000_std
value: .nan
- type: nauc_recall_at_1000_diff1
value: .nan
- type: nauc_precision_at_1_max
value: 49.3608
- type: nauc_precision_at_1_std
value: 12.742400000000002
- type: nauc_precision_at_1_diff1
value: 74.5012
- type: nauc_precision_at_3_max
value: 45.2627
- type: nauc_precision_at_3_std
value: 15.5113
- type: nauc_precision_at_3_diff1
value: 44.5108
- type: nauc_precision_at_5_max
value: 48.4003
- type: nauc_precision_at_5_std
value: 35.3791
- type: nauc_precision_at_5_diff1
value: 19.7518
- type: nauc_precision_at_10_max
value: 46.688
- type: nauc_precision_at_10_std
value: 47.9876
- type: nauc_precision_at_10_diff1
value: 0.1083
- type: nauc_precision_at_20_max
value: 41.281400000000005
- type: nauc_precision_at_20_std
value: 49.0662
- type: nauc_precision_at_20_diff1
value: -6.2035
- type: nauc_precision_at_100_max
value: 30.0167
- type: nauc_precision_at_100_std
value: 47.2561
- type: nauc_precision_at_100_diff1
value: -22.8584
- type: nauc_precision_at_1000_max
value: 23.724999999999998
- type: nauc_precision_at_1000_std
value: 45.342
- type: nauc_precision_at_1000_diff1
value: -33.29
- type: nauc_mrr_at_1_max
value: 49.3608
- type: nauc_mrr_at_1_std
value: 12.742400000000002
- type: nauc_mrr_at_1_diff1
value: 74.5012
- type: nauc_mrr_at_3_max
value: 51.1718
- type: nauc_mrr_at_3_std
value: 11.739700000000001
- type: nauc_mrr_at_3_diff1
value: 71.5992
- type: nauc_mrr_at_5_max
value: 52.2421
- type: nauc_mrr_at_5_std
value: 14.127
- type: nauc_mrr_at_5_diff1
value: 70.57
- type: nauc_mrr_at_10_max
value: 52.5587
- type: nauc_mrr_at_10_std
value: 14.5207
- type: nauc_mrr_at_10_diff1
value: 70.55709999999999
- type: nauc_mrr_at_20_max
value: 52.3699
- type: nauc_mrr_at_20_std
value: 14.310300000000002
- type: nauc_mrr_at_20_diff1
value: 70.6993
- type: nauc_mrr_at_100_max
value: 52.2734
- type: nauc_mrr_at_100_std
value: 14.0848
- type: nauc_mrr_at_100_diff1
value: 70.8146
- type: nauc_mrr_at_1000_max
value: 52.2622
- type: nauc_mrr_at_1000_std
value: 14.0715
- type: nauc_mrr_at_1000_diff1
value: 70.8239
- type: main_score
value: 73.476
- task:
type: PairClassification
dataset:
name: MTEB SprintDuplicateQuestions (default)
type: mteb/sprintduplicatequestions-pairclassification
config: default
split: test
revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46
metrics:
- type: similarity_accuracy
value: 99.87819999999999
- type: similarity_accuracy_threshold
value: 74.8
- type: similarity_f1
value: 93.79729999999999
- type: similarity_f1_threshold
value: 74.6812
- type: similarity_precision
value: 94.6083
- type: similarity_recall
value: 93.0
- type: similarity_ap
value: 97.1971
- type: cosine_accuracy
value: 99.87819999999999
- type: cosine_accuracy_threshold
value: 74.8
- type: cosine_f1
value: 93.79729999999999
- type: cosine_f1_threshold
value: 74.6812
- type: cosine_precision
value: 94.6083
- type: cosine_recall
value: 93.0
- type: cosine_ap
value: 97.1971
- type: manhattan_accuracy
value: 99.8792
- type: manhattan_accuracy_threshold
value: 47567.8925
- type: manhattan_f1
value: 93.8508
- type: manhattan_f1_threshold
value: 47567.8925
- type: manhattan_precision
value: 94.6138
- type: manhattan_recall
value: 93.10000000000001
- type: manhattan_ap
value: 97.2177
- type: euclidean_accuracy
value: 99.8812
- type: euclidean_accuracy_threshold
value: 2164.0619
- type: euclidean_f1
value: 93.9759
- type: euclidean_f1_threshold
value: 2164.0619
- type: euclidean_precision
value: 94.35480000000001
- type: euclidean_recall
value: 93.60000000000001
- type: euclidean_ap
value: 97.2412
- type: dot_accuracy
value: 99.8446
- type: dot_accuracy_threshold
value: 68470.2454
- type: dot_f1
value: 91.9939
- type: dot_f1_threshold
value: 68470.2454
- type: dot_precision
value: 93.8606
- type: dot_recall
value: 90.2
- type: dot_ap
value: 96.36829999999999
- type: max_accuracy
value: 99.8812
- type: max_f1
value: 93.9759
- type: max_precision
value: 94.6138
- type: max_recall
value: 93.60000000000001
- type: max_ap
value: 97.2412
- type: main_score
value: 97.2412
- task:
type: Clustering
dataset:
name: MTEB StackExchangeClustering (default)
type: mteb/stackexchange-clustering
config: default
split: test
revision: 6cbc1f7b2bc0622f2e39d2c77fa502909748c259
metrics:
- type: v_measure
value: 70.04010000000001
- type: v_measure_std
value: 3.9558999999999997
- type: main_score
value: 70.04010000000001
- task:
type: Clustering
dataset:
name: MTEB StackExchangeClusteringP2P (default)
type: mteb/stackexchange-clustering-p2p
config: default
split: test
revision: 815ca46b2622cec33ccafc3735d572c266efdb44
metrics:
- type: v_measure
value: 42.4207
- type: v_measure_std
value: 1.3677
- type: main_score
value: 42.4207
- task:
type: Reranking
dataset:
name: MTEB StackOverflowDupQuestions (default)
type: mteb/stackoverflowdupquestions-reranking
config: default
split: test
revision: e185fbe320c72810689fc5848eb6114e1ef5ec69
metrics:
- type: map
value: 52.7026
- type: mrr
value: 53.5668
- type: nAUC_map_max
value: 12.1758
- type: nAUC_map_std
value: 6.7148
- type: nAUC_map_diff1
value: 39.881499999999996
- type: nAUC_mrr_max
value: 13.0771
- type: nAUC_mrr_std
value: 7.7001
- type: nAUC_mrr_diff1
value: 39.6391
- type: main_score
value: 52.7026
- task:
type: Summarization
dataset:
name: MTEB SummEval (default)
type: mteb/summeval
config: default
split: test
revision: cda12ad7615edc362dbf25a00fdd61d3b1eaf93c
metrics:
- type: pearson
value: 31.346400000000003
- type: spearman
value: 31.5967
- type: cosine_spearman
value: 31.5967
- type: cosine_pearson
value: 31.346400000000003
- type: dot_spearman
value: 28.5388
- type: dot_pearson
value: 31.005300000000002
- type: main_score
value: 31.5967
- task:
type: Retrieval
dataset:
name: MTEB TRECCOVID (default)
type: mteb/trec-covid
config: default
split: test
revision: bb9466bac8153a0349341eb1b22e06409e78ef4e
metrics:
- type: ndcg_at_1
value: 87.0
- type: ndcg_at_3
value: 84.693
- type: ndcg_at_5
value: 82.211
- type: ndcg_at_10
value: 80.55
- type: ndcg_at_20
value: 77.766
- type: ndcg_at_100
value: 62.881
- type: ndcg_at_1000
value: 56.510000000000005
- type: map_at_1
value: 0.251
- type: map_at_3
value: 0.7000000000000001
- type: map_at_5
value: 1.124
- type: map_at_10
value: 2.114
- type: map_at_20
value: 3.837
- type: map_at_100
value: 12.903999999999998
- type: map_at_1000
value: 31.184
- type: recall_at_1
value: 0.251
- type: recall_at_3
value: 0.72
- type: recall_at_5
value: 1.179
- type: recall_at_10
value: 2.271
- type: recall_at_20
value: 4.242
- type: recall_at_100
value: 16.012999999999998
- type: recall_at_1000
value: 53.556000000000004
- type: precision_at_1
value: 92.0
- type: precision_at_3
value: 88.667
- type: precision_at_5
value: 86.8
- type: precision_at_10
value: 85.8
- type: precision_at_20
value: 82.39999999999999
- type: precision_at_100
value: 64.8
- type: precision_at_1000
value: 24.832
- type: mrr_at_1
value: 92.0
- type: mrr_at_3
value: 95.0
- type: mrr_at_5
value: 95.0
- type: mrr_at_10
value: 95.0
- type: mrr_at_20
value: 95.0
- type: mrr_at_100
value: 95.0
- type: mrr_at_1000
value: 95.0
- type: nauc_ndcg_at_1_max
value: 73.7596
- type: nauc_ndcg_at_1_std
value: 52.21130000000001
- type: nauc_ndcg_at_1_diff1
value: -8.4225
- type: nauc_ndcg_at_3_max
value: 68.513
- type: nauc_ndcg_at_3_std
value: 61.9698
- type: nauc_ndcg_at_3_diff1
value: -13.079099999999999
- type: nauc_ndcg_at_5_max
value: 60.7482
- type: nauc_ndcg_at_5_std
value: 66.56830000000001
- type: nauc_ndcg_at_5_diff1
value: -12.947500000000002
- type: nauc_ndcg_at_10_max
value: 57.4673
- type: nauc_ndcg_at_10_std
value: 65.25999999999999
- type: nauc_ndcg_at_10_diff1
value: -14.4235
- type: nauc_ndcg_at_20_max
value: 61.1214
- type: nauc_ndcg_at_20_std
value: 73.60640000000001
- type: nauc_ndcg_at_20_diff1
value: -18.1836
- type: nauc_ndcg_at_100_max
value: 55.3917
- type: nauc_ndcg_at_100_std
value: 80.9228
- type: nauc_ndcg_at_100_diff1
value: -13.6584
- type: nauc_ndcg_at_1000_max
value: 61.6035
- type: nauc_ndcg_at_1000_std
value: 77.73299999999999
- type: nauc_ndcg_at_1000_diff1
value: 9.456199999999999
- type: nauc_map_at_1_max
value: 3.0159
- type: nauc_map_at_1_std
value: -6.6826
- type: nauc_map_at_1_diff1
value: 19.3295
- type: nauc_map_at_3_max
value: 11.3326
- type: nauc_map_at_3_std
value: 0.2297
- type: nauc_map_at_3_diff1
value: 18.4889
- type: nauc_map_at_5_max
value: 12.8623
- type: nauc_map_at_5_std
value: 3.1086
- type: nauc_map_at_5_diff1
value: 15.2538
- type: nauc_map_at_10_max
value: 15.9145
- type: nauc_map_at_10_std
value: 5.8626
- type: nauc_map_at_10_diff1
value: 11.5455
- type: nauc_map_at_20_max
value: 24.6148
- type: nauc_map_at_20_std
value: 17.161199999999997
- type: nauc_map_at_20_diff1
value: 7.6256
- type: nauc_map_at_100_max
value: 42.070299999999996
- type: nauc_map_at_100_std
value: 48.926700000000004
- type: nauc_map_at_100_diff1
value: 0.16
- type: nauc_map_at_1000_max
value: 63.9887
- type: nauc_map_at_1000_std
value: 81.2657
- type: nauc_map_at_1000_diff1
value: 4.1088
- type: nauc_recall_at_1_max
value: 3.0159
- type: nauc_recall_at_1_std
value: -6.6826
- type: nauc_recall_at_1_diff1
value: 19.3295
- type: nauc_recall_at_3_max
value: 7.7778
- type: nauc_recall_at_3_std
value: -3.3724
- type: nauc_recall_at_3_diff1
value: 17.9181
- type: nauc_recall_at_5_max
value: 6.716900000000001
- type: nauc_recall_at_5_std
value: -2.6891000000000003
- type: nauc_recall_at_5_diff1
value: 16.3817
- type: nauc_recall_at_10_max
value: 7.7518
- type: nauc_recall_at_10_std
value: -1.9855
- type: nauc_recall_at_10_diff1
value: 13.4496
- type: nauc_recall_at_20_max
value: 14.4895
- type: nauc_recall_at_20_std
value: 7.2935
- type: nauc_recall_at_20_diff1
value: 11.2986
- type: nauc_recall_at_100_max
value: 29.8636
- type: nauc_recall_at_100_std
value: 33.5546
- type: nauc_recall_at_100_diff1
value: 7.0793
- type: nauc_recall_at_1000_max
value: 57.184000000000005
- type: nauc_recall_at_1000_std
value: 65.3208
- type: nauc_recall_at_1000_diff1
value: 15.7381
- type: nauc_precision_at_1_max
value: 93.4641
- type: nauc_precision_at_1_std
value: 80.6839
- type: nauc_precision_at_1_diff1
value: 21.592
- type: nauc_precision_at_3_max
value: 87.6596
- type: nauc_precision_at_3_std
value: 71.28370000000001
- type: nauc_precision_at_3_diff1
value: -0.5263
- type: nauc_precision_at_5_max
value: 69.3194
- type: nauc_precision_at_5_std
value: 67.4507
- type: nauc_precision_at_5_diff1
value: 5.8362
- type: nauc_precision_at_10_max
value: 62.393299999999996
- type: nauc_precision_at_10_std
value: 62.443599999999996
- type: nauc_precision_at_10_diff1
value: -5.3395
- type: nauc_precision_at_20_max
value: 63.4842
- type: nauc_precision_at_20_std
value: 68.95599999999999
- type: nauc_precision_at_20_diff1
value: -13.494100000000001
- type: nauc_precision_at_100_max
value: 59.24549999999999
- type: nauc_precision_at_100_std
value: 81.3779
- type: nauc_precision_at_100_diff1
value: -11.0792
- type: nauc_precision_at_1000_max
value: 44.8354
- type: nauc_precision_at_1000_std
value: 55.232099999999996
- type: nauc_precision_at_1000_diff1
value: -1.4931
- type: nauc_mrr_at_1_max
value: 93.4641
- type: nauc_mrr_at_1_std
value: 80.6839
- type: nauc_mrr_at_1_diff1
value: 21.592
- type: nauc_mrr_at_3_max
value: 93.8998
- type: nauc_mrr_at_3_std
value: 79.3962
- type: nauc_mrr_at_3_diff1
value: 19.3371
- type: nauc_mrr_at_5_max
value: 93.8998
- type: nauc_mrr_at_5_std
value: 79.3962
- type: nauc_mrr_at_5_diff1
value: 19.3371
- type: nauc_mrr_at_10_max
value: 93.8998
- type: nauc_mrr_at_10_std
value: 79.3962
- type: nauc_mrr_at_10_diff1
value: 19.3371
- type: nauc_mrr_at_20_max
value: 93.8998
- type: nauc_mrr_at_20_std
value: 79.3962
- type: nauc_mrr_at_20_diff1
value: 19.3371
- type: nauc_mrr_at_100_max
value: 93.8998
- type: nauc_mrr_at_100_std
value: 79.3962
- type: nauc_mrr_at_100_diff1
value: 19.3371
- type: nauc_mrr_at_1000_max
value: 93.8998
- type: nauc_mrr_at_1000_std
value: 79.3962
- type: nauc_mrr_at_1000_diff1
value: 19.3371
- type: main_score
value: 80.55
- task:
type: Retrieval
dataset:
name: MTEB Touche2020 (default)
type: mteb/touche2020
config: default
split: test
revision: a34f9a33db75fa0cbb21bb5cfc3dae8dc8bec93f
metrics:
- type: ndcg_at_1
value: 18.367
- type: ndcg_at_3
value: 23.105999999999998
- type: ndcg_at_5
value: 22.423000000000002
- type: ndcg_at_10
value: 21.83
- type: ndcg_at_20
value: 23.534
- type: ndcg_at_100
value: 33.332
- type: ndcg_at_1000
value: 44.842999999999996
- type: map_at_1
value: 1.52
- type: map_at_3
value: 3.811
- type: map_at_5
value: 5.4879999999999995
- type: map_at_10
value: 8.204
- type: map_at_20
value: 10.387
- type: map_at_100
value: 13.633000000000001
- type: map_at_1000
value: 15.156
- type: recall_at_1
value: 1.52
- type: recall_at_3
value: 5.466
- type: recall_at_5
value: 8.927
- type: recall_at_10
value: 15.237
- type: recall_at_20
value: 22.841
- type: recall_at_100
value: 44.586999999999996
- type: recall_at_1000
value: 79.199
- type: precision_at_1
value: 20.408
- type: precision_at_3
value: 25.169999999999998
- type: precision_at_5
value: 23.673
- type: precision_at_10
value: 20.408
- type: precision_at_20
value: 16.531000000000002
- type: precision_at_100
value: 7.204000000000001
- type: precision_at_1000
value: 1.473
- type: mrr_at_1
value: 20.4082
- type: mrr_at_3
value: 35.374100000000006
- type: mrr_at_5
value: 37.7211
- type: mrr_at_10
value: 39.7068
- type: mrr_at_20
value: 40.6272
- type: mrr_at_100
value: 40.7905
- type: mrr_at_1000
value: 40.805
- type: nauc_ndcg_at_1_max
value: -25.3799
- type: nauc_ndcg_at_1_std
value: -27.8526
- type: nauc_ndcg_at_1_diff1
value: 11.5616
- type: nauc_ndcg_at_3_max
value: -31.987900000000003
- type: nauc_ndcg_at_3_std
value: -18.1926
- type: nauc_ndcg_at_3_diff1
value: 15.4188
- type: nauc_ndcg_at_5_max
value: -29.2499
- type: nauc_ndcg_at_5_std
value: -18.8992
- type: nauc_ndcg_at_5_diff1
value: 9.677
- type: nauc_ndcg_at_10_max
value: -25.427899999999998
- type: nauc_ndcg_at_10_std
value: -19.0155
- type: nauc_ndcg_at_10_diff1
value: 1.5350000000000001
- type: nauc_ndcg_at_20_max
value: -25.007800000000003
- type: nauc_ndcg_at_20_std
value: -6.626899999999999
- type: nauc_ndcg_at_20_diff1
value: -2.0142
- type: nauc_ndcg_at_100_max
value: -24.7187
- type: nauc_ndcg_at_100_std
value: 18.587899999999998
- type: nauc_ndcg_at_100_diff1
value: -7.925599999999999
- type: nauc_ndcg_at_1000_max
value: -20.9609
- type: nauc_ndcg_at_1000_std
value: 27.360400000000002
- type: nauc_ndcg_at_1000_diff1
value: -5.3411
- type: nauc_map_at_1_max
value: -26.3166
- type: nauc_map_at_1_std
value: -27.701900000000002
- type: nauc_map_at_1_diff1
value: 14.4953
- type: nauc_map_at_3_max
value: -19.4984
- type: nauc_map_at_3_std
value: -26.0187
- type: nauc_map_at_3_diff1
value: 18.9316
- type: nauc_map_at_5_max
value: -17.6688
- type: nauc_map_at_5_std
value: -27.4662
- type: nauc_map_at_5_diff1
value: 16.3786
- type: nauc_map_at_10_max
value: -9.727
- type: nauc_map_at_10_std
value: -25.4592
- type: nauc_map_at_10_diff1
value: 8.434999999999999
- type: nauc_map_at_20_max
value: -14.2879
- type: nauc_map_at_20_std
value: -17.5881
- type: nauc_map_at_20_diff1
value: 2.4941
- type: nauc_map_at_100_max
value: -15.804499999999999
- type: nauc_map_at_100_std
value: -2.6222
- type: nauc_map_at_100_diff1
value: -4.3869
- type: nauc_map_at_1000_max
value: -15.4637
- type: nauc_map_at_1000_std
value: 1.8402000000000003
- type: nauc_map_at_1000_diff1
value: -5.3595
- type: nauc_recall_at_1_max
value: -26.3166
- type: nauc_recall_at_1_std
value: -27.701900000000002
- type: nauc_recall_at_1_diff1
value: 14.4953
- type: nauc_recall_at_3_max
value: -18.4525
- type: nauc_recall_at_3_std
value: -22.7019
- type: nauc_recall_at_3_diff1
value: 14.5105
- type: nauc_recall_at_5_max
value: -16.8608
- type: nauc_recall_at_5_std
value: -26.2799
- type: nauc_recall_at_5_diff1
value: 6.910299999999999
- type: nauc_recall_at_10_max
value: -11.498700000000001
- type: nauc_recall_at_10_std
value: -22.290499999999998
- type: nauc_recall_at_10_diff1
value: -1.6997000000000002
- type: nauc_recall_at_20_max
value: -16.319
- type: nauc_recall_at_20_std
value: -2.6968
- type: nauc_recall_at_20_diff1
value: -8.5511
- type: nauc_recall_at_100_max
value: -17.741
- type: nauc_recall_at_100_std
value: 36.1914
- type: nauc_recall_at_100_diff1
value: -20.1127
- type: nauc_recall_at_1000_max
value: 3.4278999999999997
- type: nauc_recall_at_1000_std
value: 65.7558
- type: nauc_recall_at_1000_diff1
value: -15.537899999999999
- type: nauc_precision_at_1_max
value: -27.3245
- type: nauc_precision_at_1_std
value: -28.615000000000002
- type: nauc_precision_at_1_diff1
value: 16.2275
- type: nauc_precision_at_3_max
value: -32.1286
- type: nauc_precision_at_3_std
value: -14.0653
- type: nauc_precision_at_3_diff1
value: 15.6075
- type: nauc_precision_at_5_max
value: -27.176299999999998
- type: nauc_precision_at_5_std
value: -15.5885
- type: nauc_precision_at_5_diff1
value: 7.3431999999999995
- type: nauc_precision_at_10_max
value: -26.9241
- type: nauc_precision_at_10_std
value: -11.737
- type: nauc_precision_at_10_diff1
value: -7.630000000000001
- type: nauc_precision_at_20_max
value: -26.901999999999997
- type: nauc_precision_at_20_std
value: 23.7519
- type: nauc_precision_at_20_diff1
value: -21.343799999999998
- type: nauc_precision_at_100_max
value: -16.9757
- type: nauc_precision_at_100_std
value: 70.6663
- type: nauc_precision_at_100_diff1
value: -32.3231
- type: nauc_precision_at_1000_max
value: 20.8431
- type: nauc_precision_at_1000_std
value: 37.8016
- type: nauc_precision_at_1000_diff1
value: -9.911200000000001
- type: nauc_mrr_at_1_max
value: -27.3245
- type: nauc_mrr_at_1_std
value: -28.615000000000002
- type: nauc_mrr_at_1_diff1
value: 16.2275
- type: nauc_mrr_at_3_max
value: -33.332499999999996
- type: nauc_mrr_at_3_std
value: -21.543499999999998
- type: nauc_mrr_at_3_diff1
value: 15.7577
- type: nauc_mrr_at_5_max
value: -34.56
- type: nauc_mrr_at_5_std
value: -21.0279
- type: nauc_mrr_at_5_diff1
value: 10.4699
- type: nauc_mrr_at_10_max
value: -35.4396
- type: nauc_mrr_at_10_std
value: -22.6385
- type: nauc_mrr_at_10_diff1
value: 8.4536
- type: nauc_mrr_at_20_max
value: -34.0343
- type: nauc_mrr_at_20_std
value: -21.4022
- type: nauc_mrr_at_20_diff1
value: 10.7134
- type: nauc_mrr_at_100_max
value: -34.190799999999996
- type: nauc_mrr_at_100_std
value: -21.5996
- type: nauc_mrr_at_100_diff1
value: 10.9828
- type: nauc_mrr_at_1000_max
value: -34.1503
- type: nauc_mrr_at_1000_std
value: -21.662300000000002
- type: nauc_mrr_at_1000_diff1
value: 10.96
- type: main_score
value: 21.83
- task:
type: Classification
dataset:
name: MTEB ToxicConversationsClassification (default)
type: mteb/toxic_conversations_50k
config: default
split: test
revision: edfaf9da55d3dd50d43143d90c1ac476895ae6de
metrics:
- type: accuracy
value: 81.4014
- type: f1
value: 64.3103
- type: f1_weighted
value: 85.0047
- type: ap
value: 22.2804
- type: ap_weighted
value: 22.2804
- type: main_score
value: 81.4014
- task:
type: Classification
dataset:
name: MTEB TweetSentimentExtractionClassification (default)
type: mteb/tweet_sentiment_extraction
config: default
split: test
revision: d604517c81ca91fe16a244d1248fc021f9ecee7a
metrics:
- type: accuracy
value: 66.4403
- type: f1
value: 66.8774
- type: f1_weighted
value: 65.9999
- type: main_score
value: 66.4403
- task:
type: Clustering
dataset:
name: MTEB TwentyNewsgroupsClustering (default)
type: mteb/twentynewsgroups-clustering
config: default
split: test
revision: 6125ec4e24fa026cec8a478383ee943acfbd5449
metrics:
- type: v_measure
value: 53.3153
- type: v_measure_std
value: 1.2923
- type: main_score
value: 53.3153
- task:
type: PairClassification
dataset:
name: MTEB TwitterSemEval2015 (default)
type: mteb/twittersemeval2015-pairclassification
config: default
split: test
revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1
metrics:
- type: similarity_accuracy
value: 85.22380000000001
- type: similarity_accuracy_threshold
value: 74.7432
- type: similarity_f1
value: 66.2828
- type: similarity_f1_threshold
value: 69.9472
- type: similarity_precision
value: 60.765299999999996
- type: similarity_recall
value: 72.9024
- type: similarity_ap
value: 72.0492
- type: cosine_accuracy
value: 85.22380000000001
- type: cosine_accuracy_threshold
value: 74.7432
- type: cosine_f1
value: 66.2828
- type: cosine_f1_threshold
value: 69.9472
- type: cosine_precision
value: 60.765299999999996
- type: cosine_recall
value: 72.9024
- type: cosine_ap
value: 72.0492
- type: manhattan_accuracy
value: 85.10459999999999
- type: manhattan_accuracy_threshold
value: 48810.3699
- type: manhattan_f1
value: 65.7133
- type: manhattan_f1_threshold
value: 53724.462900000006
- type: manhattan_precision
value: 60.3399
- type: manhattan_recall
value: 72.1372
- type: manhattan_ap
value: 71.3681
- type: euclidean_accuracy
value: 85.1404
- type: euclidean_accuracy_threshold
value: 2203.8609
- type: euclidean_f1
value: 65.8107
- type: euclidean_f1_threshold
value: 2445.96
- type: euclidean_precision
value: 59.8875
- type: euclidean_recall
value: 73.0343
- type: euclidean_ap
value: 71.3938
- type: dot_accuracy
value: 84.8781
- type: dot_accuracy_threshold
value: 74077.38040000001
- type: dot_f1
value: 65.3706
- type: dot_f1_threshold
value: 69501.5808
- type: dot_precision
value: 60.58559999999999
- type: dot_recall
value: 70.97630000000001
- type: dot_ap
value: 71.0091
- type: max_accuracy
value: 85.22380000000001
- type: max_f1
value: 66.2828
- type: max_precision
value: 60.765299999999996
- type: max_recall
value: 73.0343
- type: max_ap
value: 72.0492
- type: main_score
value: 72.0492
- task:
type: PairClassification
dataset:
name: MTEB TwitterURLCorpus (default)
type: mteb/twitterurlcorpus-pairclassification
config: default
split: test
revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf
metrics:
- type: similarity_accuracy
value: 89.145
- type: similarity_accuracy_threshold
value: 65.00280000000001
- type: similarity_f1
value: 78.78150000000001
- type: similarity_f1_threshold
value: 61.2185
- type: similarity_precision
value: 75.0279
- type: similarity_recall
value: 82.9304
- type: similarity_ap
value: 86.39949999999999
- type: cosine_accuracy
value: 89.145
- type: cosine_accuracy_threshold
value: 65.00280000000001
- type: cosine_f1
value: 78.78150000000001
- type: cosine_f1_threshold
value: 61.2185
- type: cosine_precision
value: 75.0279
- type: cosine_recall
value: 82.9304
- type: cosine_ap
value: 86.39949999999999
- type: manhattan_accuracy
value: 89.05579999999999
- type: manhattan_accuracy_threshold
value: 55381.189
- type: manhattan_f1
value: 78.6152
- type: manhattan_f1_threshold
value: 58447.6685
- type: manhattan_precision
value: 74.77080000000001
- type: manhattan_recall
value: 82.8765
- type: manhattan_ap
value: 86.2899
- type: euclidean_accuracy
value: 89.1179
- type: euclidean_accuracy_threshold
value: 2552.2853999999998
- type: euclidean_f1
value: 78.6816
- type: euclidean_f1_threshold
value: 2660.0677
- type: euclidean_precision
value: 74.4317
- type: euclidean_recall
value: 83.4463
- type: euclidean_ap
value: 86.3158
- type: dot_accuracy
value: 88.81710000000001
- type: dot_accuracy_threshold
value: 58383.1421
- type: dot_f1
value: 78.2367
- type: dot_f1_threshold
value: 54826.550299999995
- type: dot_precision
value: 73.7657
- type: dot_recall
value: 83.2846
- type: dot_ap
value: 85.5699
- type: max_accuracy
value: 89.145
- type: max_f1
value: 78.78150000000001
- type: max_precision
value: 75.0279
- type: max_recall
value: 83.4463
- type: max_ap
value: 86.39949999999999
- type: main_score
value: 86.39949999999999
---
# cde-small-v2
> [!NOTE]
> **Note on parameter count:** Although HuggingFace reports the size of this model as 281M params, really it can be thought of as 140M. That's because our weights actually contain the weights of two models (dubbed "first stage" and "second stage"), and only the second-stage model is used to compute embeddings at search time.
<a href="https://github.com/jxmorris12/cde">Github</a>
Our new model that naturally integrates "context tokens" into the embedding process. As of January 13th, 2025, `cde-small-v2` is the best small model (under 400M params) on the [MTEB leaderboard](https://huggingface.co/spaces/mteb/leaderboard) for text embedding models, with an average score of 65.58.
👉 <b><a href="https://colab.research.google.com/drive/1r8xwbp7_ySL9lP-ve4XMJAHjidB9UkbL?usp=sharing">Try on Colab</a></b>
<br>
👉 <b><a href="https://arxiv.org/abs/2410.02525">Contextual Document Embeddings (ArXiv)</a></b>
<br>
<hr>
# How to use `cde-small-v2`
Our embedding model needs to be used in *two stages*. The first stage is to gather some dataset information by embedding a subset of the corpus using our "first-stage" model. The second stage is to actually embed queries and documents, conditioning on the corpus information from the first stage. Note that we can do the first stage part offline and only use the second-stage weights at inference time.
</details>
## With Transformers
<details>
<summary>Click to learn how to use cde-small-v2 with Transformers</summary>
### Loading the model
Our model can be loaded using `transformers` out-of-the-box with "trust remote code" enabled. We use the default BERT uncased tokenizer:
```python
import transformers
model = transformers.AutoModel.from_pretrained("jxm/cde-small-v2", trust_remote_code=True)
tokenizer = transformers.AutoTokenizer.from_pretrained("answerdotai/ModernBERT-base")
```
#### Note on prefixes
*Nota bene*: Like all state-of-the-art embedding models, our model was trained with task-specific prefixes. To do retrieval, you can prepend the following strings to queries & documents:
```python
query_prefix = "search_query: "
document_prefix = "search_document: "
```
### First stage
```python
minicorpus_size = model.config.transductive_corpus_size
minicorpus_docs = [ ... ] # Put some strings here that are representative of your corpus, for example by calling random.sample(corpus, k=minicorpus_size)
assert len(minicorpus_docs) == minicorpus_size # You must use exactly this many documents in the minicorpus. You can oversample if your corpus is smaller.
minicorpus_docs = tokenizer(
[document_prefix + doc for doc in minicorpus_docs],
truncation=True,
padding=True,
max_length=512,
return_tensors="pt"
).to(model.device)
import torch
from tqdm.autonotebook import tqdm
batch_size = 32
dataset_embeddings = []
for i in tqdm(range(0, len(minicorpus_docs["input_ids"]), batch_size)):
minicorpus_docs_batch = {k: v[i:i+batch_size] for k,v in minicorpus_docs.items()}
with torch.no_grad():
dataset_embeddings.append(
model.first_stage_model(**minicorpus_docs_batch)
)
dataset_embeddings = torch.cat(dataset_embeddings)
```
### Running the second stage
Now that we have obtained "dataset embeddings" we can embed documents and queries like normal. Remember to use the document prefix for documents:
```python
docs = tokenizer(
[document_prefix + doc for doc in docs],
truncation=True,
padding=True,
max_length=512,
return_tensors="pt"
).to(model.device)
with torch.no_grad():
doc_embeddings = model.second_stage_model(
input_ids=docs["input_ids"],
attention_mask=docs["attention_mask"],
dataset_embeddings=dataset_embeddings,
)
doc_embeddings /= doc_embeddings.norm(p=2, dim=1, keepdim=True)
```
and the query prefix for queries:
```python
queries = queries.select(range(16))["text"]
queries = tokenizer(
[query_prefix + query for query in queries],
truncation=True,
padding=True,
max_length=512,
return_tensors="pt"
).to(model.device)
with torch.no_grad():
query_embeddings = model.second_stage_model(
input_ids=queries["input_ids"],
attention_mask=queries["attention_mask"],
dataset_embeddings=dataset_embeddings,
)
query_embeddings /= query_embeddings.norm(p=2, dim=1, keepdim=True)
```
these embeddings can be compared using dot product, since they're normalized.
</details>
### What if I don't know what my corpus will be ahead of time?
If you can't obtain corpus information ahead of time, you still have to pass *something* as the dataset embeddings; our model will work fine in this case, but not quite as well; without corpus information, our model performance drops from 65.0 to 63.8 on MTEB. We provide [some random strings](https://huggingface.co/jxm/cde-small-v2/resolve/main/random_strings.txt) that worked well for us that can be used as a substitute for corpus sampling.
## With Sentence Transformers
<details open="">
<summary>Click to learn how to use cde-small-v2 with Sentence Transformers</summary>
### Loading the model
Our model can be loaded using `sentence-transformers` out-of-the-box with "trust remote code" enabled:
```python
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("jxm/cde-small-v2", trust_remote_code=True)
```
#### Note on prefixes
*Nota bene*: Like all state-of-the-art embedding models, our model was trained with task-specific prefixes. To do retrieval, you can use `prompt_name="query"` and `prompt_name="document"` in the `encode` method of the model when embedding queries and documents, respectively.
### First stage
```python
minicorpus_size = model[0].config.transductive_corpus_size
minicorpus_docs = [ ... ] # Put some strings here that are representative of your corpus, for example by calling random.sample(corpus, k=minicorpus_size)
assert len(minicorpus_docs) == minicorpus_size # You must use exactly this many documents in the minicorpus. You can oversample if your corpus is smaller.
dataset_embeddings = model.encode(
minicorpus_docs,
prompt_name="document",
convert_to_tensor=True
)
```
### Running the second stage
Now that we have obtained "dataset embeddings" we can embed documents and queries like normal. Remember to use the document prompt for documents:
```python
docs = [...]
queries = [...]
doc_embeddings = model.encode(
docs,
prompt_name="document",
dataset_embeddings=dataset_embeddings,
convert_to_tensor=True,
)
query_embeddings = model.encode(
queries,
prompt_name="query",
dataset_embeddings=dataset_embeddings,
convert_to_tensor=True,
)
```
these embeddings can be compared using cosine similarity via `model.similarity`:
```python
similarities = model.similarity(query_embeddings, doc_embeddings)
topk_values, topk_indices = similarities.topk(5)
```
<details>
<summary>Click here for a full copy-paste ready example</summary>
```python
from sentence_transformers import SentenceTransformer
from datasets import load_dataset
# 1. Load the Sentence Transformer model
model = SentenceTransformer("jxm/cde-small-v2", trust_remote_code=True)
context_docs_size = model[0].config.transductive_corpus_size # 512
# 2. Load the dataset: context dataset, docs, and queries
dataset = load_dataset("sentence-transformers/natural-questions", split="train")
dataset.shuffle(seed=42)
# 10 queries, 512 context docs, 500 docs
queries = dataset["query"][:10]
docs = dataset["answer"][:2000]
context_docs = dataset["answer"][-context_docs_size:] # Last 512 docs
# 3. First stage: embed the context docs
dataset_embeddings = model.encode(
context_docs,
prompt_name="document",
convert_to_tensor=True,
)
# 4. Second stage: embed the docs and queries
doc_embeddings = model.encode(
docs,
prompt_name="document",
dataset_embeddings=dataset_embeddings,
convert_to_tensor=True,
)
query_embeddings = model.encode(
queries,
prompt_name="query",
dataset_embeddings=dataset_embeddings,
convert_to_tensor=True,
)
# 5. Compute the similarity between the queries and docs
similarities = model.similarity(query_embeddings, doc_embeddings)
topk_values, topk_indices = similarities.topk(5)
print(topk_values)
print(topk_indices)
"""
tensor([[0.5495, 0.5426, 0.5423, 0.5292, 0.5286],
[0.6357, 0.6334, 0.6177, 0.5862, 0.5794],
[0.7648, 0.5452, 0.5000, 0.4959, 0.4881],
[0.6802, 0.5225, 0.5178, 0.5160, 0.5075],
[0.6947, 0.5843, 0.5619, 0.5344, 0.5298],
[0.7742, 0.7742, 0.7742, 0.7231, 0.6224],
[0.8853, 0.6667, 0.5829, 0.5795, 0.5769],
[0.6911, 0.6127, 0.6003, 0.5986, 0.5936],
[0.6796, 0.6053, 0.6000, 0.5911, 0.5884],
[0.7624, 0.5589, 0.5428, 0.5278, 0.5275]], device='cuda:0')
tensor([[ 0, 296, 234, 1651, 1184],
[1542, 466, 438, 1207, 1911],
[ 2, 1562, 632, 1852, 382],
[ 3, 694, 932, 1765, 662],
[ 4, 35, 747, 26, 432],
[ 534, 175, 5, 1495, 575],
[ 6, 1802, 1875, 747, 21],
[ 7, 1913, 1936, 640, 6],
[ 8, 747, 167, 1318, 1743],
[ 9, 1583, 1145, 219, 357]], device='cuda:0')
"""
# As you can see, almost every query_i has document_i as the most similar document.
# 6. Print the top-k results
for query_idx, top_doc_idx in enumerate(topk_indices[:, 0]):
print(f"Query {query_idx}: {queries[query_idx]}")
print(f"Top Document: {docs[top_doc_idx]}")
print()
"""
Query 0: when did richmond last play in a preliminary final
Top Document: Richmond Football Club Richmond began 2017 with 5 straight wins, a feat it had not achieved since 1995. A series of close losses hampered the Tigers throughout the middle of the season, including a 5-point loss to the Western Bulldogs, 2-point loss to Fremantle, and a 3-point loss to the Giants. Richmond ended the season strongly with convincing victories over Fremantle and St Kilda in the final two rounds, elevating the club to 3rd on the ladder. Richmond's first final of the season against the Cats at the MCG attracted a record qualifying final crowd of 95,028; the Tigers won by 51 points. Having advanced to the first preliminary finals for the first time since 2001, Richmond defeated Greater Western Sydney by 36 points in front of a crowd of 94,258 to progress to the Grand Final against Adelaide, their first Grand Final appearance since 1982. The attendance was 100,021, the largest crowd to a grand final since 1986. The Crows led at quarter time and led by as many as 13, but the Tigers took over the game as it progressed and scored seven straight goals at one point. They eventually would win by 48 points – 16.12 (108) to Adelaide's 8.12 (60) – to end their 37-year flag drought.[22] Dustin Martin also became the first player to win a Premiership medal, the Brownlow Medal and the Norm Smith Medal in the same season, while Damien Hardwick was named AFL Coaches Association Coach of the Year. Richmond's jump from 13th to premiers also marked the biggest jump from one AFL season to the next.
Query 1: who sang what in the world's come over you
Top Document: Life's What You Make It (Talk Talk song) "Life's What You Make It" is a song by the English band Talk Talk. It was released as a single in 1986, the first from the band's album The Colour of Spring. The single was a hit in the UK, peaking at No. 16, and charted in numerous other countries, often reaching the Top 20.
Query 2: who produces the most wool in the world
Top Document: Wool Global wool production is about 2 million tonnes per year, of which 60% goes into apparel. Wool comprises ca 3% of the global textile market, but its value is higher owing to dying and other modifications of the material.[1] Australia is a leading producer of wool which is mostly from Merino sheep but has been eclipsed by China in terms of total weight.[30] New Zealand (2016) is the third-largest producer of wool, and the largest producer of crossbred wool. Breeds such as Lincoln, Romney, Drysdale, and Elliotdale produce coarser fibers, and wool from these sheep is usually used for making carpets.
Query 3: where does alaska the last frontier take place
Top Document: Alaska: The Last Frontier Alaska: The Last Frontier is an American reality cable television series on the Discovery Channel, currently in its 7th season of broadcast. The show documents the extended Kilcher family, descendants of Swiss immigrants and Alaskan pioneers, Yule and Ruth Kilcher, at their homestead 11 miles outside of Homer.[1] By living without plumbing or modern heating, the clan chooses to subsist by farming, hunting and preparing for the long winters.[2] The Kilcher family are relatives of the singer Jewel,[1][3] who has appeared on the show.[4]
Query 4: a day to remember all i want cameos
Top Document: All I Want (A Day to Remember song) The music video for the song, which was filmed in October 2010,[4] was released on January 6, 2011.[5] It features cameos of numerous popular bands and musicians. The cameos are: Tom Denney (A Day to Remember's former guitarist), Pete Wentz, Winston McCall of Parkway Drive, The Devil Wears Prada, Bring Me the Horizon, Sam Carter of Architects, Tim Lambesis of As I Lay Dying, Silverstein, Andrew WK, August Burns Red, Seventh Star, Matt Heafy of Trivium, Vic Fuentes of Pierce the Veil, Mike Herrera of MxPx, and Set Your Goals.[5] Rock Sound called the video "quite excellent".[5]
Query 5: what does the red stripes mean on the american flag
Top Document: Flag of the United States The flag of the United States of America, often referred to as the American flag, is the national flag of the United States. It consists of thirteen equal horizontal stripes of red (top and bottom) alternating with white, with a blue rectangle in the canton (referred to specifically as the "union") bearing fifty small, white, five-pointed stars arranged in nine offset horizontal rows, where rows of six stars (top and bottom) alternate with rows of five stars. The 50 stars on the flag represent the 50 states of the United States of America, and the 13 stripes represent the thirteen British colonies that declared independence from the Kingdom of Great Britain, and became the first states in the U.S.[1] Nicknames for the flag include The Stars and Stripes,[2] Old Glory,[3] and The Star-Spangled Banner.
Query 6: where did they film diary of a wimpy kid
Top Document: Diary of a Wimpy Kid (film) Filming of Diary of a Wimpy Kid was in Vancouver and wrapped up on October 16, 2009.
Query 7: where was beasts of the southern wild filmed
Top Document: Beasts of the Southern Wild The film's fictional setting, "Isle de Charles Doucet", known to its residents as the Bathtub, was inspired by several isolated and independent fishing communities threatened by erosion, hurricanes and rising sea levels in Louisiana's Terrebonne Parish, most notably the rapidly eroding Isle de Jean Charles. It was filmed in Terrebonne Parish town Montegut.[5]
Query 8: what part of the country are you likely to find the majority of the mollisols
Top Document: Mollisol Mollisols occur in savannahs and mountain valleys (such as Central Asia, or the North American Great Plains). These environments have historically been strongly influenced by fire and abundant pedoturbation from organisms such as ants and earthworms. It was estimated that in 2003, only 14 to 26 percent of grassland ecosystems still remained in a relatively natural state (that is, they were not used for agriculture due to the fertility of the A horizon). Globally, they represent ~7% of ice-free land area. As the world's most agriculturally productive soil order, the Mollisols represent one of the more economically important soil orders.
Query 9: when did fosters home for imaginary friends start
Top Document: Foster's Home for Imaginary Friends McCracken conceived the series after adopting two dogs from an animal shelter and applying the concept to imaginary friends. The show first premiered on Cartoon Network on August 13, 2004, as a 90-minute television film. On August 20, it began its normal run of twenty-to-thirty-minute episodes on Fridays, at 7 pm. The series finished its run on May 3, 2009, with a total of six seasons and seventy-nine episodes. McCracken left Cartoon Network shortly after the series ended. Reruns have aired on Boomerang from August 11, 2012 to November 3, 2013 and again from June 1, 2014 to April 3, 2017.
"""
```
</details>
### Colab demo
We've set up a short demo in a Colab notebook showing how you might use our model:
[Try our model in Colab:](https://colab.research.google.com/drive/1ddWeNj9nztHrwtoSEtaArfs7_NZhZA6k?usp=sharing)
### Training details
All non-mentioned other hyperparameters (learning, etc.) are either in the config or CDE paper. If not, please raise an issue here: https://github.com/jxmorris12/cde
#### Model details
cde-small-v2 includes a number of modeling changes from cde-small-v1:
- used the recently-released [ModernBERT](https://huggingface.co/blog/modernbert)
- added a residual connection between the model stages, which helps conditioning and gradient flow
- disabled pooling over instruction tokens
- disable position-embedding nullification over contextual tokens
- disable weight decay (not sure if this one helped or not)
#### Unsupervised training
Trained for six epochs on the nomic-unsupervised dataset with cluster size of 512 and batch size of 512, using GTR clusters and GTE-large filtering. (Probably would have performed better with GTE clustering too, but that's an expensive operation that we didn't rerun.)
#### Supervised training
Trained for four epochs on the BGE dataset with GTE clusters and GTE hard-negative filtering.
### Cite us
Used our model, method, or architecture? Want to cite us? Here's the ArXiv citation information:
```
@misc{morris2024contextualdocumentembeddings,
title={Contextual Document Embeddings},
author={John X. Morris and Alexander M. Rush},
year={2024},
eprint={2410.02525},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2410.02525},
}
``` | [
"SUMMARIZATION"
] | Non_BioNLP |
mrm8488/t5-small-finetuned-squadv2 | mrm8488 | text2text-generation | [
"transformers",
"pytorch",
"t5",
"text2text-generation",
"en",
"dataset:squad_v2",
"arxiv:1910.10683",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 1,646,263,745,000 | 2021-05-06T16:25:28 | 140 | 1 | ---
datasets:
- squad_v2
language: en
---
# T5-small fine-tuned on SQuAD v2
[Google's T5](https://ai.googleblog.com/2020/02/exploring-transfer-learning-with-t5.html) [(small)](https://huggingface.co/t5-small) fine-tuned on [SQuAD v2](https://rajpurkar.github.io/SQuAD-explorer/) for **Q&A** downstream task.
## Details of T5
The **T5** model was presented in [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://arxiv.org/pdf/1910.10683.pdf) by *Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, Peter J. Liu* in Here the abstract:
Transfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned on a downstream task, has emerged as a powerful technique in natural language processing (NLP). The effectiveness of transfer learning has given rise to a diversity of approaches, methodology, and practice. In this paper, we explore the landscape of transfer learning techniques for NLP by introducing a unified framework that converts every language problem into a text-to-text format. Our systematic study compares pre-training objectives, architectures, unlabeled datasets, transfer approaches, and other factors on dozens of language understanding tasks. By combining the insights from our exploration with scale and our new “Colossal Clean Crawled Corpus”, we achieve state-of-the-art results on many benchmarks covering summarization, question answering, text classification, and more. To facilitate future work on transfer learning for NLP, we release our dataset, pre-trained models, and code.
## Details of the downstream task (Q&A) - Dataset 📚 🧐 ❓
Dataset ID: ```squad_v2``` from [Huggingface/NLP](https://github.com/huggingface/nlp)
| Dataset | Split | # samples |
| -------- | ----- | --------- |
| squad_v2 | train | 130319 |
| squad_v2 | valid | 11873 |
How to load it from [nlp](https://github.com/huggingface/nlp)
```python
train_dataset = nlp.load_dataset('squad_v2', split=nlp.Split.TRAIN)
valid_dataset = nlp.load_dataset('squad_v2', split=nlp.Split.VALIDATION)
```
Check out more about this dataset and others in [NLP Viewer](https://huggingface.co/nlp/viewer/)
## Model fine-tuning 🏋️
The training script is a slightly modified version of [this awesome one](https://colab.research.google.com/github/patil-suraj/exploring-T5/blob/master/T5_on_TPU.ipynb) by [Suraj Patil](https://twitter.com/psuraj28)
## Results 📝
| Metric | # Value |
| ------ | --------- |
| **EM** | **69.46** |
| **F1** | **73.01** |
## Model in Action 🚀
```python
from transformers import AutoModelWithLMHead, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("mrm8488/t5-small-finetuned-squadv2")
model = AutoModelWithLMHead.from_pretrained("mrm8488/t5-small-finetuned-squadv2")
def get_answer(question, context):
input_text = "question: %s context: %s </s>" % (question, context)
features = tokenizer([input_text], return_tensors='pt')
output = model.generate(input_ids=features['input_ids'],
attention_mask=features['attention_mask'])
return tokenizer.decode(output[0])
context = "Manuel has created RuPERTa-base (a Spanish RoBERTa) with the support of HF-Transformers and Google"
question = "Who has supported Manuel?"
get_answer(question, context)
# output: 'HF-Transformers and Google'
```
> Created by [Manuel Romero/@mrm8488](https://twitter.com/mrm8488) | [LinkedIn](https://www.linkedin.com/in/manuel-romero-cs/)
> Made with <span style="color: #e25555;">♥</span> in Spain
| [
"TEXT_CLASSIFICATION",
"QUESTION_ANSWERING",
"SUMMARIZATION"
] | Non_BioNLP |
zensalaria/my-nllb-distilled | zensalaria | translation | [
"pytorch",
"nllb",
"translation",
"ace",
"acm",
"acq",
"aeb",
"af",
"ajp",
"ak",
"als",
"am",
"apc",
"ar",
"ars",
"ary",
"arz",
"as",
"ast",
"awa",
"ayr",
"azb",
"azj",
"ba",
"bm",
"ban",
"be",
"bem",
"bn",
"bho",
"bjn",
"bo",
"bs",
"bug",
"bg",
"ca",
"ceb",
"cs",
"cjk",
"ckb",
"crh",
"cy",
"da",
"de",
"dik",
"dyu",
"dz",
"el",
"en",
"eo",
"et",
"eu",
"ee",
"fo",
"fj",
"fi",
"fon",
"fr",
"fur",
"fuv",
"gaz",
"gd",
"ga",
"gl",
"gn",
"gu",
"ht",
"ha",
"he",
"hi",
"hne",
"hr",
"hu",
"hy",
"ig",
"ilo",
"id",
"is",
"it",
"jv",
"ja",
"kab",
"kac",
"kam",
"kn",
"ks",
"ka",
"kk",
"kbp",
"kea",
"khk",
"km",
"ki",
"rw",
"ky",
"kmb",
"kmr",
"knc",
"kg",
"ko",
"lo",
"lij",
"li",
"ln",
"lt",
"lmo",
"ltg",
"lb",
"lua",
"lg",
"luo",
"lus",
"lvs",
"mag",
"mai",
"ml",
"mar",
"min",
"mk",
"mt",
"mni",
"mos",
"mi",
"my",
"nl",
"nn",
"nb",
"npi",
"nso",
"nus",
"ny",
"oc",
"ory",
"pag",
"pa",
"pap",
"pbt",
"pes",
"plt",
"pl",
"pt",
"prs",
"quy",
"ro",
"rn",
"ru",
"sg",
"sa",
"sat",
"scn",
"shn",
"si",
"sk",
"sl",
"sm",
"sn",
"sd",
"so",
"st",
"es",
"sc",
"sr",
"ss",
"su",
"sv",
"swh",
"szl",
"ta",
"taq",
"tt",
"te",
"tg",
"tl",
"th",
"ti",
"tpi",
"tn",
"ts",
"tk",
"tum",
"tr",
"tw",
"tzm",
"ug",
"uk",
"umb",
"ur",
"uzn",
"vec",
"vi",
"war",
"wo",
"xh",
"ydd",
"yo",
"yue",
"zh",
"zsm",
"zu",
"dataset:flores-200",
"license:cc-by-nc-4.0",
"region:us"
] | 1,737,331,881,000 | 2025-01-25T22:17:48 | 18 | 0 | ---
datasets:
- flores-200
language:
- ace
- acm
- acq
- aeb
- af
- ajp
- ak
- als
- am
- apc
- ar
- ars
- ary
- arz
- as
- ast
- awa
- ayr
- azb
- azj
- ba
- bm
- ban
- be
- bem
- bn
- bho
- bjn
- bo
- bs
- bug
- bg
- ca
- ceb
- cs
- cjk
- ckb
- crh
- cy
- da
- de
- dik
- dyu
- dz
- el
- en
- eo
- et
- eu
- ee
- fo
- fj
- fi
- fon
- fr
- fur
- fuv
- gaz
- gd
- ga
- gl
- gn
- gu
- ht
- ha
- he
- hi
- hne
- hr
- hu
- hy
- ig
- ilo
- id
- is
- it
- jv
- ja
- kab
- kac
- kam
- kn
- ks
- ka
- kk
- kbp
- kea
- khk
- km
- ki
- rw
- ky
- kmb
- kmr
- knc
- kg
- ko
- lo
- lij
- li
- ln
- lt
- lmo
- ltg
- lb
- lua
- lg
- luo
- lus
- lvs
- mag
- mai
- ml
- mar
- min
- mk
- mt
- mni
- mos
- mi
- my
- nl
- nn
- nb
- npi
- nso
- nus
- ny
- oc
- ory
- pag
- pa
- pap
- pbt
- pes
- plt
- pl
- pt
- prs
- quy
- ro
- rn
- ru
- sg
- sa
- sat
- scn
- shn
- si
- sk
- sl
- sm
- sn
- sd
- so
- st
- es
- sc
- sr
- ss
- su
- sv
- swh
- szl
- ta
- taq
- tt
- te
- tg
- tl
- th
- ti
- tpi
- tn
- ts
- tk
- tum
- tr
- tw
- tzm
- ug
- uk
- umb
- ur
- uzn
- vec
- vi
- war
- wo
- xh
- ydd
- yo
- yue
- zh
- zsm
- zu
license: cc-by-nc-4.0
metrics:
- bleu
- spbleu
- chrf++
pipeline_tag: translation
tags:
- nllb
language_details: ace_Arab, ace_Latn, acm_Arab, acq_Arab, aeb_Arab, afr_Latn, ajp_Arab,
aka_Latn, amh_Ethi, apc_Arab, arb_Arab, ars_Arab, ary_Arab, arz_Arab, asm_Beng,
ast_Latn, awa_Deva, ayr_Latn, azb_Arab, azj_Latn, bak_Cyrl, bam_Latn, ban_Latn,bel_Cyrl,
bem_Latn, ben_Beng, bho_Deva, bjn_Arab, bjn_Latn, bod_Tibt, bos_Latn, bug_Latn,
bul_Cyrl, cat_Latn, ceb_Latn, ces_Latn, cjk_Latn, ckb_Arab, crh_Latn, cym_Latn,
dan_Latn, deu_Latn, dik_Latn, dyu_Latn, dzo_Tibt, ell_Grek, eng_Latn, epo_Latn,
est_Latn, eus_Latn, ewe_Latn, fao_Latn, pes_Arab, fij_Latn, fin_Latn, fon_Latn,
fra_Latn, fur_Latn, fuv_Latn, gla_Latn, gle_Latn, glg_Latn, grn_Latn, guj_Gujr,
hat_Latn, hau_Latn, heb_Hebr, hin_Deva, hne_Deva, hrv_Latn, hun_Latn, hye_Armn,
ibo_Latn, ilo_Latn, ind_Latn, isl_Latn, ita_Latn, jav_Latn, jpn_Jpan, kab_Latn,
kac_Latn, kam_Latn, kan_Knda, kas_Arab, kas_Deva, kat_Geor, knc_Arab, knc_Latn,
kaz_Cyrl, kbp_Latn, kea_Latn, khm_Khmr, kik_Latn, kin_Latn, kir_Cyrl, kmb_Latn,
kon_Latn, kor_Hang, kmr_Latn, lao_Laoo, lvs_Latn, lij_Latn, lim_Latn, lin_Latn,
lit_Latn, lmo_Latn, ltg_Latn, ltz_Latn, lua_Latn, lug_Latn, luo_Latn, lus_Latn,
mag_Deva, mai_Deva, mal_Mlym, mar_Deva, min_Latn, mkd_Cyrl, plt_Latn, mlt_Latn,
mni_Beng, khk_Cyrl, mos_Latn, mri_Latn, zsm_Latn, mya_Mymr, nld_Latn, nno_Latn,
nob_Latn, npi_Deva, nso_Latn, nus_Latn, nya_Latn, oci_Latn, gaz_Latn, ory_Orya,
pag_Latn, pan_Guru, pap_Latn, pol_Latn, por_Latn, prs_Arab, pbt_Arab, quy_Latn,
ron_Latn, run_Latn, rus_Cyrl, sag_Latn, san_Deva, sat_Beng, scn_Latn, shn_Mymr,
sin_Sinh, slk_Latn, slv_Latn, smo_Latn, sna_Latn, snd_Arab, som_Latn, sot_Latn,
spa_Latn, als_Latn, srd_Latn, srp_Cyrl, ssw_Latn, sun_Latn, swe_Latn, swh_Latn,
szl_Latn, tam_Taml, tat_Cyrl, tel_Telu, tgk_Cyrl, tgl_Latn, tha_Thai, tir_Ethi,
taq_Latn, taq_Tfng, tpi_Latn, tsn_Latn, tso_Latn, tuk_Latn, tum_Latn, tur_Latn,
twi_Latn, tzm_Tfng, uig_Arab, ukr_Cyrl, umb_Latn, urd_Arab, uzn_Latn, vec_Latn,
vie_Latn, war_Latn, wol_Latn, xho_Latn, ydd_Hebr, yor_Latn, yue_Hant, zho_Hans,
zho_Hant, zul_Latn
inference: false
---
# NLLB-200
This is the model card of NLLB-200's distilled 600M variant.
Here are the [metrics](https://tinyurl.com/nllb200densedst600mmetrics) for that particular checkpoint.
- Information about training algorithms, parameters, fairness constraints or other applied approaches, and features. The exact training algorithm, data and the strategies to handle data imbalances for high and low resource languages that were used to train NLLB-200 is described in the paper.
- Paper or other resource for more information NLLB Team et al, No Language Left Behind: Scaling Human-Centered Machine Translation, Arxiv, 2022
- License: CC-BY-NC
- Where to send questions or comments about the model: https://github.com/facebookresearch/fairseq/issues
## Intended Use
- Primary intended uses: NLLB-200 is a machine translation model primarily intended for research in machine translation, - especially for low-resource languages. It allows for single sentence translation among 200 languages. Information on how to - use the model can be found in Fairseq code repository along with the training code and references to evaluation and training data.
- Primary intended users: Primary users are researchers and machine translation research community.
- Out-of-scope use cases: NLLB-200 is a research model and is not released for production deployment. NLLB-200 is trained on general domain text data and is not intended to be used with domain specific texts, such as medical domain or legal domain. The model is not intended to be used for document translation. The model was trained with input lengths not exceeding 512 tokens, therefore translating longer sequences might result in quality degradation. NLLB-200 translations can not be used as certified translations.
## Metrics
• Model performance measures: NLLB-200 model was evaluated using BLEU, spBLEU, and chrF++ metrics widely adopted by machine translation community. Additionally, we performed human evaluation with the XSTS protocol and measured the toxicity of the generated translations.
## Evaluation Data
- Datasets: Flores-200 dataset is described in Section 4
- Motivation: We used Flores-200 as it provides full evaluation coverage of the languages in NLLB-200
- Preprocessing: Sentence-split raw text data was preprocessed using SentencePiece. The
SentencePiece model is released along with NLLB-200.
## Training Data
• We used parallel multilingual data from a variety of sources to train the model. We provide detailed report on data selection and construction process in Section 5 in the paper. We also used monolingual data constructed from Common Crawl. We provide more details in Section 5.2.
## Ethical Considerations
• In this work, we took a reflexive approach in technological development to ensure that we prioritize human users and minimize risks that could be transferred to them. While we reflect on our ethical considerations throughout the article, here are some additional points to highlight. For one, many languages chosen for this study are low-resource languages, with a heavy emphasis on African languages. While quality translation could improve education and information access in many in these communities, such an access could also make groups with lower levels of digital literacy more vulnerable to misinformation or online scams. The latter scenarios could arise if bad actors misappropriate our work for nefarious activities, which we conceive as an example of unintended use. Regarding data acquisition, the training data used for model development were mined from various publicly available sources on the web. Although we invested heavily in data cleaning, personally identifiable information may not be entirely eliminated. Finally, although we did our best to optimize for translation quality, mistranslations produced by the model could remain. Although the odds are low, this could have adverse impact on those who rely on these translations to make important decisions (particularly when related to health and safety).
## Caveats and Recommendations
• Our model has been tested on the Wikimedia domain with limited investigation on other domains supported in NLLB-MD. In addition, the supported languages may have variations that our model is not capturing. Users should make appropriate assessments.
## Carbon Footprint Details
• The carbon dioxide (CO2e) estimate is reported in Section 8.8. | [
"TRANSLATION"
] | Non_BioNLP |
yosefw/roberta-base-am-embed | yosefw | sentence-similarity | [
"sentence-transformers",
"safetensors",
"xlm-roberta",
"sentence-similarity",
"feature-extraction",
"base_model:rasyosef/roberta-base-amharic",
"base_model:finetune:rasyosef/roberta-base-amharic",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] | 1,736,003,113,000 | 2025-01-04T15:05:33 | 9 | 0 | ---
base_model: rasyosef/roberta-base-amharic
library_name: sentence-transformers
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
---
# SentenceTransformer based on rasyosef/roberta-base-amharic
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [rasyosef/roberta-base-amharic](https://huggingface.co/rasyosef/roberta-base-amharic). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
## Model Details
### Model Description
- **Model Type:** Sentence Transformer
- **Base model:** [rasyosef/roberta-base-amharic](https://huggingface.co/rasyosef/roberta-base-amharic) <!-- at revision 3cbc0626fac7ec1b8f73c7d4a58daed076dbacd6 -->
- **Maximum Sequence Length:** 510 tokens
- **Output Dimensionality:** 768 dimensions
- **Similarity Function:** Cosine Similarity
<!-- - **Training Dataset:** Unknown -->
<!-- - **Language:** Unknown -->
<!-- - **License:** Unknown -->
### Model Sources
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
### Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 510, 'do_lower_case': False}) with Transformer model: XLMRobertaModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
(2): Normalize()
)
```
## Usage
### Direct Usage (Sentence Transformers)
First install the Sentence Transformers library:
```bash
pip install -U sentence-transformers
```
Then you can load this model and run inference.
```python
from sentence_transformers import SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("yosefw/roberta-base-am-embed")
# Run inference
sentences = [
'The weather is lovely today.',
"It's so sunny outside!",
'He drove to the stadium.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]
```
<!--
### Direct Usage (Transformers)
<details><summary>Click to see the direct usage in Transformers</summary>
</details>
-->
<!--
### Downstream Usage (Sentence Transformers)
You can finetune this model on your own dataset.
<details><summary>Click to expand</summary>
</details>
-->
<!--
### Out-of-Scope Use
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->
<!--
## Bias, Risks and Limitations
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
-->
<!--
### Recommendations
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
-->
## Training Details
### Framework Versions
- Python: 3.10.12
- Sentence Transformers: 3.3.1
- Transformers: 4.47.1
- PyTorch: 2.5.1+cu121
- Accelerate: 1.2.1
- Datasets:
- Tokenizers: 0.21.0
## Citation
### BibTeX
<!--
## Glossary
*Clearly define terms in order to be accessible across audiences.*
-->
<!--
## Model Card Authors
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->
<!--
## Model Card Contact
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
--> | [
"TEXT_CLASSIFICATION"
] | Non_BioNLP |
dpekach/mnr_electronics_only | dpekach | sentence-similarity | [
"sentence-transformers",
"safetensors",
"xlm-roberta",
"sentence-similarity",
"feature-extraction",
"generated_from_trainer",
"dataset_size:3804390",
"loss:RZTKMatryoshka2dLoss",
"arxiv:1908.10084",
"base_model:intfloat/multilingual-e5-base",
"base_model:finetune:intfloat/multilingual-e5-base",
"model-index",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] | 1,740,501,702,000 | 2025-02-25T16:42:31 | 3 | 0 | ---
base_model: intfloat/multilingual-e5-base
library_name: sentence-transformers
metrics:
- dot_accuracy_10
- dot_precision_10
- dot_recall_10
- dot_ndcg_10
- dot_mrr_10
- dot_map_60
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:3804390
- loss:RZTKMatryoshka2dLoss
widget:
- source_sentence: 'query: чоловічіпіжами'
sentences:
- 'passage: Портативна зарядна станція EcoFlow DELTA 2 1800W 1024 W/h Зарядні станції
EcoFlow Тип акумуляторів Літій-залізо-фосфатні (LiFePO4) Призначення Для всього
будинку Призначення Для ноутбуків Країна-виробник товару Китай Вихідні інтерфейси
Розетка 220 В Вихідні інтерфейси 2 x DC-роз''єм Вихідні інтерфейси Гніздо прикурювача
Вихідні інтерфейси USB Type C Вихідні інтерфейси USB Type A Місткість зарядної
станції, Вт*год 1024 Вихідна потужність (загальна), Вт 1800 Максимальна потужність
заряджання (220В), Вт 1800'
- 'passage: Плата UPS для роутера USB/Li-ion/12V модуль підвищення Аксесуари для
акумуляторів BAT'
- 'passage: Піжама чоловіча на флісі напівбатальна темно-сірого кольору K.S.M. розмір
50-52 (195976) Чоловічі піжами KSM'
- source_sentence: 'query: чоловічіпіжами'
sentences:
- 'passage: Віскі Balvenie Doublewood 12 років витримки 0.05 л 40% (5010327529219_5010327509112)
Balvenie Об''єм, л 0.05 Міцність 40% Витримка 12 років Країна-виробник товару
Велика Британія Вид Віскі односолодовий Особливості Холодна фільтрація Поєднання
Дижестив Смак Солодкий (Sweet) Доставка Готовий до відправлення Доставка Доставка
в магазини ROZETKA'
- 'passage: Віскі GlenAllachie 15yo 0.05 л 46% (5060568320960) Glenallachie Об''єм,
л 0.05 Міцність 46% Витримка 15 років Країна-виробник товару Велика Британія Упаковка
Без упаковки Доставка Доставка в магазини ROZETKA'
- 'passage: Піжама чоловіча комбінована махра 48 темно-синій Жемчужина Стилей Aрт(4612)
Чоловічі піжами Жемчужина Стилей Сезон Демісезонний Сезон Зимовий Розмір 48 Колір
Темно-синій'
- source_sentence: 'query: піна для гоління'
sentences:
- 'passage: Пиджак удлиненный женский Koton 8YAK52518UW-999 38 Black (8681890032740)
Женские пиджаки Koton Количество грузовых мест 1 Страна регистрации бренда Турция
Страна-производитель товара Турция Размер 38 Стиль Повседневный (casual) Цвет
Черный Материал Полиэстер Материал Эластан Доставка Доставка в магазины ROZETKA'
- 'passage: Набор косметики Create it! Русалочка (84141) (8712916084532) Различные
наборы для детского творчества Create it! Гарантия 14 дней Вид Детская декоративная
косметика Пол ребенка Девочка Количество грузовых мест 1 Страна регистрации бренда
Нидерланды Страна-производитель товара Китай Детский возраст 8 лет Детский возраст
10 лет Детский возраст 6 лет Детский возраст 7 лет Детский возраст 9 лет Детский
возраст 12 лет Детский возраст 11 лет Тип гарантийного талона Гарантия по чеку
Доставка Premium Доставка Доставка в магазины ROZETKA'
- 'passage: Освежающая и тонизирующая пена для бритья Proraso 300 мл (8004395001927)
Косметика для бритья Proraso Класс косметики Профессиональная Пол Для мужчин Количество
грузовых мест 1 Страна регистрации бренда Италия Количество предметов, шт 1 Страна-производитель
товара Италия Объем 300 мл Тип кожи Для всех типов Тип гарантийного талона Гарантия
по чеку Вид Пена Доставка Premium Доставка Доставка в магазины ROZETKA'
- source_sentence: 'query: піжама дитяча'
sentences:
- 'passage: Піжама дитяча для дівчаток флісова RI-TEX М-056.5 Зірки 152-158 Пижамы
для девочек Сезон Зимний Страна-производитель товара Украина Цвет Серый Рост
152 см Рост 158 см Детский возраст 13 лет Детский возраст 12 лет'
- 'passage: Спортивний костюм для дівчат Валері-Текс 1895-20-365-017 128 см Малиновий
Спортивные костюмы для девочек Valeri-tex Страна-производитель товара Украина
Цвет Малиновый Материал Велюр Рост 128 см'
- 'passage: Насадка пылеуловитель для болгарки Craft CSH-125 Столы, стойки, насадки
Craft Гарантия 12 месяцев Назначение Для УШМ Страна-производитель товара Китай
Теги недорогие Тип Комплектующие'
- source_sentence: 'query: сумка жіноча шкіра'
sentences:
- 'passage: Жіночі спортивні шорти Overgym персикові XS Жіночі спортивні шорти Over
Gym Країна реєстрації бренда Україна Країна-виробник товару Китай Колір Персиковий
Матеріал Поліамід Матеріал Поліестер Принт Однотонний'
- 'passage: Жіноча сумка шкіряна Borsacomoda 813023 Чорна Сумки Borsacomoda Для
кого Для жінок Вид Сумки Колір Чорний Кількість вантажних місць 1 Модель сумки
Крос-боді Матеріал Шкіра Країна реєстрації бренда Україна Країна-виробник товару
Україна Тип гарантійного талона Гарантія по чеку Застібка Змійка Доставка Premium
Доставка Доставка в магазини ROZETKA'
- 'passage: Індукційна варильна поверхня Gunter&Hauer I 6 FB (6778875) Варильні
поверхні індукційні Gunter&Hauer Функції Індикатор залишкового тепла Функції Захист
від дітей Можливість під''єднання до мережі 220 В'
model-index:
- name: SentenceTransformer based on intfloat/multilingual-e5-base
results:
- task:
type: rztkinformation-retrieval
name: RZTKInformation Retrieval
dataset:
name: 'core uk matryoshka dim 768 '
type: core-uk--matryoshka_dim-768--
metrics:
- type: dot_accuracy_10
value: 0.979002624671916
name: Dot Accuracy 10
- type: dot_precision_10
value: 0.3796587926509187
name: Dot Precision 10
- type: dot_recall_10
value: 0.45280225388493106
name: Dot Recall 10
- type: dot_ndcg_10
value: 0.5583367249487432
name: Dot Ndcg 10
- type: dot_mrr_10
value: 0.8503004832729241
name: Dot Mrr 10
- type: dot_map_60
value: 0.39511574225334306
name: Dot Map 60
- task:
type: rztkinformation-retrieval
name: RZTKInformation Retrieval
dataset:
name: 'core ru matryoshka dim 768 '
type: core-ru--matryoshka_dim-768--
metrics:
- type: dot_accuracy_10
value: 0.9724409448818898
name: Dot Accuracy 10
- type: dot_precision_10
value: 0.3753280839895013
name: Dot Precision 10
- type: dot_recall_10
value: 0.44887826521684787
name: Dot Recall 10
- type: dot_ndcg_10
value: 0.5583301697325973
name: Dot Ndcg 10
- type: dot_mrr_10
value: 0.8581588759738366
name: Dot Mrr 10
- type: dot_map_60
value: 0.39791822283097145
name: Dot Map 60
- task:
type: rztkinformation-retrieval
name: RZTKInformation Retrieval
dataset:
name: 'vespa uk matryoshka dim 768 '
type: vespa-uk--matryoshka_dim-768--
metrics:
- type: dot_accuracy_10
value: 0.8913043478260869
name: Dot Accuracy 10
- type: dot_precision_10
value: 0.65
name: Dot Precision 10
- type: dot_recall_10
value: 0.21543325236733296
name: Dot Recall 10
- type: dot_ndcg_10
value: 0.7328694108300967
name: Dot Ndcg 10
- type: dot_mrr_10
value: 0.8577898550724636
name: Dot Mrr 10
- type: dot_map_60
value: 0.521722082197244
name: Dot Map 60
- task:
type: rztkinformation-retrieval
name: RZTKInformation Retrieval
dataset:
name: 'vespa ru matryoshka dim 768 '
type: vespa-ru--matryoshka_dim-768--
metrics:
- type: dot_accuracy_10
value: 0.9130434782608695
name: Dot Accuracy 10
- type: dot_precision_10
value: 0.6391304347826087
name: Dot Precision 10
- type: dot_recall_10
value: 0.214877024136512
name: Dot Recall 10
- type: dot_ndcg_10
value: 0.7176653908267321
name: Dot Ndcg 10
- type: dot_mrr_10
value: 0.8270962732919255
name: Dot Mrr 10
- type: dot_map_60
value: 0.5150948980713368
name: Dot Map 60
---
# SentenceTransformer based on intfloat/multilingual-e5-base
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [intfloat/multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base) on the core dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
## Model Details
### Model Description
- **Model Type:** Sentence Transformer
- **Base model:** [intfloat/multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base) <!-- at revision 835193815a3936a24a0ee7dc9e3d48c1fbb19c55 -->
- **Maximum Sequence Length:** 512 tokens
- **Output Dimensionality:** 768 dimensions
- **Similarity Function:** Dot Product
- **Training Dataset:**
- core
<!-- - **Language:** Unknown -->
<!-- - **License:** Unknown -->
### Model Sources
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
### Full Model Architecture
```
RZTKSentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: XLMRobertaModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
(2): Normalize()
)
```
## Usage
### Direct Usage (Sentence Transformers)
First install the Sentence Transformers library:
```bash
pip install -U sentence-transformers
```
Then you can load this model and run inference.
```python
from sentence_transformers import SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("yklymchuk-rztk/multiple-datasets-e5-jina-mnr-3-electronics-only")
# Run inference
sentences = [
'query: сумка жіноча шкіра',
'passage: Жіноча сумка шкіряна Borsacomoda 813023 Чорна Сумки Borsacomoda Для кого Для жінок Вид Сумки Колір Чорний Кількість вантажних місць 1 Модель сумки Крос-боді Матеріал Шкіра Країна реєстрації бренда Україна Країна-виробник товару Україна Тип гарантійного талона Гарантія по чеку Застібка Змійка Доставка Premium Доставка Доставка в магазини ROZETKA',
"passage: Індукційна варильна поверхня Gunter&Hauer I 6 FB (6778875) Варильні поверхні індукційні Gunter&Hauer Функції Індикатор залишкового тепла Функції Захист від дітей Можливість під'єднання до мережі 220 В",
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]
```
<!--
### Direct Usage (Transformers)
<details><summary>Click to see the direct usage in Transformers</summary>
</details>
-->
<!--
### Downstream Usage (Sentence Transformers)
You can finetune this model on your own dataset.
<details><summary>Click to expand</summary>
</details>
-->
<!--
### Out-of-Scope Use
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->
## Evaluation
### Metrics
#### RZTKInformation Retrieval
* Datasets: `core-uk--matryoshka_dim-768--`, `core-ru--matryoshka_dim-768--`, `vespa-uk--matryoshka_dim-768--` and `vespa-ru--matryoshka_dim-768--`
* Evaluated with <code>sentence_transformers_training.evaluation.information_retrieval_evaluator.RZTKInformationRetrievalEvaluator</code>
| Metric | core-uk--matryoshka_dim-768-- | core-ru--matryoshka_dim-768-- | vespa-uk--matryoshka_dim-768-- | vespa-ru--matryoshka_dim-768-- |
|:-----------------|:------------------------------|:------------------------------|:-------------------------------|:-------------------------------|
| dot_accuracy_10 | 0.979 | 0.9724 | 0.8913 | 0.913 |
| dot_precision_10 | 0.3797 | 0.3753 | 0.65 | 0.6391 |
| dot_recall_10 | 0.4528 | 0.4489 | 0.2154 | 0.2149 |
| **dot_ndcg_10** | **0.5583** | **0.5583** | **0.7329** | **0.7177** |
| dot_mrr_10 | 0.8503 | 0.8582 | 0.8578 | 0.8271 |
| dot_map_60 | 0.3951 | 0.3979 | 0.5217 | 0.5151 |
<!--
## Bias, Risks and Limitations
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
-->
<!--
### Recommendations
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
-->
## Training Details
### Training Dataset
#### core
* Dataset: core
* Size: 3,804,390 training samples
* Columns: <code>query</code> and <code>text</code>
* Approximate statistics based on the first 1000 samples:
| | query | text |
|:--------|:----------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------|
| type | string | string |
| details | <ul><li>min: 7 tokens</li><li>mean: 12.5 tokens</li><li>max: 256 tokens</li></ul> | <ul><li>min: 120 tokens</li><li>mean: 480.81 tokens</li><li>max: 512 tokens</li></ul> |
* Samples:
| query | text |
|:-----------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <code>query: 555 anker</code> | <code>passage: Зарядна станція Anker PowerHouse 555 / 1000 Вт / 1048 Вт⋅год / LiFePO4 (A1760311) Зарядні станції Anker Гарантія 5 років Тип акумуляторів Літій-залізо-фосфатні (LiFePO4) Колір Чорний Ємність батареї, мА*год 320000 Заряджається від Від мережі Призначення Для телевізорів Призначення Для ноутбуків Призначення Для персональних комп'ютерів Особливості З ліхтариком Особливості Протиударний Особливості Швидке заряджання батареї Кількість вантажних місць 1 Країна реєстрації бренда США Країна-виробник товару Китай Функції зарядки PowerIQ Функції зарядки Power Delivery Функції зарядки Наскрізна зарядка Тип гарантійного талона Гарантійний талон магазина Вихідна напруга, В 20 Вихідна напруга, В 9 Вихідна напруга, В 12 Вихідна напруга, В 220 Вихідна напруга, В 5 Вихідна напруга, В 15 Індикація З дисплеєм Одночасне заряджання пристроїв 8 Вихідні інтерфейси Розетка 220 В Вихідні інтерфейси USB Type C Вихідні інтерфейси USB Type A Вихідні інтерфейси Гніздо прикурювача Вхідні інтерфейси USB Ty...</code> |
| <code>query: 555 anker</code> | <code>passage: Зарядная станция Anker PowerHouse 555 / 1000 Вт / 1048 Вт⋅ч / LiFePO4 (A1760311) Зарядные станции Anker Гарантия 5 лет Тип аккумуляторов Литий-железо-фосфатные (LiFePO4) Цвет Черный Емкость батареи, мА*ч 320000 Заряжается от От сети Назначение Для телевизоров Назначение Для ноутбуков Назначение Для персональных компьютеров Особенности С фонариком Особенности Противоударный Особенности Быстрая зарядка батареи Количество грузовых мест 1 Страна регистрации бренда США Страна-производитель товара Китай Функции зарядки PowerIQ Функции зарядки Power Delivery Функции зарядки Сквозная зарядка Тип гарантийного талона Гарантийный талон магазина Выходное напряжение, В 20 Выходное напряжение, В 9 Выходное напряжение, В 12 Выходное напряжение, В 220 Выходное напряжение, В 5 Выходное напряжение, В 15 Индикация С дисплеем Одновременно заряжаемых устройств 8 Выходные интерфейсы Розетка 220 В Выходные интерфейсы USB Type C Выходные интерфейсы USB Type A Выходные интерфейсы Гнездо прикуривателя ...</code> |
| <code>query: anker-powerhouse-555</code> | <code>passage: Зарядная станция Anker PowerHouse 555 / 1000 Вт / 1048 Вт⋅ч / LiFePO4 (A1760311) Зарядные станции Anker Гарантия 5 лет Тип аккумуляторов Литий-железо-фосфатные (LiFePO4) Цвет Черный Емкость батареи, мА*ч 320000 Заряжается от От сети Назначение Для телевизоров Назначение Для ноутбуков Назначение Для персональных компьютеров Особенности С фонариком Особенности Противоударный Особенности Быстрая зарядка батареи Количество грузовых мест 1 Страна регистрации бренда США Страна-производитель товара Китай Функции зарядки PowerIQ Функции зарядки Power Delivery Функции зарядки Сквозная зарядка Тип гарантийного талона Гарантийный талон магазина Выходное напряжение, В 20 Выходное напряжение, В 9 Выходное напряжение, В 12 Выходное напряжение, В 220 Выходное напряжение, В 5 Выходное напряжение, В 15 Индикация С дисплеем Одновременно заряжаемых устройств 8 Выходные интерфейсы Розетка 220 В Выходные интерфейсы USB Type C Выходные интерфейсы USB Type A Выходные интерфейсы Гнездо прикуривателя ...</code> |
* Loss: <code>sentence_transformers_training.model.matryoshka2d_loss.RZTKMatryoshka2dLoss</code> with these parameters:
```json
{
"loss": "RZTKMultipleNegativesRankingLoss",
"n_layers_per_step": 1,
"last_layer_weight": 1.0,
"prior_layers_weight": 1.0,
"kl_div_weight": 1.0,
"kl_temperature": 0.3,
"matryoshka_dims": [
768,
512,
256,
128
],
"matryoshka_weights": [
1,
1,
1,
1
],
"n_dims_per_step": 1
}
```
### Evaluation Datasets
#### core_uk
* Dataset: core_uk
* Size: 3,220 evaluation samples
* Columns: <code>query</code> and <code>text</code>
* Approximate statistics based on the first 1000 samples:
| | query | text |
|:--------|:----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
| type | string | string |
| details | <ul><li>min: 8 tokens</li><li>mean: 10.66 tokens</li><li>max: 16 tokens</li></ul> | <ul><li>min: 19 tokens</li><li>mean: 114.2 tokens</li><li>max: 512 tokens</li></ul> |
* Samples:
| query | text |
|:---------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <code>query: лампочка е27</code> | <code>passage: Світлодіодна лампа Osram LED Star+ DIM A60 9W (806Lm) Е27 (4058075430754) Лампи OSRAM Гарантія 36 місяців Виробник світлодіодів Osram Тип світлодіодів SMD Тип цоколя E27 Колір світіння / Температура кольорів RGB (різнокольоровий) Колір світіння / Температура кольорів Теплий білий Світловий потік 806 Лм Еквівалент потужності лампи розжарювання 60 Вт Робоча напруга, в 230 Тип Світлодіодні лампи Форма колби Стандартна (груша) Колір колби Матовий Кількість вантажних місць 1 Країна реєстрації бренда Німеччина Кількість предметів, шт 1 Країна-виробник товару Китай Особливості З дистанційним управлінням Особливості З регулюванням яскравості (димер) Строк служби лампи, год 25000 теги лампи недорого Тип гарантійного талона Гарантія по чеку Потужність, Вт 9 Можливість доставки Почтомати Доставка Premium Доставка Доставка в магазини ROZETKA</code> |
| <code>query: лампочка е27</code> | <code>passage: Світлодіодна лампа Philips Ecohome LED Bulb 11 W E27 3000 K 1PF/20RCA (929002299567R) 2 шт. Лампи Philips Гарантія 24 місяці Тип цоколя E27 Колір світіння / Температура кольорів Теплий Світловий потік 1150 Лм Еквівалент потужності лампи розжарювання 95 Вт Робоча напруга, в 170-240 Тип Світлодіодні лампи Форма колби Стандартна (груша) Колір колби Білий Кількість вантажних місць 1 Країна реєстрації бренда Нідерланди Кількість предметів, шт 2 Країна-виробник товару Китай Строк служби лампи, год теги лампи недорого Тип гарантійного талона Гарантійний талон магазина Потужність, Вт 11 Застосування Побутові Призначення Для настільної лампи Призначення Для люстри Призначення Для стельових світильників Температура світіння 3000 К Матеріал колби Пластик Доставка Premium Доставка Доставка в магазини ROZETKA</code> |
| <code>query: лампочка е27</code> | <code>passage: Набір світлодіодних ламп Евросвет 12 W 4200 K Е27 (56702) 4 шт. Лампи Євросвітло Гарантія 12 місяців Тип світлодіодів SMD Тип цоколя E27 Колір світіння / Температура кольорів Нейтральний-білий Світловий потік 1200 Лм Еквівалент потужності лампи розжарювання 120 Вт Робоча напруга, в 220-240 Тип Світлодіодні лампи Форма колби Стандартна (груша) Кількість вантажних місць 1 Країна реєстрації бренда Україна Кількість предметів, шт 4 Країна-виробник товару Китай Строк служби лампи, год 15000 теги лампи недорого Тип гарантійного талона Гарантія по чеку Потужність, Вт 12 Застосування Побутові Призначення Для настільної лампи Призначення Для люстри Призначення Для стельових світильників Температура світіння 4200К Матеріал колби Пластик Доставка Готовий до відправлення Доставка Доставка в магазини ROZETKA</code> |
* Loss: <code>sentence_transformers_training.model.matryoshka2d_loss.RZTKMatryoshka2dLoss</code> with these parameters:
```json
{
"loss": "RZTKMultipleNegativesRankingLoss",
"n_layers_per_step": 1,
"last_layer_weight": 1.0,
"prior_layers_weight": 1.0,
"kl_div_weight": 1.0,
"kl_temperature": 0.3,
"matryoshka_dims": [
768,
512,
256,
128
],
"matryoshka_weights": [
1,
1,
1,
1
],
"n_dims_per_step": 1
}
```
#### core_ru
* Dataset: core_ru
* Size: 3,220 evaluation samples
* Columns: <code>query</code> and <code>text</code>
* Approximate statistics based on the first 1000 samples:
| | query | text |
|:--------|:----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
| type | string | string |
| details | <ul><li>min: 8 tokens</li><li>mean: 10.66 tokens</li><li>max: 16 tokens</li></ul> | <ul><li>min: 18 tokens</li><li>mean: 109.38 tokens</li><li>max: 512 tokens</li></ul> |
* Samples:
| query | text |
|:---------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <code>query: лампочка е27</code> | <code>passage: Светодиодная лампа Osram LED Star+ DIM A60 9W (806Lm) Е27 (4058075430754) Лампы OSRAM Гарантия 36 месяцев Производитель светодиодов Osram Тип светодиодов SMD Тип цоколя E27 Цвет свечения / Цветовая температура RGB (разноцветный) Цвет свечения / Цветовая температура Теплый белый Световой поток 806 Лм Эквивалент мощности лампы накаливания 60 Вт Рабочее напряжение, В 230 Тип Светодиодные лампы Форма колбы Стандартная (груша) Цвет колбы Матовый Количество грузовых мест 1 Страна регистрации бренда Германия Количество предметов, шт 1 Страна-производитель товара Китай Особенности С дистанционным управлением Особенности С регулировкой яркости (диммер) Срок службы лампы, ч 25000 теги лампы недорого Тип гарантийного талона Гарантия по чеку Мощность, Вт 9 Возможность доставки Почтоматы Доставка Premium Доставка Доставка в магазины ROZETKA</code> |
| <code>query: лампочка е27</code> | <code>passage: Светодиодная лампа Philips Ecohome LED Bulb 11W E27 3000К 1PF/20RCA (929002299567R) 2 шт. Лампы Philips Гарантия 24 месяца Тип цоколя E27 Цвет свечения / Цветовая температура Теплый Световой поток 1150 Лм Эквивалент мощности лампы накаливания 95 Вт Рабочее напряжение, В 170-240 Тип Светодиодные лампы Форма колбы Стандартная (груша) Цвет колбы Белый Количество грузовых мест 1 Страна регистрации бренда Нидерланды Количество предметов, шт 2 Страна-производитель товара Китай Срок службы лампы, ч 6000 теги лампы недорого Тип гарантийного талона Гарантийный талон магазина Мощность, Вт 11 Применение Бытовые Назначение Для настольной лампы Назначение Для люстры Назначение Для потолочных светильников Температура свечения 3000К Материал колбы Пластик Доставка Premium Доставка Доставка в магазины ROZETKA</code> |
| <code>query: лампочка е27</code> | <code>passage: Набор светодиодных ламп ЕВРОСВЕТ 12W 4200к Е27 (56702) 4 шт Лампы Євросвітло Гарантия 12 месяцев Тип светодиодов SMD Тип цоколя E27 Цвет свечения / Цветовая температура Нейтральный-белый Световой поток 1200 Лм Эквивалент мощности лампы накаливания 120 Вт Рабочее напряжение, В 220-240 Тип Светодиодные лампы Форма колбы Стандартная (груша) Количество грузовых мест 1 Страна регистрации бренда Украина Количество предметов, шт 4 Страна-производитель товара Китай Срок службы лампы, ч 15000 теги лампы недорого Тип гарантийного талона Гарантия по чеку Мощность, Вт 12 Применение Бытовые Назначение Для настольной лампы Назначение Для люстры Назначение Для потолочных светильников Температура свечения 4200К Материал колбы Пластик Доставка Готов к отправке Доставка Доставка в магазины ROZETKA</code> |
* Loss: <code>sentence_transformers_training.model.matryoshka2d_loss.RZTKMatryoshka2dLoss</code> with these parameters:
```json
{
"loss": "RZTKMultipleNegativesRankingLoss",
"n_layers_per_step": 1,
"last_layer_weight": 1.0,
"prior_layers_weight": 1.0,
"kl_div_weight": 1.0,
"kl_temperature": 0.3,
"matryoshka_dims": [
768,
512,
256,
128
],
"matryoshka_weights": [
1,
1,
1,
1
],
"n_dims_per_step": 1
}
```
#### vespa_uk
* Dataset: vespa_uk
* Size: 5,315 evaluation samples
* Columns: <code>query</code> and <code>text</code>
* Approximate statistics based on the first 1000 samples:
| | query | text |
|:--------|:---------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
| type | string | string |
| details | <ul><li>min: 7 tokens</li><li>mean: 9.58 tokens</li><li>max: 22 tokens</li></ul> | <ul><li>min: 19 tokens</li><li>mean: 89.9 tokens</li><li>max: 239 tokens</li></ul> |
* Samples:
| query | text |
|:------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------|
| <code>query: шланга диаметром 32 мм для викачки брудної води з басейну</code> | <code>passage: Перехідники для шлангу басейну Intex з 32 мм на 38 мм (IP-175136) Обладнання для басейнів Intex Вид Комплектувальні</code> |
| <code>query: шланга диаметром 32 мм для викачки брудної води з басейну</code> | <code>passage: З'єднання для шланга Peraqua діаметр 32 мм Аксесуари для басейнів Вид Інструменти для прибирання басейнів</code> |
| <code>query: шланга диаметром 32 мм для викачки брудної води з басейну</code> | <code>passage: З'єднання для шлангу Peraqua діаметр 32/38 мм Аксесуари для басейнів Вид Інструменти для прибирання басейнів</code> |
* Loss: <code>sentence_transformers_training.model.matryoshka2d_loss.RZTKMatryoshka2dLoss</code> with these parameters:
```json
{
"loss": "RZTKMultipleNegativesRankingLoss",
"n_layers_per_step": 1,
"last_layer_weight": 1.0,
"prior_layers_weight": 1.0,
"kl_div_weight": 1.0,
"kl_temperature": 0.3,
"matryoshka_dims": [
768,
512,
256,
128
],
"matryoshka_weights": [
1,
1,
1,
1
],
"n_dims_per_step": 1
}
```
#### vespa_ru
* Dataset: vespa_ru
* Size: 5,315 evaluation samples
* Columns: <code>query</code> and <code>text</code>
* Approximate statistics based on the first 1000 samples:
| | query | text |
|:--------|:---------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
| type | string | string |
| details | <ul><li>min: 7 tokens</li><li>mean: 9.58 tokens</li><li>max: 22 tokens</li></ul> | <ul><li>min: 20 tokens</li><li>mean: 87.33 tokens</li><li>max: 232 tokens</li></ul> |
* Samples:
| query | text |
|:------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------|
| <code>query: шланга диаметром 32 мм для викачки брудної води з басейну</code> | <code>passage: Переходники для шланга бассейна Intex с 32 мм на 38 мм (IP-175136) Оборудование для бассейнов Intex Вид Комплектующие</code> |
| <code>query: шланга диаметром 32 мм для викачки брудної води з басейну</code> | <code>passage: Соединение для шланга Peraqua диаметр 32 мм Аксессуары для бассейнов Вид Инструменты для уборки бассейнов</code> |
| <code>query: шланга диаметром 32 мм для викачки брудної води з басейну</code> | <code>passage: Соединение для шланга Peraqua диаметр 32/38 мм Аксессуары для бассейнов Вид Инструменты для уборки бассейнов</code> |
* Loss: <code>sentence_transformers_training.model.matryoshka2d_loss.RZTKMatryoshka2dLoss</code> with these parameters:
```json
{
"loss": "RZTKMultipleNegativesRankingLoss",
"n_layers_per_step": 1,
"last_layer_weight": 1.0,
"prior_layers_weight": 1.0,
"kl_div_weight": 1.0,
"kl_temperature": 0.3,
"matryoshka_dims": [
768,
512,
256,
128
],
"matryoshka_weights": [
1,
1,
1,
1
],
"n_dims_per_step": 1
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `eval_strategy`: steps
- `per_device_train_batch_size`: 80
- `per_device_eval_batch_size`: 16
- `learning_rate`: 2e-05
- `warmup_ratio`: 0.1
- `bf16`: True
- `bf16_full_eval`: True
- `tf32`: True
- `dataloader_num_workers`: 4
- `load_best_model_at_end`: True
- `optim`: adafactor
- `push_to_hub`: True
- `hub_model_id`: yklymchuk-rztk/multiple-datasets-e5-jina-mnr-3-electronics-only
- `hub_private_repo`: True
- `prompts`: {'query': 'query: ', 'text': 'passage: '}
- `batch_sampler`: no_duplicates
#### All Hyperparameters
<details><summary>Click to expand</summary>
- `overwrite_output_dir`: False
- `do_predict`: False
- `eval_strategy`: steps
- `prediction_loss_only`: True
- `per_device_train_batch_size`: 80
- `per_device_eval_batch_size`: 16
- `per_gpu_train_batch_size`: None
- `per_gpu_eval_batch_size`: None
- `gradient_accumulation_steps`: 1
- `eval_accumulation_steps`: None
- `torch_empty_cache_steps`: None
- `learning_rate`: 2e-05
- `weight_decay`: 0.0
- `adam_beta1`: 0.9
- `adam_beta2`: 0.999
- `adam_epsilon`: 1e-08
- `max_grad_norm`: 1.0
- `num_train_epochs`: 3
- `max_steps`: -1
- `lr_scheduler_type`: linear
- `lr_scheduler_kwargs`: {}
- `warmup_ratio`: 0.1
- `warmup_steps`: 0
- `log_level`: passive
- `log_level_replica`: warning
- `log_on_each_node`: True
- `logging_nan_inf_filter`: True
- `save_safetensors`: True
- `save_on_each_node`: False
- `save_only_model`: False
- `restore_callback_states_from_checkpoint`: False
- `no_cuda`: False
- `use_cpu`: False
- `use_mps_device`: False
- `seed`: 42
- `data_seed`: None
- `jit_mode_eval`: False
- `use_ipex`: False
- `bf16`: True
- `fp16`: False
- `fp16_opt_level`: O1
- `half_precision_backend`: auto
- `bf16_full_eval`: True
- `fp16_full_eval`: False
- `tf32`: True
- `local_rank`: 0
- `ddp_backend`: None
- `tpu_num_cores`: None
- `tpu_metrics_debug`: False
- `debug`: []
- `dataloader_drop_last`: True
- `dataloader_num_workers`: 4
- `dataloader_prefetch_factor`: None
- `past_index`: -1
- `disable_tqdm`: False
- `remove_unused_columns`: True
- `label_names`: None
- `load_best_model_at_end`: True
- `ignore_data_skip`: False
- `fsdp`: []
- `fsdp_min_num_params`: 0
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
- `fsdp_transformer_layer_cls_to_wrap`: None
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
- `deepspeed`: None
- `label_smoothing_factor`: 0.0
- `optim`: adafactor
- `optim_args`: None
- `adafactor`: False
- `group_by_length`: False
- `length_column_name`: length
- `ddp_find_unused_parameters`: None
- `ddp_bucket_cap_mb`: None
- `ddp_broadcast_buffers`: False
- `dataloader_pin_memory`: True
- `dataloader_persistent_workers`: False
- `skip_memory_metrics`: True
- `use_legacy_prediction_loop`: False
- `push_to_hub`: True
- `resume_from_checkpoint`: None
- `hub_model_id`: yklymchuk-rztk/multiple-datasets-e5-jina-mnr-3-electronics-only
- `hub_strategy`: every_save
- `hub_private_repo`: True
- `hub_always_push`: False
- `gradient_checkpointing`: False
- `gradient_checkpointing_kwargs`: None
- `include_inputs_for_metrics`: False
- `include_for_metrics`: []
- `eval_do_concat_batches`: True
- `fp16_backend`: auto
- `push_to_hub_model_id`: None
- `push_to_hub_organization`: None
- `mp_parameters`:
- `auto_find_batch_size`: False
- `full_determinism`: False
- `torchdynamo`: None
- `ray_scope`: last
- `ddp_timeout`: 1800
- `torch_compile`: False
- `torch_compile_backend`: None
- `torch_compile_mode`: None
- `dispatch_batches`: None
- `split_batches`: None
- `include_tokens_per_second`: False
- `include_num_input_tokens_seen`: False
- `neftune_noise_alpha`: None
- `optim_target_modules`: None
- `batch_eval_metrics`: False
- `eval_on_start`: False
- `use_liger_kernel`: False
- `eval_use_gather_object`: False
- `average_tokens_across_devices`: False
- `prompts`: {'query': 'query: ', 'text': 'passage: '}
- `batch_sampler`: no_duplicates
- `multi_dataset_batch_sampler`: proportional
- `ddp_static_graph`: False
- `ddp_comm_hook`: bf16
- `gradient_as_bucket_view`: False
- `num_proc`: 30
</details>
### Training Logs
<details><summary>Click to expand</summary>
| Epoch | Step | Training Loss | core uk loss | core ru loss | vespa uk loss | vespa ru loss | core-uk--matryoshka_dim-768--_dot_ndcg_10 | core-ru--matryoshka_dim-768--_dot_ndcg_10 | vespa-uk--matryoshka_dim-768--_dot_ndcg_10 | vespa-ru--matryoshka_dim-768--_dot_ndcg_10 |
|:------:|:-----:|:-------------:|:------------:|:------------:|:-------------:|:-------------:|:-----------------------------------------:|:-----------------------------------------:|:------------------------------------------:|:------------------------------------------:|
| 0.0151 | 179 | 4.8952 | - | - | - | - | - | - | - | - |
| 0.0301 | 358 | 4.9239 | - | - | - | - | - | - | - | - |
| 0.0452 | 537 | 4.7362 | - | - | - | - | - | - | - | - |
| 0.0602 | 716 | 4.4058 | - | - | - | - | - | - | - | - |
| 0.0753 | 895 | 4.2344 | - | - | - | - | - | - | - | - |
| 0.0903 | 1074 | 3.5898 | - | - | - | - | - | - | - | - |
| 0.1054 | 1253 | 3.3581 | - | - | - | - | - | - | - | - |
| 0.1205 | 1432 | 3.2171 | - | - | - | - | - | - | - | - |
| 0.1355 | 1611 | 2.9499 | - | - | - | - | - | - | - | - |
| 0.1506 | 1790 | 3.0239 | - | - | - | - | - | - | - | - |
| 0.1656 | 1969 | 2.5125 | - | - | - | - | - | - | - | - |
| 0.1807 | 2148 | 2.8661 | - | - | - | - | - | - | - | - |
| 0.1957 | 2327 | 2.7486 | - | - | - | - | - | - | - | - |
| 0.2108 | 2506 | 3.2432 | - | - | - | - | - | - | - | - |
| 0.2259 | 2685 | 3.1127 | - | - | - | - | - | - | - | - |
| 0.2409 | 2864 | 2.9176 | - | - | - | - | - | - | - | - |
| 0.2560 | 3043 | 2.5284 | - | - | - | - | - | - | - | - |
| 0.2710 | 3222 | 2.8496 | - | - | - | - | - | - | - | - |
| 0.2861 | 3401 | 2.9145 | - | - | - | - | - | - | - | - |
| 0.3001 | 3567 | - | 0.7853 | 0.7567 | 0.7556 | 0.7125 | 0.5442 | 0.5471 | 0.7309 | 0.7106 |
| 0.3011 | 3580 | 2.816 | - | - | - | - | - | - | - | - |
| 0.3162 | 3759 | 2.9181 | - | - | - | - | - | - | - | - |
| 0.3313 | 3938 | 3.0285 | - | - | - | - | - | - | - | - |
| 0.3463 | 4117 | 2.7559 | - | - | - | - | - | - | - | - |
| 0.3614 | 4296 | 2.5055 | - | - | - | - | - | - | - | - |
| 0.3764 | 4475 | 2.9042 | - | - | - | - | - | - | - | - |
| 0.3915 | 4654 | 2.7473 | - | - | - | - | - | - | - | - |
| 0.4065 | 4833 | 2.7661 | - | - | - | - | - | - | - | - |
| 0.4216 | 5012 | 2.7554 | - | - | - | - | - | - | - | - |
| 0.4367 | 5191 | 2.8431 | - | - | - | - | - | - | - | - |
| 0.4517 | 5370 | 2.4573 | - | - | - | - | - | - | - | - |
| 0.4668 | 5549 | 2.5761 | - | - | - | - | - | - | - | - |
| 0.4818 | 5728 | 2.7071 | - | - | - | - | - | - | - | - |
| 0.4969 | 5907 | 2.8493 | - | - | - | - | - | - | - | - |
| 0.5119 | 6086 | 2.8784 | - | - | - | - | - | - | - | - |
| 0.5270 | 6265 | 2.7202 | - | - | - | - | - | - | - | - |
| 0.5421 | 6444 | 2.7756 | - | - | - | - | - | - | - | - |
| 0.5571 | 6623 | 2.6471 | - | - | - | - | - | - | - | - |
| 0.5722 | 6802 | 2.7666 | - | - | - | - | - | - | - | - |
| 0.5872 | 6981 | 2.4328 | - | - | - | - | - | - | - | - |
| 0.6001 | 7134 | - | 0.7132 | 0.7699 | 0.6077 | 0.6837 | 0.5537 | 0.5558 | 0.7246 | 0.7043 |
| 0.6023 | 7160 | 2.7531 | - | - | - | - | - | - | - | - |
| 0.6173 | 7339 | 2.8405 | - | - | - | - | - | - | - | - |
| 0.6324 | 7518 | 2.5655 | - | - | - | - | - | - | - | - |
| 0.6475 | 7697 | 2.2858 | - | - | - | - | - | - | - | - |
| 0.6625 | 7876 | 2.5737 | - | - | - | - | - | - | - | - |
| 0.6776 | 8055 | 2.5102 | - | - | - | - | - | - | - | - |
| 0.6926 | 8234 | 2.7832 | - | - | - | - | - | - | - | - |
| 0.7077 | 8413 | 2.4454 | - | - | - | - | - | - | - | - |
| 0.7227 | 8592 | 2.4814 | - | - | - | - | - | - | - | - |
| 0.7378 | 8771 | 2.5788 | - | - | - | - | - | - | - | - |
| 0.7529 | 8950 | 2.3763 | - | - | - | - | - | - | - | - |
| 0.7679 | 9129 | 2.4836 | - | - | - | - | - | - | - | - |
| 0.7830 | 9308 | 2.233 | - | - | - | - | - | - | - | - |
| 0.7980 | 9487 | 2.4032 | - | - | - | - | - | - | - | - |
| 0.8131 | 9666 | 2.6613 | - | - | - | - | - | - | - | - |
| 0.8281 | 9845 | 2.2809 | - | - | - | - | - | - | - | - |
| 0.8432 | 10024 | 2.0115 | - | - | - | - | - | - | - | - |
| 0.8583 | 10203 | 2.5228 | - | - | - | - | - | - | - | - |
| 0.8733 | 10382 | 2.1149 | - | - | - | - | - | - | - | - |
| 0.8884 | 10561 | 2.5053 | - | - | - | - | - | - | - | - |
| 0.9002 | 10701 | - | 0.6233 | 0.7107 | 0.5342 | 0.5265 | 0.5634 | 0.5636 | 0.7626 | 0.7526 |
| 0.9034 | 10740 | 2.1663 | - | - | - | - | - | - | - | - |
| 0.9185 | 10919 | 2.6719 | - | - | - | - | - | - | - | - |
| 0.9335 | 11098 | 2.4423 | - | - | - | - | - | - | - | - |
| 0.9486 | 11277 | 2.8741 | - | - | - | - | - | - | - | - |
| 0.9637 | 11456 | 2.5291 | - | - | - | - | - | - | - | - |
| 0.9787 | 11635 | 2.5211 | - | - | - | - | - | - | - | - |
| 0.9938 | 11814 | 2.6053 | - | - | - | - | - | - | - | - |
| 1.0089 | 11993 | 2.1993 | - | - | - | - | - | - | - | - |
| 1.0240 | 12172 | 2.4606 | - | - | - | - | - | - | - | - |
| 1.0390 | 12351 | 2.285 | - | - | - | - | - | - | - | - |
| 1.0541 | 12530 | 2.2181 | - | - | - | - | - | - | - | - |
| 1.0691 | 12709 | 2.412 | - | - | - | - | - | - | - | - |
| 1.0842 | 12888 | 2.3145 | - | - | - | - | - | - | - | - |
| 1.0993 | 13067 | 2.1323 | - | - | - | - | - | - | - | - |
| 1.1143 | 13246 | 2.4581 | - | - | - | - | - | - | - | - |
| 1.1294 | 13425 | 2.3835 | - | - | - | - | - | - | - | - |
| 1.1444 | 13604 | 2.2885 | - | - | - | - | - | - | - | - |
| 1.1595 | 13783 | 2.0034 | - | - | - | - | - | - | - | - |
| 1.1745 | 13962 | 2.2039 | - | - | - | - | - | - | - | - |
| 1.1896 | 14141 | 2.2068 | - | - | - | - | - | - | - | - |
| 1.2003 | 14268 | - | 0.6910 | 0.6097 | 0.5389 | 0.5179 | 0.5561 | 0.5573 | 0.7319 | 0.7196 |
| 1.2047 | 14320 | 2.468 | - | - | - | - | - | - | - | - |
| 1.2197 | 14499 | 2.4987 | - | - | - | - | - | - | - | - |
| 1.2348 | 14678 | 2.4321 | - | - | - | - | - | - | - | - |
| 1.2498 | 14857 | 2.2351 | - | - | - | - | - | - | - | - |
| 1.2649 | 15036 | 2.167 | - | - | - | - | - | - | - | - |
| 1.2799 | 15215 | 2.6282 | - | - | - | - | - | - | - | - |
| 1.2950 | 15394 | 2.3824 | - | - | - | - | - | - | - | - |
| 1.3101 | 15573 | 2.4719 | - | - | - | - | - | - | - | - |
| 1.3251 | 15752 | 2.4836 | - | - | - | - | - | - | - | - |
| 1.3402 | 15931 | 2.5208 | - | - | - | - | - | - | - | - |
| 1.3552 | 16110 | 2.3985 | - | - | - | - | - | - | - | - |
| 1.3703 | 16289 | 2.3604 | - | - | - | - | - | - | - | - |
| 1.3853 | 16468 | 2.5651 | - | - | - | - | - | - | - | - |
| 1.4004 | 16647 | 2.5203 | - | - | - | - | - | - | - | - |
| 1.4155 | 16826 | 2.3643 | - | - | - | - | - | - | - | - |
| 1.4305 | 17005 | 2.4428 | - | - | - | - | - | - | - | - |
| 1.4456 | 17184 | 2.2424 | - | - | - | - | - | - | - | - |
| 1.4606 | 17363 | 2.501 | - | - | - | - | - | - | - | - |
| 1.4757 | 17542 | 2.366 | - | - | - | - | - | - | - | - |
| 1.4907 | 17721 | 2.4872 | - | - | - | - | - | - | - | - |
| 1.5003 | 17835 | - | 0.6270 | 0.6293 | 0.5664 | 0.5494 | 0.5581 | 0.5602 | 0.7362 | 0.7159 |
| 1.5058 | 17900 | 2.6305 | - | - | - | - | - | - | - | - |
| 1.5209 | 18079 | 2.421 | - | - | - | - | - | - | - | - |
| 1.5359 | 18258 | 2.628 | - | - | - | - | - | - | - | - |
| 1.5510 | 18437 | 2.4255 | - | - | - | - | - | - | - | - |
| 1.5660 | 18616 | 2.4615 | - | - | - | - | - | - | - | - |
| 1.5811 | 18795 | 2.3092 | - | - | - | - | - | - | - | - |
| 1.5961 | 18974 | 2.3587 | - | - | - | - | - | - | - | - |
| 1.6112 | 19153 | 2.8552 | - | - | - | - | - | - | - | - |
| 1.6263 | 19332 | 2.3535 | - | - | - | - | - | - | - | - |
| 1.6413 | 19511 | 2.3277 | - | - | - | - | - | - | - | - |
| 1.6564 | 19690 | 2.2047 | - | - | - | - | - | - | - | - |
| 1.6714 | 19869 | 2.4503 | - | - | - | - | - | - | - | - |
| 1.6865 | 20048 | 2.6128 | - | - | - | - | - | - | - | - |
| 1.7015 | 20227 | 2.433 | - | - | - | - | - | - | - | - |
| 1.7166 | 20406 | 2.3849 | - | - | - | - | - | - | - | - |
| 1.7317 | 20585 | 2.3902 | - | - | - | - | - | - | - | - |
| 1.7467 | 20764 | 2.2826 | - | - | - | - | - | - | - | - |
| 1.7618 | 20943 | 2.3408 | - | - | - | - | - | - | - | - |
| 1.7768 | 21122 | 2.093 | - | - | - | - | - | - | - | - |
| 1.7919 | 21301 | 2.2373 | - | - | - | - | - | - | - | - |
| 1.8004 | 21402 | - | 0.6020 | 0.6222 | 0.4753 | 0.5565 | 0.5574 | 0.5555 | 0.7510 | 0.7339 |
| 1.8069 | 21480 | 2.4067 | - | - | - | - | - | - | - | - |
| 1.8220 | 21659 | 2.303 | - | - | - | - | - | - | - | - |
| 1.8371 | 21838 | 1.8552 | - | - | - | - | - | - | - | - |
| 1.8521 | 22017 | 2.1746 | - | - | - | - | - | - | - | - |
| 1.8672 | 22196 | 2.0771 | - | - | - | - | - | - | - | - |
| 1.8822 | 22375 | 2.339 | - | - | - | - | - | - | - | - |
| 1.8973 | 22554 | 2.0942 | - | - | - | - | - | - | - | - |
| 1.9123 | 22733 | 2.3181 | - | - | - | - | - | - | - | - |
| 1.9274 | 22912 | 2.3703 | - | - | - | - | - | - | - | - |
| 1.9425 | 23091 | 2.4736 | - | - | - | - | - | - | - | - |
| 1.9575 | 23270 | 2.6902 | - | - | - | - | - | - | - | - |
| 1.9726 | 23449 | 2.2046 | - | - | - | - | - | - | - | - |
| 1.9876 | 23628 | 2.4463 | - | - | - | - | - | - | - | - |
| 2.0028 | 23807 | 2.2212 | - | - | - | - | - | - | - | - |
| 2.0178 | 23986 | 2.2298 | - | - | - | - | - | - | - | - |
| 2.0329 | 24165 | 2.4247 | - | - | - | - | - | - | - | - |
| 2.0479 | 24344 | 2.0451 | - | - | - | - | - | - | - | - |
| 2.0630 | 24523 | 2.2404 | - | - | - | - | - | - | - | - |
| 2.0781 | 24702 | 2.3939 | - | - | - | - | - | - | - | - |
| 2.0931 | 24881 | 2.0558 | - | - | - | - | - | - | - | - |
| 2.1005 | 24969 | - | 0.6300 | 0.6967 | 0.5741 | 0.5561 | 0.5425 | 0.5420 | 0.7484 | 0.7261 |
| 2.1082 | 25060 | 2.2546 | - | - | - | - | - | - | - | - |
| 2.1232 | 25239 | 2.28 | - | - | - | - | - | - | - | - |
| 2.1383 | 25418 | 2.2238 | - | - | - | - | - | - | - | - |
| 2.1533 | 25597 | 2.1565 | - | - | - | - | - | - | - | - |
| 2.1684 | 25776 | 1.9775 | - | - | - | - | - | - | - | - |
| 2.1835 | 25955 | 2.2428 | - | - | - | - | - | - | - | - |
| 2.1985 | 26134 | 2.0969 | - | - | - | - | - | - | - | - |
| 2.2136 | 26313 | 2.3999 | - | - | - | - | - | - | - | - |
| 2.2286 | 26492 | 2.4524 | - | - | - | - | - | - | - | - |
| 2.2437 | 26671 | 2.319 | - | - | - | - | - | - | - | - |
| 2.2587 | 26850 | 2.0698 | - | - | - | - | - | - | - | - |
| 2.2738 | 27029 | 2.4082 | - | - | - | - | - | - | - | - |
| 2.2889 | 27208 | 2.4815 | - | - | - | - | - | - | - | - |
| 2.3039 | 27387 | 2.3198 | - | - | - | - | - | - | - | - |
| 2.3190 | 27566 | 2.413 | - | - | - | - | - | - | - | - |
| 2.3340 | 27745 | 2.6617 | - | - | - | - | - | - | - | - |
| 2.3491 | 27924 | 2.3676 | - | - | - | - | - | - | - | - |
| 2.3641 | 28103 | 2.1355 | - | - | - | - | - | - | - | - |
| 2.3792 | 28282 | 2.6304 | - | - | - | - | - | - | - | - |
| 2.3943 | 28461 | 2.274 | - | - | - | - | - | - | - | - |
| 2.4006 | 28536 | - | 0.6525 | 0.6612 | 0.5334 | 0.5171 | 0.5543 | 0.5561 | 0.7376 | 0.7215 |
| 2.4093 | 28640 | 2.3882 | - | - | - | - | - | - | - | - |
| 2.4244 | 28819 | 2.3836 | - | - | - | - | - | - | - | - |
| 2.4394 | 28998 | 2.5454 | - | - | - | - | - | - | - | - |
| 2.4545 | 29177 | 2.2851 | - | - | - | - | - | - | - | - |
| 2.4695 | 29356 | 2.2482 | - | - | - | - | - | - | - | - |
| 2.4846 | 29535 | 2.3114 | - | - | - | - | - | - | - | - |
| 2.4997 | 29714 | 2.6511 | - | - | - | - | - | - | - | - |
| 2.5147 | 29893 | 2.4293 | - | - | - | - | - | - | - | - |
| 2.5298 | 30072 | 2.5897 | - | - | - | - | - | - | - | - |
| 2.5448 | 30251 | 2.4804 | - | - | - | - | - | - | - | - |
| 2.5599 | 30430 | 2.3792 | - | - | - | - | - | - | - | - |
| 2.5749 | 30609 | 2.4037 | - | - | - | - | - | - | - | - |
| 2.5900 | 30788 | 2.2137 | - | - | - | - | - | - | - | - |
| 2.6051 | 30967 | 2.755 | - | - | - | - | - | - | - | - |
| 2.6201 | 31146 | 2.4339 | - | - | - | - | - | - | - | - |
| 2.6352 | 31325 | 2.3045 | - | - | - | - | - | - | - | - |
| 2.6502 | 31504 | 2.1352 | - | - | - | - | - | - | - | - |
| 2.6653 | 31683 | 2.4401 | - | - | - | - | - | - | - | - |
| 2.6803 | 31862 | 2.481 | - | - | - | - | - | - | - | - |
| 2.6954 | 32041 | 2.55 | - | - | - | - | - | - | - | - |
| 2.7006 | 32103 | - | 0.5987 | 0.6102 | 0.4596 | 0.5642 | 0.5583 | 0.5583 | 0.7329 | 0.7177 |
</details>
### Framework Versions
- Python: 3.11.10
- Sentence Transformers: 3.3.0
- Transformers: 4.46.3
- PyTorch: 2.5.1+cu124
- Accelerate: 1.1.1
- Datasets: 3.1.0
- Tokenizers: 0.20.3
## Citation
### BibTeX
#### Sentence Transformers
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "https://arxiv.org/abs/1908.10084",
}
```
<!--
## Glossary
*Clearly define terms in order to be accessible across audiences.*
-->
<!--
## Model Card Authors
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->
<!--
## Model Card Contact
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
--> | [
"TEXT_CLASSIFICATION"
] | Non_BioNLP |
ravi259/ModernBERT-base-nli-v2 | ravi259 | sentence-similarity | [
"sentence-transformers",
"safetensors",
"modernbert",
"sentence-similarity",
"feature-extraction",
"generated_from_trainer",
"dataset_size:557850",
"loss:MultipleNegativesRankingLoss",
"en",
"dataset:sentence-transformers/all-nli",
"arxiv:1908.10084",
"arxiv:1705.00652",
"base_model:answerdotai/ModernBERT-base",
"base_model:finetune:answerdotai/ModernBERT-base",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 1,740,265,831,000 | 2025-02-23T00:11:31 | 27 | 0 | ---
base_model: answerdotai/ModernBERT-base
datasets:
- sentence-transformers/all-nli
language:
- en
library_name: sentence-transformers
metrics:
- pearson_cosine
- spearman_cosine
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:557850
- loss:MultipleNegativesRankingLoss
widget:
- source_sentence: A man dressed in yellow rescue gear walks in a field.
sentences:
- A person messes with some papers.
- The man is outdoors.
- The man is bowling.
- source_sentence: A young woman tennis player dressed in black carries many tennis
balls on her racket.
sentences:
- A young woman tennis player have many tennis balls.
- Two men are fishing.
- A young woman never wears white dress.
- source_sentence: An older gentleman enjoys a scenic stroll through the countryside.
sentences:
- A pirate boards the spaceship.
- A man walks the countryside.
- Girls standing at a whiteboard in front of class.
- source_sentence: A kid in a red and black coat is laying on his back in the snow
with his arm in the air and a red sled is next to him.
sentences:
- It is a cold day.
- A girl with her hands in a tub.
- The kid is on a sugar high.
- source_sentence: A young boy playing in the grass.
sentences:
- A woman in a restaurant.
- The boy is in the sand.
- There is a child in the grass.
model-index:
- name: SentenceTransformer based on answerdotai/ModernBERT-base
results:
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: sts dev
type: sts-dev
metrics:
- type: pearson_cosine
value: 0.7500819739694012
name: Pearson Cosine
- type: spearman_cosine
value: 0.7642960771418298
name: Spearman Cosine
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: sts test
type: sts-test
metrics:
- type: pearson_cosine
value: 0.6960229997567589
name: Pearson Cosine
- type: spearman_cosine
value: 0.689295049927495
name: Spearman Cosine
---
# SentenceTransformer based on answerdotai/ModernBERT-base
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on the [all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
## Model Details
### Model Description
- **Model Type:** Sentence Transformer
- **Base model:** [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) <!-- at revision 8949b909ec900327062f0ebf497f51aef5e6f0c8 -->
- **Maximum Sequence Length:** 8192 tokens
- **Output Dimensionality:** 768 dimensions
- **Similarity Function:** Cosine Similarity
- **Training Dataset:**
- [all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli)
- **Language:** en
<!-- - **License:** Unknown -->
### Model Sources
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
### Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 8192, 'do_lower_case': False}) with Transformer model: ModernBertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)
```
## Test Evaluation
```python
# Run inference
sentences = [
"The cat sat on the windowsill, watching the birds outside.",
"Quantum computing has the potential to revolutionize cryptography.",
"A delicious homemade pizza requires fresh ingredients and patience.",
"The stock market fluctuates based on economic and political events.",
"Machine learning models improve with more diverse and high-quality data.",
"Quantum computing SOLVES many problems in stock market."
]
f_embeddings = finetuned_model.encode(sentences)
embeddings = model.encode(sentences)
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# Get the similarity scores for the embeddings
f_similarities = finetuned_model.similarity(f_embeddings, f_embeddings)
print(f_similarities)
```
### Output
## Model Embedding Similarity Before and After Fine-Tuning
Below are the cosine similarity matrices before and after fine-tuning:
### **simlarity matrix Before and after Fine-Tuning:**
```python
tensor([[1.0000, 0.9052, 0.9002, 0.9080, 0.8959, 0.8925],
[0.9052, 1.0000, 0.8940, 0.9162, 0.9148, 0.9144],
[0.9002, 0.8940, 1.0000, 0.8995, 0.9033, 0.8940],
[0.9080, 0.9162, 0.8995, 1.0000, 0.9209, 0.9153],
[0.8959, 0.9148, 0.9033, 0.9209, 1.0000, 0.9142],
[0.8925, 0.9144, 0.8940, 0.9153, 0.9142, 1.0000]])
tensor([[1.0000, 0.3817, 0.3830, 0.3936, 0.3612, 0.4211],
[0.3817, 1.0000, 0.4469, 0.5501, 0.5800, 0.6188],
[0.3830, 0.4469, 1.0000, 0.4487, 0.4868, 0.5096],
[0.3936, 0.5501, 0.4487, 1.0000, 0.5981, 0.5528],
[0.3612, 0.5800, 0.4868, 0.5981, 1.0000, 0.5553],
[0.4211, 0.6188, 0.5096, 0.5528, 0.5553, 1.0000]])
```
## Model Embedding Visualization
Here is a heatmap of the embedding similarity matrix after fine-tuning:
## Usage
### Direct Usage (Sentence Transformers)
First install the Sentence Transformers library:
```bash
pip install -U sentence-transformers
```
Then you can load this model and run inference.
```python
from sentence_transformers import SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("ravi259/ModernBERT-base-nli-v2")
# Run inference
sentences = [
'A young boy playing in the grass.',
'There is a child in the grass.',
'The boy is in the sand.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]
```
<!--
### Direct Usage (Transformers)
<details><summary>Click to see the direct usage in Transformers</summary>
</details>
-->
<!--
### Downstream Usage (Sentence Transformers)
You can finetune this model on your own dataset.
<details><summary>Click to expand</summary>
</details>
-->
<!--
### Out-of-Scope Use
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->
## Evaluation
### Metrics
#### Semantic Similarity
* Datasets: `sts-dev` and `sts-test`
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
| Metric | sts-dev | sts-test |
|:--------------------|:-----------|:-----------|
| pearson_cosine | 0.7501 | 0.696 |
| **spearman_cosine** | **0.7643** | **0.6893** |
<!--
## Bias, Risks and Limitations
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
-->
<!--
### Recommendations
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
-->
## Training Details
### Training Dataset
#### all-nli
* Dataset: [all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) at [d482672](https://huggingface.co/datasets/sentence-transformers/all-nli/tree/d482672c8e74ce18da116f430137434ba2e52fab)
* Size: 557,850 training samples
* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
* Approximate statistics based on the first 1000 samples:
| | anchor | positive | negative |
|:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
| type | string | string | string |
| details | <ul><li>min: 7 tokens</li><li>mean: 10.46 tokens</li><li>max: 46 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 12.91 tokens</li><li>max: 40 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 13.49 tokens</li><li>max: 51 tokens</li></ul> |
* Samples:
| anchor | positive | negative |
|:---------------------------------------------------------------------------|:-------------------------------------------------|:-----------------------------------------------------------|
| <code>A person on a horse jumps over a broken down airplane.</code> | <code>A person is outdoors, on a horse.</code> | <code>A person is at a diner, ordering an omelette.</code> |
| <code>Children smiling and waving at camera</code> | <code>There are children present</code> | <code>The kids are frowning</code> |
| <code>A boy is jumping on skateboard in the middle of a red bridge.</code> | <code>The boy does a skateboarding trick.</code> | <code>The boy skates down the sidewalk.</code> |
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "cos_sim"
}
```
### Evaluation Dataset
#### all-nli
* Dataset: [all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) at [d482672](https://huggingface.co/datasets/sentence-transformers/all-nli/tree/d482672c8e74ce18da116f430137434ba2e52fab)
* Size: 6,584 evaluation samples
* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
* Approximate statistics based on the first 1000 samples:
| | anchor | positive | negative |
|:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
| type | string | string | string |
| details | <ul><li>min: 6 tokens</li><li>mean: 18.25 tokens</li><li>max: 69 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 9.88 tokens</li><li>max: 30 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 10.48 tokens</li><li>max: 29 tokens</li></ul> |
* Samples:
| anchor | positive | negative |
|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------|:--------------------------------------------------------|
| <code>Two women are embracing while holding to go packages.</code> | <code>Two woman are holding packages.</code> | <code>The men are fighting outside a deli.</code> |
| <code>Two young children in blue jerseys, one with the number 9 and one with the number 2 are standing on wooden steps in a bathroom and washing their hands in a sink.</code> | <code>Two kids in numbered jerseys wash their hands.</code> | <code>Two kids in jackets walk to school.</code> |
| <code>A man selling donuts to a customer during a world exhibition event held in the city of Angeles</code> | <code>A man selling donuts to a customer.</code> | <code>A woman drinks her coffee in a small cafe.</code> |
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "cos_sim"
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `eval_strategy`: steps
- `per_device_train_batch_size`: 128
- `per_device_eval_batch_size`: 128
- `num_train_epochs`: 1
- `warmup_ratio`: 0.1
- `fp16`: True
- `batch_sampler`: no_duplicates
#### All Hyperparameters
<details><summary>Click to expand</summary>
- `overwrite_output_dir`: False
- `do_predict`: False
- `eval_strategy`: steps
- `prediction_loss_only`: True
- `per_device_train_batch_size`: 128
- `per_device_eval_batch_size`: 128
- `per_gpu_train_batch_size`: None
- `per_gpu_eval_batch_size`: None
- `gradient_accumulation_steps`: 1
- `eval_accumulation_steps`: None
- `torch_empty_cache_steps`: None
- `learning_rate`: 5e-05
- `weight_decay`: 0.0
- `adam_beta1`: 0.9
- `adam_beta2`: 0.999
- `adam_epsilon`: 1e-08
- `max_grad_norm`: 1.0
- `num_train_epochs`: 1
- `max_steps`: -1
- `lr_scheduler_type`: linear
- `lr_scheduler_kwargs`: {}
- `warmup_ratio`: 0.1
- `warmup_steps`: 0
- `log_level`: passive
- `log_level_replica`: warning
- `log_on_each_node`: True
- `logging_nan_inf_filter`: True
- `save_safetensors`: True
- `save_on_each_node`: False
- `save_only_model`: False
- `restore_callback_states_from_checkpoint`: False
- `no_cuda`: False
- `use_cpu`: False
- `use_mps_device`: False
- `seed`: 42
- `data_seed`: None
- `jit_mode_eval`: False
- `use_ipex`: False
- `bf16`: False
- `fp16`: True
- `fp16_opt_level`: O1
- `half_precision_backend`: auto
- `bf16_full_eval`: False
- `fp16_full_eval`: False
- `tf32`: None
- `local_rank`: 0
- `ddp_backend`: None
- `tpu_num_cores`: None
- `tpu_metrics_debug`: False
- `debug`: []
- `dataloader_drop_last`: False
- `dataloader_num_workers`: 0
- `dataloader_prefetch_factor`: None
- `past_index`: -1
- `disable_tqdm`: False
- `remove_unused_columns`: True
- `label_names`: None
- `load_best_model_at_end`: False
- `ignore_data_skip`: False
- `fsdp`: []
- `fsdp_min_num_params`: 0
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
- `fsdp_transformer_layer_cls_to_wrap`: None
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
- `deepspeed`: None
- `label_smoothing_factor`: 0.0
- `optim`: adamw_torch
- `optim_args`: None
- `adafactor`: False
- `group_by_length`: False
- `length_column_name`: length
- `ddp_find_unused_parameters`: None
- `ddp_bucket_cap_mb`: None
- `ddp_broadcast_buffers`: False
- `dataloader_pin_memory`: True
- `dataloader_persistent_workers`: False
- `skip_memory_metrics`: True
- `use_legacy_prediction_loop`: False
- `push_to_hub`: False
- `resume_from_checkpoint`: None
- `hub_model_id`: None
- `hub_strategy`: every_save
- `hub_private_repo`: None
- `hub_always_push`: False
- `gradient_checkpointing`: False
- `gradient_checkpointing_kwargs`: None
- `include_inputs_for_metrics`: False
- `include_for_metrics`: []
- `eval_do_concat_batches`: True
- `fp16_backend`: auto
- `push_to_hub_model_id`: None
- `push_to_hub_organization`: None
- `mp_parameters`:
- `auto_find_batch_size`: False
- `full_determinism`: False
- `torchdynamo`: None
- `ray_scope`: last
- `ddp_timeout`: 1800
- `torch_compile`: False
- `torch_compile_backend`: None
- `torch_compile_mode`: None
- `dispatch_batches`: None
- `split_batches`: None
- `include_tokens_per_second`: False
- `include_num_input_tokens_seen`: False
- `neftune_noise_alpha`: None
- `optim_target_modules`: None
- `batch_eval_metrics`: False
- `eval_on_start`: False
- `use_liger_kernel`: False
- `eval_use_gather_object`: False
- `average_tokens_across_devices`: False
- `prompts`: None
- `batch_sampler`: no_duplicates
- `multi_dataset_batch_sampler`: proportional
</details>
### Training Logs
| Epoch | Step | Validation Loss | sts-dev_spearman_cosine | sts-test_spearman_cosine |
|:------:|:----:|:---------------:|:-----------------------:|:------------------------:|
| -1 | -1 | - | 0.5566 | - |
| 0.1266 | 10 | 2.9276 | 0.7376 | - |
| 0.2532 | 20 | 1.6373 | 0.7721 | - |
| 0.3797 | 30 | 1.5806 | 0.7676 | - |
| 0.5063 | 40 | 1.7071 | 0.7613 | - |
| 0.6329 | 50 | 1.7604 | 0.7640 | - |
| 0.7595 | 60 | 1.7851 | 0.7665 | - |
| 0.8861 | 70 | 1.9029 | 0.7643 | - |
| -1 | -1 | - | - | 0.6893 |
### Framework Versions
- Python: 3.11.11
- Sentence Transformers: 3.4.1
- Transformers: 4.48.3
- PyTorch: 2.5.1+cu124
- Accelerate: 1.3.0
- Datasets: 3.3.2
- Tokenizers: 0.21.0
## Citation
### BibTeX
#### Sentence Transformers
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "https://arxiv.org/abs/1908.10084",
}
```
#### MultipleNegativesRankingLoss
```bibtex
@misc{henderson2017efficient,
title={Efficient Natural Language Response Suggestion for Smart Reply},
author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
year={2017},
eprint={1705.00652},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
<!--
## Glossary
*Clearly define terms in order to be accessible across audiences.*
-->
<!--
## Model Card Authors
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->
<!--
## Model Card Contact
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
--> | [
"TEXT_CLASSIFICATION",
"SEMANTIC_SIMILARITY"
] | Non_BioNLP |
gokuls/BERT-tiny-emotion-intent | gokuls | text-classification | [
"transformers",
"pytorch",
"tensorboard",
"bert",
"text-classification",
"generated_from_trainer",
"dataset:emotion",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 1,664,028,097,000 | 2022-09-24T14:11:28 | 116 | 2 | ---
datasets:
- emotion
license: apache-2.0
metrics:
- accuracy
tags:
- generated_from_trainer
model-index:
- name: BERT-tiny-emotion-intent
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: emotion
type: emotion
config: default
split: train
args: default
metrics:
- type: accuracy
value: 0.91
name: Accuracy
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# BERT-tiny-emotion-intent
This model is a fine-tuned version of [google/bert_uncased_L-2_H-128_A-2](https://huggingface.co/google/bert_uncased_L-2_H-128_A-2) on the emotion dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3620
- Accuracy: 0.91
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 33
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 1.2603 | 1.0 | 1000 | 0.7766 | 0.7815 |
| 0.5919 | 2.0 | 2000 | 0.4117 | 0.884 |
| 0.367 | 3.0 | 3000 | 0.3188 | 0.8995 |
| 0.2848 | 4.0 | 4000 | 0.2928 | 0.8985 |
| 0.2395 | 5.0 | 5000 | 0.2906 | 0.898 |
| 0.2094 | 6.0 | 6000 | 0.2887 | 0.907 |
| 0.1884 | 7.0 | 7000 | 0.2831 | 0.9065 |
| 0.1603 | 8.0 | 8000 | 0.3044 | 0.9065 |
| 0.1519 | 9.0 | 9000 | 0.3124 | 0.9095 |
| 0.1291 | 10.0 | 10000 | 0.3256 | 0.9065 |
| 0.1179 | 11.0 | 11000 | 0.3651 | 0.9035 |
| 0.1091 | 12.0 | 12000 | 0.3620 | 0.91 |
| 0.0977 | 13.0 | 13000 | 0.3992 | 0.907 |
| 0.0914 | 14.0 | 14000 | 0.4285 | 0.908 |
| 0.0876 | 15.0 | 15000 | 0.4268 | 0.9055 |
### Framework versions
- Transformers 4.22.1
- Pytorch 1.12.1+cu113
- Datasets 2.5.1
- Tokenizers 0.12.1
| [
"TEXT_CLASSIFICATION"
] | Non_BioNLP |
daekeun-ml/Phi-3-medium-4k-instruct-ko-poc-v0.1 | daekeun-ml | text-generation | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"unsloth",
"phi-3",
"conversational",
"ko",
"en",
"dataset:nampdn-ai/tiny-codes",
"dataset:nlpai-lab/openassistant-guanaco-ko",
"dataset:philschmid/guanaco-sharegpt-style",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | 1,716,686,260,000 | 2024-05-26T02:22:28 | 21 | 1 | ---
datasets:
- nampdn-ai/tiny-codes
- nlpai-lab/openassistant-guanaco-ko
- philschmid/guanaco-sharegpt-style
language:
- ko
- en
library_name: transformers
license: apache-2.0
pipeline_tag: text-generation
tags:
- unsloth
- phi-3
inference: false
---
# Phi-3-medium-4k-instruct-ko-poc-v0.1
## Model Details
This model is trained using unsloth toolkit based on Microsoft's phi-3 Phi-3-medium-4k-instruct model (https://huggingface.co/unsloth/Phi-3-medium-4k-instruct) with some Korean instruction data added to enhance its Korean generation performance
Since my role is not as a working developer, but as ML Technical Specialist helping customers with quick PoCs/prototypes, and I was limited by Azure GPU resources available, I only trained with 40,000 samples on a single VM Azure Standard_NC24ads_A100_v4 for PoC purposes. Because I have not done any tokenizer extensions, you need a lot more tokens than English for text generation.
### Dataset
The dataset used for training is as follows. To prevent catastrophic forgetting, I included non-Korean corpus as training data. Note that we did not use all of the data, but only sampled some of it. Korean textbooks were converted to Q&A format. The Guanaco dataset has been reformatted to fit the multiturn format like <|user|>\n{Q1}<|end|>\n<|assistant|>\n{A1}<|end|>\n<|user|>\n{Q2}<|end|>\n<|assistant|>\n{A2}<|end|>.
- Korean textbooks (https://huggingface.co/datasets/nampdn-ai/tiny-codes)
- Korean translation of Guanaco (https://huggingface.co/datasets/nlpai-lab/openassistant-guanaco-ko)
- Guanaco Sharegpt style (https://huggingface.co/datasets/philschmid/guanaco-sharegpt-style)
## How to Get Started with the Model
### Code snippets
```python
### Load model
import torch
from unsloth import FastLanguageModel
from unsloth.chat_templates import get_chat_template
from transformers import TextStreamer
max_seq_length = 2048 # Choose any! We auto support RoPE Scaling internally!
dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+
load_in_4bit = True # Use 4bit quantization to reduce memory usage. Can be False.
model_path = "daekeun-ml/Phi-3-medium-4k-instruct-ko-poc-v0.1"
model, tokenizer = FastLanguageModel.from_pretrained(
model_name = model_tar_dir, # Choose ANY! eg teknium/OpenHermes-2.5-Mistral-7B
max_seq_length = max_seq_length,
dtype = dtype,
load_in_4bit = load_in_4bit,
# token = "hf_...", # use one if using gated models like meta-llama/Llama-2-7b-hf
)
tokenizer = get_chat_template(
tokenizer,
chat_template = "phi-3", # Supports zephyr, chatml, mistral, llama, alpaca, vicuna, vicuna_old, unsloth
mapping = {"role" : "from", "content" : "value", "user" : "human", "assistant" : "gpt"}, # ShareGPT style
)
params = {
"max_new_tokens": 256,
"use_cache": True,
"temperature": 0.05,
"do_sample": True
}
### Inference
FastLanguageModel.for_inference(model) # Enable native 2x faster inference
# 1st example
messages = [
{"from": "human", "value": "Continue the fibonnaci sequence in Korean: 1, 1, 2, 3, 5, 8,"},
{"from": "assistant", "value": "피보나치 수열의 다음 숫자는 13, 21, 34, 55, 89 등입니다. 각 숫자는 앞의 두 숫자의 합입니다."},
{"from": "human", "value": "Compute 2x+3=12 in Korean"},
]
inputs = tokenizer.apply_chat_template(
messages,
tokenize = True,
add_generation_prompt = True, # Must add for generation
return_tensors = "pt",
).to("cuda")
text_streamer = TextStreamer(tokenizer)
_ = model.generate(input_ids = inputs, streamer = text_streamer, **params)
# 2nd example
messages = [
{"from": "human", "value": "What is Machine Learning in Korean?"},
{"from": "assistant", "value": "인공지능의 한 분야로 방대한 데이터를 분석해 향후 패턴을 예측하는 기법입니다."},
{"from": "human", "value": "What is Deep Learning in Korean?"},
]
inputs = tokenizer.apply_chat_template(
messages,
tokenize = True,
add_generation_prompt = True, # Must add for generation
return_tensors = "pt",
).to("cuda")
from transformers import TextStreamer
text_streamer = TextStreamer(tokenizer)
_ = model.generate(input_ids = inputs, streamer = text_streamer, **params)
```
### Inference results
```python
# 1st example
<s><|user|> Continue the fibonnaci sequence in Korean: 1, 1, 2, 3, 5, 8,<|end|><|assistant|> 피보나치 수열의 다음 숫자는 13, 21, 34, 55, 89 등입니다. 각 숫자는 앞의 두 숫자의 합입니다.<|end|><|user|> Compute 2x+3=12 in Korean<|end|><|assistant|> 방정식 2x + 3 = 12에서 x를 풀려면 다음 단계를 따르십시오.
1. 방정식의 양쪽에서 3을 빼서 방정식의 한쪽에 대해 x를 분리합니다.
2x + 3 - 3 = 12 - 3
2x = 9
2. 이제 방정식의 양쪽을 2로 나누어 x의 값을 구합니다.
2배 / 2 = 9 / 2
x = 4.5
따라서 방정식 2x + 3 = 12에 대한 해는 x = 4.5입니다.<|end|>
# 2nd example
<s><|user|> What is Machine Learning in Korean?<|end|><|assistant|> 인공지능의 한 분야로 방대한 데이터를 분석해 향후 패턴을 예측하는 기법입니다.<|end|><|user|> What is Deep Learning in Korean?<|end|><|assistant|> 복잡한 데이터 세트를 분석하고 복잡한 패턴을 인식하고 학습하는 데 사용되는 딥러닝은 많은 레이어로 구성된 신경망의 하위 집합입니다. 이 기술은 이미지 인식, 자연어 처리 및 자율 운전과 같은 다양한 응용 분야에서 큰 발전을 이뤘습니다.<|end|>
```
### References
- Base model: [unsloth/Phi-3-medium-4k-instruct](https://huggingface.co/unsloth/Phi-3-medium-4k-instruct)
## Notes
### License
apache 2.0; The license of phi-3 is MIT, but I considered the licensing of the dataset and library used for training.
### Caution
This model was created as a personal experiment, unrelated to the organization I work for. The model may not operate correctly because separate verification was not performed. Please be careful unless it is for personal experimentation or PoC (Proof of Concept)! | [
"TRANSLATION"
] | TBD |
minnehwg/finetune-newwiki-summarization-ver2 | minnehwg | text2text-generation | [
"transformers",
"pytorch",
"tensorboard",
"t5",
"text2text-generation",
"generated_from_trainer",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 1,715,596,424,000 | 2024-05-13T12:48:58 | 14 | 0 | ---
license: mit
metrics:
- rouge
tags:
- generated_from_trainer
model-index:
- name: finetune-newwiki-summarization-ver2
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# finetune-newwiki-summarization-ver2
This model is a fine-tuned version of [minnehwg/finetune-newwiki-summarization-ver1](https://huggingface.co/minnehwg/finetune-newwiki-summarization-ver1) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4697
- Rouge1: 48.1659
- Rouge2: 25.1491
- Rougel: 34.7794
- Rougelsum: 37.0893
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 7
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
| 0.4912 | 1.0 | 990 | 0.4701 | 48.1754 | 25.0221 | 34.7613 | 37.0734 |
| 0.4748 | 2.0 | 1980 | 0.4694 | 48.3629 | 25.3649 | 35.0239 | 37.3084 |
| 0.4755 | 3.0 | 2970 | 0.4695 | 48.2770 | 25.1907 | 34.8456 | 37.1930 |
| 0.4703 | 4.0 | 3960 | 0.4696 | 48.1801 | 25.1769 | 34.8004 | 37.0817 |
| 0.468 | 5.0 | 4950 | 0.4697 | 48.1659 | 25.1491 | 34.7794 | 37.0893 |
### Framework versions
- Transformers 4.17.0
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2
| [
"SUMMARIZATION"
] | Non_BioNLP |
ccdv/lsg-albert-base-v2-4096 | ccdv | fill-mask | [
"transformers",
"pytorch",
"albert",
"fill-mask",
"long context",
"custom_code",
"en",
"arxiv:2210.15497",
"arxiv:1909.11942",
"autotrain_compatible",
"region:us"
] | 1,658,861,993,000 | 2023-12-17T21:09:53 | 44 | 0 | ---
language:
- en
pipeline_tag: fill-mask
tags:
- albert
- long context
---
# LSG model
**Transformers >= 4.36.1**\
**This model relies on a custom modeling file, you need to add trust_remote_code=True**\
**See [\#13467](https://github.com/huggingface/transformers/pull/13467)**
LSG ArXiv [paper](https://arxiv.org/abs/2210.15497). \
Github/conversion script is available at this [link](https://github.com/ccdv-ai/convert_checkpoint_to_lsg).
* [Usage](#usage)
* [Parameters](#parameters)
* [Sparse selection type](#sparse-selection-type)
* [Tasks](#tasks)
This model is adapted from [AlBERT-base-v2](https://huggingface.co/albert-base-v2) without additional pretraining. It uses the same number of parameters/layers and the same tokenizer.
This model can handle long sequences but faster and more efficiently than Longformer (LED) or BigBird (Pegasus) from the hub and relies on Local + Sparse + Global attention (LSG).
The model requires sequences whose length is a multiple of the block size. The model is "adaptive" and automatically pads the sequences if needed (adaptive=True in config). It is however recommended, thanks to the tokenizer, to truncate the inputs (truncation=True) and optionally to pad with a multiple of the block size (pad_to_multiple_of=...).
Implemented in PyTorch.
## Usage
The model relies on a custom modeling file, you need to add trust_remote_code=True to use it.
```python:
from transformers import AutoModel, AutoTokenizer
model = AutoModel.from_pretrained("ccdv/lsg-albert-base-v2-4096", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("ccdv/lsg-albert-base-v2-4096")
```
## Parameters
You can change various parameters like :
* the number of global tokens (num_global_tokens=1)
* local block size (block_size=128)
* sparse block size (sparse_block_size=128)
* sparsity factor (sparsity_factor=2)
* mask_first_token (mask first token since it is redundant with the first global token)
* see config.json file
Default parameters work well in practice. If you are short on memory, reduce block sizes, increase sparsity factor and remove dropout in the attention score matrix.
```python:
from transformers import AutoModel
model = AutoModel.from_pretrained("ccdv/lsg-albert-base-v2-4096",
trust_remote_code=True,
num_global_tokens=16,
block_size=64,
sparse_block_size=64,
attention_probs_dropout_prob=0.0
sparsity_factor=4,
sparsity_type="none",
mask_first_token=True
)
```
## Sparse selection type
There are 6 different sparse selection patterns. The best type is task dependent. \
If `sparse_block_size=0` or `sparsity_type="none"`, only local attention is considered. \
Note that for sequences with length < 2*block_size, the type has no effect.
* `sparsity_type="bos_pooling"` (new)
* weighted average pooling using the BOS token
* Works best in general, especially with a rather large sparsity_factor (8, 16, 32)
* Additional parameters:
* None
* `sparsity_type="norm"`, select highest norm tokens
* Works best for a small sparsity_factor (2 to 4)
* Additional parameters:
* None
* `sparsity_type="pooling"`, use average pooling to merge tokens
* Works best for a small sparsity_factor (2 to 4)
* Additional parameters:
* None
* `sparsity_type="lsh"`, use the LSH algorithm to cluster similar tokens
* Works best for a large sparsity_factor (4+)
* LSH relies on random projections, thus inference may differ slightly with different seeds
* Additional parameters:
* lsg_num_pre_rounds=1, pre merge tokens n times before computing centroids
* `sparsity_type="stride"`, use a striding mecanism per head
* Each head will use different tokens strided by sparsify_factor
* Not recommended if sparsify_factor > num_heads
* `sparsity_type="block_stride"`, use a striding mecanism per head
* Each head will use block of tokens strided by sparsify_factor
* Not recommended if sparsify_factor > num_heads
## Tasks
Seq2Seq example for summarization:
```python:
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
model = AutoModelForSeq2SeqLM.from_pretrained("ccdv/lsg-albert-base-v2-4096",
trust_remote_code=True,
pass_global_tokens_to_decoder=True, # Pass encoder global tokens to decoder
)
tokenizer = AutoTokenizer.from_pretrained("ccdv/lsg-albert-base-v2-4096")
SENTENCE = "This is a test sequence to test the model. " * 300
token_ids = tokenizer(
SENTENCE,
return_tensors="pt",
padding="max_length", # Optional but recommended
truncation=True # Optional but recommended
)
output = model(**token_ids)
```
Classification example:
```python:
from transformers import AutoModelForSequenceClassification, AutoTokenizer
model = AutoModelForSequenceClassification.from_pretrained("ccdv/lsg-albert-base-v2-4096",
trust_remote_code=True,
pass_global_tokens_to_decoder=True, # Pass encoder global tokens to decoder
)
tokenizer = AutoTokenizer.from_pretrained("ccdv/lsg-albert-base-v2-4096")
SENTENCE = "This is a test sequence to test the model. " * 300
token_ids = tokenizer(
SENTENCE,
return_tensors="pt",
#pad_to_multiple_of=... # Optional
truncation=True
)
output = model(**token_ids)
> SequenceClassifierOutput(loss=None, logits=tensor([[-0.3051, -0.1762]], grad_fn=<AddmmBackward>), hidden_states=None, attentions=None)
```
**AlBERT**
```
@article{DBLP:journals/corr/abs-1909-11942,
author = {Zhenzhong Lan and
Mingda Chen and
Sebastian Goodman and
Kevin Gimpel and
Piyush Sharma and
Radu Soricut},
title = {{ALBERT:} {A} Lite {BERT} for Self-supervised Learning of Language
Representations},
journal = {CoRR},
volume = {abs/1909.11942},
year = {2019},
url = {http://arxiv.org/abs/1909.11942},
archivePrefix = {arXiv},
eprint = {1909.11942},
timestamp = {Fri, 27 Sep 2019 13:04:21 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1909-11942.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
``` | [
"SUMMARIZATION"
] | Non_BioNLP |
firqaaa/indo-setfit-bert-base-p3 | firqaaa | text-classification | [
"setfit",
"safetensors",
"bert",
"sentence-transformers",
"text-classification",
"generated_from_setfit_trainer",
"arxiv:2209.11055",
"base_model:firqaaa/indo-sentence-bert-base",
"base_model:finetune:firqaaa/indo-sentence-bert-base",
"model-index",
"region:us"
] | 1,707,367,307,000 | 2024-02-08T05:28:10 | 7 | 0 | ---
base_model: firqaaa/indo-sentence-bert-base
library_name: setfit
metrics:
- accuracy
pipeline_tag: text-classification
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: Aku sudah lebih tua dan hidupku sangat berbeda. Aku bisa merasakan betapa
takjubnya aku pagi itu
- text: Saya merasa cukup href http kata-kata yang tak terucapkan disimpan di dalam
- text: Aku melihat ke dalam dompetku dan aku merasakan hawa dingin
- text: Aku menurunkan Erik dengan perasaan agak tidak puas dengan malam itu
- text: Aku bertanya-tanya apa yang siswa lain di kelasku rasakan ketika aku tidak
takut untuk memberikan jawaban di luar sana
inference: true
model-index:
- name: SetFit with firqaaa/indo-sentence-bert-base
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: firqaaa/emotion-bahasa
type: unknown
split: test
metrics:
- type: accuracy
value: 0.718
name: Accuracy
---
# SetFit with firqaaa/indo-sentence-bert-base
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [firqaaa/indo-sentence-bert-base](https://huggingface.co/firqaaa/indo-sentence-bert-base) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
The model has been trained using an efficient few-shot learning technique that involves:
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.
## Model Details
### Model Description
- **Model Type:** SetFit
- **Sentence Transformer body:** [firqaaa/indo-sentence-bert-base](https://huggingface.co/firqaaa/indo-sentence-bert-base)
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
- **Maximum Sequence Length:** 512 tokens
- **Number of Classes:** 6 classes
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
<!-- - **Language:** Unknown -->
<!-- - **License:** Unknown -->
### Model Sources
- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
### Model Labels
| Label | Examples |
|:----------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| kesedihan | <ul><li>'Saya merasa agak kecewa, saya rasa harus menyerahkan sesuatu yang tidak menarik hanya untuk memenuhi tenggat waktu'</li><li>'Aku merasa seperti aku telah cukup lalai terhadap blogku dan aku hanya mengatakan bahwa kita di sini hidup dan bahagia'</li><li>'Aku tahu dan aku selalu terkoyak karenanya karena aku merasa tidak berdaya dan tidak berguna'</li></ul> |
| sukacita | <ul><li>'aku mungkin tidak merasa begitu keren'</li><li>'saya merasa baik-baik saja'</li><li>'saya merasa seperti saya seorang ibu dengan mengorbankan produktivitas'</li></ul> |
| cinta | <ul><li>'aku merasa mencintaimu'</li><li>'aku akan merasa sangat nostalgia di usia yang begitu muda'</li><li>'Saya merasa diberkati bahwa saya tinggal di Amerika memiliki keluarga yang luar biasa dan Dorothy Kelsey adalah bagian dari hidup saya'</li></ul> |
| amarah | <ul><li>'Aku terlalu memikirkan cara dudukku, suaraku terdengar jika ada makanan di mulutku, dan perasaan bahwa aku harus berjalan ke semua orang agar tidak bersikap kasar'</li><li>'aku merasa memberontak sedikit kesal gila terkurung'</li><li>'Aku merasakan perasaan itu muncul kembali dari perasaan paranoid dan cemburu yang penuh kebencian yang selalu menyiksaku tanpa henti'</li></ul> |
| takut | <ul><li>'aku merasa seperti diserang oleh landak titanium'</li><li>'Aku membiarkan diriku memikirkan perilakuku terhadapmu saat kita masih kecil. Aku merasakan campuran aneh antara rasa bersalah dan kekaguman atas ketangguhanmu'</li><li>'saya marah karena majikan saya tidak berinvestasi pada kami sama sekali, gaji pelatihan, kenaikan hari libur bank dan rasanya seperti ketidakadilan sehingga saya merasa tidak berdaya'</li></ul> |
| kejutan | <ul><li>'Aku membaca bagian ol feefyefo Aku merasa takjub melihat betapa aku bisa mengoceh dan betapa transparannya aku dalam hidupku'</li><li>'saya menemukan seni di sisi lain saya merasa sangat terkesan dengan karya saya'</li><li>'aku merasa penasaran, bersemangat dan tidak sabar'</li></ul> |
## Evaluation
### Metrics
| Label | Accuracy |
|:--------|:---------|
| **all** | 0.718 |
## Uses
### Direct Use for Inference
First install the SetFit library:
```bash
pip install setfit
```
Then you can load this model and run inference.
```python
from setfit import SetFitModel
# Download from the 🤗 Hub
model = SetFitModel.from_pretrained("firqaaa/indo-setfit-bert-base-p3")
# Run inference
preds = model("Aku melihat ke dalam dompetku dan aku merasakan hawa dingin")
```
<!--
### Downstream Use
*List how someone could finetune this model on their own dataset.*
-->
<!--
### Out-of-Scope Use
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->
<!--
## Bias, Risks and Limitations
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
-->
<!--
### Recommendations
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
-->
## Training Details
### Training Set Metrics
| Training set | Min | Median | Max |
|:-------------|:----|:--------|:----|
| Word count | 2 | 16.7928 | 56 |
| Label | Training Sample Count |
|:----------|:----------------------|
| kesedihan | 300 |
| sukacita | 300 |
| cinta | 300 |
| amarah | 300 |
| takut | 300 |
| kejutan | 300 |
### Training Hyperparameters
- batch_size: (128, 128)
- num_epochs: (1, 1)
- max_steps: -1
- sampling_strategy: oversampling
- body_learning_rate: (2e-05, 1e-05)
- head_learning_rate: 0.01
- loss: CosineSimilarityLoss
- distance_metric: cosine_distance
- margin: 0.25
- end_to_end: False
- use_amp: False
- warmup_proportion: 0.1
- seed: 42
- eval_max_steps: -1
- load_best_model_at_end: True
### Training Results
| Epoch | Step | Training Loss | Validation Loss |
|:-------:|:---------:|:-------------:|:---------------:|
| 0.0000 | 1 | 0.2927 | - |
| 0.0024 | 50 | 0.2605 | - |
| 0.0047 | 100 | 0.2591 | - |
| 0.0071 | 150 | 0.2638 | - |
| 0.0095 | 200 | 0.245 | - |
| 0.0119 | 250 | 0.226 | - |
| 0.0142 | 300 | 0.222 | - |
| 0.0166 | 350 | 0.1968 | - |
| 0.0190 | 400 | 0.1703 | - |
| 0.0213 | 450 | 0.1703 | - |
| 0.0237 | 500 | 0.1587 | - |
| 0.0261 | 550 | 0.1087 | - |
| 0.0284 | 600 | 0.1203 | - |
| 0.0308 | 650 | 0.0844 | - |
| 0.0332 | 700 | 0.0696 | - |
| 0.0356 | 750 | 0.0606 | - |
| 0.0379 | 800 | 0.0333 | - |
| 0.0403 | 850 | 0.0453 | - |
| 0.0427 | 900 | 0.033 | - |
| 0.0450 | 950 | 0.0142 | - |
| 0.0474 | 1000 | 0.004 | - |
| 0.0498 | 1050 | 0.0097 | - |
| 0.0521 | 1100 | 0.0065 | - |
| 0.0545 | 1150 | 0.0081 | - |
| 0.0569 | 1200 | 0.0041 | - |
| 0.0593 | 1250 | 0.0044 | - |
| 0.0616 | 1300 | 0.0013 | - |
| 0.0640 | 1350 | 0.0024 | - |
| 0.0664 | 1400 | 0.001 | - |
| 0.0687 | 1450 | 0.0012 | - |
| 0.0711 | 1500 | 0.0013 | - |
| 0.0735 | 1550 | 0.0006 | - |
| 0.0759 | 1600 | 0.0033 | - |
| 0.0782 | 1650 | 0.0006 | - |
| 0.0806 | 1700 | 0.0013 | - |
| 0.0830 | 1750 | 0.0008 | - |
| 0.0853 | 1800 | 0.0006 | - |
| 0.0877 | 1850 | 0.0008 | - |
| 0.0901 | 1900 | 0.0004 | - |
| 0.0924 | 1950 | 0.0005 | - |
| 0.0948 | 2000 | 0.0004 | - |
| 0.0972 | 2050 | 0.0002 | - |
| 0.0996 | 2100 | 0.0002 | - |
| 0.1019 | 2150 | 0.0003 | - |
| 0.1043 | 2200 | 0.0006 | - |
| 0.1067 | 2250 | 0.0005 | - |
| 0.1090 | 2300 | 0.0003 | - |
| 0.1114 | 2350 | 0.0018 | - |
| 0.1138 | 2400 | 0.0003 | - |
| 0.1161 | 2450 | 0.0002 | - |
| 0.1185 | 2500 | 0.0018 | - |
| 0.1209 | 2550 | 0.0003 | - |
| 0.1233 | 2600 | 0.0008 | - |
| 0.1256 | 2650 | 0.0002 | - |
| 0.1280 | 2700 | 0.0007 | - |
| 0.1304 | 2750 | 0.006 | - |
| 0.1327 | 2800 | 0.0002 | - |
| 0.1351 | 2850 | 0.0001 | - |
| 0.1375 | 2900 | 0.0001 | - |
| 0.1399 | 2950 | 0.0001 | - |
| 0.1422 | 3000 | 0.0001 | - |
| 0.1446 | 3050 | 0.0001 | - |
| 0.1470 | 3100 | 0.0001 | - |
| 0.1493 | 3150 | 0.0001 | - |
| 0.1517 | 3200 | 0.0002 | - |
| 0.1541 | 3250 | 0.0003 | - |
| 0.1564 | 3300 | 0.0004 | - |
| 0.1588 | 3350 | 0.0001 | - |
| 0.1612 | 3400 | 0.0001 | - |
| 0.1636 | 3450 | 0.0014 | - |
| 0.1659 | 3500 | 0.0005 | - |
| 0.1683 | 3550 | 0.0003 | - |
| 0.1707 | 3600 | 0.0001 | - |
| 0.1730 | 3650 | 0.0001 | - |
| 0.1754 | 3700 | 0.0001 | - |
| 0.1778 | 3750 | 0.0001 | - |
| 0.1801 | 3800 | 0.0001 | - |
| 0.1825 | 3850 | 0.0001 | - |
| 0.1849 | 3900 | 0.0001 | - |
| 0.1873 | 3950 | 0.0001 | - |
| 0.1896 | 4000 | 0.0001 | - |
| 0.1920 | 4050 | 0.0001 | - |
| 0.1944 | 4100 | 0.0003 | - |
| 0.1967 | 4150 | 0.0006 | - |
| 0.1991 | 4200 | 0.0001 | - |
| 0.2015 | 4250 | 0.0 | - |
| 0.2038 | 4300 | 0.0 | - |
| 0.2062 | 4350 | 0.0001 | - |
| 0.2086 | 4400 | 0.0 | - |
| 0.2110 | 4450 | 0.0 | - |
| 0.2133 | 4500 | 0.0001 | - |
| 0.2157 | 4550 | 0.0002 | - |
| 0.2181 | 4600 | 0.0003 | - |
| 0.2204 | 4650 | 0.0018 | - |
| 0.2228 | 4700 | 0.0003 | - |
| 0.2252 | 4750 | 0.0145 | - |
| 0.2276 | 4800 | 0.0001 | - |
| 0.2299 | 4850 | 0.0006 | - |
| 0.2323 | 4900 | 0.0001 | - |
| 0.2347 | 4950 | 0.0007 | - |
| 0.2370 | 5000 | 0.0001 | - |
| 0.2394 | 5050 | 0.0 | - |
| 0.2418 | 5100 | 0.0 | - |
| 0.2441 | 5150 | 0.0001 | - |
| 0.2465 | 5200 | 0.0003 | - |
| 0.2489 | 5250 | 0.0 | - |
| 0.2513 | 5300 | 0.0 | - |
| 0.2536 | 5350 | 0.0 | - |
| 0.2560 | 5400 | 0.0 | - |
| 0.2584 | 5450 | 0.0004 | - |
| 0.2607 | 5500 | 0.0 | - |
| 0.2631 | 5550 | 0.0 | - |
| 0.2655 | 5600 | 0.0 | - |
| 0.2678 | 5650 | 0.0 | - |
| 0.2702 | 5700 | 0.0 | - |
| 0.2726 | 5750 | 0.0002 | - |
| 0.2750 | 5800 | 0.0 | - |
| 0.2773 | 5850 | 0.0 | - |
| 0.2797 | 5900 | 0.0 | - |
| 0.2821 | 5950 | 0.0 | - |
| 0.2844 | 6000 | 0.0 | - |
| 0.2868 | 6050 | 0.0 | - |
| 0.2892 | 6100 | 0.0 | - |
| 0.2916 | 6150 | 0.0 | - |
| 0.2939 | 6200 | 0.0 | - |
| 0.2963 | 6250 | 0.0 | - |
| 0.2987 | 6300 | 0.0001 | - |
| 0.3010 | 6350 | 0.0003 | - |
| 0.3034 | 6400 | 0.0048 | - |
| 0.3058 | 6450 | 0.0 | - |
| 0.3081 | 6500 | 0.0 | - |
| 0.3105 | 6550 | 0.0 | - |
| 0.3129 | 6600 | 0.0 | - |
| 0.3153 | 6650 | 0.0 | - |
| 0.3176 | 6700 | 0.0 | - |
| 0.3200 | 6750 | 0.0 | - |
| 0.3224 | 6800 | 0.0 | - |
| 0.3247 | 6850 | 0.0 | - |
| 0.3271 | 6900 | 0.0 | - |
| 0.3295 | 6950 | 0.0 | - |
| 0.3318 | 7000 | 0.0 | - |
| 0.3342 | 7050 | 0.0 | - |
| 0.3366 | 7100 | 0.0 | - |
| 0.3390 | 7150 | 0.0011 | - |
| 0.3413 | 7200 | 0.0002 | - |
| 0.3437 | 7250 | 0.0 | - |
| 0.3461 | 7300 | 0.0 | - |
| 0.3484 | 7350 | 0.0001 | - |
| 0.3508 | 7400 | 0.0001 | - |
| 0.3532 | 7450 | 0.0002 | - |
| 0.3556 | 7500 | 0.0 | - |
| 0.3579 | 7550 | 0.0 | - |
| 0.3603 | 7600 | 0.0 | - |
| 0.3627 | 7650 | 0.0 | - |
| 0.3650 | 7700 | 0.0 | - |
| 0.3674 | 7750 | 0.0 | - |
| 0.3698 | 7800 | 0.0001 | - |
| 0.3721 | 7850 | 0.0 | - |
| 0.3745 | 7900 | 0.0 | - |
| 0.3769 | 7950 | 0.0 | - |
| 0.3793 | 8000 | 0.0 | - |
| 0.3816 | 8050 | 0.0 | - |
| 0.3840 | 8100 | 0.0 | - |
| 0.3864 | 8150 | 0.0 | - |
| 0.3887 | 8200 | 0.0 | - |
| 0.3911 | 8250 | 0.0 | - |
| 0.3935 | 8300 | 0.0 | - |
| 0.3958 | 8350 | 0.0 | - |
| 0.3982 | 8400 | 0.0 | - |
| 0.4006 | 8450 | 0.0 | - |
| 0.4030 | 8500 | 0.0 | - |
| 0.4053 | 8550 | 0.0001 | - |
| 0.4077 | 8600 | 0.0001 | - |
| 0.4101 | 8650 | 0.0008 | - |
| 0.4124 | 8700 | 0.0001 | - |
| 0.4148 | 8750 | 0.0 | - |
| 0.4172 | 8800 | 0.0 | - |
| 0.4196 | 8850 | 0.0001 | - |
| 0.4219 | 8900 | 0.0 | - |
| 0.4243 | 8950 | 0.0 | - |
| 0.4267 | 9000 | 0.0 | - |
| 0.4290 | 9050 | 0.0 | - |
| 0.4314 | 9100 | 0.0 | - |
| 0.4338 | 9150 | 0.0 | - |
| 0.4361 | 9200 | 0.0 | - |
| 0.4385 | 9250 | 0.0 | - |
| 0.4409 | 9300 | 0.0 | - |
| 0.4433 | 9350 | 0.0 | - |
| 0.4456 | 9400 | 0.0 | - |
| 0.4480 | 9450 | 0.0 | - |
| 0.4504 | 9500 | 0.0 | - |
| 0.4527 | 9550 | 0.0 | - |
| 0.4551 | 9600 | 0.0 | - |
| 0.4575 | 9650 | 0.0 | - |
| 0.4598 | 9700 | 0.0 | - |
| 0.4622 | 9750 | 0.0001 | - |
| 0.4646 | 9800 | 0.0 | - |
| 0.4670 | 9850 | 0.0 | - |
| 0.4693 | 9900 | 0.0 | - |
| 0.4717 | 9950 | 0.0 | - |
| 0.4741 | 10000 | 0.0 | - |
| 0.4764 | 10050 | 0.0 | - |
| 0.4788 | 10100 | 0.0006 | - |
| 0.4812 | 10150 | 0.0 | - |
| 0.4835 | 10200 | 0.0 | - |
| 0.4859 | 10250 | 0.0 | - |
| 0.4883 | 10300 | 0.0 | - |
| 0.4907 | 10350 | 0.0 | - |
| 0.4930 | 10400 | 0.0 | - |
| 0.4954 | 10450 | 0.0 | - |
| 0.4978 | 10500 | 0.0 | - |
| 0.5001 | 10550 | 0.0 | - |
| 0.5025 | 10600 | 0.0 | - |
| 0.5049 | 10650 | 0.0 | - |
| 0.5073 | 10700 | 0.0 | - |
| 0.5096 | 10750 | 0.0 | - |
| 0.5120 | 10800 | 0.0 | - |
| 0.5144 | 10850 | 0.0 | - |
| 0.5167 | 10900 | 0.0 | - |
| 0.5191 | 10950 | 0.0 | - |
| 0.5215 | 11000 | 0.0 | - |
| 0.5238 | 11050 | 0.0 | - |
| 0.5262 | 11100 | 0.0 | - |
| 0.5286 | 11150 | 0.0 | - |
| 0.5310 | 11200 | 0.0 | - |
| 0.5333 | 11250 | 0.0 | - |
| 0.5357 | 11300 | 0.0 | - |
| 0.5381 | 11350 | 0.0 | - |
| 0.5404 | 11400 | 0.0 | - |
| 0.5428 | 11450 | 0.0 | - |
| 0.5452 | 11500 | 0.0 | - |
| 0.5475 | 11550 | 0.0 | - |
| 0.5499 | 11600 | 0.0 | - |
| 0.5523 | 11650 | 0.0001 | - |
| 0.5547 | 11700 | 0.0 | - |
| 0.5570 | 11750 | 0.0043 | - |
| 0.5594 | 11800 | 0.0 | - |
| 0.5618 | 11850 | 0.0 | - |
| 0.5641 | 11900 | 0.0 | - |
| 0.5665 | 11950 | 0.0 | - |
| 0.5689 | 12000 | 0.0 | - |
| 0.5713 | 12050 | 0.0 | - |
| 0.5736 | 12100 | 0.0 | - |
| 0.5760 | 12150 | 0.0 | - |
| 0.5784 | 12200 | 0.0 | - |
| 0.5807 | 12250 | 0.0029 | - |
| 0.5831 | 12300 | 0.0 | - |
| 0.5855 | 12350 | 0.0 | - |
| 0.5878 | 12400 | 0.0 | - |
| 0.5902 | 12450 | 0.0 | - |
| 0.5926 | 12500 | 0.0 | - |
| 0.5950 | 12550 | 0.0 | - |
| 0.5973 | 12600 | 0.0 | - |
| 0.5997 | 12650 | 0.0 | - |
| 0.6021 | 12700 | 0.0 | - |
| 0.6044 | 12750 | 0.0 | - |
| 0.6068 | 12800 | 0.0 | - |
| 0.6092 | 12850 | 0.0 | - |
| 0.6115 | 12900 | 0.0 | - |
| 0.6139 | 12950 | 0.0 | - |
| 0.6163 | 13000 | 0.0 | - |
| 0.6187 | 13050 | 0.0 | - |
| 0.6210 | 13100 | 0.0 | - |
| 0.6234 | 13150 | 0.0001 | - |
| 0.6258 | 13200 | 0.0 | - |
| 0.6281 | 13250 | 0.0 | - |
| 0.6305 | 13300 | 0.0 | - |
| 0.6329 | 13350 | 0.0 | - |
| 0.6353 | 13400 | 0.0001 | - |
| 0.6376 | 13450 | 0.0 | - |
| 0.6400 | 13500 | 0.0 | - |
| 0.6424 | 13550 | 0.0 | - |
| 0.6447 | 13600 | 0.0 | - |
| 0.6471 | 13650 | 0.0 | - |
| 0.6495 | 13700 | 0.0 | - |
| 0.6518 | 13750 | 0.0 | - |
| 0.6542 | 13800 | 0.0 | - |
| 0.6566 | 13850 | 0.0 | - |
| 0.6590 | 13900 | 0.0 | - |
| 0.6613 | 13950 | 0.0 | - |
| 0.6637 | 14000 | 0.0 | - |
| 0.6661 | 14050 | 0.0 | - |
| 0.6684 | 14100 | 0.0 | - |
| 0.6708 | 14150 | 0.0 | - |
| 0.6732 | 14200 | 0.0 | - |
| 0.6755 | 14250 | 0.0 | - |
| 0.6779 | 14300 | 0.0 | - |
| 0.6803 | 14350 | 0.0 | - |
| 0.6827 | 14400 | 0.0 | - |
| 0.6850 | 14450 | 0.0 | - |
| 0.6874 | 14500 | 0.0 | - |
| 0.6898 | 14550 | 0.0 | - |
| 0.6921 | 14600 | 0.0 | - |
| 0.6945 | 14650 | 0.0 | - |
| 0.6969 | 14700 | 0.0 | - |
| 0.6993 | 14750 | 0.0 | - |
| 0.7016 | 14800 | 0.0 | - |
| 0.7040 | 14850 | 0.0 | - |
| 0.7064 | 14900 | 0.0 | - |
| 0.7087 | 14950 | 0.0 | - |
| 0.7111 | 15000 | 0.0 | - |
| 0.7135 | 15050 | 0.0 | - |
| 0.7158 | 15100 | 0.0 | - |
| 0.7182 | 15150 | 0.0 | - |
| 0.7206 | 15200 | 0.0 | - |
| 0.7230 | 15250 | 0.0 | - |
| 0.7253 | 15300 | 0.0 | - |
| 0.7277 | 15350 | 0.0 | - |
| 0.7301 | 15400 | 0.0 | - |
| 0.7324 | 15450 | 0.0 | - |
| 0.7348 | 15500 | 0.0 | - |
| 0.7372 | 15550 | 0.0 | - |
| 0.7395 | 15600 | 0.0 | - |
| 0.7419 | 15650 | 0.0 | - |
| 0.7443 | 15700 | 0.0 | - |
| 0.7467 | 15750 | 0.0 | - |
| 0.7490 | 15800 | 0.0 | - |
| 0.7514 | 15850 | 0.0 | - |
| 0.7538 | 15900 | 0.0 | - |
| 0.7561 | 15950 | 0.0 | - |
| 0.7585 | 16000 | 0.0 | - |
| 0.7609 | 16050 | 0.0 | - |
| 0.7633 | 16100 | 0.0 | - |
| 0.7656 | 16150 | 0.0 | - |
| 0.7680 | 16200 | 0.0 | - |
| 0.7704 | 16250 | 0.0 | - |
| 0.7727 | 16300 | 0.0 | - |
| 0.7751 | 16350 | 0.0 | - |
| 0.7775 | 16400 | 0.0 | - |
| 0.7798 | 16450 | 0.0 | - |
| 0.7822 | 16500 | 0.0 | - |
| 0.7846 | 16550 | 0.0 | - |
| 0.7870 | 16600 | 0.0 | - |
| 0.7893 | 16650 | 0.0 | - |
| 0.7917 | 16700 | 0.0 | - |
| 0.7941 | 16750 | 0.0 | - |
| 0.7964 | 16800 | 0.0 | - |
| 0.7988 | 16850 | 0.0 | - |
| 0.8012 | 16900 | 0.0 | - |
| 0.8035 | 16950 | 0.0 | - |
| 0.8059 | 17000 | 0.0 | - |
| 0.8083 | 17050 | 0.0 | - |
| 0.8107 | 17100 | 0.0 | - |
| 0.8130 | 17150 | 0.0 | - |
| 0.8154 | 17200 | 0.0 | - |
| 0.8178 | 17250 | 0.0 | - |
| 0.8201 | 17300 | 0.0 | - |
| 0.8225 | 17350 | 0.0 | - |
| 0.8249 | 17400 | 0.0 | - |
| 0.8272 | 17450 | 0.0 | - |
| 0.8296 | 17500 | 0.0 | - |
| 0.8320 | 17550 | 0.0 | - |
| 0.8344 | 17600 | 0.0 | - |
| 0.8367 | 17650 | 0.0 | - |
| 0.8391 | 17700 | 0.0 | - |
| 0.8415 | 17750 | 0.0 | - |
| 0.8438 | 17800 | 0.0 | - |
| 0.8462 | 17850 | 0.0 | - |
| 0.8486 | 17900 | 0.0 | - |
| 0.8510 | 17950 | 0.0 | - |
| 0.8533 | 18000 | 0.0 | - |
| 0.8557 | 18050 | 0.0 | - |
| 0.8581 | 18100 | 0.0 | - |
| 0.8604 | 18150 | 0.0 | - |
| 0.8628 | 18200 | 0.0 | - |
| 0.8652 | 18250 | 0.0 | - |
| 0.8675 | 18300 | 0.0 | - |
| 0.8699 | 18350 | 0.0 | - |
| 0.8723 | 18400 | 0.0 | - |
| 0.8747 | 18450 | 0.0 | - |
| 0.8770 | 18500 | 0.0 | - |
| 0.8794 | 18550 | 0.0 | - |
| 0.8818 | 18600 | 0.0 | - |
| 0.8841 | 18650 | 0.0 | - |
| 0.8865 | 18700 | 0.0 | - |
| 0.8889 | 18750 | 0.0 | - |
| 0.8912 | 18800 | 0.0 | - |
| 0.8936 | 18850 | 0.0 | - |
| 0.8960 | 18900 | 0.0 | - |
| 0.8984 | 18950 | 0.0 | - |
| 0.9007 | 19000 | 0.0 | - |
| 0.9031 | 19050 | 0.0 | - |
| 0.9055 | 19100 | 0.0 | - |
| 0.9078 | 19150 | 0.0 | - |
| 0.9102 | 19200 | 0.0 | - |
| 0.9126 | 19250 | 0.0 | - |
| 0.9150 | 19300 | 0.0 | - |
| 0.9173 | 19350 | 0.0 | - |
| 0.9197 | 19400 | 0.0 | - |
| 0.9221 | 19450 | 0.0 | - |
| 0.9244 | 19500 | 0.0 | - |
| 0.9268 | 19550 | 0.0 | - |
| 0.9292 | 19600 | 0.0 | - |
| 0.9315 | 19650 | 0.0 | - |
| 0.9339 | 19700 | 0.0 | - |
| 0.9363 | 19750 | 0.0 | - |
| 0.9387 | 19800 | 0.0 | - |
| 0.9410 | 19850 | 0.0 | - |
| 0.9434 | 19900 | 0.0 | - |
| 0.9458 | 19950 | 0.0 | - |
| 0.9481 | 20000 | 0.0 | - |
| 0.9505 | 20050 | 0.0 | - |
| 0.9529 | 20100 | 0.0 | - |
| 0.9552 | 20150 | 0.0 | - |
| 0.9576 | 20200 | 0.0 | - |
| 0.9600 | 20250 | 0.0 | - |
| 0.9624 | 20300 | 0.0 | - |
| 0.9647 | 20350 | 0.0 | - |
| 0.9671 | 20400 | 0.0 | - |
| 0.9695 | 20450 | 0.0 | - |
| 0.9718 | 20500 | 0.0 | - |
| 0.9742 | 20550 | 0.0 | - |
| 0.9766 | 20600 | 0.0 | - |
| 0.9790 | 20650 | 0.0 | - |
| 0.9813 | 20700 | 0.0 | - |
| 0.9837 | 20750 | 0.0 | - |
| 0.9861 | 20800 | 0.0 | - |
| 0.9884 | 20850 | 0.0 | - |
| 0.9908 | 20900 | 0.0 | - |
| 0.9932 | 20950 | 0.0 | - |
| 0.9955 | 21000 | 0.0 | - |
| 0.9979 | 21050 | 0.0 | - |
| **1.0** | **21094** | **-** | **0.2251** |
* The bold row denotes the saved checkpoint.
### Framework Versions
- Python: 3.10.13
- SetFit: 1.0.3
- Sentence Transformers: 2.2.2
- Transformers: 4.36.2
- PyTorch: 2.1.2+cu121
- Datasets: 2.16.1
- Tokenizers: 0.15.0
## Citation
### BibTeX
```bibtex
@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
<!--
## Glossary
*Clearly define terms in order to be accessible across audiences.*
-->
<!--
## Model Card Authors
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->
<!--
## Model Card Contact
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
--> | [
"TEXT_CLASSIFICATION"
] | Non_BioNLP |
abhishekgupta/autotrain-question-generation4-2116768409 | abhishekgupta | summarization | [
"transformers",
"pytorch",
"autotrain",
"summarization",
"unk",
"dataset:abhishekgupta/autotrain-data-question-generation4",
"co2_eq_emissions",
"endpoints_compatible",
"region:us"
] | 1,668,590,897,000 | 2022-11-16T09:31:25 | 11 | 0 | ---
datasets:
- abhishekgupta/autotrain-data-question-generation4
language:
- unk
tags:
- autotrain
- summarization
widget:
- text: I love AutoTrain 🤗
co2_eq_emissions:
emissions: 4.8068340904981115
---
# Model Trained Using AutoTrain
- Problem type: Summarization
- Model ID: 2116768409
- CO2 Emissions (in grams): 4.8068
## Validation Metrics
- Loss: 1.092
- Rouge1: 32.336
- Rouge2: 15.558
- RougeL: 30.175
- RougeLsum: 30.191
- Gen Len: 14.493
## Usage
You can use cURL to access this model:
```
$ curl -X POST -H "Authorization: Bearer YOUR_HUGGINGFACE_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "I love AutoTrain"}' https://api-inference.huggingface.co/abhishekgupta/autotrain-question-generation4-2116768409
``` | [
"SUMMARIZATION"
] | Non_BioNLP |
gaudi/opus-mt-ca-es-ctranslate2 | gaudi | translation | [
"transformers",
"marian",
"ctranslate2",
"translation",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | 1,721,229,643,000 | 2024-10-18T23:25:32 | 6 | 0 | ---
license: apache-2.0
tags:
- ctranslate2
- translation
---
# Repository General Information
## Inspired by and derived from the work of [Helsinki-NLP](https://huggingface.co/Helsinki-NLP), [CTranslate2](https://github.com/OpenNMT/CTranslate2), and [michaelfeil](https://huggingface.co/michaelfeil)!
- Link to Original Model ([Helsinki-NLP](https://huggingface.co/Helsinki-NLP)): [Model Link](https://huggingface.co/Helsinki-NLP/opus-mt-ca-es)
- This respository was based on the work of [CTranslate2](https://github.com/OpenNMT/CTranslate2).
- This repository was based on the work of [michaelfeil](https://huggingface.co/michaelfeil).
# What is CTranslate2?
[CTranslate2](https://opennmt.net/CTranslate2/) is a C++ and Python library for efficient inference with Transformer models.
CTranslate2 implements a custom runtime that applies many performance optimization techniques such as weights quantization, layers fusion, batch reordering, etc., to accelerate and reduce the memory usage of Transformer models on CPU and GPU.
CTranslate2 is one of the most performant ways of hosting translation models at scale. Current supported models include:
- Encoder-decoder models: Transformer base/big, M2M-100, NLLB, BART, mBART, Pegasus, T5, Whisper
- Decoder-only models: GPT-2, GPT-J, GPT-NeoX, OPT, BLOOM, MPT, Llama, Mistral, Gemma, CodeGen, GPTBigCode, Falcon
- Encoder-only models: BERT, DistilBERT, XLM-RoBERTa
The project is production-oriented and comes with backward compatibility guarantees, but it also includes experimental features related to model compression and inference acceleration.
# CTranslate2 Benchmarks
Please note that the results presented below are only valid for the configuration used during this benchmark: absolute and relative performance may change with different settings. Tested against `newstest2014` (En -> De) dataset.
The benchmark reports the number of target tokens generated per second (higher is better). The results are aggregated over multiple runs. See the benchmark scripts for more details and reproduce these numbers.
Please note that the results presented below are only valid for the configuration used during this benchmark: absolute and relative performance may change with different settings.
## CPU Benchmarks for Generic Opus-MT Models
| Library | Tokens per Second | Max Memory Usage | BLEU |
| :----: | :----: | :----: | :----: |
| Transformers 4.26.1 (with PyTorch 1.13.1) | 147.3 | 2332MB | 27.90 |
| Marian 1.11.0 (int16) | 330.2 | 5901MB | 27.65 |
| Marian 1.11.0 (int8) | 355.8 | 4763MB | 27.27 |
| CTranslate2 3.6.0 (int16) | 596.1 | 660MB | 27.53 |
| CTranslate2 3.6.0 (int8) | 696.1 | 516MB | 27.65 |
## GPU Benchmarks for Generic Opus-MT Models
| Library | Tokens per Second | Max GPU Memory Usage | Max Memory Usage | BLEU |
| :----: | :----: | :----: | :----: | :----: |
| Transformers 4.26.1 (with PyTorch 1.13.1) | 1022.9 | 4097MB | 2109MB | 27.90 |
| Marian 1.11.0 (float16) | 3962.4 | 3239MB | 1976MB | 27.94 |
| CTranslate2 3.6.0 (float16) | 9296.7 | 909MB | 814MB | 27.9 |
| CTranslate2 3.6.0 (int8 + float16) | 8362.7 | 813MB | 766MB | 27.9 |
`Executed with 4 threads on a c5.2xlarge Amazon EC2 instance equipped with an Intel(R) Xeon(R) Platinum 8275CL CPU.`
**Source to benchmark information can be found [here](https://github.com/OpenNMT/CTranslate2).**<br />
**Original model BLEU scores can be found [here](https://huggingface.co/Helsinki-NLP/opus-mt-ca-es).**
## Internal Benchmarks
Internal testing on our end showed **inference times reduced by 6x-10x** on average compared the vanilla checkpoints using the *transformers* library. A **slight reduction on BLEU scores (~5%)** was also identified in comparison to the vanilla checkpoints with a few exceptions. This is likely due to several factors, one being the quantization applied. Further testing is needed from our end to better assess the reduction in translation quality. The command used to compile the vanilla checkpoint into a CTranslate2 model can be found below. Modifying this command can yield differing balances between inferencing performance and translation quality.
# CTranslate2 Installation
```bash
pip install hf-hub-ctranslate2>=1.0.0 ctranslate2>=3.13.0
```
### ct2-transformers-converter Command Used:
```bash
ct2-transformers-converter --model Helsinki-NLP/opus-mt-ca-es --output_dir ./ctranslate2/opus-mt-ca-es-ctranslate2 --force --copy_files README.md generation_config.json tokenizer_config.json vocab.json source.spm .gitattributes target.spm --quantization float16
```
# CTranslate2 Converted Checkpoint Information:
**Compatible With:**
- [ctranslate2](https://github.com/OpenNMT/CTranslate2)
- [hf-hub-ctranslate2](https://github.com/michaelfeil/hf-hub-ctranslate2)
**Compute Type:**
- `compute_type=int8_float16` for `device="cuda"`
- `compute_type=int8` for `device="cpu"`
# Sample Code - ctranslate2
#### Clone the repository to the working directory or wherever you wish to store the model artifacts. ####
```bash
git clone https://huggingface.co/gaudi/opus-mt-ca-es-ctranslate2
```
#### Take the python code below and update the 'model_dir' variable to the location of the cloned repository. ####
```python
from ctranslate2 import Translator
import transformers
model_dir = "./opus-mt-ca-es-ctranslate2" # Path to model directory.
translator = Translator(
model_path=model_dir,
device="cuda", # cpu, cuda, or auto.
inter_threads=1, # Maximum number of parallel translations.
intra_threads=4, # Number of OpenMP threads per translator.
compute_type="int8_float16", # int8 for cpu or int8_float16 for cuda.
)
tokenizer = transformers.AutoTokenizer.from_pretrained(model_dir)
source = tokenizer.convert_ids_to_tokens(tokenizer.encode("XXXXXX, XXX XX XXXXXX."))
results = translator.translate_batch([source])
target = results[0].hypotheses[0]
print(tokenizer.decode(tokenizer.convert_tokens_to_ids(target)))
```
# Sample Code - hf-hub-ctranslate2
**Derived From [michaelfeil](https://huggingface.co/michaelfeil):**
```python
from hf_hub_ctranslate2 import TranslatorCT2fromHfHub, GeneratorCT2fromHfHub
from transformers import AutoTokenizer
model_name = "gaudi/opus-mt-ca-es-ctranslate2"
model = TranslatorCT2fromHfHub(
model_name_or_path=model_name,
device="cuda",
compute_type="int8_float16",
tokenizer=AutoTokenizer.from_pretrained(model_name)
)
outputs = model.generate(
text=["XXX XX XXX XXXXXXX XXXX?", "XX XX XXXX XX XXX!"],
)
print(outputs)
```
# License and other remarks:
License conditions are intended to be idential to [original huggingface repository](https://huggingface.co/Helsinki-NLP/opus-mt-ca-es) by Helsinki-NLP.
| [
"TRANSLATION"
] | Non_BioNLP |
RichardErkhov/next-tat_-_tat-llm-7b-fft-8bits | RichardErkhov | null | [
"safetensors",
"llama",
"arxiv:2401.13223",
"8-bit",
"bitsandbytes",
"region:us"
] | 1,736,603,744,000 | 2025-01-11T13:58:50 | 9 | 0 | ---
{}
---
Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
tat-llm-7b-fft - bnb 8bits
- Model creator: https://huggingface.co/next-tat/
- Original model: https://huggingface.co/next-tat/tat-llm-7b-fft/
Original model description:
---
language:
- en
license: llama2
---
# TAT-LLM: A Specialized Language Model for Discrete Reasoning over Tabular and Textual Data
Paper: https://arxiv.org/abs/2401.13223
Code: https://github.com/fengbinzhu/TAT-LLM
## Introduction
We present TAT-LLM, a specialized language model crafted through the innovative Step-wise Pipeline approach, focusing on the nuanced realm of tabular and textual question answering (QA). This model is the fruit of rigorously fine-tuning the LLaMA 2 architecture with a novel dataset, autonomously generated from expertly annotated resources. TAT-LLM stands at the intersection of tabular comprehension and textual analysis, engineered to excel by embodying three fundamental phases: Extraction, Reasoning, and Execution. Our empirical findings illuminate TAT-LLM's remarkable capability to eclipse traditional benchmarks, surmounting even the most advanced models and colossal language models such as GPT-4 across a suite of demanding financial QA tasks like FinQA, TAT-QA, and TAT-DQA. This endeavor not only sets a new standard for task-specific language models but also paves the way for future explorations in optimizing smaller models for highly specialized functions.
| Model | Size | FINQA | TATQA | TATDQA |
| --- | --- | --- | --- | --- |
| GPT-3.5-Turbo | - | 58.00 | 59.47 | 52.74 |
| GPT-4 | - | 63.91 | 71.92 | 64.46 |
| [TAT-LLM-7B-LORA](https://huggingface.co/next-tat/tat-llm-7b-lora) | 7B | 65.13 | 76.49 | 71.38 |
| [TAT-LLM-7B-FFT](https://huggingface.co/next-tat/tat-llm-7b-fft) | 7B | 69.75 | 76.91 | 72.64 |
| [TAT-LLM-13B-LORA](https://huggingface.co/next-tat/tat-llm-13b-lora) | 13B | 71.93 | 77.51 | 72.22 |
| [TAT-LLM-13B-FFT](https://huggingface.co/next-tat/tat-llm-13b-fft) | 13B | 72.97 | 78.41 | 73.18 |
| [TAT-LLM-70B-LORA](https://huggingface.co/next-tat/tat-llm-70b-lora) | 70B | **76.81** | 81.42 | 76.55 |
| [TAT-LLM-70B-FFT](https://huggingface.co/next-tat/tat-llm-70b-fft) | 70B | 76.11 | **82.20** | **76.97** |
## Training
We train our TAT-LLM model in various sizes, including 7B, 13B, and 70B, using different methods such as parameter-efficient fine-tuning and full-parameter fine-tuning of LLaMA 2 on a combination of financial data from the FinQA, TAT-QA, and TAT-DQA training sets([🤗HuggingFace Repo](https://huggingface.co/datasets/next-tat/tat-llm-instructions)). To refine accuracy, we introduce an External Executor, enhancing the model by processing intermediate outputs to derive conclusive answers. Please refer to the [paper](https://arxiv.org/abs/2401.13223) for more details.
## Inference & Evaluation
Please refer to code [here](https://github.com/fengbinzhu/TAT-LLM)
## Citation
If you find this model helpful, please consider citing our paper:
```
@misc{zhu2024tatllm,
title={TAT-LLM: A Specialized Language Model for Discrete Reasoning over Tabular and Textual Data},
author={Fengbin Zhu and Ziyang Liu and Fuli Feng and Chao Wang and Moxin Li and Tat-Seng Chua},
year={2024},
eprint={2401.13223},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
| [
"QUESTION_ANSWERING"
] | Non_BioNLP |
Saxo/Linkbricks-Horizon-AI-Korean-Pro-22B | Saxo | text-generation | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"ko",
"en",
"jp",
"cn",
"dataset:Saxo/ko_cn_translation_tech_social_science_linkbricks_single_dataset",
"dataset:Saxo/ko_jp_translation_tech_social_science_linkbricks_single_dataset",
"dataset:Saxo/en_ko_translation_tech_science_linkbricks_single_dataset_with_prompt_text_huggingface",
"dataset:Saxo/en_ko_translation_social_science_linkbricks_single_dataset_with_prompt_text_huggingface",
"dataset:Saxo/ko_aspect_sentiment_sns_mall_sentiment_linkbricks_single_dataset_with_prompt_text_huggingface",
"dataset:Saxo/ko_summarization_linkbricks_single_dataset_with_prompt_text_huggingface",
"dataset:Saxo/OpenOrca_cleaned_kor_linkbricks_single_dataset_with_prompt_text_huggingface",
"dataset:Saxo/ko_government_qa_total_linkbricks_single_dataset_with_prompt_text_huggingface_sampled",
"dataset:Saxo/ko-news-corpus-1",
"dataset:Saxo/ko-news-corpus-2",
"dataset:Saxo/ko-news-corpus-3",
"dataset:Saxo/ko-news-corpus-4",
"dataset:Saxo/ko-news-corpus-5",
"dataset:Saxo/ko-news-corpus-6",
"dataset:Saxo/ko-news-corpus-7",
"dataset:Saxo/ko-news-corpus-8",
"dataset:Saxo/ko-news-corpus-9",
"dataset:maywell/ko_Ultrafeedback_binarized",
"dataset:youjunhyeok/ko-orca-pair-and-ultrafeedback-dpo",
"dataset:lilacai/glaive-function-calling-v2-sharegpt",
"dataset:kuotient/gsm8k-ko",
"base_model:mistralai/Mistral-Small-Instruct-2409",
"base_model:finetune:mistralai/Mistral-Small-Instruct-2409",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 1,731,040,276,000 | 2025-02-24T08:56:16 | 2,105 | 1 | ---
base_model: mistralai/Mistral-Small-Instruct-2409
datasets:
- Saxo/ko_cn_translation_tech_social_science_linkbricks_single_dataset
- Saxo/ko_jp_translation_tech_social_science_linkbricks_single_dataset
- Saxo/en_ko_translation_tech_science_linkbricks_single_dataset_with_prompt_text_huggingface
- Saxo/en_ko_translation_social_science_linkbricks_single_dataset_with_prompt_text_huggingface
- Saxo/ko_aspect_sentiment_sns_mall_sentiment_linkbricks_single_dataset_with_prompt_text_huggingface
- Saxo/ko_summarization_linkbricks_single_dataset_with_prompt_text_huggingface
- Saxo/OpenOrca_cleaned_kor_linkbricks_single_dataset_with_prompt_text_huggingface
- Saxo/ko_government_qa_total_linkbricks_single_dataset_with_prompt_text_huggingface_sampled
- Saxo/ko-news-corpus-1
- Saxo/ko-news-corpus-2
- Saxo/ko-news-corpus-3
- Saxo/ko-news-corpus-4
- Saxo/ko-news-corpus-5
- Saxo/ko-news-corpus-6
- Saxo/ko-news-corpus-7
- Saxo/ko-news-corpus-8
- Saxo/ko-news-corpus-9
- maywell/ko_Ultrafeedback_binarized
- youjunhyeok/ko-orca-pair-and-ultrafeedback-dpo
- lilacai/glaive-function-calling-v2-sharegpt
- kuotient/gsm8k-ko
language:
- ko
- en
- jp
- cn
library_name: transformers
license: apache-2.0
pipeline_tag: text-generation
---
# Model Card for Model ID
<div align="center">
<img src="http://www.linkbricks.com/wp-content/uploads/2024/11/fulllogo.png" />
</div>
AI 전문 기업인 Linkbricks Horizon-AI 의 데이터사이언티스트인 지윤성(Saxo) 대표가 <br>
Mistral-Small-Instruct-2409 베이스모델을 사용해서 H100-80G 8개를 통해 약 35%정도의 파라미터를 한국어 CPT(Continued-Pretraining)->SFT->DPO 한 한글 언어 모델<br>
9천만건의 한글 뉴스 코퍼스를 기준으로 다양한 테스크별 한국어-중국어-영어-일본어 교차 학습 데이터와 수학 및 논리판단 데이터를 통하여 한중일영 언어 교차 증강 처리와 복잡한 논리 문제 역시 대응 가능하도록 훈련한 모델이다.<br>
-토크나이저는 단어 확장 없이 베이스 모델 그대로 사용<br>
-고객 리뷰나 소셜 포스팅 고차원 분석 및 코딩과 작문, 수학, 논리판단 등이 강화된 모델<br>
-32k 시퀀스 길이<br>
-펑션콜 지원<br>
-Deepspeed Stage=3, rslora 및 BAdam Layer Mode 사용 <br>
<br><br>
Finetuned by CEO Yunsung Ji (Saxo), a data scientist at Linkbricks Horizon-AI, a company specializing in AI and big data analytics <br>
about 35% of total parameters Korean CPT(Continued-Pretraining)->SFT->DPO training model based on Mistral-Small-Instruct-2409 through 8 H100-80Gs as a Korean language model <br>
It is a model that has been trained to handle Korean-Chinese-English-Japanese cross-training data and 90M korean news corpus and logic judgment data for various tasks to enable cross-fertilization processing and complex Korean logic & math problems. <br>
-Tokenizer uses the base model without word expansion<br>
-Models enhanced with high-dimensional analysis of customer reviews and social posts, as well as coding, writing, math and decision making<br>
-32k sequence length<br>
-Function calling<br>
-Deepspeed Stage=3, use rslora and BAdam Layer Mode<br>
<br><br>
<a href="www.horizonai.ai">www.horizonai.ai</a>, <a href="www.linkbricks.com">www.linkbricks.com</a>, <a href="www.linkbricks.vc">www.linkbricks.vc</a>
| [
"TRANSLATION",
"SUMMARIZATION"
] | Non_BioNLP |
Lots-of-LoRAs/Mistral-7B-Instruct-v0.2-4b-r16-task1058 | Lots-of-LoRAs | null | [
"pytorch",
"safetensors",
"en",
"arxiv:1910.09700",
"arxiv:2407.00066",
"base_model:mistralai/Mistral-7B-Instruct-v0.2",
"base_model:finetune:mistralai/Mistral-7B-Instruct-v0.2",
"license:mit",
"region:us"
] | 1,735,928,051,000 | 2025-01-03T18:14:16 | 0 | 0 | ---
base_model: mistralai/Mistral-7B-Instruct-v0.2
language: en
library_name: pytorch
license: mit
---
# Model Card for Mistral-7B-Instruct-v0.2-4b-r16-task1058
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
LoRA trained on task1058_pib_translation_urdu_english
- **Developed by:** bruel
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** LoRA
- **Language(s) (NLP):** en
- **License:** mit
- **Finetuned from model [optional]:** mistralai/Mistral-7B-Instruct-v0.2
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** https://github.com/bruel-gabrielsson
- **Paper [optional]:** "Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead" (2024), Rickard Brüel Gabrielsson, Jiacheng Zhu, Onkar Bhardwaj, Leshem Choshen, Kristjan Greenewald, Mikhail Yurochkin and Justin Solomon
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
https://huggingface.co/datasets/Lots-of-LoRAs/task1058_pib_translation_urdu_english sourced from https://github.com/allenai/natural-instructions
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
@misc{brüelgabrielsson2024compressserveservingthousands,
title={Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead},
author={Rickard Brüel-Gabrielsson and Jiacheng Zhu and Onkar Bhardwaj and Leshem Choshen and Kristjan Greenewald and Mikhail Yurochkin and Justin Solomon},
year={2024},
eprint={2407.00066},
archivePrefix={arXiv},
primaryClass={cs.DC},
url={https://arxiv.org/abs/2407.00066},
}
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | [
"TRANSLATION"
] | Non_BioNLP |
AIDC-AI/Marco-LLM-GLO | AIDC-AI | null | [
"safetensors",
"qwen2",
"ar",
"bn",
"cs",
"de",
"es",
"en",
"el",
"fr",
"id",
"it",
"he",
"hu",
"ja",
"kk",
"ko",
"ro",
"ru",
"az",
"uk",
"ur",
"vi",
"zh",
"ms",
"nl",
"ne",
"th",
"tr",
"pt",
"pl",
"arxiv:2412.04003",
"base_model:Qwen/Qwen2-7B",
"base_model:finetune:Qwen/Qwen2-7B",
"license:apache-2.0",
"region:us"
] | 1,740,656,405,000 | 2025-02-28T10:07:33 | 1,809 | 2 | ---
base_model:
- Qwen/Qwen2-7B
language:
- ar
- bn
- cs
- de
- es
- en
- el
- fr
- id
- it
- he
- hu
- ja
- kk
- ko
- ro
- ru
- az
- uk
- ur
- vi
- zh
- ms
- nl
- ne
- th
- tr
- pt
- pl
license: apache-2.0
---
# Marco-LLM-GLO
## Introduction
Marco-LLM is a series of advanced multilingual language models designed to bridge the performance gap between high-resource languages and low-resource languages. This repository contains the Marco-LLM base language model with 7 billion parameters.
The model has undergone extensive multilingual continual pretraining on a diverse dataset containing over 5 trillion tokens, with a particular focus on enhancing performance in low-resource languages while maintaining strong capabilities in high-resource languages like English and Chinese.
Compared to state-of-the-art open-source language models, Marco-LLM demonstrates significant improvements in multilingual tasks, including machine translation, question answering, and reasoning across multiple languages.
For more details, please refer to our [Hugging Face page](https://huggingface.co/AIDC-AI/Marco-LLM-GLO).
## Model Details
Marco-LLM includes a 7B parameter model based on the Transformer architecture. The key features of Marco-LLM are:
- Multilingual Training: The model is trained on a large-scale multilingual dataset covering 29 languages, including both high-resource languages (e.g., English, Chinese) and low-resource languages (e.g., Kazakh, Nepali).
- Enhanced Tokenizer: An improved tokenizer is used to better handle multilingual data, ensuring higher efficiency and accuracy in tokenization.
- Post-Training: Marco-LLM supports various post-training methods, such as Supervised Fine-tuning (SFT) and Direct Preference Optimization (DPO), to further enhance performance for specific tasks and languages.
## Usage
It is not advised to use the base language models for direct text generation tasks. Instead, it is recommended to apply post-training methods such as Supervised Fine-tuning (SFT), Reinforcement Learning with Human Feedback (RLHF), or continued pretraining to adapt the models for specific use cases.
## Citation
If you find our work helpful, please give us a citation.
```
@article{unique_identifier,
title={Marco-LLM: Bridging Languages via Massive Multilingual Training for Cross-Lingual Enhancement},
journal={arXiv},
volume={},
number={2412.04003},
year={2024},
url={https://arxiv.org/abs/2412.04003}
}
``` | [
"QUESTION_ANSWERING",
"TRANSLATION"
] | Non_BioNLP |
Helsinki-NLP/opus-mt-nso-es | Helsinki-NLP | translation | [
"transformers",
"pytorch",
"tf",
"marian",
"text2text-generation",
"translation",
"nso",
"es",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 1,646,263,744,000 | 2023-08-16T12:02:04 | 31 | 0 | ---
license: apache-2.0
tags:
- translation
---
### opus-mt-nso-es
* source languages: nso
* target languages: es
* OPUS readme: [nso-es](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/nso-es/README.md)
* dataset: opus
* model: transformer-align
* pre-processing: normalization + SentencePiece
* download original weights: [opus-2020-01-16.zip](https://object.pouta.csc.fi/OPUS-MT-models/nso-es/opus-2020-01-16.zip)
* test set translations: [opus-2020-01-16.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/nso-es/opus-2020-01-16.test.txt)
* test set scores: [opus-2020-01-16.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/nso-es/opus-2020-01-16.eval.txt)
## Benchmarks
| testset | BLEU | chr-F |
|-----------------------|-------|-------|
| JW300.nso.es | 29.5 | 0.485 |
| [
"TRANSLATION"
] | Non_BioNLP |
openai/whisper-large-v3 | openai | automatic-speech-recognition | [
"transformers",
"pytorch",
"jax",
"safetensors",
"whisper",
"automatic-speech-recognition",
"audio",
"hf-asr-leaderboard",
"en",
"zh",
"de",
"es",
"ru",
"ko",
"fr",
"ja",
"pt",
"tr",
"pl",
"ca",
"nl",
"ar",
"sv",
"it",
"id",
"hi",
"fi",
"vi",
"he",
"uk",
"el",
"ms",
"cs",
"ro",
"da",
"hu",
"ta",
"no",
"th",
"ur",
"hr",
"bg",
"lt",
"la",
"mi",
"ml",
"cy",
"sk",
"te",
"fa",
"lv",
"bn",
"sr",
"az",
"sl",
"kn",
"et",
"mk",
"br",
"eu",
"is",
"hy",
"ne",
"mn",
"bs",
"kk",
"sq",
"sw",
"gl",
"mr",
"pa",
"si",
"km",
"sn",
"yo",
"so",
"af",
"oc",
"ka",
"be",
"tg",
"sd",
"gu",
"am",
"yi",
"lo",
"uz",
"fo",
"ht",
"ps",
"tk",
"nn",
"mt",
"sa",
"lb",
"my",
"bo",
"tl",
"mg",
"as",
"tt",
"haw",
"ln",
"ha",
"ba",
"jw",
"su",
"arxiv:2212.04356",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | 1,699,382,474,000 | 2024-08-12T10:20:10 | 4,407,347 | 4,174 | ---
language:
- en
- zh
- de
- es
- ru
- ko
- fr
- ja
- pt
- tr
- pl
- ca
- nl
- ar
- sv
- it
- id
- hi
- fi
- vi
- he
- uk
- el
- ms
- cs
- ro
- da
- hu
- ta
- false
- th
- ur
- hr
- bg
- lt
- la
- mi
- ml
- cy
- sk
- te
- fa
- lv
- bn
- sr
- az
- sl
- kn
- et
- mk
- br
- eu
- is
- hy
- ne
- mn
- bs
- kk
- sq
- sw
- gl
- mr
- pa
- si
- km
- sn
- yo
- so
- af
- oc
- ka
- be
- tg
- sd
- gu
- am
- yi
- lo
- uz
- fo
- ht
- ps
- tk
- nn
- mt
- sa
- lb
- my
- bo
- tl
- mg
- as
- tt
- haw
- ln
- ha
- ba
- jw
- su
license: apache-2.0
pipeline_tag: automatic-speech-recognition
tags:
- audio
- automatic-speech-recognition
- hf-asr-leaderboard
widget:
- example_title: Librispeech sample 1
src: https://cdn-media.huggingface.co/speech_samples/sample1.flac
- example_title: Librispeech sample 2
src: https://cdn-media.huggingface.co/speech_samples/sample2.flac
---
# Whisper
Whisper is a state-of-the-art model for automatic speech recognition (ASR) and speech translation, proposed in the paper
[Robust Speech Recognition via Large-Scale Weak Supervision](https://huggingface.co/papers/2212.04356) by Alec Radford
et al. from OpenAI. Trained on >5M hours of labeled data, Whisper demonstrates a strong ability to generalise to many
datasets and domains in a zero-shot setting.
Whisper large-v3 has the same architecture as the previous [large](https://huggingface.co/openai/whisper-large) and [large-v2](https://huggingface.co/openai/whisper-large-v2)
models, except for the following minor differences:
1. The spectrogram input uses 128 Mel frequency bins instead of 80
2. A new language token for Cantonese
The Whisper large-v3 model was trained on 1 million hours of weakly labeled audio and 4 million hours of pseudo-labeled
audio collected using Whisper [large-v2](https://huggingface.co/openai/whisper-large-v2) . The model was trained for 2.0 epochs over this mixture dataset.
The large-v3 model shows improved performance over a wide variety of languages, showing 10% to 20% reduction of errors
compared to Whisper [large-v2](https://huggingface.co/openai/whisper-large-v2) . For more details on the different checkpoints available, refer to the section [Model details](#model-details).
**Disclaimer**: Content for this model card has partly been written by the 🤗 Hugging Face team, and partly copied and
pasted from the original model card.
## Usage
Whisper large-v3 is supported in Hugging Face 🤗 Transformers. To run the model, first install the Transformers
library. For this example, we'll also install 🤗 Datasets to load toy audio dataset from the Hugging Face Hub, and
🤗 Accelerate to reduce the model loading time:
```bash
pip install --upgrade pip
pip install --upgrade transformers datasets[audio] accelerate
```
The model can be used with the [`pipeline`](https://huggingface.co/docs/transformers/main_classes/pipelines#transformers.AutomaticSpeechRecognitionPipeline)
class to transcribe audios of arbitrary length:
```python
import torch
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
from datasets import load_dataset
device = "cuda:0" if torch.cuda.is_available() else "cpu"
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
model_id = "openai/whisper-large-v3"
model = AutoModelForSpeechSeq2Seq.from_pretrained(
model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True
)
model.to(device)
processor = AutoProcessor.from_pretrained(model_id)
pipe = pipeline(
"automatic-speech-recognition",
model=model,
tokenizer=processor.tokenizer,
feature_extractor=processor.feature_extractor,
torch_dtype=torch_dtype,
device=device,
)
dataset = load_dataset("distil-whisper/librispeech_long", "clean", split="validation")
sample = dataset[0]["audio"]
result = pipe(sample)
print(result["text"])
```
To transcribe a local audio file, simply pass the path to your audio file when you call the pipeline:
```python
result = pipe("audio.mp3")
```
Multiple audio files can be transcribed in parallel by specifying them as a list and setting the `batch_size` parameter:
```python
result = pipe(["audio_1.mp3", "audio_2.mp3"], batch_size=2)
```
Transformers is compatible with all Whisper decoding strategies, such as temperature fallback and condition on previous
tokens. The following example demonstrates how to enable these heuristics:
```python
generate_kwargs = {
"max_new_tokens": 448,
"num_beams": 1,
"condition_on_prev_tokens": False,
"compression_ratio_threshold": 1.35, # zlib compression ratio threshold (in token space)
"temperature": (0.0, 0.2, 0.4, 0.6, 0.8, 1.0),
"logprob_threshold": -1.0,
"no_speech_threshold": 0.6,
"return_timestamps": True,
}
result = pipe(sample, generate_kwargs=generate_kwargs)
```
Whisper predicts the language of the source audio automatically. If the source audio language is known *a-priori*, it
can be passed as an argument to the pipeline:
```python
result = pipe(sample, generate_kwargs={"language": "english"})
```
By default, Whisper performs the task of *speech transcription*, where the source audio language is the same as the target
text language. To perform *speech translation*, where the target text is in English, set the task to `"translate"`:
```python
result = pipe(sample, generate_kwargs={"task": "translate"})
```
Finally, the model can be made to predict timestamps. For sentence-level timestamps, pass the `return_timestamps` argument:
```python
result = pipe(sample, return_timestamps=True)
print(result["chunks"])
```
And for word-level timestamps:
```python
result = pipe(sample, return_timestamps="word")
print(result["chunks"])
```
The above arguments can be used in isolation or in combination. For example, to perform the task of speech transcription
where the source audio is in French, and we want to return sentence-level timestamps, the following can be used:
```python
result = pipe(sample, return_timestamps=True, generate_kwargs={"language": "french", "task": "translate"})
print(result["chunks"])
```
<details>
<summary> For more control over the generation parameters, use the model + processor API directly: </summary>
```python
import torch
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor
from datasets import Audio, load_dataset
device = "cuda:0" if torch.cuda.is_available() else "cpu"
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
model_id = "openai/whisper-large-v3"
model = AutoModelForSpeechSeq2Seq.from_pretrained(
model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True
)
model.to(device)
processor = AutoProcessor.from_pretrained(model_id)
dataset = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
dataset = dataset.cast_column("audio", Audio(processor.feature_extractor.sampling_rate))
sample = dataset[0]["audio"]
inputs = processor(
sample["array"],
sampling_rate=sample["sampling_rate"],
return_tensors="pt",
truncation=False,
padding="longest",
return_attention_mask=True,
)
inputs = inputs.to(device, dtype=torch_dtype)
gen_kwargs = {
"max_new_tokens": 448,
"num_beams": 1,
"condition_on_prev_tokens": False,
"compression_ratio_threshold": 1.35, # zlib compression ratio threshold (in token space)
"temperature": (0.0, 0.2, 0.4, 0.6, 0.8, 1.0),
"logprob_threshold": -1.0,
"no_speech_threshold": 0.6,
"return_timestamps": True,
}
pred_ids = model.generate(**inputs, **gen_kwargs)
pred_text = processor.batch_decode(pred_ids, skip_special_tokens=True, decode_with_timestamps=False)
print(pred_text)
```
</details>
## Additional Speed & Memory Improvements
You can apply additional speed and memory improvements to Whisper to further reduce the inference speed and VRAM
requirements.
### Chunked Long-Form
Whisper has a receptive field of 30-seconds. To transcribe audios longer than this, one of two long-form algorithms are
required:
1. **Sequential:** uses a "sliding window" for buffered inference, transcribing 30-second slices one after the other
2. **Chunked:** splits long audio files into shorter ones (with a small overlap between segments), transcribes each segment independently, and stitches the resulting transcriptions at the boundaries
The sequential long-form algorithm should be used in either of the following scenarios:
1. Transcription accuracy is the most important factor, and speed is less of a consideration
2. You are transcribing **batches** of long audio files, in which case the latency of sequential is comparable to chunked, while being up to 0.5% WER more accurate
Conversely, the chunked algorithm should be used when:
1. Transcription speed is the most important factor
2. You are transcribing a **single** long audio file
By default, Transformers uses the sequential algorithm. To enable the chunked algorithm, pass the `chunk_length_s`
parameter to the `pipeline`. For large-v3, a chunk length of 30-seconds is optimal. To activate batching over long
audio files, pass the argument `batch_size`:
```python
import torch
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
from datasets import load_dataset
device = "cuda:0" if torch.cuda.is_available() else "cpu"
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
model_id = "openai/whisper-large-v3"
model = AutoModelForSpeechSeq2Seq.from_pretrained(
model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True
)
model.to(device)
processor = AutoProcessor.from_pretrained(model_id)
pipe = pipeline(
"automatic-speech-recognition",
model=model,
tokenizer=processor.tokenizer,
feature_extractor=processor.feature_extractor,
chunk_length_s=30,
batch_size=16, # batch size for inference - set based on your device
torch_dtype=torch_dtype,
device=device,
)
dataset = load_dataset("distil-whisper/librispeech_long", "clean", split="validation")
sample = dataset[0]["audio"]
result = pipe(sample)
print(result["text"])
```
#### Torch compile
The Whisper forward pass is compatible with [`torch.compile`](https://pytorch.org/docs/stable/generated/torch.compile.html)
for 4.5x speed-ups.
**Note:** `torch.compile` is currently not compatible with the Chunked long-form algorithm or Flash Attention 2 ⚠️
```python
import torch
from torch.nn.attention import SDPBackend, sdpa_kernel
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
from datasets import load_dataset
from tqdm import tqdm
torch.set_float32_matmul_precision("high")
device = "cuda:0" if torch.cuda.is_available() else "cpu"
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
model_id = "openai/whisper-large-v3"
model = AutoModelForSpeechSeq2Seq.from_pretrained(
model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True
).to(device)
# Enable static cache and compile the forward pass
model.generation_config.cache_implementation = "static"
model.generation_config.max_new_tokens = 256
model.forward = torch.compile(model.forward, mode="reduce-overhead", fullgraph=True)
processor = AutoProcessor.from_pretrained(model_id)
pipe = pipeline(
"automatic-speech-recognition",
model=model,
tokenizer=processor.tokenizer,
feature_extractor=processor.feature_extractor,
torch_dtype=torch_dtype,
device=device,
)
dataset = load_dataset("distil-whisper/librispeech_long", "clean", split="validation")
sample = dataset[0]["audio"]
# 2 warmup steps
for _ in tqdm(range(2), desc="Warm-up step"):
with sdpa_kernel(SDPBackend.MATH):
result = pipe(sample.copy(), generate_kwargs={"min_new_tokens": 256, "max_new_tokens": 256})
# fast run
with sdpa_kernel(SDPBackend.MATH):
result = pipe(sample.copy())
print(result["text"])
```
#### Flash Attention 2
We recommend using [Flash-Attention 2](https://huggingface.co/docs/transformers/main/en/perf_infer_gpu_one#flashattention-2) if your GPU supports it and you are not using [torch.compile](#torch-compile).
To do so, first install [Flash Attention](https://github.com/Dao-AILab/flash-attention):
```
pip install flash-attn --no-build-isolation
```
Then pass `attn_implementation="flash_attention_2"` to `from_pretrained`:
```python
model = AutoModelForSpeechSeq2Seq.from_pretrained(model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, attn_implementation="flash_attention_2")
```
#### Torch Scale-Product-Attention (SDPA)
If your GPU does not support Flash Attention, we recommend making use of PyTorch [scaled dot-product attention (SDPA)](https://pytorch.org/docs/stable/generated/torch.nn.functional.scaled_dot_product_attention.html).
This attention implementation is activated **by default** for PyTorch versions 2.1.1 or greater. To check
whether you have a compatible PyTorch version, run the following Python code snippet:
```python
from transformers.utils import is_torch_sdpa_available
print(is_torch_sdpa_available())
```
If the above returns `True`, you have a valid version of PyTorch installed and SDPA is activated by default. If it
returns `False`, you need to upgrade your PyTorch version according to the [official instructions](https://pytorch.org/get-started/locally/)
Once a valid PyTorch version is installed, SDPA is activated by default. It can also be set explicitly by specifying
`attn_implementation="sdpa"` as follows:
```python
model = AutoModelForSpeechSeq2Seq.from_pretrained(model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, attn_implementation="sdpa")
```
For more information about how to use the SDPA refer to the [Transformers SDPA documentation](https://huggingface.co/docs/transformers/en/perf_infer_gpu_one#pytorch-scaled-dot-product-attention).
## Model details
Whisper is a Transformer based encoder-decoder model, also referred to as a _sequence-to-sequence_ model. There are two
flavours of Whisper model: English-only and multilingual. The English-only models were trained on the task of English
speech recognition. The multilingual models were trained simultaneously on multilingual speech recognition and speech
translation. For speech recognition, the model predicts transcriptions in the *same* language as the audio. For speech
translation, the model predicts transcriptions to a *different* language to the audio.
Whisper checkpoints come in five configurations of varying model sizes. The smallest four are available as English-only
and multilingual. The largest checkpoints are multilingual only. All ten of the pre-trained checkpoints
are available on the [Hugging Face Hub](https://huggingface.co/models?search=openai/whisper). The
checkpoints are summarised in the following table with links to the models on the Hub:
| Size | Parameters | English-only | Multilingual |
|----------|------------|------------------------------------------------------|-----------------------------------------------------|
| tiny | 39 M | [✓](https://huggingface.co/openai/whisper-tiny.en) | [✓](https://huggingface.co/openai/whisper-tiny) |
| base | 74 M | [✓](https://huggingface.co/openai/whisper-base.en) | [✓](https://huggingface.co/openai/whisper-base) |
| small | 244 M | [✓](https://huggingface.co/openai/whisper-small.en) | [✓](https://huggingface.co/openai/whisper-small) |
| medium | 769 M | [✓](https://huggingface.co/openai/whisper-medium.en) | [✓](https://huggingface.co/openai/whisper-medium) |
| large | 1550 M | x | [✓](https://huggingface.co/openai/whisper-large) |
| large-v2 | 1550 M | x | [✓](https://huggingface.co/openai/whisper-large-v2) |
| large-v3 | 1550 M | x | [✓](https://huggingface.co/openai/whisper-large-v3) |
## Fine-Tuning
The pre-trained Whisper model demonstrates a strong ability to generalise to different datasets and domains. However,
its predictive capabilities can be improved further for certain languages and tasks through *fine-tuning*. The blog
post [Fine-Tune Whisper with 🤗 Transformers](https://huggingface.co/blog/fine-tune-whisper) provides a step-by-step
guide to fine-tuning the Whisper model with as little as 5 hours of labelled data.
### Evaluated Use
The primary intended users of these models are AI researchers studying robustness, generalization, capabilities, biases, and constraints of the current model. However, Whisper is also potentially quite useful as an ASR solution for developers, especially for English speech recognition. We recognize that once models are released, it is impossible to restrict access to only “intended” uses or to draw reasonable guidelines around what is or is not research.
The models are primarily trained and evaluated on ASR and speech translation to English tasks. They show strong ASR results in ~10 languages. They may exhibit additional capabilities, particularly if fine-tuned on certain tasks like voice activity detection, speaker classification, or speaker diarization but have not been robustly evaluated in these areas. We strongly recommend that users perform robust evaluations of the models in a particular context and domain before deploying them.
In particular, we caution against using Whisper models to transcribe recordings of individuals taken without their consent or purporting to use these models for any kind of subjective classification. We recommend against use in high-risk domains like decision-making contexts, where flaws in accuracy can lead to pronounced flaws in outcomes. The models are intended to transcribe and translate speech, use of the model for classification is not only not evaluated but also not appropriate, particularly to infer human attributes.
## Training Data
The large-v3 checkpoint is trained on 1 million hours of weakly labeled audio and 4 million hours of pseudo-labeled audio collected using Whisper large-v2.
As discussed in [the accompanying paper](https://cdn.openai.com/papers/whisper.pdf), we see that performance on transcription in a given language is directly correlated with the amount of training data we employ in that language.
## Performance and Limitations
Our studies show that, over many existing ASR systems, the models exhibit improved robustness to accents, background noise, technical language, as well as zero shot translation from multiple languages into English; and that accuracy on speech recognition and translation is near the state-of-the-art level.
However, because the models are trained in a weakly supervised manner using large-scale noisy data, the predictions may include texts that are not actually spoken in the audio input (i.e. hallucination). We hypothesize that this happens because, given their general knowledge of language, the models combine trying to predict the next word in audio with trying to transcribe the audio itself.
Our models perform unevenly across languages, and we observe lower accuracy on low-resource and/or low-discoverability languages or languages where we have less training data. The models also exhibit disparate performance on different accents and dialects of particular languages, which may include higher word error rate across speakers of different genders, races, ages, or other demographic criteria. Our full evaluation results are presented in [the paper accompanying this release](https://cdn.openai.com/papers/whisper.pdf).
In addition, the sequence-to-sequence architecture of the model makes it prone to generating repetitive texts, which can be mitigated to some degree by beam search and temperature scheduling but not perfectly. Further analysis on these limitations are provided in [the paper](https://cdn.openai.com/papers/whisper.pdf). It is likely that this behavior and hallucinations may be worse on lower-resource and/or lower-discoverability languages.
## Broader Implications
We anticipate that Whisper models’ transcription capabilities may be used for improving accessibility tools. While Whisper models cannot be used for real-time transcription out of the box – their speed and size suggest that others may be able to build applications on top of them that allow for near-real-time speech recognition and translation. The real value of beneficial applications built on top of Whisper models suggests that the disparate performance of these models may have real economic implications.
There are also potential dual use concerns that come with releasing Whisper. While we hope the technology will be used primarily for beneficial purposes, making ASR technology more accessible could enable more actors to build capable surveillance technologies or scale up existing surveillance efforts, as the speed and accuracy allow for affordable automatic transcription and translation of large volumes of audio communication. Moreover, these models may have some capabilities to recognize specific individuals out of the box, which in turn presents safety concerns related both to dual use and disparate performance. In practice, we expect that the cost of transcription is not the limiting factor of scaling up surveillance projects.
### BibTeX entry and citation info
```bibtex
@misc{radford2022whisper,
doi = {10.48550/ARXIV.2212.04356},
url = {https://arxiv.org/abs/2212.04356},
author = {Radford, Alec and Kim, Jong Wook and Xu, Tao and Brockman, Greg and McLeavey, Christine and Sutskever, Ilya},
title = {Robust Speech Recognition via Large-Scale Weak Supervision},
publisher = {arXiv},
year = {2022},
copyright = {arXiv.org perpetual, non-exclusive license}
}
``` | [
"TRANSLATION"
] | Non_BioNLP |
triplee/torchtune_1B_lr1.5e-5_0epoch_full_finetuned_llama3.2_millfield_241227_meta_before_user_15epoch | triplee | text-generation | [
"transformers",
"safetensors",
"llama",
"text-generation",
"facebook",
"meta",
"pytorch",
"llama-3",
"conversational",
"en",
"de",
"fr",
"it",
"pt",
"hi",
"es",
"th",
"arxiv:2204.05149",
"arxiv:2405.16406",
"license:llama3.2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 1,735,232,876,000 | 2024-12-26T17:08:49 | 13 | 0 | ---
language:
- en
- de
- fr
- it
- pt
- hi
- es
- th
library_name: transformers
license: llama3.2
pipeline_tag: text-generation
tags:
- facebook
- meta
- pytorch
- llama
- llama-3
extra_gated_prompt: "### LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\n\nLlama 3.2 Version\
\ Release Date: September 25, 2024\n\n“Agreement” means the terms and conditions\
\ for use, reproduction, distribution and modification of the Llama Materials set\
\ forth herein.\n\n“Documentation” means the specifications, manuals and documentation\
\ accompanying Llama 3.2 distributed by Meta at https://llama.meta.com/doc/overview.\n\
\n“Licensee” or “you” means you, or your employer or any other person or entity\
\ (if you are entering into this Agreement on such person or entity’s behalf),\
\ of the age required under applicable laws, rules or regulations to provide legal\
\ consent and that has legal authority to bind your employer or such other person\
\ or entity if you are entering in this Agreement on their behalf.\n\n“Llama 3.2”\
\ means the foundational large language models and software and algorithms, including\
\ machine-learning model code, trained model weights, inference-enabling code, training-enabling\
\ code, fine-tuning enabling code and other elements of the foregoing distributed\
\ by Meta at https://www.llama.com/llama-downloads.\n\n“Llama Materials” means,\
\ collectively, Meta’s proprietary Llama 3.2 and Documentation (and any portion\
\ thereof) made available under this Agreement.\n\n“Meta” or “we” means Meta Platforms\
\ Ireland Limited (if you are located in or, if you are an entity, your principal\
\ place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if\
\ you are located outside of the EEA or Switzerland). \n\nBy clicking “I Accept”\
\ below or by using or distributing any portion or element of the Llama Materials,\
\ you agree to be bound by this Agreement.\n\n1. License Rights and Redistribution.\n\
a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable\
\ and royalty-free limited license under Meta’s intellectual property or other rights\
\ owned by Meta embodied in the Llama Materials to use, reproduce, distribute,\
\ copy, create derivative works of, and make modifications to the Llama Materials.\
\ \nb. Redistribution and Use. \ni. If you distribute or make available the Llama\
\ Materials (or any derivative works thereof), or a product or service (including\
\ another AI model) that contains any of them, you shall (A) provide a copy of this\
\ Agreement with any such Llama Materials; and (B) prominently display “Built with\
\ Llama” on a related website, user interface, blogpost, about page, or product\
\ documentation. If you use the Llama Materials or any outputs or results of the\
\ Llama Materials to create, train, fine tune, or otherwise improve an AI model,\
\ which is distributed or made available, you shall also include “Llama” at the\
\ beginning of any such AI model name.\nii. If you receive Llama Materials, or any\
\ derivative works thereof, from a Licensee as part of an integrated end user product,\
\ then Section 2 of this Agreement will not apply to you. \niii. You must retain\
\ in all copies of the Llama Materials that you distribute the following attribution\
\ notice within a “Notice” text file distributed as a part of such copies: “Llama\
\ 3.2 is licensed under the Llama 3.2 Community License, Copyright © Meta Platforms,\
\ Inc. All Rights Reserved.”\niv. Your use of the Llama Materials must comply with\
\ applicable laws and regulations (including trade compliance laws and regulations)\
\ and adhere to the Acceptable Use Policy for the Llama Materials (available at\
\ https://www.llama.com/llama3_2/use-policy), which is hereby incorporated by reference\
\ into this Agreement.\n \n2. Additional Commercial Terms. If, on the Llama 3.2\
\ version release date, the monthly active users of the products or services made\
\ available by or for Licensee, or Licensee’s affiliates, is greater than 700 million\
\ monthly active users in the preceding calendar month, you must request a license\
\ from Meta, which Meta may grant to you in its sole discretion, and you are not\
\ authorized to exercise any of the rights under this Agreement unless or until\
\ Meta otherwise expressly grants you such rights.\n3. Disclaimer of Warranty. UNLESS\
\ REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM\
\ ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS\
\ ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION,\
\ ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR\
\ PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING\
\ OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR\
\ USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\n4. Limitation of Liability.\
\ IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY,\
\ WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING\
\ OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL,\
\ INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE\
\ BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n5. Intellectual Property.\n\
a. No trademark licenses are granted under this Agreement, and in connection with\
\ the Llama Materials, neither Meta nor Licensee may use any name or mark owned\
\ by or associated with the other or any of its affiliates, except as required\
\ for reasonable and customary use in describing and redistributing the Llama Materials\
\ or as set forth in this Section 5(a). Meta hereby grants you a license to use\
\ “Llama” (the “Mark”) solely as required to comply with the last sentence of Section\
\ 1.b.i. You will comply with Meta’s brand guidelines (currently accessible at\
\ https://about.meta.com/brand/resources/meta/company-brand/). All goodwill arising\
\ out of your use of the Mark will inure to the benefit of Meta.\nb. Subject to\
\ Meta’s ownership of Llama Materials and derivatives made by or for Meta, with\
\ respect to any derivative works and modifications of the Llama Materials that\
\ are made by you, as between you and Meta, you are and will be the owner of such\
\ derivative works and modifications.\nc. If you institute litigation or other proceedings\
\ against Meta or any entity (including a cross-claim or counterclaim in a lawsuit)\
\ alleging that the Llama Materials or Llama 3.2 outputs or results, or any portion\
\ of any of the foregoing, constitutes infringement of intellectual property or\
\ other rights owned or licensable by you, then any licenses granted to you under\
\ this Agreement shall terminate as of the date such litigation or claim is filed\
\ or instituted. You will indemnify and hold harmless Meta from and against any\
\ claim by any third party arising out of or related to your use or distribution\
\ of the Llama Materials.\n6. Term and Termination. The term of this Agreement will\
\ commence upon your acceptance of this Agreement or access to the Llama Materials\
\ and will continue in full force and effect until terminated in accordance with\
\ the terms and conditions herein. Meta may terminate this Agreement if you are\
\ in breach of any term or condition of this Agreement. Upon termination of this\
\ Agreement, you shall delete and cease use of the Llama Materials. Sections 3,\
\ 4 and 7 shall survive the termination of this Agreement. \n7. Governing Law and\
\ Jurisdiction. This Agreement will be governed and construed under the laws of\
\ the State of California without regard to choice of law principles, and the UN\
\ Convention on Contracts for the International Sale of Goods does not apply to\
\ this Agreement. The courts of California shall have exclusive jurisdiction of\
\ any dispute arising out of this Agreement. \n### Llama 3.2 Acceptable Use Policy\n\
Meta is committed to promoting safe and fair use of its tools and features, including\
\ Llama 3.2. If you access or use Llama 3.2, you agree to this Acceptable Use Policy\
\ (“**Policy**”). The most recent copy of this policy can be found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\n\
#### Prohibited Uses\nWe want everyone to use Llama 3.2 safely and responsibly.\
\ You agree you will not use, or allow others to use, Llama 3.2 to:\n1. Violate\
\ the law or others’ rights, including to:\n 1. Engage in, promote, generate,\
\ contribute to, encourage, plan, incite, or further illegal or unlawful activity\
\ or content, such as:\n 1. Violence or terrorism\n 2. Exploitation\
\ or harm to children, including the solicitation, creation, acquisition, or dissemination\
\ of child exploitative content or failure to report Child Sexual Abuse Material\n\
\ 3. Human trafficking, exploitation, and sexual violence\n 4. The\
\ illegal distribution of information or materials to minors, including obscene\
\ materials, or failure to employ legally required age-gating in connection with\
\ such information or materials.\n 5. Sexual solicitation\n 6. Any\
\ other criminal activity\n 1. Engage in, promote, incite, or facilitate the\
\ harassment, abuse, threatening, or bullying of individuals or groups of individuals\n\
\ 2. Engage in, promote, incite, or facilitate discrimination or other unlawful\
\ or harmful conduct in the provision of employment, employment benefits, credit,\
\ housing, other economic benefits, or other essential goods and services\n 3.\
\ Engage in the unauthorized or unlicensed practice of any profession including,\
\ but not limited to, financial, legal, medical/health, or related professional\
\ practices\n 4. Collect, process, disclose, generate, or infer private or sensitive\
\ information about individuals, including information about individuals’ identity,\
\ health, or demographic information, unless you have obtained the right to do so\
\ in accordance with applicable law\n 5. Engage in or facilitate any action or\
\ generate any content that infringes, misappropriates, or otherwise violates any\
\ third-party rights, including the outputs or results of any products or services\
\ using the Llama Materials\n 6. Create, generate, or facilitate the creation\
\ of malicious code, malware, computer viruses or do anything else that could disable,\
\ overburden, interfere with or impair the proper working, integrity, operation\
\ or appearance of a website or computer system\n 7. Engage in any action, or\
\ facilitate any action, to intentionally circumvent or remove usage restrictions\
\ or other safety measures, or to enable functionality disabled by Meta \n2. Engage\
\ in, promote, incite, facilitate, or assist in the planning or development of activities\
\ that present a risk of death or bodily harm to individuals, including use of Llama\
\ 3.2 related to the following:\n 8. Military, warfare, nuclear industries or\
\ applications, espionage, use for materials or activities that are subject to the\
\ International Traffic Arms Regulations (ITAR) maintained by the United States\
\ Department of State or to the U.S. Biological Weapons Anti-Terrorism Act of 1989\
\ or the Chemical Weapons Convention Implementation Act of 1997\n 9. Guns and\
\ illegal weapons (including weapon development)\n 10. Illegal drugs and regulated/controlled\
\ substances\n 11. Operation of critical infrastructure, transportation technologies,\
\ or heavy machinery\n 12. Self-harm or harm to others, including suicide, cutting,\
\ and eating disorders\n 13. Any content intended to incite or promote violence,\
\ abuse, or any infliction of bodily harm to an individual\n3. Intentionally deceive\
\ or mislead others, including use of Llama 3.2 related to the following:\n 14.\
\ Generating, promoting, or furthering fraud or the creation or promotion of disinformation\n\
\ 15. Generating, promoting, or furthering defamatory content, including the\
\ creation of defamatory statements, images, or other content\n 16. Generating,\
\ promoting, or further distributing spam\n 17. Impersonating another individual\
\ without consent, authorization, or legal right\n 18. Representing that the\
\ use of Llama 3.2 or outputs are human-generated\n 19. Generating or facilitating\
\ false online engagement, including fake reviews and other means of fake online\
\ engagement \n4. Fail to appropriately disclose to end users any known dangers\
\ of your AI system 5. Interact with third party tools, models, or software designed\
\ to generate unlawful content or engage in unlawful or harmful conduct and/or represent\
\ that the outputs of such tools, models, or software are associated with Meta or\
\ Llama 3.2\n\nWith respect to any multimodal models included in Llama 3.2, the\
\ rights granted under Section 1(a) of the Llama 3.2 Community License Agreement\
\ are not being granted to you if you are an individual domiciled in, or a company\
\ with a principal place of business in, the European Union. This restriction does\
\ not apply to end users of a product or service that incorporates any such multimodal\
\ models.\n\nPlease report any violation of this Policy, software “bug,” or other\
\ problems that could lead to a violation of this Policy through one of the following\
\ means:\n\n* Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues&h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\n\
* Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\n\
* Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\n\
* Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama\
\ 3.2: [email protected]"
extra_gated_fields:
First Name: text
Last Name: text
Date of birth: date_picker
Country: country
Affiliation: text
Job title:
type: select
options:
- Student
- Research Graduate
- AI researcher
- AI developer/engineer
- Reporter
- Other
geo: ip_location
? By clicking Submit below I accept the terms of the license and acknowledge that
the information I provide will be collected stored processed and shared in accordance
with the Meta Privacy Policy
: checkbox
extra_gated_description: The information you provide will be collected, stored, processed
and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).
extra_gated_button_content: Submit
---
## Model Information
The Llama 3.2 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction-tuned generative models in 1B and 3B sizes (text in/text out). The Llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks. They outperform many of the available open source and closed chat models on common industry benchmarks.
**Model Developer:** Meta
**Model Architecture:** Llama 3.2 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.
| | Training Data | Params | Input modalities | Output modalities | Context Length | GQA | Shared Embeddings | Token count | Knowledge cutoff |
| :---- | :---- | :---- | :---- | :---- | :---- | :---- | :---- | :---- | :---- |
| Llama 3.2 (text only) | A new mix of publicly available online data. | 1B (1.23B) | Multilingual Text | Multilingual Text and code | 128k | Yes | Yes | Up to 9T tokens | December 2023 |
| | | 3B (3.21B) | Multilingual Text | Multilingual Text and code | | | | | |
| Llama 3.2 Quantized (text only) | A new mix of publicly available online data. | 1B (1.23B) | Multilingual Text | Multilingual Text and code | 8k | Yes | Yes | Up to 9T tokens | December 2023 |
| | | 3B (3.21B) | Multilingual Text | Multilingual Text and code | | | | | |
**Supported Languages:** English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai are officially supported. Llama 3.2 has been trained on a broader collection of languages than these 8 supported languages. Developers may fine-tune Llama 3.2 models for languages beyond these supported languages, provided they comply with the Llama 3.2 Community License and the Acceptable Use Policy. Developers are always expected to ensure that their deployments, including those that involve additional languages, are completed safely and responsibly.
**Llama 3.2 Model Family:** Token counts refer to pretraining data only. All model versions use Grouped-Query Attention (GQA) for improved inference scalability.
**Model Release Date:** Sept 25, 2024
**Status:** This is a static model trained on an offline dataset. Future versions may be released that improve model capabilities and safety.
**License:** Use of Llama 3.2 is governed by the [Llama 3.2 Community License](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/LICENSE) (a custom, commercial license agreement).
**Feedback:** Instructions on how to provide feedback or comments on the model can be found in the Llama Models [README](https://github.com/meta-llama/llama-models/blob/main/README.md). For more technical information about generation parameters and recipes for how to use Llama 3.2 in applications, please go [here](https://github.com/meta-llama/llama-recipes).
## Intended Use
**Intended Use Cases:** Llama 3.2 is intended for commercial and research use in multiple languages. Instruction tuned text only models are intended for assistant-like chat and agentic applications like knowledge retrieval and summarization, mobile AI powered writing assistants and query and prompt rewriting. Pretrained models can be adapted for a variety of additional natural language generation tasks. Similarly, quantized models can be adapted for a variety of on-device use-cases with limited compute resources.
**Out of Scope:** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3.2 Community License. Use in languages beyond those explicitly referenced as supported in this model card.
## How to use
This repository contains two versions of Llama-3.2-1B-Instruct, for use with transformers and with the original `llama` codebase.
### Use with transformers
Starting with `transformers >= 4.43.0` onward, you can run conversational inference using the Transformers `pipeline` abstraction or by leveraging the Auto classes with the `generate()` function.
Make sure to update your transformers installation via `pip install --upgrade transformers`.
```python
import torch
from transformers import pipeline
model_id = "meta-llama/Llama-3.2-1B-Instruct"
pipe = pipeline(
"text-generation",
model=model_id,
torch_dtype=torch.bfloat16,
device_map="auto",
)
messages = [
{"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
{"role": "user", "content": "Who are you?"},
]
outputs = pipe(
messages,
max_new_tokens=256,
)
print(outputs[0]["generated_text"][-1])
```
Note: You can also find detailed recipes on how to use the model locally, with `torch.compile()`, assisted generations, quantised and more at [`huggingface-llama-recipes`](https://github.com/huggingface/huggingface-llama-recipes)
### Use with `llama`
Please, follow the instructions in the [repository](https://github.com/meta-llama/llama)
To download Original checkpoints, see the example command below leveraging `huggingface-cli`:
```
huggingface-cli download meta-llama/Llama-3.2-1B-Instruct --include "original/*" --local-dir Llama-3.2-1B-Instruct
```
## Hardware and Software
**Training Factors:** We used custom training libraries, Meta's custom built GPU cluster, and production infrastructure for pretraining. Fine-tuning, quantization, annotation, and evaluation were also performed on production infrastructure.
**Training Energy Use:** Training utilized a cumulative of **916k** GPU hours of computation on H100-80GB (TDP of 700W) type hardware, per the table below. Training time is the total GPU time required for training each model and power consumption is the peak power capacity per GPU device used, adjusted for power usage efficiency.
**Training Greenhouse Gas Emissions:** Estimated total location-based greenhouse gas emissions were **240** tons CO2eq for training. Since 2020, Meta has maintained net zero greenhouse gas emissions in its global operations and matched 100% of its electricity use with renewable energy; therefore, the total market-based greenhouse gas emissions for training were 0 tons CO2eq.
| | Training Time (GPU hours) | Logit Generation Time (GPU Hours) | Training Power Consumption (W) | Training Location-Based Greenhouse Gas Emissions (tons CO2eq) | Training Market-Based Greenhouse Gas Emissions (tons CO2eq) |
| :---- | :---: | ----- | :---: | :---: | :---: |
| Llama 3.2 1B | 370k | \- | 700 | 107 | 0 |
| Llama 3.2 3B | 460k | \- | 700 | 133 | 0 |
| Llama 3.2 1B SpinQuant | 1.7 | 0 | 700 | *Negligible*\*\* | 0 |
| Llama 3.2 3B SpinQuant | 2.4 | 0 | 700 | *Negligible*\*\* | 0 |
| Llama 3.2 1B QLora | 1.3k | 0 | 700 | 0.381 | 0 |
| Llama 3.2 3B QLora | 1.6k | 0 | 700 | 0.461 | 0 |
| Total | 833k | 86k | | 240 | 0 |
\*\* The location-based CO2e emissions of Llama 3.2 1B SpinQuant and Llama 3.2 3B SpinQuant are less than 0.001 metric tonnes each. This is due to the minimal training GPU hours that are required.
The methodology used to determine training energy use and greenhouse gas emissions can be found [here](https://arxiv.org/pdf/2204.05149). Since Meta is openly releasing these models, the training energy use and greenhouse gas emissions will not be incurred by others.
## Training Data
**Overview:** Llama 3.2 was pretrained on up to 9 trillion tokens of data from publicly available sources. For the 1B and 3B Llama 3.2 models, we incorporated logits from the Llama 3.1 8B and 70B models into the pretraining stage of the model development, where outputs (logits) from these larger models were used as token-level targets. Knowledge distillation was used after pruning to recover performance. In post-training we used a similar recipe as Llama 3.1 and produced final chat models by doing several rounds of alignment on top of the pre-trained model. Each round involved Supervised Fine-Tuning (SFT), Rejection Sampling (RS), and Direct Preference Optimization (DPO).
**Data Freshness:** The pretraining data has a cutoff of December 2023\.
## Quantization
### Quantization Scheme
We designed the current quantization scheme with the [PyTorch’s ExecuTorch](https://github.com/pytorch/executorch) inference framework and Arm CPU backend in mind, taking into account metrics including model quality, prefill/decoding speed, and memory footprint. Our quantization scheme involves three parts:
- All linear layers in all transformer blocks are quantized to a 4-bit groupwise scheme (with a group size of 32) for weights and 8-bit per-token dynamic quantization for activations.
- The classification layer is quantized to 8-bit per-channel for weight and 8-bit per token dynamic quantization for activation.
- Similar to classification layer, an 8-bit per channel quantization is used for embedding layer.
### Quantization-Aware Training and LoRA
The quantization-aware training (QAT) with low-rank adaptation (LoRA) models went through only post-training stages, using the same data as the full precision models. To initialize QAT, we utilize BF16 Llama 3.2 model checkpoints obtained after supervised fine-tuning (SFT) and perform an additional full round of SFT training with QAT. We then freeze the backbone of the QAT model and perform another round of SFT with LoRA adaptors applied to all layers within the transformer block. Meanwhile, the LoRA adaptors' weights and activations are maintained in BF16. Because our approach is similar to QLoRA of Dettmers et al., (2023) (i.e., quantization followed by LoRA adapters), we refer this method as QLoRA. Finally, we fine-tune the resulting model (both backbone and LoRA adaptors) using direct preference optimization (DPO).
### SpinQuant
[SpinQuant](https://arxiv.org/abs/2405.16406) was applied, together with generative post-training quantization (GPTQ). For the SpinQuant rotation matrix fine-tuning, we optimized for 100 iterations, using 800 samples with sequence-length 2048 from the WikiText 2 dataset. For GPTQ, we used 128 samples from the same dataset with the same sequence-length.
## Benchmarks \- English Text
In this section, we report the results for Llama 3.2 models on standard automatic benchmarks. For all these evaluations, we used our internal evaluations library.
### Base Pretrained Models
| Category | Benchmark | \# Shots | Metric | Llama 3.2 1B | Llama 3.2 3B | Llama 3.1 8B |
| ----- | ----- | :---: | :---: | :---: | :---: | :---: |
| General | MMLU | 5 | macro\_avg/acc\_char | 32.2 | 58 | 66.7 |
| | AGIEval English | 3-5 | average/acc\_char | 23.3 | 39.2 | 47.8 |
| | ARC-Challenge | 25 | acc\_char | 32.8 | 69.1 | 79.7 |
| Reading comprehension | SQuAD | 1 | em | 49.2 | 67.7 | 77 |
| | QuAC (F1) | 1 | f1 | 37.9 | 42.9 | 44.9 |
| | DROP (F1) | 3 | f1 | 28.0 | 45.2 | 59.5 |
| Long Context | Needle in Haystack | 0 | em | 96.8 | 1 | 1 |
### Instruction Tuned Models
| Capability | | Benchmark | \# Shots | Metric | Llama 3.2 1B bf16 | Llama 3.2 1B Vanilla PTQ\*\* | Llama 3.2 1B Spin Quant | Llama 3.2 1B QLoRA | Llama 3.2 3B bf16 | Llama 3.2 3B Vanilla PTQ\*\* | Llama 3.2 3B Spin Quant | Llama 3.2 3B QLoRA | Llama 3.1 8B |
| :---: | ----- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
| General | | MMLU | 5 | macro\_avg/acc | 49.3 | 43.3 | 47.3 | 49.0 | 63.4 | 60.5 | 62 | 62.4 | 69.4 |
| Re-writing | | Open-rewrite eval | 0 | micro\_avg/rougeL | 41.6 | 39.2 | 40.9 | 41.2 | 40.1 | 40.3 | 40.8 | 40.7 | 40.9 |
| Summarization | | TLDR9+ (test) | 1 | rougeL | 16.8 | 14.9 | 16.7 | 16.8 | 19.0 | 19.1 | 19.2 | 19.1 | 17.2 |
| Instruction following | | IFEval | 0 | Avg(Prompt/Instruction acc Loose/Strict) | 59.5 | 51.5 | 58.4 | 55.6 | 77.4 | 73.9 | 73.5 | 75.9 | 80.4 |
| Math | | GSM8K (CoT) | 8 | em\_maj1@1 | 44.4 | 33.1 | 40.6 | 46.5 | 77.7 | 72.9 | 75.7 | 77.9 | 84.5 |
| | | MATH (CoT) | 0 | final\_em | 30.6 | 20.5 | 25.3 | 31.0 | 48.0 | 44.2 | 45.3 | 49.2 | 51.9 |
| Reasoning | | ARC-C | 0 | acc | 59.4 | 54.3 | 57 | 60.7 | 78.6 | 75.6 | 77.6 | 77.6 | 83.4 |
| | | GPQA | 0 | acc | 27.2 | 25.9 | 26.3 | 25.9 | 32.8 | 32.8 | 31.7 | 33.9 | 32.8 |
| | | Hellaswag | 0 | acc | 41.2 | 38.1 | 41.3 | 41.5 | 69.8 | 66.3 | 68 | 66.3 | 78.7 |
| Tool Use | | BFCL V2 | 0 | acc | 25.7 | 14.3 | 15.9 | 23.7 | 67.0 | 53.4 | 60.1 | 63.5 | 67.1 |
| | | Nexus | 0 | macro\_avg/acc | 13.5 | 5.2 | 9.6 | 12.5 | 34.3 | 32.4 | 31.5 | 30.1 | 38.5 |
| Long Context | | InfiniteBench/En.QA | 0 | longbook\_qa/f1 | 20.3 | N/A | N/A | N/A | 19.8 | N/A | N/A | N/A | 27.3 |
| | | InfiniteBench/En.MC | 0 | longbook\_choice/acc | 38.0 | N/A | N/A | N/A | 63.3 | N/A | N/A | N/A | 72.2 |
| | | NIH/Multi-needle | 0 | recall | 75.0 | N/A | N/A | N/A | 84.7 | N/A | N/A | N/A | 98.8 |
| Multilingual | | MGSM (CoT) | 0 | em | 24.5 | 13.7 | 18.2 | 24.4 | 58.2 | 48.9 | 54.3 | 56.8 | 68.9 |
\*\*for comparison purposes only. Model not released.
### Multilingual Benchmarks
| Category | Benchmark | Language | Llama 3.2 1B | Llama 3.2 1B Vanilla PTQ\*\* | Llama 3.2 1B Spin Quant | Llama 3.2 1B QLoRA | Llama 3.2 3B | Llama 3.2 3B Vanilla PTQ\*\* | Llama 3.2 3B Spin Quant | Llama 3.2 3B QLoRA | Llama 3.1 8B |
| :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
| General | MMLU (5-shot, macro_avg/acc) | Portuguese | 39.8 | 34.9 | 38.9 | 40.2 | 54.5 | 50.9 | 53.3 | 53.4 | 62.1 |
| | | Spanish | 41.5 | 36.0 | 39.8 | 41.8 | 55.1 | 51.9 | 53.6 | 53.6 | 62.5 |
| | | Italian | 39.8 | 34.9 | 38.1 | 40.6 | 53.8 | 49.9 | 52.1 | 51.7 | 61.6 |
| | | German | 39.2 | 34.9 | 37.5 | 39.6 | 53.3 | 50.0 | 52.2 | 51.3 | 60.6 |
| | | French | 40.5 | 34.8 | 39.2 | 40.8 | 54.6 | 51.2 | 53.3 | 53.3 | 62.3 |
| | | Hindi | 33.5 | 30.0 | 32.1 | 34.0 | 43.3 | 40.4 | 42.0 | 42.1 | 50.9 |
| | | Thai | 34.7 | 31.2 | 32.4 | 34.9 | 44.5 | 41.3 | 44.0 | 42.2 | 50.3 |
\*\*for comparison purposes only. Model not released.
## Inference time
In the below table, we compare the performance metrics of different quantization methods (SpinQuant and QAT \+ LoRA) with the BF16 baseline. The evaluation was done using the [ExecuTorch](https://github.com/pytorch/executorch) framework as the inference engine, with the ARM CPU as a backend using Android OnePlus 12 device.
| Category | Decode (tokens/sec) | Time-to-first-token (sec) | Prefill (tokens/sec) | Model size (PTE file size in MB) | Memory size (RSS in MB) |
| :---- | ----- | ----- | ----- | ----- | ----- |
| 1B BF16 (baseline) | 19.2 | 1.0 | 60.3 | 2358 | 3,185 |
| 1B SpinQuant | 50.2 (2.6x) | 0.3 (-76.9%) | 260.5 (4.3x) | 1083 (-54.1%) | 1,921 (-39.7%) |
| 1B QLoRA | 45.8 (2.4x) | 0.3 (-76.0%) | 252.0 (4.2x) | 1127 (-52.2%) | 2,255 (-29.2%) |
| 3B BF16 (baseline) | 7.6 | 3.0 | 21.2 | 6129 | 7,419 |
| 3B SpinQuant | 19.7 (2.6x) | 0.7 (-76.4%) | 89.7 (4.2x) | 2435 (-60.3%) | 3,726 (-49.8%) |
| 3B QLoRA | 18.5 (2.4x) | 0.7 (-76.1%) | 88.8 (4.2x) | 2529 (-58.7%) | 4,060 (-45.3%) |
(\*) The performance measurement is done using an adb binary-based approach.
(\*\*) It is measured on an Android OnePlus 12 device.
(\*\*\*) Time-to-first-token (TTFT) is measured with prompt length=64
*Footnote:*
- *Decode (tokens/second) is for how quickly it keeps generating. Higher is better.*
- *Time-to-first-token (TTFT for shorthand) is for how fast it generates the first token for a given prompt. Lower is better.*
- *Prefill is the inverse of TTFT (aka 1/TTFT) in tokens/second. Higher is better*
- *Model size \- how big is the model, measured by, PTE file, a binary file format for ExecuTorch*
- *RSS size \- Memory usage in resident set size (RSS)*
## Responsibility & Safety
As part of our Responsible release approach, we followed a three-pronged strategy to managing trust & safety risks:
1. Enable developers to deploy helpful, safe and flexible experiences for their target audience and for the use cases supported by Llama
2. Protect developers against adversarial users aiming to exploit Llama capabilities to potentially cause harm
3. Provide protections for the community to help prevent the misuse of our models
### Responsible Deployment
**Approach:** Llama is a foundational technology designed to be used in a variety of use cases. Examples on how Meta’s Llama models have been responsibly deployed can be found in our [Community Stories webpage](https://llama.meta.com/community-stories/). Our approach is to build the most helpful models, enabling the world to benefit from the technology power, by aligning our model safety for generic use cases and addressing a standard set of harms. Developers are then in the driver’s seat to tailor safety for their use cases, defining their own policies and deploying the models with the necessary safeguards in their Llama systems. Llama 3.2 was developed following the best practices outlined in our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide/).
#### Llama 3.2 Instruct
**Objective:** Our main objectives for conducting safety fine-tuning are to provide the research community with a valuable resource for studying the robustness of safety fine-tuning, as well as to offer developers a readily available, safe, and powerful model for various applications to reduce the developer workload to deploy safe AI systems. We implemented the same set of safety mitigations as in Llama 3, and you can learn more about these in the Llama 3 [paper](https://ai.meta.com/research/publications/the-llama-3-herd-of-models/).
**Fine-Tuning Data:** We employ a multi-faceted approach to data collection, combining human-generated data from our vendors with synthetic data to mitigate potential safety risks. We’ve developed many large language model (LLM)-based classifiers that enable us to thoughtfully select high-quality prompts and responses, enhancing data quality control.
**Refusals and Tone:** Building on the work we started with Llama 3, we put a great emphasis on model refusals to benign prompts as well as refusal tone. We included both borderline and adversarial prompts in our safety data strategy, and modified our safety data responses to follow tone guidelines.
#### Llama 3.2 Systems
**Safety as a System:** Large language models, including Llama 3.2, **are not designed to be deployed in isolation** but instead should be deployed as part of an overall AI system with additional safety guardrails as required. Developers are expected to deploy system safeguards when building agentic systems. Safeguards are key to achieve the right helpfulness-safety alignment as well as mitigating safety and security risks inherent to the system and any integration of the model or system with external tools. As part of our responsible release approach, we provide the community with [safeguards](https://llama.meta.com/trust-and-safety/) that developers should deploy with Llama models or other LLMs, including Llama Guard, Prompt Guard and Code Shield. All our [reference implementations](https://github.com/meta-llama/llama-agentic-system) demos contain these safeguards by default so developers can benefit from system-level safety out-of-the-box.
### New Capabilities and Use Cases
**Technological Advancement:** Llama releases usually introduce new capabilities that require specific considerations in addition to the best practices that generally apply across all Generative AI use cases. For prior release capabilities also supported by Llama 3.2, see [Llama 3.1 Model Card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/MODEL_CARD.md), as the same considerations apply here as well.
**Constrained Environments:** Llama 3.2 1B and 3B models are expected to be deployed in highly constrained environments, such as mobile devices. LLM Systems using smaller models will have a different alignment profile and safety/helpfulness tradeoff than more complex, larger systems. Developers should ensure the safety of their system meets the requirements of their use case. We recommend using lighter system safeguards for such use cases, like Llama Guard 3-1B or its mobile-optimized version.
### Evaluations
**Scaled Evaluations:** We built dedicated, adversarial evaluation datasets and evaluated systems composed of Llama models and Purple Llama safeguards to filter input prompt and output response. It is important to evaluate applications in context, and we recommend building dedicated evaluation dataset for your use case.
**Red Teaming:** We conducted recurring red teaming exercises with the goal of discovering risks via adversarial prompting and we used the learnings to improve our benchmarks and safety tuning datasets. We partnered early with subject-matter experts in critical risk areas to understand the nature of these real-world harms and how such models may lead to unintended harm for society. Based on these conversations, we derived a set of adversarial goals for the red team to attempt to achieve, such as extracting harmful information or reprogramming the model to act in a potentially harmful capacity. The red team consisted of experts in cybersecurity, adversarial machine learning, responsible AI, and integrity in addition to multilingual content specialists with background in integrity issues in specific geographic markets.
### Critical Risks
In addition to our safety work above, we took extra care on measuring and/or mitigating the following critical risk areas:
**1\. CBRNE (Chemical, Biological, Radiological, Nuclear, and Explosive Weapons):** Llama 3.2 1B and 3B models are smaller and less capable derivatives of Llama 3.1. For Llama 3.1 70B and 405B, to assess risks related to proliferation of chemical and biological weapons, we performed uplift testing designed to assess whether use of Llama 3.1 models could meaningfully increase the capabilities of malicious actors to plan or carry out attacks using these types of weapons and have determined that such testing also applies to the smaller 1B and 3B models.
**2\. Child Safety:** Child Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors including the additional languages Llama 3 is trained on. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.
**3\. Cyber Attacks:** For Llama 3.1 405B, our cyber attack uplift study investigated whether LLMs can enhance human capabilities in hacking tasks, both in terms of skill level and speed.
Our attack automation study focused on evaluating the capabilities of LLMs when used as autonomous agents in cyber offensive operations, specifically in the context of ransomware attacks. This evaluation was distinct from previous studies that considered LLMs as interactive assistants. The primary objective was to assess whether these models could effectively function as independent agents in executing complex cyber-attacks without human intervention. Because Llama 3.2’s 1B and 3B models are smaller and less capable models than Llama 3.1 405B, we broadly believe that the testing conducted for the 405B model also applies to Llama 3.2 models.
### Community
**Industry Partnerships:** Generative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership on AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our [Github repository](https://github.com/meta-llama/PurpleLlama).
**Grants:** We also set up the [Llama Impact Grants](https://llama.meta.com/llama-impact-grants/) program to identify and support the most compelling applications of Meta’s Llama model for societal benefit across three categories: education, climate and open innovation. The 20 finalists from the hundreds of applications can be found [here](https://llama.meta.com/llama-impact-grants/#finalists).
**Reporting:** Finally, we put in place a set of resources including an [output reporting mechanism](https://developers.facebook.com/llama_output_feedback) and [bug bounty program](https://www.facebook.com/whitehat) to continuously improve the Llama technology with the help of the community.
## Ethical Considerations and Limitations
**Values:** The core values of Llama 3.2 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3.2 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.
**Testing:** Llama 3.2 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3.2’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3.2 models, developers should perform safety testing and tuning tailored to their specific applications of the model. Please refer to available resources including our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide), [Trust and Safety](https://llama.meta.com/trust-and-safety/) solutions, and other [resources](https://llama.meta.com/docs/get-started/) to learn more about responsible development.
| [
"SUMMARIZATION"
] | Non_BioNLP |
QHWU1228/mt5-small-finetuned-amazon-en-es | QHWU1228 | summarization | [
"transformers",
"tensorboard",
"safetensors",
"mt5",
"text2text-generation",
"summarization",
"generated_from_trainer",
"base_model:google/mt5-small",
"base_model:finetune:google/mt5-small",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 1,732,765,191,000 | 2024-12-04T23:16:46 | 17 | 0 | ---
base_model: google/mt5-small
library_name: transformers
license: apache-2.0
metrics:
- rouge
tags:
- summarization
- generated_from_trainer
model-index:
- name: mt5-small-finetuned-amazon-en-es
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# mt5-small-finetuned-amazon-en-es
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 3.0197
- Rouge1: 16.6252
- Rouge2: 7.8463
- Rougel: 16.5669
- Rougelsum: 16.5091
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5.6e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 8
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|
| 2.9379 | 1.0 | 1209 | 3.3203 | 19.0063 | 9.7984 | 18.5969 | 18.4743 |
| 3.5668 | 2.0 | 2418 | 3.0886 | 17.4365 | 8.614 | 17.0761 | 17.0194 |
| 3.3727 | 3.0 | 3627 | 3.0707 | 16.7181 | 8.3534 | 16.5387 | 16.4384 |
| 3.2658 | 4.0 | 4836 | 3.0663 | 16.7178 | 8.2583 | 16.5202 | 16.4407 |
| 3.1784 | 5.0 | 6045 | 3.0332 | 16.6095 | 7.7741 | 16.3874 | 16.3206 |
| 3.1276 | 6.0 | 7254 | 3.0291 | 16.2199 | 7.3083 | 15.9939 | 15.8797 |
| 3.1038 | 7.0 | 8463 | 3.0194 | 16.5163 | 7.8339 | 16.3592 | 16.2554 |
| 3.0796 | 8.0 | 9672 | 3.0197 | 16.6252 | 7.8463 | 16.5669 | 16.5091 |
### Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3
| [
"SUMMARIZATION"
] | Non_BioNLP |
joyebright/Top2-without-mixing | joyebright | translation | [
"translation",
"en",
"fr",
"dataset:wmt",
"dataset:iwslt2014",
"license:apache-2.0",
"region:us"
] | 1,646,263,745,000 | 2021-10-14T10:08:58 | 0 | 0 | ---
datasets:
- wmt
- iwslt2014
language:
- en
- fr
license: apache-2.0
metrics:
- bleu
- ter
- chrf2
- sacrebleu
tags:
- translation
---
| [
"TRANSLATION"
] | Non_BioNLP |
tmnam20/mdeberta-v3-base-mrpc-10 | tmnam20 | text-classification | [
"transformers",
"safetensors",
"deberta-v2",
"text-classification",
"generated_from_trainer",
"en",
"dataset:tmnam20/VieGLUE",
"base_model:microsoft/mdeberta-v3-base",
"base_model:finetune:microsoft/mdeberta-v3-base",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 1,705,392,728,000 | 2024-01-16T08:14:00 | 5 | 0 | ---
base_model: microsoft/mdeberta-v3-base
datasets:
- tmnam20/VieGLUE
language:
- en
license: mit
metrics:
- accuracy
- f1
tags:
- generated_from_trainer
model-index:
- name: mdeberta-v3-base-mrpc-10
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: tmnam20/VieGLUE/MRPC
type: tmnam20/VieGLUE
config: mrpc
split: validation
args: mrpc
metrics:
- type: accuracy
value: 0.8504901960784313
name: Accuracy
- type: f1
value: 0.893169877408056
name: F1
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# mdeberta-v3-base-mrpc-10
This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on the tmnam20/VieGLUE/MRPC dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3609
- Accuracy: 0.8505
- F1: 0.8932
- Combined Score: 0.8718
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 16
- seed: 10
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Training results
### Framework versions
- Transformers 4.35.2
- Pytorch 2.2.0.dev20231203+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
| [
"TEXT_CLASSIFICATION"
] | Non_BioNLP |
gokulsrinivasagan/bert_tiny_olda_book_5_v1_stsb | gokulsrinivasagan | text-classification | [
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"en",
"dataset:glue",
"base_model:gokulsrinivasagan/bert_tiny_olda_book_5_v1",
"base_model:finetune:gokulsrinivasagan/bert_tiny_olda_book_5_v1",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 1,739,302,740,000 | 2025-02-11T19:40:03 | 8 | 0 | ---
base_model: gokulsrinivasagan/bert_tiny_olda_book_5_v1
datasets:
- glue
language:
- en
library_name: transformers
metrics:
- spearmanr
tags:
- generated_from_trainer
model-index:
- name: bert_tiny_olda_book_5_v1_stsb
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: GLUE STSB
type: glue
args: stsb
metrics:
- type: spearmanr
value: 0.3909057078280815
name: Spearmanr
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bert_tiny_olda_book_5_v1_stsb
This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_olda_book_5_v1](https://huggingface.co/gokulsrinivasagan/bert_tiny_olda_book_5_v1) on the GLUE STSB dataset.
It achieves the following results on the evaluation set:
- Loss: 2.0791
- Pearson: 0.3873
- Spearmanr: 0.3909
- Combined Score: 0.3891
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 256
- eval_batch_size: 256
- seed: 10
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss | Pearson | Spearmanr | Combined Score |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:|:--------------:|
| 6.666 | 1.0 | 23 | 3.1262 | 0.0081 | 0.0056 | 0.0069 |
| 2.4779 | 2.0 | 46 | 2.6620 | 0.0570 | -0.0124 | 0.0223 |
| 2.1647 | 3.0 | 69 | 2.2854 | 0.1253 | 0.1253 | 0.1253 |
| 2.0395 | 4.0 | 92 | 2.3712 | 0.1357 | 0.1386 | 0.1371 |
| 1.8801 | 5.0 | 115 | 2.3718 | 0.1949 | 0.1957 | 0.1953 |
| 1.74 | 6.0 | 138 | 2.2306 | 0.2877 | 0.2822 | 0.2850 |
| 1.5258 | 7.0 | 161 | 2.2584 | 0.3352 | 0.3433 | 0.3392 |
| 1.3517 | 8.0 | 184 | 2.1435 | 0.3680 | 0.3726 | 0.3703 |
| 1.173 | 9.0 | 207 | 2.0791 | 0.3873 | 0.3909 | 0.3891 |
| 1.0636 | 10.0 | 230 | 2.1585 | 0.3870 | 0.3912 | 0.3891 |
| 0.9475 | 11.0 | 253 | 2.5705 | 0.3772 | 0.3945 | 0.3859 |
| 0.8403 | 12.0 | 276 | 2.1378 | 0.4000 | 0.4003 | 0.4002 |
| 0.7236 | 13.0 | 299 | 2.3459 | 0.3771 | 0.3813 | 0.3792 |
| 0.688 | 14.0 | 322 | 2.2095 | 0.4002 | 0.4023 | 0.4013 |
### Framework versions
- Transformers 4.46.1
- Pytorch 2.2.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.1
| [
"TEXT_CLASSIFICATION"
] | Non_BioNLP |
NTIS/text2sql_encoder | NTIS | text-classification | [
"setfit",
"safetensors",
"roberta",
"sentence-transformers",
"text-classification",
"generated_from_setfit_trainer",
"arxiv:2209.11055",
"base_model:jhgan/ko-sroberta-multitask",
"base_model:finetune:jhgan/ko-sroberta-multitask",
"model-index",
"region:us"
] | 1,725,842,994,000 | 2024-09-19T02:16:47 | 8 | 0 | ---
base_model: jhgan/ko-sroberta-multitask
library_name: setfit
metrics:
- accuracy
pipeline_tag: text-classification
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: 2018년부터 2022년까지 반도체 기술 중점분류코드에 대해 연도별로 논문, 특허, 기술이전, 사업화 건수를 조회해주세요. 비밀 과제는
제외하고, 논문은 SCI와 NSCI 논문만 포함해주세요. 결과는 연도별로 정렬해주세요.
- text: 2015년부터 2021년까지 양자전체 중점기술코드에 대해 연도별 정부 투자 연구비 총액, 프로젝트 수, 전체 연구비 총액, 전체 프로젝트
수, 연구비 상대 중요도, 프로젝트 수 상대 중요도를 조회해주세요.
- text: 2020년부터 2022년까지 반도체에 해당하는 중점 기술 분류 코드가 'NAT0' 인 과제의 총 연구비 현물 금액을 조회해주세요.
- text: 2020년부터 2022년까지 AI 관련 중점기술코드에 대한 상위 5개 지역별 연도별 민간 연구비 합계를 억 단위로 조회해주세요. 각
지역명에서 '특별시', '광역시', '특별자치시', '특별자치'는 제외하고, 연구비가 5천만 원 미만인 경우 1억 원으로 간주하여 계산한 결과를
보여주세요.
- text: 2018년부터 2022년까지 인공지능 중점기술코드('AI')와 관련된 연도별 연구비 현금합계금액과 총 연구비 합계금액을 조회해 주세요.
또한 각 연도별 연구비 비중을 함께 보여주세요.
inference: true
model-index:
- name: SetFit with jhgan/ko-sroberta-multitask
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: Unknown
type: unknown
split: test
metrics:
- type: accuracy
value: 0.8922829581993569
name: Accuracy
---
# SetFit with jhgan/ko-sroberta-multitask
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [jhgan/ko-sroberta-multitask](https://huggingface.co/jhgan/ko-sroberta-multitask) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
The model has been trained using an efficient few-shot learning technique that involves:
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.
## Model Details
### Model Description
- **Model Type:** SetFit
- **Sentence Transformer body:** [jhgan/ko-sroberta-multitask](https://huggingface.co/jhgan/ko-sroberta-multitask)
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
- **Maximum Sequence Length:** 128 tokens
- **Number of Classes:** 29 classes
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
<!-- - **Language:** Unknown -->
<!-- - **License:** Unknown -->
### Model Sources
- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
### Model Labels
| Label | Examples |
|:------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| 15 | <ul><li>"2020년부터 2022년까지 인공지능(AI) 기술을 활용하는 연구과제 중에, 연구비 총액이 1억 원 이상인 연구과제의 지역별 연도별 연구비 총액을 억 단위로 조회해주세요. 각 지역명에서 '특별시', '광역시', '특별자치시', '특별자치'는 제외하고, 연구비가 5천만 원 미만인 경우 1억 원으로 간주하여 계산한 결과를 보여주세요."</li><li>"2021년부터 2022년까지 '인공지능' 중점기술코드에 대한 상위 5개 지역별 연도별 민간 연구비 현금금액 합계를 억 단위로 조회해주세요. 각 지역명에서 '특별시', '광역시', '특별자치시', '특별자치'는 제외하고, 연구비가 5천만 원 미만인 경우 1억 원으로 간주하여 계산한 결과를 보여주세요."</li><li>'2020년부터 2022년까지 AI 관련 연구개발비 현금금액이 1억 원 이상인 과제에 대한 연도별 연구개발비 현금금액 합계를 억 단위로 조회해주세요.'</li></ul> |
| 28 | <ul><li>'2020년부터 2022년까지 "인공지능" 중점기술코드에 대해 연도별로 각 납부 방식에 따른 금액의 합계를 억 단위로 변환하여 보여주세요. 또한, 각 연도의 금액 합계도 포함해주세요.'</li><li>'2018년부터 2022년까지 감염병 전략기술코드에 해당하는 과제에 대해 각 납부 방식에 따른 금액의 합계를 억 단위로 변환하여 보여주세요. 또한, 각 연도의 금액 합계도 포함해주세요.'</li><li>'2022년 감염병 중점기술코드에 대해 납부 방식별 금액의 합계를 억 단위로 변환하여 보여주세요. 또한, 납부 방식별 금액 합계도 포함해주세요.'</li></ul> |
| 22 | <ul><li>'2022년 인공지능(AI)과 반도체(semiconductor) 분야에 대한 연도별 연구비 총액을 조회해주세요.'</li><li>"2018년부터 2022년까지 '인공지능' 중점기술대분류코드_연구재단에 해당하는 연도별 사업화 건수의 합계를 조회해주세요."</li><li>'2020년부터 2022년까지 반도체 기술 분야에 대한 연도별 사업화 건수의 합계를 조회해주세요.'</li></ul> |
| 14 | <ul><li>"2022년 반도체 중점기술코드에 대한 상위 5개 지역별 연도별 민간 연구비 합계를 억 단위로 조회해주세요. 각 지역명에서 '특별시', '광역시', '특별자치시', '특별자치'는 제외하고, 연구비가 5천만 원 미만인 경우 1억 원으로 간주하여 계산한 결과를 보여주세요."</li><li>"2022년 기준으로, 반도체 전체 중점기술코드에 해당하는 과제의 연구비 현금금액이 1억 원 이상인 과제를 대상으로, 연구책임자의 성별과 학위별로 과제 개수를 조회해주세요. 연구책임자의 학위가 '박사'인 경우를 기준으로, 학위가 '석사'인 경우의 과제 개수는 몇 건인지 조회해주세요."</li><li>"2022년 양자전체 기술코드에 해당하는 상위 5개 지역별 연구비 현물금액의 합계를 조회해주세요. 각 지역명에서 '특별시', '광역시', '특별자치시', '특별자치'는 제외하고, 연구비가 5천만 원 미만인 경우 1억 원으로 간주하여 계산한 결과를 보여주세요."</li></ul> |
| 9 | <ul><li>'2022년 인공지능 중점기술코드에 대해 과제명, 연구책임자명, 연구책임자소속기관명, 연구비총현금금액, 연구비총현물금액을 조회해주세요.'</li><li>'2020년부터 2023년까지 반도체 중점기술코드에 대해 연도별로 민간연구비총현물금액과 정부투자연구비합계금액을 조회해주세요. 민간연구비총현물금액은 억 단위로 변환하며, 0인 경우 1로 표시해주세요.'</li><li>'2021년부터 2022년까지 반도체 소재·부품·장비 중점기술코드에 대해 연도별로 정부 투자 연구비 합계와 전체 연구비 합계를 조회해주세요. 정부 투자 연구비 합계는 억 단위로 변환하며, 0인 경우 1로 표시해주세요.'</li></ul> |
| 8 | <ul><li>'2022년부터 2025년까지 인공지능 중점기술코드에 대해 연도별 정부 투자 연구비 총액, 프로젝트 수, 전체 연구비 총액, 전체 프로젝트 수, 연구비 상대 중요도, 프로젝트 수 상대 중요도를 조회해주세요.'</li><li>'2015년부터 2021년까지 반도체 전체에 대해 연도별 정부 투자 연구비 총액, 프로젝트 수, 전체 연구비 총액, 전체 프로젝트 수, 연구비 상대 중요도, 프로젝트 수 상대 중요도를 조회해주세요.'</li><li>'2020년부터 2022년까지 양자컴퓨팅(QUC) 중점기술코드에 대해 연도별 정부 투자 연구비 총액, 프로젝트 수, 전체 연구비 총액, 전체 프로젝트 수, 연구비 상대 중요도, 프로젝트 수 상대 중요도를 조회해주세요.'</li></ul> |
| 7 | <ul><li>"2018년부터 2022년까지 양자컴퓨팅('QUC') 중점기술코드와 관련된 프로젝트에서 연구책임자의 총 연구비 금액이 가장 높은 상위 10개의 과제의 과제고유번호, 연구책임자총연구비금액, 연구책임자지식재산권건수, 연구책임자논문건수, 연구책임자과제건수를 조회해 주세요."</li><li>"2022년에 양자전체('QUG')와 관련된 프로젝트에서 연구책임자가 총 연구비금액이 가장 높은 상위 5명을 조회해 주세요."</li><li>"2015년부터 2020년까지 반도체('semi')와 관련된 프로젝트에서 사용된 상위 50개의 한국어 키워드와 해당 키워드의 사용 횟수를 조회해 주세요."</li></ul> |
| 17 | <ul><li>'2020년부터 2023년까지 인공지능(AI) 중점기술코드에 대한 연도별 연구비와 연구비 비중을 조회해주세요. 연구비가 1억 원 미만인 경우 1억 원으로 간주하여 억 단위로 변환한 결과를 보여주세요.'</li><li>'2020년부터 2023년까지 반도체 중점기술코드에 대한 연도별 기초연구, 개발연구, 응용연구 단계의 연구비와 연구비 비중을 조회해주세요. 연구비가 1억 원 미만인 경우 1억 원으로 간주하여 억 단위로 변환한 결과를 보여주세요.'</li><li>'2018년부터 2022년까지 양자전체 중점기술코드에 대한 연도별 기초연구, 개발연구, 응용연구, 기타연구 단계의 연구비와 연구비 비중을 조회해주세요. 연구비가 5천만 원 미만인 경우 1억 원으로 간주하여 억 단위로 변환한 결과를 보여주세요.'</li></ul> |
| 5 | <ul><li>"2018년부터 2022년까지 반도체('semi') 중점기술코드와 관련된 연도별 연구비 합계금액과 전체 연구비 합계금액을 조회해 주세요."</li><li>"2018년부터 2022년까지 인공지능 중점기술코드('AI')와 관련된 연도별 연구비금액 합계와 전체 연구비금액 합계를 조회해 주세요."</li><li>"2020년부터 2022년까지 양자전체('QUG') 중점기술코드와 관련된 연도별 연구비금액 합계와 전체 연구비금액 합계를 조회해 주세요."</li></ul> |
| 25 | <ul><li>'2022년까지 반도체 중점기술코드에 대해 연도별로 SCI 및 NSCI 논문의 수를 조회하고, 각 논문의 수를 소수점 두 자리까지 반올림하여 보여주세요.'</li><li>'2022년 친환경자동차 중점기술코드에 대해 연도별로 SCI 및 NSCI 논문의 수를 조회하고, 각 논문의 수를 소수점 두 자리까지 반올림하여 보여주세요.'</li><li>'2020년부터 2022년까지 양자전체 중점기술코드에 대해 연도별로 SCI 및 NSCI 논문의 수를 조회하고, 각 논문의 수를 소수점 두 자리까지 반올림하여 보여주세요.'</li></ul> |
| 4 | <ul><li>"2018년부터 2022년까지 반도체('NAT0R') 중점기술코드와 관련된 연도별 연구비 현금 합계 금액과 그 비중을 조회해 주세요. 연구비 현금 합계 금액은 전략기술코드별로 구분되어야 합니다."</li><li>"2018년부터 2022년까지 반도체 중점기술코드('NAT0')와 관련된 연도별 연구비 금액과 그 비중을 조회해 주세요. 연구비 유형은 정부 투자 연구비, 출연연 연구비, 중소기업 연구비, 대학 연구비, 병원 연구비, 기타 연구비입니다. 또한 각 연도의 총 연구비 금액도 함께 보여주세요."</li><li>"2018년부터 2022년까지 인공지능('AI') 중점기술코드와 관련된 연도별 연구비 총액과 그 비중을 조회해 주세요. 또한 각 연도의 총 연구비 총액도 함께 보여주세요."</li></ul> |
| 20 | <ul><li>'양자컴퓨팅 중점기술코드에 대해 2020년부터 2022년까지의 연도별 논문, 특허, 기술이전, 사업화 건수를 조회해 주세요. 비밀 과제는 제외하고, 논문은 SCI와 NSCI 논문만 포함해 주세요. 결과는 연도별로 정렬해 주세요.'</li><li>'2022년 인공지능 중점기술코드에 속한 과제의 수행기관 및 연구책임자 정보를 조회해주세요.'</li><li>'2018년부터 2022년까지 양자컴퓨팅 중점기술코드에 대해 연도별로 논문, 특허, 기술이전, 사업화 건수를 조회해주세요. 비밀 과제는 제외하고, 논문은 SCI와 NSCI 논문만 포함해주세요. 결과는 연도별로 정렬해주세요.'</li></ul> |
| 6 | <ul><li>"2015년부터 2021년까지 반도체('semi')와 관련된 프로젝트에서 사용된 상위 50개의 영어 키워드와 해당 키워드의 사용 횟수를 조회해 주세요."</li><li>'2018년부터 2022년까지 양자전체(QUG) 중점기술코드와 관련된 프로젝트에서 사용된 상위 50개의 영어 키워드와 해당 키워드의 사용 횟수를 조회해 주세요.'</li><li>"2020년부터 2022년까지 양자컴퓨팅('QUC')과 양자전체('QUG') 중점기술코드에 해당하는 프로젝트에서 사용된 상위 50개의 영어 키워드와 해당 키워드의 사용 횟수를 조회해 주세요."</li></ul> |
| 23 | <ul><li>'2022년 인공지능 중점기술코드에 대해 각 부처별로 연구비 합계와 해당 부처가 차지하는 비중을 조회해주세요. 결과는 연구비 합계를 억 단위로 변환하고, 비중은 백분율로 표시해주세요. 상위 10개의 부처만 포함되어야 합니다'</li><li>'2022년 인공지능 중점기술코드에 대해 과제 수행 기관의 유형별 연구비 합계를 조회해주세요.'</li><li>'2020년부터 2022년까지 AI 기술 분야에 속하는 과제들의 연구비 총액은 얼마이며, 각 부처별로 AI 기술 분야에 속하는 과제들의 연구비 총액은 얼마인가?'</li></ul> |
| 1 | <ul><li>"2015년부터 2020년까지 인공지능('AI')과 관련된 연도별 중국 자금 지원 금액을 조회해주세요. 자금 지원 총액을 백만 단위로 변환하여 보여주세요."</li><li>"2015년부터 2020년까지 양자전체('QUG')와 관련된 연도별 영국 자금 지원 금액을 조회해주세요. 자금 지원 총액을 백만 단위로 변환하여 보여주세요."</li><li>"2020년부터 2022년까지 인공지능('AI')과 관련된 연도별 한국 자금 지원 금액을 조회해주세요. 자금 지원 총액을 백만 단위로 변환하여 보여주세요."</li></ul> |
| 24 | <ul><li>'2022년 인공지능 분야 중점기술코드에 대해 각 부처별로 연구비 합계와 해당 부처가 차지하는 비중을 조회해주세요. 결과는 연구비 합계를 억 단위로 변환하고, 비중은 백분율로 표시해주세요. 상위 10개의 부처만 포함되어야 합니다.'</li><li>'2022년 반도체 중점기술코드에 대해 부처별 연구비 합계와 해당 부처가 차지하는 비중을 연도별로 조회해주세요. 결과는 연구비 합계를 억 단위로 변환하고, 비중은 백분율로 표시해주세요. 상위 10개의 부처만 포함되어야 합니다.'</li><li>'2022년 반도체 중점기술코드에 대해 각 부처별로 연구비 합계와 해당 부처가 차지하는 비중을 연도별로 조회해주세요. 결과는 연구비 합계를 억 단위로 변환하고, 비중은 백분율로 표시해주세요. 상위 10개의 부처만 포함되어야 합니다.'</li></ul> |
| 13 | <ul><li>'2020년부터 2022년까지 인공지능 중점기술코드에 대해 연구 수행 주체별 정부 투자 연구비 합계와 각 연구비의 억 단위 금액 및 전체 연구비 대비 상대적 중요도를 조회해주세요. 연구 수행 주체는 다음과 같습니다 대기업, 중소기업, 기타 기업, 대학, 정부출연연구소, 비영리기관, 병원, 기타. 5천만 원 미만인 경우 1억 원으로 간주하여 계산한 결과를 보여주세요.'</li><li>'2020년부터 2022년까지 양자전체 중점기술코드에 대해 연구 수행 주체별 정부 투자 연구비 합계와 각 연구비의 억 단위 금액 및 전체 연구비 대비 상대적 중요도를 조회해주세요. 연구 수행 주체는 다음과 같습니다 대기업, 중소기업, 기타 기업, 대학, 정부출연연구소, 비영리기관, 병원, 기타. 5천만 원 미만인 경우 1억 원으로 간주하여 계산한 결과를 보여주세요.'</li><li>'2022년 현재 반도체 기술 분야에 속하는 연구 수행 주체별 정부 투자 연구비 합계와 각 연구비의 억 단위 금액 및 전체 연구비 대비 상대적 중요도를 조회해주세요. 연구 수행 주체는 다음과 같습니다 대기업, 중소기업, 기타 기업, 대학, 정부출연연구소, 비영리기관, 병원, 기타. 5천만 원 미만인 경우 1억 원으로 간주하여 계산한 결과를 보여주세요.'</li></ul> |
| 0 | <ul><li>"2022년에 반도체('semi')와 관련된 유럽 자금 지원 금액을 조회해주세요. 자금 지원 총액을 백만 단위로 변환하여 보여주세요."</li><li>"2018년부터 2022년까지 양자컴퓨팅('QUC')과 관련된 연도별 유럽 자금 지원 금액을 조회해주세요. 자금 지원 총액을 백만 단위로 변환하여 보여주세요."</li><li>"2022년부터 2023년까지 양자전체('QUG')와 관련된 연도별 유럽 자금 지원 금액을 조회해주세요. 자금 지원 총액을 백만 단위로 변환하여 보여주세요."</li></ul> |
| 26 | <ul><li>'2018년부터 2022년까지 양자전체 중점기술코드에 대해 연도별로 국내 및 해외 특허 건수, 국내 및 해외 특허 출원수, 국내 및 해외 특허 등록수, 그리고 특허 기여율을 조회해주세요.'</li><li>'2018년부터 2022년까지 반도체 중점기술코드에 대해 연도별로 국내 및 해외 특허 건수, 특허 등록 건수, 기술 거래 건수를 조회해주세요.'</li><li>'2018년부터 2022년까지 양자컴퓨팅 중점기술코드에 대해 연도별로 국내 및 해외 특허 건수, 기술거래 건수, 논문 건수를 조회해주세요.'</li></ul> |
| 3 | <ul><li>"2022년부터 2023년까지 인공지능('AI') 중점기술코드와 관련된 국내 및 해외 특허 출원 및 등록 건수를 조회해주세요. 각 연도별로 국내 특허 출원 건수, 등록 건수, 총 건수와 해외 특허 출원 건수, 등록 건수, 총 건수를 포함해주세요."</li><li>"2022년까지 인공지능 중점기술코드('AI')와 관련된 국내 및 해외 특허 출원 및 등록 건수를 조회해주세요. 각 연도별로 국내 특허 출원 건수, 등록 건수, 총 건수와 해외 특허 출원 건수, 등록 건수, 총 건수를 포함해주세요."</li><li>"2018년부터 2022년까지 인공지능 중점기술코드('AI')와 관련된 국내 및 해외 특허 출원 및 등록 건수를 조회해주세요. 각 연도별로 국내 특허 출원 건수, 등록 건수, 총 건수와 해외 특허 출원 건수, 등록 건수, 총 건수를 포함해주세요."</li></ul> |
| 18 | <ul><li>"2020년부터 2022년까지 석유화학 중점기술 코드와 관련된 데이터를 조회해주세요. 연구 프로젝트의 총 정부 투자 연구비를 억 단위로 변환하여 중점기술 코드와 코드명을 함께 보여주세요. 코드명에 '전체'가 포함되지 않은 경우만 조회합니다."</li><li>"2020년부터 2023년까지 비밀 과제가 아닌 연구 프로젝트 중 인공지능(AI) 중점기술 코드와 관련된 데이터를 조회해주세요. 연구 프로젝트의 총 정부 투자 연구비를 억 단위로 변환하여 중점기술 코드와 코드명을 함께 보여주세요. 코드명에 '전체'가 포함되지 않은 경우만 조회합니다."</li><li>'2022년에 진행된 연구 프로젝트 중 양자컴퓨팅(QUC) 중점기술 코드와 관련된 데이터를 조회해주세요. 연구 프로젝트의 총 정부 투자 연구비를 억 단위로 변환하여 중점기술 코드와 코드명을 함께 보여주세요.'</li></ul> |
| 11 | <ul><li>'2022년 양자전체(QUG) 중점기술코드에 해당하는 과제의 세부 기술코드(FCTC_LCLS_CD)와 그에 해당하는 기술코드 이름(CD_NM)을 조회해 주세요.'</li><li>'2020년부터 2022년까지 양자전체(QUG)에 대한 연도별 정부 투자 연구비(GOV_IVT_RNDCO_AMT)를 억 단위로 조회해주세요.'</li><li>'2022년 기준으로 반도체 소재·부품·장비 중점기술코드에 대해 세부 기술코드(FCTC_LCLS_CD)별로 그에 해당하는 기술 코드 이름(CD_NM)과 총 연구비 금액(TOT_RNDCO_AMT)을 조회해주세요.'</li></ul> |
| 2 | <ul><li>"2018년부터 2022년까지 반도체('NAT0R')와 관련된 연도별 국내 및 해외 특허 출원 및 등록 건수를 조회해주세요. 각 연도별로 국내 특허 출원 건수, 등록 건수, 총 건수와 해외 특허 출원 건수, 등록 건수, 총 건수를 포함해주세요."</li><li>"2018년부터 2022년까지 반도체('NAT0') 중점기술코드와 관련된 연도별 국내 및 해외 특허 출원 및 등록 건수를 조회해주세요. 각 연도별로 국내 특허 출원 건수, 등록 건수, 총 건수와 해외 특허 출원 건수, 등록 건수, 총 건수를 포함해주세요."</li><li>'2018년부터 2022년까지 인공지능(AI) 중점기술코드와 관련된 연도별 국내 및 해외 특허 출원 및 등록 건수를 조회해주세요. 각 연도별로 국내 특허 출원 건수, 등록 건수, 총 건수와 해외 특허 출원 건수, 등록 건수, 총 건수를 포함해주세요.'</li></ul> |
| 10 | <ul><li>'2020년부터 2022년까지 양자컴퓨팅 중점기술코드에 대해 연도별로 각 세부 기술코드(FCTC_LCLS_CD)와 그에 해당하는 기술 코드 이름(CD_NM)의 정부 투자 연구비 합계를 억 단위로 조회해주세요. 각 세부 기술코드는 총 연구비 금액에 따라 내림차순으로 정렬해주세요.'</li><li>'2022년 기준으로 반도체 기술 중점분류코드(NAT0)와 그에 해당하는 기술 코드 이름(CD_NM)의 정부 투자 연구비 합계를 억 단위로 조회해주세요. 각 세부 기술코드는 총 연구비 금액에 따라 내림차순으로 정렬해주세요.'</li><li>"2022년 현재 반도체 기술 분야에서 중점 기술코드가 'NAT0'인 과제에 대해 과제명, 중점 기술코드, 정부 투자 연구비, 민간 투자 연구비의 총액을 조회해주세요."</li></ul> |
| 21 | <ul><li>'2022년 인공지능 중점기술코드에 해당하는 과제의 전체 연구비 금액의 합계를 조회해주세요.'</li><li>'2022년 인공지능 기술을 활용한 연구과제의 총 연구비 현물금액과 총 연구비 현금금액을 조회해주세요.'</li><li>'2021년 인공지능 기술을 적용한 사업화 건수의 합계를 조회해주세요. 각 기술별 건수는 막대 그래프로 표시될 수 있습니다.'</li></ul> |
| 19 | <ul><li>'2020년부터 2022년까지 반도체 중점기술코드에 대해 연도별 논문, 특허, 기술이전, 사업화 건수를 조회해주세요.'</li><li>'2022년에 양자전체(QUG) 중점기술코드에 대해 응용연구단계의 논문, 특허, 기술이전, 사업화 건수를 조회해주세요.'</li><li>'2022년 인공지능 중점기술코드에 대해 논문, 특허, 기술이전, 사업화 건수를 조회해주세요.'</li></ul> |
| 12 | <ul><li>'2020년부터 2023년까지 인공지능 중점기술코드에 대해 연구 수행 주체별 정부 투자 연구비 합계와 각 연구비의 억 단위 금액 및 상대적 중요도를 조회해주세요. 연구 수행 주체는 다음과 같습니다 대기업, 중소기업, 기타 기업, 대학, 정부출연연구소, 비영리기관, 병원, 기타. 5천만 원 미만인 경우 1억 원으로 간주하여 계산한 결과를 보여주세요.'</li><li>'2020년부터 2023년까지 반도체 중점기술코드에 대해 연구 수행 주체별 정부 투자 연구비 합계와 각 연구비의 억 단위 금액 및 상대적 중요도를 조회해주세요. 연구 수행 주체는 다음과 같습니다 대기업, 중소기업, 기타 기업, 대학, 정부출연연구소, 비영리기관, 병원, 기타. 5천만 원 미만인 경우 1억 원으로 간주하여 계산한 결과를 보여주세요.'</li><li>'2018년부터 2022년까지 반도체 중점기술코드에 대해 연구 수행 주체별 정부 투자 연구비 합계와 각 연구비의 억 단위 금액 및 상대적 중요도를 조회해주세요. 연구 수행 주체는 다음과 같습니다 대기업, 중소기업, 기타 기업, 대학, 정부출연연구소, 비영리기관, 병원, 기타. 5천만 원 미만인 경우 1억 원으로 간주하여 계산한 결과를 보여주세요.'</li></ul> |
| 27 | <ul><li>'2020년부터 2023년까지 반도체 중점기술코드에 대해 연도별로 각 납부 방식에 따른 금액의 합계를 억 단위로 변환하여 보여주세요. 또한, 각 연도의 금액 합계도 포함해주세요.'</li><li>'2020년부터 2022년까지 인공지능(AI) 중점기술코드에 대해 연도별로 각 납부 방식에 따른 금액의 합계를 억 단위로 변환하여 보여주세요. 또한, 각 연도의 금액 합계도 포함해주세요.'</li><li>'2022년부터 2023년까지 인공지능(AI) 중점기술코드에 대해 연도별로 각 납부 방식에 따른 금액의 합계를 억 단위로 변환하여 보여주세요. 또한, 각 연도의 금액 합계도 포함해주세요.'</li></ul> |
| 16 | <ul><li>'2018년부터 2022년까지 반도체 중점기술코드에 대한 연도별 기초연구, 개발연구, 응용연구, 기타연구 단계의 연구비와 연구비 비중을 조회해주세요. 연구비가 5천만 원 미만인 경우 1억 원으로 간주하여 억 단위로 변환한 결과를 보여주세요. 또한, 2018년부터 2022년까지 연구개발 단계별 총 연구비와 각 단계별 연구비 비중을 조회해주세요.'</li><li>'2018년부터 2022년까지 인공지능(AI) 중점기술코드에 대한 연도별 기초연구, 개발연구, 응용연구, 기타연구 단계의 연구비와 연구비 비중을 조회해주세요. 연구비가 5천만 원 미만인 경우 1억 원으로 간주하여 억 단위로 변환한 결과를 보여주세요. 또한, 2018년부터 2022년까지 연구개발 단계별 총 연구비와 각 단계별 연구비 비중을 조회해주세요.'</li></ul> |
## Evaluation
### Metrics
| Label | Accuracy |
|:--------|:---------|
| **all** | 0.8923 |
## Uses
### Direct Use for Inference
First install the SetFit library:
```bash
pip install setfit
```
Then you can load this model and run inference.
```python
from setfit import SetFitModel
# Download from the 🤗 Hub
model = SetFitModel.from_pretrained("NTIS/text2sql_encoder")
# Run inference
preds = model("2020년부터 2022년까지 반도체에 해당하는 중점 기술 분류 코드가 'NAT0' 인 과제의 총 연구비 현물 금액을 조회해주세요.")
```
<!--
### Downstream Use
*List how someone could finetune this model on their own dataset.*
-->
<!--
### Out-of-Scope Use
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->
<!--
## Bias, Risks and Limitations
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
-->
<!--
### Recommendations
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
-->
## Training Details
### Training Set Metrics
| Training set | Min | Median | Max |
|:-------------|:----|:--------|:----|
| Word count | 6 | 22.2116 | 75 |
| Label | Training Sample Count |
|:------|:----------------------|
| 0 | 34 |
| 1 | 96 |
| 2 | 11 |
| 3 | 61 |
| 4 | 212 |
| 5 | 77 |
| 6 | 74 |
| 7 | 93 |
| 8 | 28 |
| 9 | 35 |
| 10 | 38 |
| 11 | 28 |
| 12 | 4 |
| 13 | 16 |
| 14 | 84 |
| 15 | 50 |
| 16 | 2 |
| 17 | 24 |
| 18 | 82 |
| 19 | 13 |
| 20 | 49 |
| 21 | 39 |
| 22 | 120 |
| 23 | 48 |
| 24 | 22 |
| 25 | 22 |
| 26 | 48 |
| 27 | 39 |
| 28 | 82 |
### Training Hyperparameters
- batch_size: (128, 128)
- num_epochs: (5, 5)
- max_steps: -1
- sampling_strategy: oversampling
- body_learning_rate: (2e-05, 1e-05)
- head_learning_rate: 0.01
- loss: CosineSimilarityLoss
- distance_metric: cosine_distance
- margin: 0.25
- end_to_end: False
- use_amp: False
- warmup_proportion: 0.1
- seed: 42
- eval_max_steps: -1
- load_best_model_at_end: True
### Training Results
| Epoch | Step | Training Loss | Validation Loss |
|:-------:|:---------:|:-------------:|:---------------:|
| 0.0001 | 1 | 0.2513 | - |
| 0.0029 | 50 | 0.2362 | - |
| 0.0058 | 100 | 0.1945 | - |
| 0.0087 | 150 | 0.1388 | - |
| 0.0116 | 200 | 0.1059 | - |
| 0.0145 | 250 | 0.0774 | - |
| 0.0174 | 300 | 0.1072 | - |
| 0.0203 | 350 | 0.0599 | - |
| 0.0232 | 400 | 0.067 | - |
| 0.0261 | 450 | 0.0712 | - |
| 0.0289 | 500 | 0.0682 | - |
| 0.0318 | 550 | 0.04 | - |
| 0.0347 | 600 | 0.0531 | - |
| 0.0376 | 650 | 0.0556 | - |
| 0.0405 | 700 | 0.0603 | - |
| 0.0434 | 750 | 0.0483 | - |
| 0.0463 | 800 | 0.0439 | - |
| 0.0492 | 850 | 0.019 | - |
| 0.0521 | 900 | 0.0359 | - |
| 0.0550 | 950 | 0.0253 | - |
| 0.0579 | 1000 | 0.029 | - |
| 0.0608 | 1050 | 0.0271 | - |
| 0.0637 | 1100 | 0.0232 | - |
| 0.0666 | 1150 | 0.0162 | - |
| 0.0695 | 1200 | 0.0269 | - |
| 0.0724 | 1250 | 0.0191 | - |
| 0.0753 | 1300 | 0.0113 | - |
| 0.0782 | 1350 | 0.0158 | - |
| 0.0810 | 1400 | 0.0137 | - |
| 0.0839 | 1450 | 0.015 | - |
| 0.0868 | 1500 | 0.0075 | - |
| 0.0897 | 1550 | 0.008 | - |
| 0.0926 | 1600 | 0.014 | - |
| 0.0955 | 1650 | 0.0129 | - |
| 0.0984 | 1700 | 0.0102 | - |
| 0.1013 | 1750 | 0.0119 | - |
| 0.1042 | 1800 | 0.0129 | - |
| 0.1071 | 1850 | 0.0104 | - |
| 0.1100 | 1900 | 0.01 | - |
| 0.1129 | 1950 | 0.0034 | - |
| 0.1158 | 2000 | 0.0076 | - |
| 0.1187 | 2050 | 0.0118 | - |
| 0.1216 | 2100 | 0.0052 | - |
| 0.1245 | 2150 | 0.0015 | - |
| 0.1274 | 2200 | 0.009 | - |
| 0.1303 | 2250 | 0.002 | - |
| 0.1331 | 2300 | 0.0019 | - |
| 0.1360 | 2350 | 0.0108 | - |
| 0.1389 | 2400 | 0.0092 | - |
| 0.1418 | 2450 | 0.0013 | - |
| 0.1447 | 2500 | 0.001 | - |
| 0.1476 | 2550 | 0.0008 | - |
| 0.1505 | 2600 | 0.0009 | - |
| 0.1534 | 2650 | 0.0084 | - |
| 0.1563 | 2700 | 0.0027 | - |
| 0.1592 | 2750 | 0.0009 | - |
| 0.1621 | 2800 | 0.0078 | - |
| 0.1650 | 2850 | 0.0014 | - |
| 0.1679 | 2900 | 0.0154 | - |
| 0.1708 | 2950 | 0.0007 | - |
| 0.1737 | 3000 | 0.0147 | - |
| 0.1766 | 3050 | 0.0004 | - |
| 0.1795 | 3100 | 0.0087 | - |
| 0.1824 | 3150 | 0.0069 | - |
| 0.1852 | 3200 | 0.0007 | - |
| 0.1881 | 3250 | 0.0076 | - |
| 0.1910 | 3300 | 0.001 | - |
| 0.1939 | 3350 | 0.0078 | - |
| 0.1968 | 3400 | 0.0009 | - |
| 0.1997 | 3450 | 0.0007 | - |
| 0.2026 | 3500 | 0.0112 | - |
| 0.2055 | 3550 | 0.008 | - |
| 0.2084 | 3600 | 0.0004 | - |
| 0.2113 | 3650 | 0.0005 | - |
| 0.2142 | 3700 | 0.0003 | - |
| 0.2171 | 3750 | 0.0004 | - |
| 0.2200 | 3800 | 0.0003 | - |
| 0.2229 | 3850 | 0.0152 | - |
| 0.2258 | 3900 | 0.0143 | - |
| 0.2287 | 3950 | 0.0081 | - |
| 0.2316 | 4000 | 0.0088 | - |
| 0.2345 | 4050 | 0.0052 | - |
| 0.2374 | 4100 | 0.0042 | - |
| 0.2402 | 4150 | 0.0014 | - |
| 0.2431 | 4200 | 0.0003 | - |
| 0.2460 | 4250 | 0.0228 | - |
| 0.2489 | 4300 | 0.0104 | - |
| 0.2518 | 4350 | 0.0002 | - |
| 0.2547 | 4400 | 0.0147 | - |
| 0.2576 | 4450 | 0.0145 | - |
| 0.2605 | 4500 | 0.0082 | - |
| 0.2634 | 4550 | 0.0004 | - |
| 0.2663 | 4600 | 0.0003 | - |
| 0.2692 | 4650 | 0.0073 | - |
| 0.2721 | 4700 | 0.0026 | - |
| 0.2750 | 4750 | 0.001 | - |
| 0.2779 | 4800 | 0.0081 | - |
| 0.2808 | 4850 | 0.0111 | - |
| 0.2837 | 4900 | 0.0014 | - |
| 0.2866 | 4950 | 0.0008 | - |
| 0.2895 | 5000 | 0.0077 | - |
| 0.2923 | 5050 | 0.0002 | - |
| 0.2952 | 5100 | 0.0002 | - |
| 0.2981 | 5150 | 0.0002 | - |
| 0.3010 | 5200 | 0.0008 | - |
| 0.3039 | 5250 | 0.0003 | - |
| 0.3068 | 5300 | 0.0072 | - |
| 0.3097 | 5350 | 0.0022 | - |
| 0.3126 | 5400 | 0.0002 | - |
| 0.3155 | 5450 | 0.0001 | - |
| 0.3184 | 5500 | 0.0001 | - |
| 0.3213 | 5550 | 0.0075 | - |
| 0.3242 | 5600 | 0.0077 | - |
| 0.3271 | 5650 | 0.0008 | - |
| 0.3300 | 5700 | 0.0074 | - |
| 0.3329 | 5750 | 0.0003 | - |
| 0.3358 | 5800 | 0.0001 | - |
| 0.3387 | 5850 | 0.0001 | - |
| 0.3416 | 5900 | 0.0003 | - |
| 0.3444 | 5950 | 0.0009 | - |
| 0.3473 | 6000 | 0.0061 | - |
| 0.3502 | 6050 | 0.0005 | - |
| 0.3531 | 6100 | 0.0079 | - |
| 0.3560 | 6150 | 0.0101 | - |
| 0.3589 | 6200 | 0.0001 | - |
| 0.3618 | 6250 | 0.0002 | - |
| 0.3647 | 6300 | 0.0077 | - |
| 0.3676 | 6350 | 0.0001 | - |
| 0.3705 | 6400 | 0.0002 | - |
| 0.3734 | 6450 | 0.0001 | - |
| 0.3763 | 6500 | 0.0077 | - |
| 0.3792 | 6550 | 0.0001 | - |
| 0.3821 | 6600 | 0.0002 | - |
| 0.3850 | 6650 | 0.0079 | - |
| 0.3879 | 6700 | 0.0001 | - |
| 0.3908 | 6750 | 0.0149 | - |
| 0.3937 | 6800 | 0.0001 | - |
| 0.3965 | 6850 | 0.0071 | - |
| 0.3994 | 6900 | 0.0004 | - |
| 0.4023 | 6950 | 0.0077 | - |
| 0.4052 | 7000 | 0.0001 | - |
| 0.4081 | 7050 | 0.0075 | - |
| 0.4110 | 7100 | 0.0075 | - |
| 0.4139 | 7150 | 0.0066 | - |
| 0.4168 | 7200 | 0.0001 | - |
| 0.4197 | 7250 | 0.0001 | - |
| 0.4226 | 7300 | 0.0063 | - |
| 0.4255 | 7350 | 0.0001 | - |
| 0.4284 | 7400 | 0.0001 | - |
| 0.4313 | 7450 | 0.0133 | - |
| 0.4342 | 7500 | 0.0001 | - |
| 0.4371 | 7550 | 0.0001 | - |
| 0.4400 | 7600 | 0.0002 | - |
| 0.4429 | 7650 | 0.0005 | - |
| 0.4458 | 7700 | 0.0081 | - |
| 0.4487 | 7750 | 0.0006 | - |
| 0.4515 | 7800 | 0.0139 | - |
| 0.4544 | 7850 | 0.0012 | - |
| 0.4573 | 7900 | 0.0005 | - |
| 0.4602 | 7950 | 0.0003 | - |
| 0.4631 | 8000 | 0.0073 | - |
| 0.4660 | 8050 | 0.0002 | - |
| 0.4689 | 8100 | 0.0078 | - |
| 0.4718 | 8150 | 0.0075 | - |
| 0.4747 | 8200 | 0.0001 | - |
| 0.4776 | 8250 | 0.0077 | - |
| 0.4805 | 8300 | 0.0001 | - |
| 0.4834 | 8350 | 0.0001 | - |
| 0.4863 | 8400 | 0.0006 | - |
| 0.4892 | 8450 | 0.0002 | - |
| 0.4921 | 8500 | 0.0001 | - |
| 0.4950 | 8550 | 0.0001 | - |
| 0.4979 | 8600 | 0.0002 | - |
| 0.5008 | 8650 | 0.0001 | - |
| 0.5036 | 8700 | 0.0002 | - |
| 0.5065 | 8750 | 0.0074 | - |
| 0.5094 | 8800 | 0.0003 | - |
| 0.5123 | 8850 | 0.0001 | - |
| 0.5152 | 8900 | 0.0002 | - |
| 0.5181 | 8950 | 0.0002 | - |
| 0.5210 | 9000 | 0.0002 | - |
| 0.5239 | 9050 | 0.0008 | - |
| 0.5268 | 9100 | 0.007 | - |
| 0.5297 | 9150 | 0.0044 | - |
| 0.5326 | 9200 | 0.0131 | - |
| 0.5355 | 9250 | 0.0001 | - |
| 0.5384 | 9300 | 0.0002 | - |
| 0.5413 | 9350 | 0.0001 | - |
| 0.5442 | 9400 | 0.0071 | - |
| 0.5471 | 9450 | 0.0085 | - |
| 0.5500 | 9500 | 0.0078 | - |
| 0.5529 | 9550 | 0.0139 | - |
| 0.5557 | 9600 | 0.0 | - |
| 0.5586 | 9650 | 0.0001 | - |
| 0.5615 | 9700 | 0.0148 | - |
| 0.5644 | 9750 | 0.0001 | - |
| 0.5673 | 9800 | 0.0001 | - |
| 0.5702 | 9850 | 0.0001 | - |
| 0.5731 | 9900 | 0.0001 | - |
| 0.5760 | 9950 | 0.0001 | - |
| 0.5789 | 10000 | 0.0001 | - |
| 0.5818 | 10050 | 0.0002 | - |
| 0.5847 | 10100 | 0.0072 | - |
| 0.5876 | 10150 | 0.0078 | - |
| 0.5905 | 10200 | 0.0069 | - |
| 0.5934 | 10250 | 0.0058 | - |
| 0.5963 | 10300 | 0.0003 | - |
| 0.5992 | 10350 | 0.0001 | - |
| 0.6021 | 10400 | 0.015 | - |
| 0.6050 | 10450 | 0.0154 | - |
| 0.6078 | 10500 | 0.0075 | - |
| 0.6107 | 10550 | 0.0001 | - |
| 0.6136 | 10600 | 0.0001 | - |
| 0.6165 | 10650 | 0.0001 | - |
| 0.6194 | 10700 | 0.0004 | - |
| 0.6223 | 10750 | 0.0001 | - |
| 0.6252 | 10800 | 0.0001 | - |
| 0.6281 | 10850 | 0.0003 | - |
| 0.6310 | 10900 | 0.0001 | - |
| 0.6339 | 10950 | 0.0001 | - |
| 0.6368 | 11000 | 0.0 | - |
| 0.6397 | 11050 | 0.0081 | - |
| 0.6426 | 11100 | 0.0002 | - |
| 0.6455 | 11150 | 0.0213 | - |
| 0.6484 | 11200 | 0.0031 | - |
| 0.6513 | 11250 | 0.0159 | - |
| 0.6542 | 11300 | 0.0033 | - |
| 0.6571 | 11350 | 0.0046 | - |
| 0.6600 | 11400 | 0.0002 | - |
| 0.6628 | 11450 | 0.0001 | - |
| 0.6657 | 11500 | 0.0077 | - |
| 0.6686 | 11550 | 0.0002 | - |
| 0.6715 | 11600 | 0.0001 | - |
| 0.6744 | 11650 | 0.0073 | - |
| 0.6773 | 11700 | 0.0 | - |
| 0.6802 | 11750 | 0.0006 | - |
| 0.6831 | 11800 | 0.0 | - |
| 0.6860 | 11850 | 0.0001 | - |
| 0.6889 | 11900 | 0.0002 | - |
| 0.6918 | 11950 | 0.0001 | - |
| 0.6947 | 12000 | 0.0001 | - |
| 0.6976 | 12050 | 0.0073 | - |
| 0.7005 | 12100 | 0.0001 | - |
| 0.7034 | 12150 | 0.003 | - |
| 0.7063 | 12200 | 0.0001 | - |
| 0.7092 | 12250 | 0.0002 | - |
| 0.7121 | 12300 | 0.0002 | - |
| 0.7149 | 12350 | 0.0013 | - |
| 0.7178 | 12400 | 0.0003 | - |
| 0.7207 | 12450 | 0.0001 | - |
| 0.7236 | 12500 | 0.0003 | - |
| 0.7265 | 12550 | 0.0001 | - |
| 0.7294 | 12600 | 0.0078 | - |
| 0.7323 | 12650 | 0.0003 | - |
| 0.7352 | 12700 | 0.0001 | - |
| 0.7381 | 12750 | 0.0001 | - |
| 0.7410 | 12800 | 0.0001 | - |
| 0.7439 | 12850 | 0.0001 | - |
| 0.7468 | 12900 | 0.0073 | - |
| 0.7497 | 12950 | 0.0071 | - |
| 0.7526 | 13000 | 0.0049 | - |
| 0.7555 | 13050 | 0.0002 | - |
| 0.7584 | 13100 | 0.014 | - |
| 0.7613 | 13150 | 0.0001 | - |
| 0.7642 | 13200 | 0.0074 | - |
| 0.7670 | 13250 | 0.0002 | - |
| 0.7699 | 13300 | 0.0078 | - |
| 0.7728 | 13350 | 0.0 | - |
| 0.7757 | 13400 | 0.0003 | - |
| 0.7786 | 13450 | 0.0002 | - |
| 0.7815 | 13500 | 0.006 | - |
| 0.7844 | 13550 | 0.0001 | - |
| 0.7873 | 13600 | 0.0039 | - |
| 0.7902 | 13650 | 0.0001 | - |
| 0.7931 | 13700 | 0.0077 | - |
| 0.7960 | 13750 | 0.0003 | - |
| 0.7989 | 13800 | 0.0001 | - |
| 0.8018 | 13850 | 0.0011 | - |
| 0.8047 | 13900 | 0.0017 | - |
| 0.8076 | 13950 | 0.0003 | - |
| 0.8105 | 14000 | 0.0077 | - |
| 0.8134 | 14050 | 0.0001 | - |
| 0.8163 | 14100 | 0.013 | - |
| 0.8192 | 14150 | 0.0001 | - |
| 0.8220 | 14200 | 0.0068 | - |
| 0.8249 | 14250 | 0.0073 | - |
| 0.8278 | 14300 | 0.0086 | - |
| 0.8307 | 14350 | 0.0 | - |
| 0.8336 | 14400 | 0.0001 | - |
| 0.8365 | 14450 | 0.0001 | - |
| 0.8394 | 14500 | 0.0105 | - |
| 0.8423 | 14550 | 0.0001 | - |
| 0.8452 | 14600 | 0.0002 | - |
| 0.8481 | 14650 | 0.0001 | - |
| 0.8510 | 14700 | 0.0073 | - |
| 0.8539 | 14750 | 0.0005 | - |
| 0.8568 | 14800 | 0.0006 | - |
| 0.8597 | 14850 | 0.0001 | - |
| 0.8626 | 14900 | 0.0021 | - |
| 0.8655 | 14950 | 0.0001 | - |
| 0.8684 | 15000 | 0.0002 | - |
| 0.8713 | 15050 | 0.0002 | - |
| 0.8741 | 15100 | 0.0001 | - |
| 0.8770 | 15150 | 0.0001 | - |
| 0.8799 | 15200 | 0.0001 | - |
| 0.8828 | 15250 | 0.0002 | - |
| 0.8857 | 15300 | 0.0072 | - |
| 0.8886 | 15350 | 0.0003 | - |
| 0.8915 | 15400 | 0.0 | - |
| 0.8944 | 15450 | 0.0072 | - |
| 0.8973 | 15500 | 0.0001 | - |
| 0.9002 | 15550 | 0.0076 | - |
| 0.9031 | 15600 | 0.0001 | - |
| 0.9060 | 15650 | 0.0001 | - |
| 0.9089 | 15700 | 0.007 | - |
| 0.9118 | 15750 | 0.0002 | - |
| 0.9147 | 15800 | 0.0007 | - |
| 0.9176 | 15850 | 0.0005 | - |
| 0.9205 | 15900 | 0.0004 | - |
| 0.9234 | 15950 | 0.0001 | - |
| 0.9262 | 16000 | 0.0001 | - |
| 0.9291 | 16050 | 0.0003 | - |
| 0.9320 | 16100 | 0.0053 | - |
| 0.9349 | 16150 | 0.0 | - |
| 0.9378 | 16200 | 0.0001 | - |
| 0.9407 | 16250 | 0.0001 | - |
| 0.9436 | 16300 | 0.0067 | - |
| 0.9465 | 16350 | 0.0002 | - |
| 0.9494 | 16400 | 0.0045 | - |
| 0.9523 | 16450 | 0.0015 | - |
| 0.9552 | 16500 | 0.0001 | - |
| 0.9581 | 16550 | 0.0001 | - |
| 0.9610 | 16600 | 0.0002 | - |
| 0.9639 | 16650 | 0.0004 | - |
| 0.9668 | 16700 | 0.0001 | - |
| 0.9697 | 16750 | 0.0001 | - |
| 0.9726 | 16800 | 0.0002 | - |
| 0.9755 | 16850 | 0.0001 | - |
| 0.9783 | 16900 | 0.0074 | - |
| 0.9812 | 16950 | 0.0005 | - |
| 0.9841 | 17000 | 0.0 | - |
| 0.9870 | 17050 | 0.0002 | - |
| 0.9899 | 17100 | 0.0001 | - |
| 0.9928 | 17150 | 0.0001 | - |
| 0.9957 | 17200 | 0.0006 | - |
| 0.9986 | 17250 | 0.0 | - |
| **1.0** | **17274** | **-** | **0.0243** |
| 1.0015 | 17300 | 0.0002 | - |
| 1.0044 | 17350 | 0.0002 | - |
| 1.0073 | 17400 | 0.0 | - |
| 1.0102 | 17450 | 0.0001 | - |
| 1.0131 | 17500 | 0.0001 | - |
| 1.0160 | 17550 | 0.0 | - |
| 1.0189 | 17600 | 0.0008 | - |
| 1.0218 | 17650 | 0.0042 | - |
| 1.0247 | 17700 | 0.0014 | - |
| 1.0276 | 17750 | 0.0 | - |
| 1.0305 | 17800 | 0.0077 | - |
| 1.0333 | 17850 | 0.0076 | - |
| 1.0362 | 17900 | 0.0004 | - |
| 1.0391 | 17950 | 0.0072 | - |
| 1.0420 | 18000 | 0.0 | - |
| 1.0449 | 18050 | 0.0076 | - |
| 1.0478 | 18100 | 0.0 | - |
| 1.0507 | 18150 | 0.0 | - |
| 1.0536 | 18200 | 0.0001 | - |
| 1.0565 | 18250 | 0.0 | - |
| 1.0594 | 18300 | 0.0 | - |
| 1.0623 | 18350 | 0.0001 | - |
| 1.0652 | 18400 | 0.0 | - |
| 1.0681 | 18450 | 0.0 | - |
| 1.0710 | 18500 | 0.0 | - |
| 1.0739 | 18550 | 0.0001 | - |
| 1.0768 | 18600 | 0.0075 | - |
| 1.0797 | 18650 | 0.0002 | - |
| 1.0826 | 18700 | 0.0 | - |
| 1.0854 | 18750 | 0.0001 | - |
| 1.0883 | 18800 | 0.0007 | - |
| 1.0912 | 18850 | 0.0 | - |
| 1.0941 | 18900 | 0.0 | - |
| 1.0970 | 18950 | 0.0 | - |
| 1.0999 | 19000 | 0.0 | - |
| 1.1028 | 19050 | 0.0 | - |
| 1.1057 | 19100 | 0.0 | - |
| 1.1086 | 19150 | 0.0001 | - |
| 1.1115 | 19200 | 0.0 | - |
| 1.1144 | 19250 | 0.0 | - |
| 1.1173 | 19300 | 0.0047 | - |
| 1.1202 | 19350 | 0.0001 | - |
| 1.1231 | 19400 | 0.0 | - |
| 1.1260 | 19450 | 0.0 | - |
| 1.1289 | 19500 | 0.0 | - |
| 1.1318 | 19550 | 0.0 | - |
| 1.1347 | 19600 | 0.0 | - |
| 1.1375 | 19650 | 0.0003 | - |
| 1.1404 | 19700 | 0.0033 | - |
| 1.1433 | 19750 | 0.0001 | - |
| 1.1462 | 19800 | 0.0003 | - |
| 1.1491 | 19850 | 0.0001 | - |
| 1.1520 | 19900 | 0.0001 | - |
| 1.1549 | 19950 | 0.0003 | - |
| 1.1578 | 20000 | 0.0009 | - |
| 1.1607 | 20050 | 0.0008 | - |
| 1.1636 | 20100 | 0.0001 | - |
| 1.1665 | 20150 | 0.0 | - |
| 1.1694 | 20200 | 0.0001 | - |
| 1.1723 | 20250 | 0.0 | - |
| 1.1752 | 20300 | 0.0004 | - |
| 1.1781 | 20350 | 0.0001 | - |
| 1.1810 | 20400 | 0.0004 | - |
| 1.1839 | 20450 | 0.0001 | - |
| 1.1868 | 20500 | 0.0001 | - |
| 1.1896 | 20550 | 0.0001 | - |
| 1.1925 | 20600 | 0.0001 | - |
| 1.1954 | 20650 | 0.0001 | - |
| 1.1983 | 20700 | 0.0001 | - |
| 1.2012 | 20750 | 0.0003 | - |
| 1.2041 | 20800 | 0.0002 | - |
| 1.2070 | 20850 | 0.0 | - |
| 1.2099 | 20900 | 0.0001 | - |
| 1.2128 | 20950 | 0.0001 | - |
| 1.2157 | 21000 | 0.0004 | - |
| 1.2186 | 21050 | 0.0 | - |
| 1.2215 | 21100 | 0.0 | - |
| 1.2244 | 21150 | 0.0001 | - |
| 1.2273 | 21200 | 0.0 | - |
| 1.2302 | 21250 | 0.0018 | - |
| 1.2331 | 21300 | 0.007 | - |
| 1.2360 | 21350 | 0.0 | - |
| 1.2389 | 21400 | 0.0001 | - |
| 1.2418 | 21450 | 0.0005 | - |
| 1.2446 | 21500 | 0.0024 | - |
| 1.2475 | 21550 | 0.0 | - |
| 1.2504 | 21600 | 0.0001 | - |
| 1.2533 | 21650 | 0.0 | - |
| 1.2562 | 21700 | 0.0001 | - |
| 1.2591 | 21750 | 0.0 | - |
| 1.2620 | 21800 | 0.0001 | - |
| 1.2649 | 21850 | 0.0 | - |
| 1.2678 | 21900 | 0.0003 | - |
| 1.2707 | 21950 | 0.0001 | - |
| 1.2736 | 22000 | 0.0002 | - |
| 1.2765 | 22050 | 0.0001 | - |
| 1.2794 | 22100 | 0.0 | - |
| 1.2823 | 22150 | 0.0 | - |
| 1.2852 | 22200 | 0.0 | - |
| 1.2881 | 22250 | 0.0 | - |
| 1.2910 | 22300 | 0.0 | - |
| 1.2939 | 22350 | 0.0 | - |
| 1.2967 | 22400 | 0.0 | - |
| 1.2996 | 22450 | 0.0076 | - |
| 1.3025 | 22500 | 0.0001 | - |
| 1.3054 | 22550 | 0.0001 | - |
| 1.3083 | 22600 | 0.0005 | - |
| 1.3112 | 22650 | 0.0 | - |
| 1.3141 | 22700 | 0.0001 | - |
| 1.3170 | 22750 | 0.0 | - |
| 1.3199 | 22800 | 0.0002 | - |
| 1.3228 | 22850 | 0.0 | - |
| 1.3257 | 22900 | 0.0 | - |
| 1.3286 | 22950 | 0.0 | - |
| 1.3315 | 23000 | 0.0001 | - |
| 1.3344 | 23050 | 0.0 | - |
| 1.3373 | 23100 | 0.0 | - |
| 1.3402 | 23150 | 0.0 | - |
| 1.3431 | 23200 | 0.0002 | - |
| 1.3460 | 23250 | 0.0002 | - |
| 1.3488 | 23300 | 0.0002 | - |
| 1.3517 | 23350 | 0.0001 | - |
| 1.3546 | 23400 | 0.0 | - |
| 1.3575 | 23450 | 0.0 | - |
| 1.3604 | 23500 | 0.0 | - |
| 1.3633 | 23550 | 0.0001 | - |
| 1.3662 | 23600 | 0.0078 | - |
| 1.3691 | 23650 | 0.0 | - |
| 1.3720 | 23700 | 0.0011 | - |
| 1.3749 | 23750 | 0.0003 | - |
| 1.3778 | 23800 | 0.0 | - |
| 1.3807 | 23850 | 0.0 | - |
| 1.3836 | 23900 | 0.0 | - |
| 1.3865 | 23950 | 0.0025 | - |
| 1.3894 | 24000 | 0.0 | - |
| 1.3923 | 24050 | 0.0 | - |
| 1.3952 | 24100 | 0.0056 | - |
| 1.3981 | 24150 | 0.0 | - |
| 1.4009 | 24200 | 0.0 | - |
| 1.4038 | 24250 | 0.0 | - |
| 1.4067 | 24300 | 0.0003 | - |
| 1.4096 | 24350 | 0.0 | - |
| 1.4125 | 24400 | 0.0 | - |
| 1.4154 | 24450 | 0.0 | - |
| 1.4183 | 24500 | 0.0 | - |
| 1.4212 | 24550 | 0.0054 | - |
| 1.4241 | 24600 | 0.0001 | - |
| 1.4270 | 24650 | 0.0 | - |
| 1.4299 | 24700 | 0.0 | - |
| 1.4328 | 24750 | 0.0 | - |
| 1.4357 | 24800 | 0.0 | - |
| 1.4386 | 24850 | 0.0001 | - |
| 1.4415 | 24900 | 0.0 | - |
| 1.4444 | 24950 | 0.0 | - |
| 1.4473 | 25000 | 0.0 | - |
| 1.4502 | 25050 | 0.0 | - |
| 1.4531 | 25100 | 0.0001 | - |
| 1.4559 | 25150 | 0.0 | - |
| 1.4588 | 25200 | 0.0 | - |
| 1.4617 | 25250 | 0.0 | - |
| 1.4646 | 25300 | 0.0008 | - |
| 1.4675 | 25350 | 0.0003 | - |
| 1.4704 | 25400 | 0.0 | - |
| 1.4733 | 25450 | 0.0 | - |
| 1.4762 | 25500 | 0.0 | - |
| 1.4791 | 25550 | 0.0008 | - |
| 1.4820 | 25600 | 0.0 | - |
| 1.4849 | 25650 | 0.0001 | - |
| 1.4878 | 25700 | 0.0 | - |
| 1.4907 | 25750 | 0.0 | - |
| 1.4936 | 25800 | 0.0 | - |
| 1.4965 | 25850 | 0.0 | - |
| 1.4994 | 25900 | 0.0 | - |
| 1.5023 | 25950 | 0.0 | - |
| 1.5052 | 26000 | 0.0001 | - |
| 1.5080 | 26050 | 0.0 | - |
| 1.5109 | 26100 | 0.0006 | - |
| 1.5138 | 26150 | 0.0 | - |
| 1.5167 | 26200 | 0.0 | - |
| 1.5196 | 26250 | 0.0 | - |
| 1.5225 | 26300 | 0.0 | - |
| 1.5254 | 26350 | 0.0 | - |
| 1.5283 | 26400 | 0.0 | - |
| 1.5312 | 26450 | 0.0 | - |
| 1.5341 | 26500 | 0.0 | - |
| 1.5370 | 26550 | 0.0 | - |
| 1.5399 | 26600 | 0.0 | - |
| 1.5428 | 26650 | 0.0 | - |
| 1.5457 | 26700 | 0.0001 | - |
| 1.5486 | 26750 | 0.0 | - |
| 1.5515 | 26800 | 0.0 | - |
| 1.5544 | 26850 | 0.0 | - |
| 1.5573 | 26900 | 0.0 | - |
| 1.5601 | 26950 | 0.0 | - |
| 1.5630 | 27000 | 0.0 | - |
| 1.5659 | 27050 | 0.0 | - |
| 1.5688 | 27100 | 0.0 | - |
| 1.5717 | 27150 | 0.001 | - |
| 1.5746 | 27200 | 0.0008 | - |
| 1.5775 | 27250 | 0.0021 | - |
| 1.5804 | 27300 | 0.0001 | - |
| 1.5833 | 27350 | 0.0 | - |
| 1.5862 | 27400 | 0.0 | - |
| 1.5891 | 27450 | 0.0 | - |
| 1.5920 | 27500 | 0.0 | - |
| 1.5949 | 27550 | 0.0 | - |
| 1.5978 | 27600 | 0.0 | - |
| 1.6007 | 27650 | 0.0006 | - |
| 1.6036 | 27700 | 0.0 | - |
| 1.6065 | 27750 | 0.0 | - |
| 1.6094 | 27800 | 0.0002 | - |
| 1.6122 | 27850 | 0.0 | - |
| 1.6151 | 27900 | 0.0 | - |
| 1.6180 | 27950 | 0.0 | - |
| 1.6209 | 28000 | 0.0 | - |
| 1.6238 | 28050 | 0.0 | - |
| 1.6267 | 28100 | 0.0 | - |
| 1.6296 | 28150 | 0.0 | - |
| 1.6325 | 28200 | 0.0 | - |
| 1.6354 | 28250 | 0.0 | - |
| 1.6383 | 28300 | 0.0 | - |
| 1.6412 | 28350 | 0.0 | - |
| 1.6441 | 28400 | 0.0 | - |
| 1.6470 | 28450 | 0.0 | - |
| 1.6499 | 28500 | 0.0 | - |
| 1.6528 | 28550 | 0.0 | - |
| 1.6557 | 28600 | 0.0 | - |
| 1.6586 | 28650 | 0.0 | - |
| 1.6615 | 28700 | 0.0 | - |
| 1.6644 | 28750 | 0.0 | - |
| 1.6672 | 28800 | 0.0 | - |
| 1.6701 | 28850 | 0.0 | - |
| 1.6730 | 28900 | 0.0 | - |
| 1.6759 | 28950 | 0.0 | - |
| 1.6788 | 29000 | 0.0 | - |
| 1.6817 | 29050 | 0.0 | - |
| 1.6846 | 29100 | 0.0 | - |
| 1.6875 | 29150 | 0.0 | - |
| 1.6904 | 29200 | 0.0 | - |
| 1.6933 | 29250 | 0.0 | - |
| 1.6962 | 29300 | 0.0 | - |
| 1.6991 | 29350 | 0.0 | - |
| 1.7020 | 29400 | 0.0 | - |
| 1.7049 | 29450 | 0.0 | - |
| 1.7078 | 29500 | 0.0 | - |
| 1.7107 | 29550 | 0.0 | - |
| 1.7136 | 29600 | 0.0 | - |
| 1.7165 | 29650 | 0.0 | - |
| 1.7193 | 29700 | 0.0 | - |
| 1.7222 | 29750 | 0.0 | - |
| 1.7251 | 29800 | 0.0 | - |
| 1.7280 | 29850 | 0.0 | - |
| 1.7309 | 29900 | 0.0 | - |
| 1.7338 | 29950 | 0.0 | - |
| 1.7367 | 30000 | 0.0 | - |
| 1.7396 | 30050 | 0.0 | - |
| 1.7425 | 30100 | 0.0 | - |
| 1.7454 | 30150 | 0.0 | - |
| 1.7483 | 30200 | 0.0 | - |
| 1.7512 | 30250 | 0.0 | - |
| 1.7541 | 30300 | 0.0 | - |
| 1.7570 | 30350 | 0.0 | - |
| 1.7599 | 30400 | 0.0 | - |
| 1.7628 | 30450 | 0.0 | - |
| 1.7657 | 30500 | 0.0 | - |
| 1.7686 | 30550 | 0.0 | - |
| 1.7714 | 30600 | 0.0 | - |
| 1.7743 | 30650 | 0.0 | - |
| 1.7772 | 30700 | 0.0 | - |
| 1.7801 | 30750 | 0.0 | - |
| 1.7830 | 30800 | 0.0 | - |
| 1.7859 | 30850 | 0.0 | - |
| 1.7888 | 30900 | 0.0 | - |
| 1.7917 | 30950 | 0.0 | - |
| 1.7946 | 31000 | 0.0 | - |
| 1.7975 | 31050 | 0.0 | - |
| 1.8004 | 31100 | 0.0 | - |
| 1.8033 | 31150 | 0.0 | - |
| 1.8062 | 31200 | 0.0 | - |
| 1.8091 | 31250 | 0.0 | - |
| 1.8120 | 31300 | 0.0 | - |
| 1.8149 | 31350 | 0.0 | - |
| 1.8178 | 31400 | 0.0 | - |
| 1.8207 | 31450 | 0.0 | - |
| 1.8235 | 31500 | 0.0 | - |
| 1.8264 | 31550 | 0.0 | - |
| 1.8293 | 31600 | 0.0 | - |
| 1.8322 | 31650 | 0.0 | - |
| 1.8351 | 31700 | 0.0 | - |
| 1.8380 | 31750 | 0.0 | - |
| 1.8409 | 31800 | 0.0 | - |
| 1.8438 | 31850 | 0.0 | - |
| 1.8467 | 31900 | 0.0 | - |
| 1.8496 | 31950 | 0.0 | - |
| 1.8525 | 32000 | 0.0 | - |
| 1.8554 | 32050 | 0.0 | - |
| 1.8583 | 32100 | 0.0 | - |
| 1.8612 | 32150 | 0.0 | - |
| 1.8641 | 32200 | 0.0 | - |
| 1.8670 | 32250 | 0.0 | - |
| 1.8699 | 32300 | 0.0 | - |
| 1.8728 | 32350 | 0.0 | - |
| 1.8757 | 32400 | 0.0 | - |
| 1.8785 | 32450 | 0.0 | - |
| 1.8814 | 32500 | 0.0001 | - |
| 1.8843 | 32550 | 0.0 | - |
| 1.8872 | 32600 | 0.0 | - |
| 1.8901 | 32650 | 0.0 | - |
| 1.8930 | 32700 | 0.0001 | - |
| 1.8959 | 32750 | 0.0 | - |
| 1.8988 | 32800 | 0.0 | - |
| 1.9017 | 32850 | 0.0 | - |
| 1.9046 | 32900 | 0.0 | - |
| 1.9075 | 32950 | 0.0 | - |
| 1.9104 | 33000 | 0.0053 | - |
| 1.9133 | 33050 | 0.0049 | - |
| 1.9162 | 33100 | 0.0001 | - |
| 1.9191 | 33150 | 0.0 | - |
| 1.9220 | 33200 | 0.0003 | - |
| 1.9249 | 33250 | 0.0 | - |
| 1.9278 | 33300 | 0.0 | - |
| 1.9306 | 33350 | 0.0 | - |
| 1.9335 | 33400 | 0.0001 | - |
| 1.9364 | 33450 | 0.0 | - |
| 1.9393 | 33500 | 0.0 | - |
| 1.9422 | 33550 | 0.0 | - |
| 1.9451 | 33600 | 0.0 | - |
| 1.9480 | 33650 | 0.0 | - |
| 1.9509 | 33700 | 0.0 | - |
| 1.9538 | 33750 | 0.0001 | - |
| 1.9567 | 33800 | 0.0 | - |
| 1.9596 | 33850 | 0.0 | - |
| 1.9625 | 33900 | 0.0077 | - |
| 1.9654 | 33950 | 0.0 | - |
| 1.9683 | 34000 | 0.0 | - |
| 1.9712 | 34050 | 0.0 | - |
| 1.9741 | 34100 | 0.0 | - |
| 1.9770 | 34150 | 0.0075 | - |
| 1.9799 | 34200 | 0.0002 | - |
| 1.9827 | 34250 | 0.0 | - |
| 1.9856 | 34300 | 0.0 | - |
| 1.9885 | 34350 | 0.0 | - |
| 1.9914 | 34400 | 0.0 | - |
| 1.9943 | 34450 | 0.0 | - |
| 1.9972 | 34500 | 0.0001 | - |
| 2.0 | 34548 | - | 0.0412 |
| 2.0001 | 34550 | 0.0 | - |
| 2.0030 | 34600 | 0.0 | - |
| 2.0059 | 34650 | 0.0 | - |
| 2.0088 | 34700 | 0.0 | - |
| 2.0117 | 34750 | 0.0 | - |
| 2.0146 | 34800 | 0.0 | - |
| 2.0175 | 34850 | 0.0001 | - |
| 2.0204 | 34900 | 0.0 | - |
| 2.0233 | 34950 | 0.0 | - |
| 2.0262 | 35000 | 0.0 | - |
| 2.0291 | 35050 | 0.0 | - |
| 2.0320 | 35100 | 0.0 | - |
| 2.0349 | 35150 | 0.0 | - |
| 2.0377 | 35200 | 0.0001 | - |
| 2.0406 | 35250 | 0.0 | - |
| 2.0435 | 35300 | 0.0 | - |
| 2.0464 | 35350 | 0.0 | - |
| 2.0493 | 35400 | 0.0 | - |
| 2.0522 | 35450 | 0.0 | - |
| 2.0551 | 35500 | 0.0 | - |
| 2.0580 | 35550 | 0.0 | - |
| 2.0609 | 35600 | 0.0 | - |
| 2.0638 | 35650 | 0.0 | - |
| 2.0667 | 35700 | 0.0065 | - |
| 2.0696 | 35750 | 0.0 | - |
| 2.0725 | 35800 | 0.0 | - |
| 2.0754 | 35850 | 0.0 | - |
| 2.0783 | 35900 | 0.0 | - |
| 2.0812 | 35950 | 0.0 | - |
| 2.0841 | 36000 | 0.0 | - |
| 2.0870 | 36050 | 0.0 | - |
| 2.0898 | 36100 | 0.0 | - |
| 2.0927 | 36150 | 0.0 | - |
| 2.0956 | 36200 | 0.0 | - |
| 2.0985 | 36250 | 0.0 | - |
| 2.1014 | 36300 | 0.0 | - |
| 2.1043 | 36350 | 0.0 | - |
| 2.1072 | 36400 | 0.0 | - |
| 2.1101 | 36450 | 0.0 | - |
| 2.1130 | 36500 | 0.0 | - |
| 2.1159 | 36550 | 0.0 | - |
| 2.1188 | 36600 | 0.0 | - |
| 2.1217 | 36650 | 0.0 | - |
| 2.1246 | 36700 | 0.0 | - |
| 2.1275 | 36750 | 0.0 | - |
| 2.1304 | 36800 | 0.0 | - |
| 2.1333 | 36850 | 0.0 | - |
| 2.1362 | 36900 | 0.0 | - |
| 2.1391 | 36950 | 0.0002 | - |
| 2.1419 | 37000 | 0.0001 | - |
| 2.1448 | 37050 | 0.0 | - |
| 2.1477 | 37100 | 0.0001 | - |
| 2.1506 | 37150 | 0.0068 | - |
| 2.1535 | 37200 | 0.0001 | - |
| 2.1564 | 37250 | 0.0 | - |
| 2.1593 | 37300 | 0.0 | - |
| 2.1622 | 37350 | 0.0 | - |
| 2.1651 | 37400 | 0.0 | - |
| 2.1680 | 37450 | 0.0 | - |
| 2.1709 | 37500 | 0.0 | - |
| 2.1738 | 37550 | 0.0 | - |
| 2.1767 | 37600 | 0.0 | - |
| 2.1796 | 37650 | 0.0 | - |
| 2.1825 | 37700 | 0.0 | - |
| 2.1854 | 37750 | 0.0 | - |
| 2.1883 | 37800 | 0.0 | - |
| 2.1912 | 37850 | 0.0 | - |
| 2.1940 | 37900 | 0.0 | - |
| 2.1969 | 37950 | 0.0 | - |
| 2.1998 | 38000 | 0.0 | - |
| 2.2027 | 38050 | 0.0 | - |
| 2.2056 | 38100 | 0.0 | - |
| 2.2085 | 38150 | 0.0 | - |
| 2.2114 | 38200 | 0.0 | - |
| 2.2143 | 38250 | 0.0 | - |
| 2.2172 | 38300 | 0.0 | - |
| 2.2201 | 38350 | 0.0 | - |
| 2.2230 | 38400 | 0.0 | - |
| 2.2259 | 38450 | 0.0 | - |
| 2.2288 | 38500 | 0.0 | - |
| 2.2317 | 38550 | 0.0 | - |
| 2.2346 | 38600 | 0.0 | - |
| 2.2375 | 38650 | 0.0 | - |
| 2.2404 | 38700 | 0.0 | - |
| 2.2433 | 38750 | 0.0 | - |
| 2.2462 | 38800 | 0.0 | - |
| 2.2490 | 38850 | 0.0078 | - |
| 2.2519 | 38900 | 0.0 | - |
| 2.2548 | 38950 | 0.013 | - |
| 2.2577 | 39000 | 0.0 | - |
| 2.2606 | 39050 | 0.0 | - |
| 2.2635 | 39100 | 0.0 | - |
| 2.2664 | 39150 | 0.0077 | - |
| 2.2693 | 39200 | 0.0005 | - |
| 2.2722 | 39250 | 0.0 | - |
| 2.2751 | 39300 | 0.0 | - |
| 2.2780 | 39350 | 0.0 | - |
| 2.2809 | 39400 | 0.0 | - |
| 2.2838 | 39450 | 0.0 | - |
| 2.2867 | 39500 | 0.0 | - |
| 2.2896 | 39550 | 0.0 | - |
| 2.2925 | 39600 | 0.0 | - |
| 2.2954 | 39650 | 0.0 | - |
| 2.2983 | 39700 | 0.0 | - |
| 2.3011 | 39750 | 0.0 | - |
| 2.3040 | 39800 | 0.0001 | - |
| 2.3069 | 39850 | 0.0 | - |
| 2.3098 | 39900 | 0.0001 | - |
| 2.3127 | 39950 | 0.0001 | - |
| 2.3156 | 40000 | 0.0 | - |
| 2.3185 | 40050 | 0.0 | - |
| 2.3214 | 40100 | 0.0 | - |
| 2.3243 | 40150 | 0.0 | - |
| 2.3272 | 40200 | 0.0 | - |
| 2.3301 | 40250 | 0.0 | - |
| 2.3330 | 40300 | 0.0 | - |
| 2.3359 | 40350 | 0.0001 | - |
| 2.3388 | 40400 | 0.0 | - |
| 2.3417 | 40450 | 0.0001 | - |
| 2.3446 | 40500 | 0.0 | - |
| 2.3475 | 40550 | 0.0 | - |
| 2.3504 | 40600 | 0.0 | - |
| 2.3532 | 40650 | 0.0 | - |
| 2.3561 | 40700 | 0.0 | - |
| 2.3590 | 40750 | 0.0004 | - |
| 2.3619 | 40800 | 0.0 | - |
| 2.3648 | 40850 | 0.0 | - |
| 2.3677 | 40900 | 0.0 | - |
| 2.3706 | 40950 | 0.0 | - |
| 2.3735 | 41000 | 0.0 | - |
| 2.3764 | 41050 | 0.0 | - |
| 2.3793 | 41100 | 0.0 | - |
| 2.3822 | 41150 | 0.0 | - |
| 2.3851 | 41200 | 0.0 | - |
| 2.3880 | 41250 | 0.0 | - |
| 2.3909 | 41300 | 0.0 | - |
| 2.3938 | 41350 | 0.0 | - |
| 2.3967 | 41400 | 0.0 | - |
| 2.3996 | 41450 | 0.0 | - |
| 2.4025 | 41500 | 0.0 | - |
| 2.4053 | 41550 | 0.0 | - |
| 2.4082 | 41600 | 0.0 | - |
| 2.4111 | 41650 | 0.0 | - |
| 2.4140 | 41700 | 0.0 | - |
| 2.4169 | 41750 | 0.0 | - |
| 2.4198 | 41800 | 0.0 | - |
| 2.4227 | 41850 | 0.0 | - |
| 2.4256 | 41900 | 0.0 | - |
| 2.4285 | 41950 | 0.0 | - |
| 2.4314 | 42000 | 0.0 | - |
| 2.4343 | 42050 | 0.0001 | - |
| 2.4372 | 42100 | 0.0 | - |
| 2.4401 | 42150 | 0.0 | - |
| 2.4430 | 42200 | 0.0 | - |
| 2.4459 | 42250 | 0.0 | - |
| 2.4488 | 42300 | 0.0 | - |
| 2.4517 | 42350 | 0.0 | - |
| 2.4546 | 42400 | 0.0 | - |
| 2.4575 | 42450 | 0.0 | - |
| 2.4603 | 42500 | 0.0 | - |
| 2.4632 | 42550 | 0.0 | - |
| 2.4661 | 42600 | 0.0001 | - |
| 2.4690 | 42650 | 0.0002 | - |
| 2.4719 | 42700 | 0.0 | - |
| 2.4748 | 42750 | 0.0 | - |
| 2.4777 | 42800 | 0.0 | - |
| 2.4806 | 42850 | 0.0 | - |
| 2.4835 | 42900 | 0.0 | - |
| 2.4864 | 42950 | 0.0 | - |
| 2.4893 | 43000 | 0.0 | - |
| 2.4922 | 43050 | 0.0 | - |
| 2.4951 | 43100 | 0.0 | - |
| 2.4980 | 43150 | 0.0 | - |
| 2.5009 | 43200 | 0.0 | - |
| 2.5038 | 43250 | 0.0 | - |
| 2.5067 | 43300 | 0.0 | - |
| 2.5096 | 43350 | 0.0 | - |
| 2.5124 | 43400 | 0.0 | - |
| 2.5153 | 43450 | 0.0 | - |
| 2.5182 | 43500 | 0.0 | - |
| 2.5211 | 43550 | 0.0 | - |
| 2.5240 | 43600 | 0.0 | - |
| 2.5269 | 43650 | 0.0 | - |
| 2.5298 | 43700 | 0.0 | - |
| 2.5327 | 43750 | 0.0 | - |
| 2.5356 | 43800 | 0.0 | - |
| 2.5385 | 43850 | 0.0 | - |
| 2.5414 | 43900 | 0.0 | - |
| 2.5443 | 43950 | 0.0 | - |
| 2.5472 | 44000 | 0.0 | - |
| 2.5501 | 44050 | 0.0 | - |
| 2.5530 | 44100 | 0.0017 | - |
| 2.5559 | 44150 | 0.0 | - |
| 2.5588 | 44200 | 0.0 | - |
| 2.5617 | 44250 | 0.0 | - |
| 2.5645 | 44300 | 0.0 | - |
| 2.5674 | 44350 | 0.0003 | - |
| 2.5703 | 44400 | 0.0 | - |
| 2.5732 | 44450 | 0.0 | - |
| 2.5761 | 44500 | 0.0 | - |
| 2.5790 | 44550 | 0.0 | - |
| 2.5819 | 44600 | 0.0 | - |
| 2.5848 | 44650 | 0.0 | - |
| 2.5877 | 44700 | 0.0 | - |
| 2.5906 | 44750 | 0.0 | - |
| 2.5935 | 44800 | 0.0 | - |
| 2.5964 | 44850 | 0.0 | - |
| 2.5993 | 44900 | 0.0 | - |
| 2.6022 | 44950 | 0.0 | - |
| 2.6051 | 45000 | 0.0 | - |
| 2.6080 | 45050 | 0.0 | - |
| 2.6109 | 45100 | 0.0 | - |
| 2.6138 | 45150 | 0.0 | - |
| 2.6166 | 45200 | 0.0 | - |
| 2.6195 | 45250 | 0.0 | - |
| 2.6224 | 45300 | 0.0 | - |
| 2.6253 | 45350 | 0.0 | - |
| 2.6282 | 45400 | 0.0 | - |
| 2.6311 | 45450 | 0.0 | - |
| 2.6340 | 45500 | 0.0 | - |
| 2.6369 | 45550 | 0.0 | - |
| 2.6398 | 45600 | 0.0 | - |
| 2.6427 | 45650 | 0.0 | - |
| 2.6456 | 45700 | 0.0 | - |
| 2.6485 | 45750 | 0.0 | - |
| 2.6514 | 45800 | 0.0 | - |
| 2.6543 | 45850 | 0.0 | - |
| 2.6572 | 45900 | 0.0 | - |
| 2.6601 | 45950 | 0.0 | - |
| 2.6630 | 46000 | 0.0 | - |
| 2.6659 | 46050 | 0.0 | - |
| 2.6688 | 46100 | 0.0 | - |
| 2.6716 | 46150 | 0.0 | - |
| 2.6745 | 46200 | 0.0 | - |
| 2.6774 | 46250 | 0.0 | - |
| 2.6803 | 46300 | 0.0 | - |
| 2.6832 | 46350 | 0.0 | - |
| 2.6861 | 46400 | 0.0 | - |
| 2.6890 | 46450 | 0.0 | - |
| 2.6919 | 46500 | 0.0 | - |
| 2.6948 | 46550 | 0.0 | - |
| 2.6977 | 46600 | 0.0 | - |
| 2.7006 | 46650 | 0.0 | - |
| 2.7035 | 46700 | 0.0 | - |
| 2.7064 | 46750 | 0.0 | - |
| 2.7093 | 46800 | 0.0 | - |
| 2.7122 | 46850 | 0.0 | - |
| 2.7151 | 46900 | 0.0 | - |
| 2.7180 | 46950 | 0.0 | - |
| 2.7209 | 47000 | 0.0 | - |
| 2.7237 | 47050 | 0.0 | - |
| 2.7266 | 47100 | 0.0 | - |
| 2.7295 | 47150 | 0.0 | - |
| 2.7324 | 47200 | 0.0 | - |
| 2.7353 | 47250 | 0.0 | - |
| 2.7382 | 47300 | 0.0 | - |
| 2.7411 | 47350 | 0.0 | - |
| 2.7440 | 47400 | 0.0 | - |
| 2.7469 | 47450 | 0.0 | - |
| 2.7498 | 47500 | 0.0 | - |
| 2.7527 | 47550 | 0.0 | - |
| 2.7556 | 47600 | 0.0 | - |
| 2.7585 | 47650 | 0.0 | - |
| 2.7614 | 47700 | 0.0 | - |
| 2.7643 | 47750 | 0.0 | - |
| 2.7672 | 47800 | 0.0 | - |
| 2.7701 | 47850 | 0.0 | - |
| 2.7730 | 47900 | 0.0 | - |
| 2.7758 | 47950 | 0.0 | - |
| 2.7787 | 48000 | 0.0 | - |
| 2.7816 | 48050 | 0.0 | - |
| 2.7845 | 48100 | 0.0 | - |
| 2.7874 | 48150 | 0.0 | - |
| 2.7903 | 48200 | 0.0 | - |
| 2.7932 | 48250 | 0.0 | - |
| 2.7961 | 48300 | 0.0 | - |
| 2.7990 | 48350 | 0.0 | - |
| 2.8019 | 48400 | 0.0 | - |
| 2.8048 | 48450 | 0.0 | - |
| 2.8077 | 48500 | 0.0 | - |
| 2.8106 | 48550 | 0.0 | - |
| 2.8135 | 48600 | 0.0 | - |
| 2.8164 | 48650 | 0.0 | - |
| 2.8193 | 48700 | 0.0 | - |
| 2.8222 | 48750 | 0.0 | - |
| 2.8251 | 48800 | 0.0002 | - |
| 2.8279 | 48850 | 0.0006 | - |
| 2.8308 | 48900 | 0.0 | - |
| 2.8337 | 48950 | 0.0 | - |
| 2.8366 | 49000 | 0.0001 | - |
| 2.8395 | 49050 | 0.0 | - |
| 2.8424 | 49100 | 0.0 | - |
| 2.8453 | 49150 | 0.0 | - |
| 2.8482 | 49200 | 0.0 | - |
| 2.8511 | 49250 | 0.0 | - |
| 2.8540 | 49300 | 0.0 | - |
| 2.8569 | 49350 | 0.0 | - |
| 2.8598 | 49400 | 0.0 | - |
| 2.8627 | 49450 | 0.0 | - |
| 2.8656 | 49500 | 0.0 | - |
| 2.8685 | 49550 | 0.0 | - |
| 2.8714 | 49600 | 0.0 | - |
| 2.8743 | 49650 | 0.0 | - |
| 2.8772 | 49700 | 0.0 | - |
| 2.8801 | 49750 | 0.0 | - |
| 2.8829 | 49800 | 0.0 | - |
| 2.8858 | 49850 | 0.0 | - |
| 2.8887 | 49900 | 0.0 | - |
| 2.8916 | 49950 | 0.0 | - |
| 2.8945 | 50000 | 0.0 | - |
| 2.8974 | 50050 | 0.0 | - |
| 2.9003 | 50100 | 0.0 | - |
| 2.9032 | 50150 | 0.0043 | - |
| 2.9061 | 50200 | 0.0 | - |
| 2.9090 | 50250 | 0.0 | - |
| 2.9119 | 50300 | 0.0001 | - |
| 2.9148 | 50350 | 0.0 | - |
| 2.9177 | 50400 | 0.0 | - |
| 2.9206 | 50450 | 0.0 | - |
| 2.9235 | 50500 | 0.0 | - |
| 2.9264 | 50550 | 0.0 | - |
| 2.9293 | 50600 | 0.0 | - |
| 2.9322 | 50650 | 0.0 | - |
| 2.9350 | 50700 | 0.0 | - |
| 2.9379 | 50750 | 0.0 | - |
| 2.9408 | 50800 | 0.0 | - |
| 2.9437 | 50850 | 0.0 | - |
| 2.9466 | 50900 | 0.0 | - |
| 2.9495 | 50950 | 0.0 | - |
| 2.9524 | 51000 | 0.0 | - |
| 2.9553 | 51050 | 0.0 | - |
| 2.9582 | 51100 | 0.0 | - |
| 2.9611 | 51150 | 0.0 | - |
| 2.9640 | 51200 | 0.0 | - |
| 2.9669 | 51250 | 0.0 | - |
| 2.9698 | 51300 | 0.0 | - |
| 2.9727 | 51350 | 0.0 | - |
| 2.9756 | 51400 | 0.0 | - |
| 2.9785 | 51450 | 0.0 | - |
| 2.9814 | 51500 | 0.0 | - |
| 2.9843 | 51550 | 0.0 | - |
| 2.9871 | 51600 | 0.0 | - |
| 2.9900 | 51650 | 0.0 | - |
| 2.9929 | 51700 | 0.0 | - |
| 2.9958 | 51750 | 0.0 | - |
| 2.9987 | 51800 | 0.0 | - |
| 3.0 | 51822 | - | 0.0394 |
| 3.0016 | 51850 | 0.0 | - |
| 3.0045 | 51900 | 0.0 | - |
| 3.0074 | 51950 | 0.0 | - |
| 3.0103 | 52000 | 0.0 | - |
| 3.0132 | 52050 | 0.0 | - |
| 3.0161 | 52100 | 0.0 | - |
| 3.0190 | 52150 | 0.0 | - |
| 3.0219 | 52200 | 0.0 | - |
| 3.0248 | 52250 | 0.0 | - |
| 3.0277 | 52300 | 0.0 | - |
| 3.0306 | 52350 | 0.0 | - |
| 3.0335 | 52400 | 0.0 | - |
| 3.0364 | 52450 | 0.0 | - |
| 3.0392 | 52500 | 0.0 | - |
| 3.0421 | 52550 | 0.0 | - |
| 3.0450 | 52600 | 0.0 | - |
| 3.0479 | 52650 | 0.0 | - |
| 3.0508 | 52700 | 0.0 | - |
| 3.0537 | 52750 | 0.0 | - |
| 3.0566 | 52800 | 0.0 | - |
| 3.0595 | 52850 | 0.0 | - |
| 3.0624 | 52900 | 0.0 | - |
| 3.0653 | 52950 | 0.0 | - |
| 3.0682 | 53000 | 0.0 | - |
| 3.0711 | 53050 | 0.0 | - |
| 3.0740 | 53100 | 0.0 | - |
| 3.0769 | 53150 | 0.0 | - |
| 3.0798 | 53200 | 0.0 | - |
| 3.0827 | 53250 | 0.0 | - |
| 3.0856 | 53300 | 0.0 | - |
| 3.0885 | 53350 | 0.0 | - |
| 3.0914 | 53400 | 0.0 | - |
| 3.0942 | 53450 | 0.0 | - |
| 3.0971 | 53500 | 0.0 | - |
| 3.1000 | 53550 | 0.0 | - |
| 3.1029 | 53600 | 0.0 | - |
| 3.1058 | 53650 | 0.0 | - |
| 3.1087 | 53700 | 0.0 | - |
| 3.1116 | 53750 | 0.0 | - |
| 3.1145 | 53800 | 0.0 | - |
| 3.1174 | 53850 | 0.0 | - |
| 3.1203 | 53900 | 0.0 | - |
| 3.1232 | 53950 | 0.0 | - |
| 3.1261 | 54000 | 0.0 | - |
| 3.1290 | 54050 | 0.0 | - |
| 3.1319 | 54100 | 0.0 | - |
| 3.1348 | 54150 | 0.0 | - |
| 3.1377 | 54200 | 0.0 | - |
| 3.1406 | 54250 | 0.0 | - |
| 3.1435 | 54300 | 0.0 | - |
| 3.1463 | 54350 | 0.0 | - |
| 3.1492 | 54400 | 0.0 | - |
| 3.1521 | 54450 | 0.0 | - |
| 3.1550 | 54500 | 0.0 | - |
| 3.1579 | 54550 | 0.0 | - |
| 3.1608 | 54600 | 0.0 | - |
| 3.1637 | 54650 | 0.0 | - |
| 3.1666 | 54700 | 0.0 | - |
| 3.1695 | 54750 | 0.0 | - |
| 3.1724 | 54800 | 0.0 | - |
| 3.1753 | 54850 | 0.0 | - |
| 3.1782 | 54900 | 0.0 | - |
| 3.1811 | 54950 | 0.0 | - |
| 3.1840 | 55000 | 0.0 | - |
| 3.1869 | 55050 | 0.0 | - |
| 3.1898 | 55100 | 0.0 | - |
| 3.1927 | 55150 | 0.0 | - |
| 3.1956 | 55200 | 0.0 | - |
| 3.1984 | 55250 | 0.0 | - |
| 3.2013 | 55300 | 0.0 | - |
| 3.2042 | 55350 | 0.0 | - |
| 3.2071 | 55400 | 0.0 | - |
| 3.2100 | 55450 | 0.0 | - |
| 3.2129 | 55500 | 0.0 | - |
| 3.2158 | 55550 | 0.0 | - |
| 3.2187 | 55600 | 0.0 | - |
| 3.2216 | 55650 | 0.0 | - |
| 3.2245 | 55700 | 0.0 | - |
| 3.2274 | 55750 | 0.0 | - |
| 3.2303 | 55800 | 0.0 | - |
| 3.2332 | 55850 | 0.0 | - |
| 3.2361 | 55900 | 0.0 | - |
| 3.2390 | 55950 | 0.0 | - |
| 3.2419 | 56000 | 0.0 | - |
| 3.2448 | 56050 | 0.0 | - |
| 3.2477 | 56100 | 0.0 | - |
| 3.2505 | 56150 | 0.0 | - |
| 3.2534 | 56200 | 0.0 | - |
| 3.2563 | 56250 | 0.0 | - |
| 3.2592 | 56300 | 0.0 | - |
| 3.2621 | 56350 | 0.0 | - |
| 3.2650 | 56400 | 0.0 | - |
| 3.2679 | 56450 | 0.0 | - |
| 3.2708 | 56500 | 0.0 | - |
| 3.2737 | 56550 | 0.0 | - |
| 3.2766 | 56600 | 0.0 | - |
| 3.2795 | 56650 | 0.0 | - |
| 3.2824 | 56700 | 0.0 | - |
| 3.2853 | 56750 | 0.0 | - |
| 3.2882 | 56800 | 0.0 | - |
| 3.2911 | 56850 | 0.0 | - |
| 3.2940 | 56900 | 0.0 | - |
| 3.2969 | 56950 | 0.0 | - |
| 3.2998 | 57000 | 0.0 | - |
| 3.3027 | 57050 | 0.0 | - |
| 3.3055 | 57100 | 0.0 | - |
| 3.3084 | 57150 | 0.0 | - |
| 3.3113 | 57200 | 0.0 | - |
| 3.3142 | 57250 | 0.0 | - |
| 3.3171 | 57300 | 0.0 | - |
| 3.3200 | 57350 | 0.0 | - |
| 3.3229 | 57400 | 0.0 | - |
| 3.3258 | 57450 | 0.0 | - |
| 3.3287 | 57500 | 0.0 | - |
| 3.3316 | 57550 | 0.0 | - |
| 3.3345 | 57600 | 0.0 | - |
| 3.3374 | 57650 | 0.0 | - |
| 3.3403 | 57700 | 0.0 | - |
| 3.3432 | 57750 | 0.0 | - |
| 3.3461 | 57800 | 0.0 | - |
| 3.3490 | 57850 | 0.0 | - |
| 3.3519 | 57900 | 0.0 | - |
| 3.3548 | 57950 | 0.0 | - |
| 3.3576 | 58000 | 0.0 | - |
| 3.3605 | 58050 | 0.0 | - |
| 3.3634 | 58100 | 0.0 | - |
| 3.3663 | 58150 | 0.0 | - |
| 3.3692 | 58200 | 0.0 | - |
| 3.3721 | 58250 | 0.0 | - |
| 3.3750 | 58300 | 0.0 | - |
| 3.3779 | 58350 | 0.0 | - |
| 3.3808 | 58400 | 0.0 | - |
| 3.3837 | 58450 | 0.0 | - |
| 3.3866 | 58500 | 0.0 | - |
| 3.3895 | 58550 | 0.0 | - |
| 3.3924 | 58600 | 0.0 | - |
| 3.3953 | 58650 | 0.0 | - |
| 3.3982 | 58700 | 0.0 | - |
| 3.4011 | 58750 | 0.0 | - |
| 3.4040 | 58800 | 0.0 | - |
| 3.4069 | 58850 | 0.0 | - |
| 3.4097 | 58900 | 0.0 | - |
| 3.4126 | 58950 | 0.0 | - |
| 3.4155 | 59000 | 0.0 | - |
| 3.4184 | 59050 | 0.0 | - |
| 3.4213 | 59100 | 0.0 | - |
| 3.4242 | 59150 | 0.0 | - |
| 3.4271 | 59200 | 0.0 | - |
| 3.4300 | 59250 | 0.0 | - |
| 3.4329 | 59300 | 0.0 | - |
| 3.4358 | 59350 | 0.0 | - |
| 3.4387 | 59400 | 0.0 | - |
| 3.4416 | 59450 | 0.0 | - |
| 3.4445 | 59500 | 0.0 | - |
| 3.4474 | 59550 | 0.0 | - |
| 3.4503 | 59600 | 0.0 | - |
| 3.4532 | 59650 | 0.0 | - |
| 3.4561 | 59700 | 0.0 | - |
| 3.4590 | 59750 | 0.0 | - |
| 3.4619 | 59800 | 0.0 | - |
| 3.4647 | 59850 | 0.0 | - |
| 3.4676 | 59900 | 0.0 | - |
| 3.4705 | 59950 | 0.0 | - |
| 3.4734 | 60000 | 0.0 | - |
| 3.4763 | 60050 | 0.0 | - |
| 3.4792 | 60100 | 0.0 | - |
| 3.4821 | 60150 | 0.0 | - |
| 3.4850 | 60200 | 0.0 | - |
| 3.4879 | 60250 | 0.0 | - |
| 3.4908 | 60300 | 0.0 | - |
| 3.4937 | 60350 | 0.0 | - |
| 3.4966 | 60400 | 0.0 | - |
| 3.4995 | 60450 | 0.0 | - |
| 3.5024 | 60500 | 0.0 | - |
| 3.5053 | 60550 | 0.0 | - |
| 3.5082 | 60600 | 0.0 | - |
| 3.5111 | 60650 | 0.0 | - |
| 3.5140 | 60700 | 0.0 | - |
| 3.5168 | 60750 | 0.0 | - |
| 3.5197 | 60800 | 0.0 | - |
| 3.5226 | 60850 | 0.0 | - |
| 3.5255 | 60900 | 0.0 | - |
| 3.5284 | 60950 | 0.0 | - |
| 3.5313 | 61000 | 0.0 | - |
| 3.5342 | 61050 | 0.0 | - |
| 3.5371 | 61100 | 0.0 | - |
| 3.5400 | 61150 | 0.0 | - |
| 3.5429 | 61200 | 0.0 | - |
| 3.5458 | 61250 | 0.0 | - |
| 3.5487 | 61300 | 0.0 | - |
| 3.5516 | 61350 | 0.0 | - |
| 3.5545 | 61400 | 0.0 | - |
| 3.5574 | 61450 | 0.0 | - |
| 3.5603 | 61500 | 0.0 | - |
| 3.5632 | 61550 | 0.0 | - |
| 3.5661 | 61600 | 0.0 | - |
| 3.5689 | 61650 | 0.0 | - |
| 3.5718 | 61700 | 0.0 | - |
| 3.5747 | 61750 | 0.0 | - |
| 3.5776 | 61800 | 0.0 | - |
| 3.5805 | 61850 | 0.0 | - |
| 3.5834 | 61900 | 0.0 | - |
| 3.5863 | 61950 | 0.0 | - |
| 3.5892 | 62000 | 0.0 | - |
| 3.5921 | 62050 | 0.0 | - |
| 3.5950 | 62100 | 0.0 | - |
| 3.5979 | 62150 | 0.0 | - |
| 3.6008 | 62200 | 0.0 | - |
| 3.6037 | 62250 | 0.0 | - |
| 3.6066 | 62300 | 0.0 | - |
| 3.6095 | 62350 | 0.0 | - |
| 3.6124 | 62400 | 0.0 | - |
| 3.6153 | 62450 | 0.0 | - |
| 3.6182 | 62500 | 0.0 | - |
| 3.6210 | 62550 | 0.0 | - |
| 3.6239 | 62600 | 0.0 | - |
| 3.6268 | 62650 | 0.0 | - |
| 3.6297 | 62700 | 0.0 | - |
| 3.6326 | 62750 | 0.0 | - |
| 3.6355 | 62800 | 0.0 | - |
| 3.6384 | 62850 | 0.0 | - |
| 3.6413 | 62900 | 0.0 | - |
| 3.6442 | 62950 | 0.0 | - |
| 3.6471 | 63000 | 0.0 | - |
| 3.6500 | 63050 | 0.0 | - |
| 3.6529 | 63100 | 0.0 | - |
| 3.6558 | 63150 | 0.0 | - |
| 3.6587 | 63200 | 0.0 | - |
| 3.6616 | 63250 | 0.0 | - |
| 3.6645 | 63300 | 0.0 | - |
| 3.6674 | 63350 | 0.0 | - |
| 3.6703 | 63400 | 0.0 | - |
| 3.6732 | 63450 | 0.0 | - |
| 3.6760 | 63500 | 0.0 | - |
| 3.6789 | 63550 | 0.0 | - |
| 3.6818 | 63600 | 0.0 | - |
| 3.6847 | 63650 | 0.0 | - |
| 3.6876 | 63700 | 0.0 | - |
| 3.6905 | 63750 | 0.0 | - |
| 3.6934 | 63800 | 0.0 | - |
| 3.6963 | 63850 | 0.0 | - |
| 3.6992 | 63900 | 0.0 | - |
| 3.7021 | 63950 | 0.0 | - |
| 3.7050 | 64000 | 0.0 | - |
| 3.7079 | 64050 | 0.0 | - |
| 3.7108 | 64100 | 0.0 | - |
| 3.7137 | 64150 | 0.0 | - |
| 3.7166 | 64200 | 0.0 | - |
| 3.7195 | 64250 | 0.0 | - |
| 3.7224 | 64300 | 0.0 | - |
| 3.7253 | 64350 | 0.0 | - |
| 3.7281 | 64400 | 0.0 | - |
| 3.7310 | 64450 | 0.0 | - |
| 3.7339 | 64500 | 0.0 | - |
| 3.7368 | 64550 | 0.0 | - |
| 3.7397 | 64600 | 0.0 | - |
| 3.7426 | 64650 | 0.0 | - |
| 3.7455 | 64700 | 0.0 | - |
| 3.7484 | 64750 | 0.0 | - |
| 3.7513 | 64800 | 0.0 | - |
| 3.7542 | 64850 | 0.0 | - |
| 3.7571 | 64900 | 0.0 | - |
| 3.7600 | 64950 | 0.0 | - |
| 3.7629 | 65000 | 0.0 | - |
| 3.7658 | 65050 | 0.0 | - |
| 3.7687 | 65100 | 0.0 | - |
| 3.7716 | 65150 | 0.0 | - |
| 3.7745 | 65200 | 0.0 | - |
| 3.7774 | 65250 | 0.0 | - |
| 3.7802 | 65300 | 0.0 | - |
| 3.7831 | 65350 | 0.0 | - |
| 3.7860 | 65400 | 0.0 | - |
| 3.7889 | 65450 | 0.0 | - |
| 3.7918 | 65500 | 0.0 | - |
| 3.7947 | 65550 | 0.0 | - |
| 3.7976 | 65600 | 0.0 | - |
| 3.8005 | 65650 | 0.0 | - |
| 3.8034 | 65700 | 0.0 | - |
| 3.8063 | 65750 | 0.0 | - |
| 3.8092 | 65800 | 0.0 | - |
| 3.8121 | 65850 | 0.0 | - |
| 3.8150 | 65900 | 0.0 | - |
| 3.8179 | 65950 | 0.0 | - |
| 3.8208 | 66000 | 0.0 | - |
| 3.8237 | 66050 | 0.0 | - |
| 3.8266 | 66100 | 0.0 | - |
| 3.8295 | 66150 | 0.0 | - |
| 3.8323 | 66200 | 0.0 | - |
| 3.8352 | 66250 | 0.0 | - |
| 3.8381 | 66300 | 0.0 | - |
| 3.8410 | 66350 | 0.0 | - |
| 3.8439 | 66400 | 0.0 | - |
| 3.8468 | 66450 | 0.0 | - |
| 3.8497 | 66500 | 0.0 | - |
| 3.8526 | 66550 | 0.0 | - |
| 3.8555 | 66600 | 0.0 | - |
| 3.8584 | 66650 | 0.0 | - |
| 3.8613 | 66700 | 0.0 | - |
| 3.8642 | 66750 | 0.0 | - |
| 3.8671 | 66800 | 0.0 | - |
| 3.8700 | 66850 | 0.0 | - |
| 3.8729 | 66900 | 0.0001 | - |
| 3.8758 | 66950 | 0.0 | - |
| 3.8787 | 67000 | 0.0 | - |
| 3.8816 | 67050 | 0.0 | - |
| 3.8845 | 67100 | 0.0 | - |
| 3.8873 | 67150 | 0.0 | - |
| 3.8902 | 67200 | 0.0 | - |
| 3.8931 | 67250 | 0.0 | - |
| 3.8960 | 67300 | 0.0 | - |
| 3.8989 | 67350 | 0.0 | - |
| 3.9018 | 67400 | 0.0 | - |
| 3.9047 | 67450 | 0.0 | - |
| 3.9076 | 67500 | 0.0 | - |
| 3.9105 | 67550 | 0.0 | - |
| 3.9134 | 67600 | 0.0 | - |
| 3.9163 | 67650 | 0.0 | - |
| 3.9192 | 67700 | 0.0 | - |
| 3.9221 | 67750 | 0.0 | - |
| 3.9250 | 67800 | 0.0 | - |
| 3.9279 | 67850 | 0.0 | - |
| 3.9308 | 67900 | 0.0 | - |
| 3.9337 | 67950 | 0.0 | - |
| 3.9366 | 68000 | 0.0 | - |
| 3.9394 | 68050 | 0.0 | - |
| 3.9423 | 68100 | 0.0 | - |
| 3.9452 | 68150 | 0.0 | - |
| 3.9481 | 68200 | 0.0 | - |
| 3.9510 | 68250 | 0.0 | - |
| 3.9539 | 68300 | 0.0 | - |
| 3.9568 | 68350 | 0.0 | - |
| 3.9597 | 68400 | 0.0 | - |
| 3.9626 | 68450 | 0.0 | - |
| 3.9655 | 68500 | 0.0 | - |
| 3.9684 | 68550 | 0.0 | - |
| 3.9713 | 68600 | 0.0 | - |
| 3.9742 | 68650 | 0.0 | - |
| 3.9771 | 68700 | 0.0 | - |
| 3.9800 | 68750 | 0.0 | - |
| 3.9829 | 68800 | 0.0 | - |
| 3.9858 | 68850 | 0.0 | - |
| 3.9887 | 68900 | 0.0 | - |
| 3.9915 | 68950 | 0.0 | - |
| 3.9944 | 69000 | 0.0 | - |
| 3.9973 | 69050 | 0.0 | - |
| 4.0 | 69096 | - | 0.0482 |
| 4.0002 | 69100 | 0.0 | - |
| 4.0031 | 69150 | 0.0 | - |
| 4.0060 | 69200 | 0.0 | - |
| 4.0089 | 69250 | 0.0 | - |
| 4.0118 | 69300 | 0.0 | - |
| 4.0147 | 69350 | 0.0 | - |
| 4.0176 | 69400 | 0.0 | - |
| 4.0205 | 69450 | 0.0 | - |
| 4.0234 | 69500 | 0.0 | - |
| 4.0263 | 69550 | 0.0005 | - |
| 4.0292 | 69600 | 0.0 | - |
| 4.0321 | 69650 | 0.0 | - |
| 4.0350 | 69700 | 0.0 | - |
| 4.0379 | 69750 | 0.0 | - |
| 4.0408 | 69800 | 0.0 | - |
| 4.0436 | 69850 | 0.0 | - |
| 4.0465 | 69900 | 0.0 | - |
| 4.0494 | 69950 | 0.0 | - |
| 4.0523 | 70000 | 0.0 | - |
| 4.0552 | 70050 | 0.0 | - |
| 4.0581 | 70100 | 0.0 | - |
| 4.0610 | 70150 | 0.0 | - |
| 4.0639 | 70200 | 0.0 | - |
| 4.0668 | 70250 | 0.0 | - |
| 4.0697 | 70300 | 0.0 | - |
| 4.0726 | 70350 | 0.0 | - |
| 4.0755 | 70400 | 0.0 | - |
| 4.0784 | 70450 | 0.0 | - |
| 4.0813 | 70500 | 0.0 | - |
| 4.0842 | 70550 | 0.0 | - |
| 4.0871 | 70600 | 0.0 | - |
| 4.0900 | 70650 | 0.0 | - |
| 4.0929 | 70700 | 0.0 | - |
| 4.0958 | 70750 | 0.0 | - |
| 4.0986 | 70800 | 0.0 | - |
| 4.1015 | 70850 | 0.0 | - |
| 4.1044 | 70900 | 0.0 | - |
| 4.1073 | 70950 | 0.0 | - |
| 4.1102 | 71000 | 0.0 | - |
| 4.1131 | 71050 | 0.0 | - |
| 4.1160 | 71100 | 0.0 | - |
| 4.1189 | 71150 | 0.0 | - |
| 4.1218 | 71200 | 0.0 | - |
| 4.1247 | 71250 | 0.0 | - |
| 4.1276 | 71300 | 0.0 | - |
| 4.1305 | 71350 | 0.0 | - |
| 4.1334 | 71400 | 0.0 | - |
| 4.1363 | 71450 | 0.0 | - |
| 4.1392 | 71500 | 0.0 | - |
| 4.1421 | 71550 | 0.0 | - |
| 4.1450 | 71600 | 0.0 | - |
| 4.1479 | 71650 | 0.0 | - |
| 4.1507 | 71700 | 0.0 | - |
| 4.1536 | 71750 | 0.0 | - |
| 4.1565 | 71800 | 0.0 | - |
| 4.1594 | 71850 | 0.0 | - |
| 4.1623 | 71900 | 0.0 | - |
| 4.1652 | 71950 | 0.0 | - |
| 4.1681 | 72000 | 0.0 | - |
| 4.1710 | 72050 | 0.0 | - |
| 4.1739 | 72100 | 0.0 | - |
| 4.1768 | 72150 | 0.0 | - |
| 4.1797 | 72200 | 0.0 | - |
| 4.1826 | 72250 | 0.0 | - |
| 4.1855 | 72300 | 0.0 | - |
| 4.1884 | 72350 | 0.0 | - |
| 4.1913 | 72400 | 0.0 | - |
| 4.1942 | 72450 | 0.0 | - |
| 4.1971 | 72500 | 0.0 | - |
| 4.2000 | 72550 | 0.0 | - |
| 4.2028 | 72600 | 0.0 | - |
| 4.2057 | 72650 | 0.0 | - |
| 4.2086 | 72700 | 0.0 | - |
| 4.2115 | 72750 | 0.0 | - |
| 4.2144 | 72800 | 0.0 | - |
| 4.2173 | 72850 | 0.0 | - |
| 4.2202 | 72900 | 0.0 | - |
| 4.2231 | 72950 | 0.0 | - |
| 4.2260 | 73000 | 0.0 | - |
| 4.2289 | 73050 | 0.0 | - |
| 4.2318 | 73100 | 0.0 | - |
| 4.2347 | 73150 | 0.0 | - |
| 4.2376 | 73200 | 0.0 | - |
| 4.2405 | 73250 | 0.0 | - |
| 4.2434 | 73300 | 0.0 | - |
| 4.2463 | 73350 | 0.0 | - |
| 4.2492 | 73400 | 0.0 | - |
| 4.2521 | 73450 | 0.0 | - |
| 4.2549 | 73500 | 0.0 | - |
| 4.2578 | 73550 | 0.0 | - |
| 4.2607 | 73600 | 0.0 | - |
| 4.2636 | 73650 | 0.0 | - |
| 4.2665 | 73700 | 0.0 | - |
| 4.2694 | 73750 | 0.0 | - |
| 4.2723 | 73800 | 0.0 | - |
| 4.2752 | 73850 | 0.0 | - |
| 4.2781 | 73900 | 0.0 | - |
| 4.2810 | 73950 | 0.0 | - |
| 4.2839 | 74000 | 0.0 | - |
| 4.2868 | 74050 | 0.0 | - |
| 4.2897 | 74100 | 0.0 | - |
| 4.2926 | 74150 | 0.0 | - |
| 4.2955 | 74200 | 0.0 | - |
| 4.2984 | 74250 | 0.0 | - |
| 4.3013 | 74300 | 0.0 | - |
| 4.3042 | 74350 | 0.0 | - |
| 4.3071 | 74400 | 0.0 | - |
| 4.3099 | 74450 | 0.0 | - |
| 4.3128 | 74500 | 0.0 | - |
| 4.3157 | 74550 | 0.0 | - |
| 4.3186 | 74600 | 0.0 | - |
| 4.3215 | 74650 | 0.0 | - |
| 4.3244 | 74700 | 0.0 | - |
| 4.3273 | 74750 | 0.0 | - |
| 4.3302 | 74800 | 0.0 | - |
| 4.3331 | 74850 | 0.0 | - |
| 4.3360 | 74900 | 0.0 | - |
| 4.3389 | 74950 | 0.0 | - |
| 4.3418 | 75000 | 0.0 | - |
| 4.3447 | 75050 | 0.0 | - |
| 4.3476 | 75100 | 0.0 | - |
| 4.3505 | 75150 | 0.0 | - |
| 4.3534 | 75200 | 0.0 | - |
| 4.3563 | 75250 | 0.0 | - |
| 4.3592 | 75300 | 0.0 | - |
| 4.3620 | 75350 | 0.0 | - |
| 4.3649 | 75400 | 0.0 | - |
| 4.3678 | 75450 | 0.0 | - |
| 4.3707 | 75500 | 0.0 | - |
| 4.3736 | 75550 | 0.0 | - |
| 4.3765 | 75600 | 0.0 | - |
| 4.3794 | 75650 | 0.0 | - |
| 4.3823 | 75700 | 0.0 | - |
| 4.3852 | 75750 | 0.0 | - |
| 4.3881 | 75800 | 0.0 | - |
| 4.3910 | 75850 | 0.0 | - |
| 4.3939 | 75900 | 0.0 | - |
| 4.3968 | 75950 | 0.0 | - |
| 4.3997 | 76000 | 0.0 | - |
| 4.4026 | 76050 | 0.0 | - |
| 4.4055 | 76100 | 0.0 | - |
| 4.4084 | 76150 | 0.0 | - |
| 4.4113 | 76200 | 0.0 | - |
| 4.4141 | 76250 | 0.0 | - |
| 4.4170 | 76300 | 0.0 | - |
| 4.4199 | 76350 | 0.0 | - |
| 4.4228 | 76400 | 0.0 | - |
| 4.4257 | 76450 | 0.0 | - |
| 4.4286 | 76500 | 0.0 | - |
| 4.4315 | 76550 | 0.0 | - |
| 4.4344 | 76600 | 0.0 | - |
| 4.4373 | 76650 | 0.0 | - |
| 4.4402 | 76700 | 0.0 | - |
| 4.4431 | 76750 | 0.0 | - |
| 4.4460 | 76800 | 0.0 | - |
| 4.4489 | 76850 | 0.0 | - |
| 4.4518 | 76900 | 0.0 | - |
| 4.4547 | 76950 | 0.0 | - |
| 4.4576 | 77000 | 0.0 | - |
| 4.4605 | 77050 | 0.0 | - |
| 4.4634 | 77100 | 0.0 | - |
| 4.4662 | 77150 | 0.0 | - |
| 4.4691 | 77200 | 0.0 | - |
| 4.4720 | 77250 | 0.0 | - |
| 4.4749 | 77300 | 0.0 | - |
| 4.4778 | 77350 | 0.0 | - |
| 4.4807 | 77400 | 0.0 | - |
| 4.4836 | 77450 | 0.0 | - |
| 4.4865 | 77500 | 0.0 | - |
| 4.4894 | 77550 | 0.0 | - |
| 4.4923 | 77600 | 0.0 | - |
| 4.4952 | 77650 | 0.0 | - |
| 4.4981 | 77700 | 0.0 | - |
| 4.5010 | 77750 | 0.0 | - |
| 4.5039 | 77800 | 0.0 | - |
| 4.5068 | 77850 | 0.0 | - |
| 4.5097 | 77900 | 0.0 | - |
| 4.5126 | 77950 | 0.0 | - |
| 4.5155 | 78000 | 0.0 | - |
| 4.5184 | 78050 | 0.0 | - |
| 4.5212 | 78100 | 0.0 | - |
| 4.5241 | 78150 | 0.0 | - |
| 4.5270 | 78200 | 0.0 | - |
| 4.5299 | 78250 | 0.0 | - |
| 4.5328 | 78300 | 0.0 | - |
| 4.5357 | 78350 | 0.0 | - |
| 4.5386 | 78400 | 0.0 | - |
| 4.5415 | 78450 | 0.0 | - |
| 4.5444 | 78500 | 0.0 | - |
| 4.5473 | 78550 | 0.0 | - |
| 4.5502 | 78600 | 0.0 | - |
| 4.5531 | 78650 | 0.0 | - |
| 4.5560 | 78700 | 0.0 | - |
| 4.5589 | 78750 | 0.0 | - |
| 4.5618 | 78800 | 0.0 | - |
| 4.5647 | 78850 | 0.0 | - |
| 4.5676 | 78900 | 0.0 | - |
| 4.5705 | 78950 | 0.0 | - |
| 4.5733 | 79000 | 0.0 | - |
| 4.5762 | 79050 | 0.0 | - |
| 4.5791 | 79100 | 0.0 | - |
| 4.5820 | 79150 | 0.0 | - |
| 4.5849 | 79200 | 0.0 | - |
| 4.5878 | 79250 | 0.0 | - |
| 4.5907 | 79300 | 0.0 | - |
| 4.5936 | 79350 | 0.0 | - |
| 4.5965 | 79400 | 0.0 | - |
| 4.5994 | 79450 | 0.0 | - |
| 4.6023 | 79500 | 0.0 | - |
| 4.6052 | 79550 | 0.0 | - |
| 4.6081 | 79600 | 0.0 | - |
| 4.6110 | 79650 | 0.0 | - |
| 4.6139 | 79700 | 0.0 | - |
| 4.6168 | 79750 | 0.0 | - |
| 4.6197 | 79800 | 0.0 | - |
| 4.6226 | 79850 | 0.0 | - |
| 4.6254 | 79900 | 0.0 | - |
| 4.6283 | 79950 | 0.0 | - |
| 4.6312 | 80000 | 0.0 | - |
| 4.6341 | 80050 | 0.0 | - |
| 4.6370 | 80100 | 0.0 | - |
| 4.6399 | 80150 | 0.0 | - |
| 4.6428 | 80200 | 0.0 | - |
| 4.6457 | 80250 | 0.0 | - |
| 4.6486 | 80300 | 0.0 | - |
| 4.6515 | 80350 | 0.0 | - |
| 4.6544 | 80400 | 0.0 | - |
| 4.6573 | 80450 | 0.0 | - |
| 4.6602 | 80500 | 0.0 | - |
| 4.6631 | 80550 | 0.0 | - |
| 4.6660 | 80600 | 0.0 | - |
| 4.6689 | 80650 | 0.0 | - |
| 4.6718 | 80700 | 0.0 | - |
| 4.6747 | 80750 | 0.0 | - |
| 4.6776 | 80800 | 0.0 | - |
| 4.6804 | 80850 | 0.0 | - |
| 4.6833 | 80900 | 0.0 | - |
| 4.6862 | 80950 | 0.0 | - |
| 4.6891 | 81000 | 0.0 | - |
| 4.6920 | 81050 | 0.0 | - |
| 4.6949 | 81100 | 0.0 | - |
| 4.6978 | 81150 | 0.0 | - |
| 4.7007 | 81200 | 0.0 | - |
| 4.7036 | 81250 | 0.0 | - |
| 4.7065 | 81300 | 0.0 | - |
| 4.7094 | 81350 | 0.0 | - |
| 4.7123 | 81400 | 0.0 | - |
| 4.7152 | 81450 | 0.0 | - |
| 4.7181 | 81500 | 0.0 | - |
| 4.7210 | 81550 | 0.0 | - |
| 4.7239 | 81600 | 0.0 | - |
| 4.7268 | 81650 | 0.0 | - |
| 4.7297 | 81700 | 0.0 | - |
| 4.7325 | 81750 | 0.0 | - |
| 4.7354 | 81800 | 0.0 | - |
| 4.7383 | 81850 | 0.0 | - |
| 4.7412 | 81900 | 0.0 | - |
| 4.7441 | 81950 | 0.0 | - |
| 4.7470 | 82000 | 0.0 | - |
| 4.7499 | 82050 | 0.0 | - |
| 4.7528 | 82100 | 0.0 | - |
| 4.7557 | 82150 | 0.0 | - |
| 4.7586 | 82200 | 0.0 | - |
| 4.7615 | 82250 | 0.0 | - |
| 4.7644 | 82300 | 0.0 | - |
| 4.7673 | 82350 | 0.0 | - |
| 4.7702 | 82400 | 0.0 | - |
| 4.7731 | 82450 | 0.0 | - |
| 4.7760 | 82500 | 0.0 | - |
| 4.7789 | 82550 | 0.0 | - |
| 4.7818 | 82600 | 0.0 | - |
| 4.7846 | 82650 | 0.0 | - |
| 4.7875 | 82700 | 0.0 | - |
| 4.7904 | 82750 | 0.0 | - |
| 4.7933 | 82800 | 0.0 | - |
| 4.7962 | 82850 | 0.0 | - |
| 4.7991 | 82900 | 0.0 | - |
| 4.8020 | 82950 | 0.0 | - |
| 4.8049 | 83000 | 0.0 | - |
| 4.8078 | 83050 | 0.0 | - |
| 4.8107 | 83100 | 0.0 | - |
| 4.8136 | 83150 | 0.0 | - |
| 4.8165 | 83200 | 0.0 | - |
| 4.8194 | 83250 | 0.0 | - |
| 4.8223 | 83300 | 0.0 | - |
| 4.8252 | 83350 | 0.0 | - |
| 4.8281 | 83400 | 0.0 | - |
| 4.8310 | 83450 | 0.0 | - |
| 4.8339 | 83500 | 0.0 | - |
| 4.8367 | 83550 | 0.0 | - |
| 4.8396 | 83600 | 0.0 | - |
| 4.8425 | 83650 | 0.0 | - |
| 4.8454 | 83700 | 0.0 | - |
| 4.8483 | 83750 | 0.0 | - |
| 4.8512 | 83800 | 0.0 | - |
| 4.8541 | 83850 | 0.0 | - |
| 4.8570 | 83900 | 0.0 | - |
| 4.8599 | 83950 | 0.0 | - |
| 4.8628 | 84000 | 0.0 | - |
| 4.8657 | 84050 | 0.0 | - |
| 4.8686 | 84100 | 0.0 | - |
| 4.8715 | 84150 | 0.0 | - |
| 4.8744 | 84200 | 0.0 | - |
| 4.8773 | 84250 | 0.0 | - |
| 4.8802 | 84300 | 0.0 | - |
| 4.8831 | 84350 | 0.0 | - |
| 4.8860 | 84400 | 0.0 | - |
| 4.8889 | 84450 | 0.0 | - |
| 4.8917 | 84500 | 0.0 | - |
| 4.8946 | 84550 | 0.0 | - |
| 4.8975 | 84600 | 0.0 | - |
| 4.9004 | 84650 | 0.0 | - |
| 4.9033 | 84700 | 0.0 | - |
| 4.9062 | 84750 | 0.0 | - |
| 4.9091 | 84800 | 0.0 | - |
| 4.9120 | 84850 | 0.0 | - |
| 4.9149 | 84900 | 0.0 | - |
| 4.9178 | 84950 | 0.0 | - |
| 4.9207 | 85000 | 0.0 | - |
| 4.9236 | 85050 | 0.0 | - |
| 4.9265 | 85100 | 0.0 | - |
| 4.9294 | 85150 | 0.0 | - |
| 4.9323 | 85200 | 0.0 | - |
| 4.9352 | 85250 | 0.0 | - |
| 4.9381 | 85300 | 0.0 | - |
| 4.9410 | 85350 | 0.0 | - |
| 4.9438 | 85400 | 0.0 | - |
| 4.9467 | 85450 | 0.0 | - |
| 4.9496 | 85500 | 0.0 | - |
| 4.9525 | 85550 | 0.0 | - |
| 4.9554 | 85600 | 0.0 | - |
| 4.9583 | 85650 | 0.0 | - |
| 4.9612 | 85700 | 0.0 | - |
| 4.9641 | 85750 | 0.0 | - |
| 4.9670 | 85800 | 0.0 | - |
| 4.9699 | 85850 | 0.0 | - |
| 4.9728 | 85900 | 0.0 | - |
| 4.9757 | 85950 | 0.0 | - |
| 4.9786 | 86000 | 0.0 | - |
| 4.9815 | 86050 | 0.0 | - |
| 4.9844 | 86100 | 0.0 | - |
| 4.9873 | 86150 | 0.0 | - |
| 4.9902 | 86200 | 0.0 | - |
| 4.9931 | 86250 | 0.0 | - |
| 4.9959 | 86300 | 0.0 | - |
| 4.9988 | 86350 | 0.0 | - |
| 5.0 | 86370 | - | 0.0477 |
* The bold row denotes the saved checkpoint.
### Framework Versions
- Python: 3.11.9
- SetFit: 1.0.3
- Sentence Transformers: 3.0.1
- Transformers: 4.39.0
- PyTorch: 2.0.1+cu117
- Datasets: 2.20.0
- Tokenizers: 0.15.2
## Citation
### BibTeX
```bibtex
@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
<!--
## Glossary
*Clearly define terms in order to be accessible across audiences.*
-->
<!--
## Model Card Authors
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->
<!--
## Model Card Contact
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
--> | [
"TEXT_CLASSIFICATION"
] | Non_BioNLP |
gokuls/distilbert_add_GLUE_Experiment_qqp_96 | gokuls | text-classification | [
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"text-classification",
"generated_from_trainer",
"en",
"dataset:glue",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 1,674,737,428,000 | 2023-01-26T14:35:04 | 128 | 0 | ---
datasets:
- glue
language:
- en
license: apache-2.0
metrics:
- accuracy
- f1
tags:
- generated_from_trainer
model-index:
- name: distilbert_add_GLUE_Experiment_qqp_96
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: GLUE QQP
type: glue
config: qqp
split: validation
args: qqp
metrics:
- type: accuracy
value: 0.7905763047242147
name: Accuracy
- type: f1
value: 0.7103813921669232
name: F1
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert_add_GLUE_Experiment_qqp_96
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the GLUE QQP dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4726
- Accuracy: 0.7906
- F1: 0.7104
- Combined Score: 0.7505
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 256
- eval_batch_size: 256
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:--------------:|
| 0.5993 | 1.0 | 1422 | 0.5459 | 0.7243 | 0.6353 | 0.6798 |
| 0.5167 | 2.0 | 2844 | 0.5176 | 0.7471 | 0.6481 | 0.6976 |
| 0.4956 | 3.0 | 4266 | 0.5036 | 0.7588 | 0.6463 | 0.7025 |
| 0.4849 | 4.0 | 5688 | 0.5056 | 0.7546 | 0.6610 | 0.7078 |
| 0.4762 | 5.0 | 7110 | 0.5127 | 0.7530 | 0.6705 | 0.7118 |
| 0.4689 | 6.0 | 8532 | 0.5218 | 0.7476 | 0.6754 | 0.7115 |
| 0.4622 | 7.0 | 9954 | 0.4935 | 0.7661 | 0.6571 | 0.7116 |
| 0.4554 | 8.0 | 11376 | 0.5039 | 0.7605 | 0.6537 | 0.7071 |
| 0.4483 | 9.0 | 12798 | 0.5009 | 0.7625 | 0.6732 | 0.7178 |
| 0.4393 | 10.0 | 14220 | 0.4991 | 0.7594 | 0.6857 | 0.7226 |
| 0.4293 | 11.0 | 15642 | 0.4857 | 0.7761 | 0.6548 | 0.7155 |
| 0.4162 | 12.0 | 17064 | 0.4897 | 0.7735 | 0.6935 | 0.7335 |
| 0.4021 | 13.0 | 18486 | 0.4758 | 0.7822 | 0.6881 | 0.7352 |
| 0.3871 | 14.0 | 19908 | 0.4801 | 0.7815 | 0.7050 | 0.7433 |
| 0.3714 | 15.0 | 21330 | 0.4846 | 0.7827 | 0.7111 | 0.7469 |
| 0.3556 | 16.0 | 22752 | 0.4726 | 0.7906 | 0.7104 | 0.7505 |
| 0.341 | 17.0 | 24174 | 0.4787 | 0.7942 | 0.7047 | 0.7494 |
| 0.3269 | 18.0 | 25596 | 0.4914 | 0.7884 | 0.7198 | 0.7541 |
| 0.3127 | 19.0 | 27018 | 0.4774 | 0.7950 | 0.7156 | 0.7553 |
| 0.3 | 20.0 | 28440 | 0.4862 | 0.7965 | 0.7253 | 0.7609 |
| 0.2885 | 21.0 | 29862 | 0.4982 | 0.7939 | 0.7300 | 0.7620 |
### Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.8.0
- Tokenizers 0.13.2
| [
"TEXT_CLASSIFICATION"
] | Non_BioNLP |
leeloolee/intention | leeloolee | sentence-similarity | [
"sentence-transformers",
"safetensors",
"new",
"text-classification",
"mteb",
"transformers",
"multilingual",
"sentence-similarity",
"custom_code",
"af",
"ar",
"az",
"be",
"bg",
"bn",
"ca",
"ceb",
"cs",
"cy",
"da",
"de",
"el",
"en",
"es",
"et",
"eu",
"fa",
"fi",
"fr",
"gl",
"gu",
"he",
"hi",
"hr",
"ht",
"hu",
"hy",
"id",
"is",
"it",
"ja",
"jv",
"ka",
"kk",
"km",
"kn",
"ko",
"ky",
"lo",
"lt",
"lv",
"mk",
"ml",
"mn",
"mr",
"ms",
"my",
"ne",
"nl",
"no",
"pa",
"pl",
"pt",
"qu",
"ro",
"ru",
"si",
"sk",
"sl",
"so",
"sq",
"sr",
"sv",
"sw",
"ta",
"te",
"th",
"tl",
"tr",
"uk",
"ur",
"vi",
"yo",
"zh",
"arxiv:2407.19669",
"arxiv:2210.09984",
"arxiv:2402.03216",
"arxiv:2007.15207",
"arxiv:2104.08663",
"arxiv:2402.07440",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] | 1,725,686,650,000 | 2024-09-07T05:39:09 | 74 | 3 | ---
language:
- af
- ar
- az
- be
- bg
- bn
- ca
- ceb
- cs
- cy
- da
- de
- el
- en
- es
- et
- eu
- fa
- fi
- fr
- gl
- gu
- he
- hi
- hr
- ht
- hu
- hy
- id
- is
- it
- ja
- jv
- ka
- kk
- km
- kn
- ko
- ky
- lo
- lt
- lv
- mk
- ml
- mn
- mr
- ms
- my
- ne
- nl
- 'no'
- pa
- pl
- pt
- qu
- ro
- ru
- si
- sk
- sl
- so
- sq
- sr
- sv
- sw
- ta
- te
- th
- tl
- tr
- uk
- ur
- vi
- yo
- zh
license: apache-2.0
tags:
- mteb
- sentence-transformers
- transformers
- multilingual
- sentence-similarity
model-index:
- name: gte-multilingual-base (dense)
results:
- task:
type: Clustering
dataset:
name: MTEB 8TagsClustering
type: PL-MTEB/8tags-clustering
config: default
split: test
revision: None
metrics:
- type: v_measure
value: 33.66681726329994
- task:
type: STS
dataset:
name: MTEB AFQMC
type: C-MTEB/AFQMC
config: default
split: validation
revision: b44c3b011063adb25877c13823db83bb193913c4
metrics:
- type: cos_sim_spearman
value: 43.54760696384009
- task:
type: STS
dataset:
name: MTEB ATEC
type: C-MTEB/ATEC
config: default
split: test
revision: 0f319b1142f28d00e055a6770f3f726ae9b7d865
metrics:
- type: cos_sim_spearman
value: 48.91186363417501
- task:
type: Classification
dataset:
name: MTEB AllegroReviews
type: PL-MTEB/allegro-reviews
config: default
split: test
revision: None
metrics:
- type: accuracy
value: 41.689860834990064
- task:
type: Clustering
dataset:
name: MTEB AlloProfClusteringP2P
type: lyon-nlp/alloprof
config: default
split: test
revision: 392ba3f5bcc8c51f578786c1fc3dae648662cb9b
metrics:
- type: v_measure
value: 54.20241337977897
- type: v_measure
value: 44.34083695608643
- task:
type: Reranking
dataset:
name: MTEB AlloprofReranking
type: lyon-nlp/mteb-fr-reranking-alloprof-s2p
config: default
split: test
revision: 666fdacebe0291776e86f29345663dfaf80a0db9
metrics:
- type: map
value: 64.91495250072002
- task:
type: Retrieval
dataset:
name: MTEB AlloprofRetrieval
type: lyon-nlp/alloprof
config: default
split: test
revision: 392ba3f5bcc8c51f578786c1fc3dae648662cb9b
metrics:
- type: ndcg_at_10
value: 53.638
- task:
type: Classification
dataset:
name: MTEB AmazonCounterfactualClassification (en)
type: mteb/amazon_counterfactual
config: en
split: test
revision: e8379541af4e31359cca9fbcf4b00f2671dba205
metrics:
- type: accuracy
value: 75.95522388059702
- task:
type: Classification
dataset:
name: MTEB AmazonPolarityClassification
type: mteb/amazon_polarity
config: default
split: test
revision: e2d317d38cd51312af73b3d32a06d1a08b442046
metrics:
- type: accuracy
value: 80.717625
- task:
type: Classification
dataset:
name: MTEB AmazonReviewsClassification (en)
type: mteb/amazon_reviews_multi
config: en
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 43.64199999999999
- task:
type: Classification
dataset:
name: MTEB AmazonReviewsClassification (de)
type: mteb/amazon_reviews_multi
config: de
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 40.108
- task:
type: Classification
dataset:
name: MTEB AmazonReviewsClassification (es)
type: mteb/amazon_reviews_multi
config: es
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 40.169999999999995
- task:
type: Classification
dataset:
name: MTEB AmazonReviewsClassification (fr)
type: mteb/amazon_reviews_multi
config: fr
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 39.56799999999999
- task:
type: Classification
dataset:
name: MTEB AmazonReviewsClassification (ja)
type: mteb/amazon_reviews_multi
config: ja
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 35.75000000000001
- task:
type: Classification
dataset:
name: MTEB AmazonReviewsClassification (zh)
type: mteb/amazon_reviews_multi
config: zh
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 33.342000000000006
- task:
type: Retrieval
dataset:
name: MTEB ArguAna
type: mteb/arguana
config: default
split: test
revision: c22ab2a51041ffd869aaddef7af8d8215647e41a
metrics:
- type: ndcg_at_10
value: 58.231
- task:
type: Retrieval
dataset:
name: MTEB ArguAna-PL
type: clarin-knext/arguana-pl
config: default
split: test
revision: 63fc86750af76253e8c760fc9e534bbf24d260a2
metrics:
- type: ndcg_at_10
value: 53.166000000000004
- task:
type: Clustering
dataset:
name: MTEB ArxivClusteringP2P
type: mteb/arxiv-clustering-p2p
config: default
split: test
revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d
metrics:
- type: v_measure
value: 46.01900557959478
- task:
type: Clustering
dataset:
name: MTEB ArxivClusteringS2S
type: mteb/arxiv-clustering-s2s
config: default
split: test
revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53
metrics:
- type: v_measure
value: 41.06626465345723
- task:
type: Reranking
dataset:
name: MTEB AskUbuntuDupQuestions
type: mteb/askubuntudupquestions-reranking
config: default
split: test
revision: 2000358ca161889fa9c082cb41daa8dcfb161a54
metrics:
- type: map
value: 61.87514497610431
- task:
type: STS
dataset:
name: MTEB BIOSSES
type: mteb/biosses-sts
config: default
split: test
revision: d3fb88f8f02e40887cd149695127462bbcf29b4a
metrics:
- type: cos_sim_spearman
value: 81.21450112991194
- task:
type: STS
dataset:
name: MTEB BQ
type: C-MTEB/BQ
config: default
split: test
revision: e3dda5e115e487b39ec7e618c0c6a29137052a55
metrics:
- type: cos_sim_spearman
value: 51.71589543397271
- task:
type: Retrieval
dataset:
name: MTEB BSARDRetrieval
type: maastrichtlawtech/bsard
config: default
split: test
revision: 5effa1b9b5fa3b0f9e12523e6e43e5f86a6e6d59
metrics:
- type: ndcg_at_10
value: 26.115
- task:
type: BitextMining
dataset:
name: MTEB BUCC (de-en)
type: mteb/bucc-bitext-mining
config: de-en
split: test
revision: d51519689f32196a32af33b075a01d0e7c51e252
metrics:
- type: f1
value: 98.6169102296451
- task:
type: BitextMining
dataset:
name: MTEB BUCC (fr-en)
type: mteb/bucc-bitext-mining
config: fr-en
split: test
revision: d51519689f32196a32af33b075a01d0e7c51e252
metrics:
- type: f1
value: 97.89603052314916
- task:
type: BitextMining
dataset:
name: MTEB BUCC (ru-en)
type: mteb/bucc-bitext-mining
config: ru-en
split: test
revision: d51519689f32196a32af33b075a01d0e7c51e252
metrics:
- type: f1
value: 97.12388869645537
- task:
type: BitextMining
dataset:
name: MTEB BUCC (zh-en)
type: mteb/bucc-bitext-mining
config: zh-en
split: test
revision: d51519689f32196a32af33b075a01d0e7c51e252
metrics:
- type: f1
value: 98.15692469720906
- task:
type: Classification
dataset:
name: MTEB Banking77Classification
type: mteb/banking77
config: default
split: test
revision: 0fd18e25b25c072e09e0d92ab615fda904d66300
metrics:
- type: accuracy
value: 85.36038961038962
- task:
type: Clustering
dataset:
name: MTEB BiorxivClusteringP2P
type: mteb/biorxiv-clustering-p2p
config: default
split: test
revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40
metrics:
- type: v_measure
value: 37.5903826674123
- task:
type: Clustering
dataset:
name: MTEB BiorxivClusteringS2S
type: mteb/biorxiv-clustering-s2s
config: default
split: test
revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908
metrics:
- type: v_measure
value: 34.21474277151329
- task:
type: Classification
dataset:
name: MTEB CBD
type: PL-MTEB/cbd
config: default
split: test
revision: None
metrics:
- type: accuracy
value: 62.519999999999996
- task:
type: PairClassification
dataset:
name: MTEB CDSC-E
type: PL-MTEB/cdsce-pairclassification
config: default
split: test
revision: None
metrics:
- type: cos_sim_ap
value: 74.90132799162956
- task:
type: STS
dataset:
name: MTEB CDSC-R
type: PL-MTEB/cdscr-sts
config: default
split: test
revision: None
metrics:
- type: cos_sim_spearman
value: 90.30727955142524
- task:
type: Clustering
dataset:
name: MTEB CLSClusteringP2P
type: C-MTEB/CLSClusteringP2P
config: default
split: test
revision: 4b6227591c6c1a73bc76b1055f3b7f3588e72476
metrics:
- type: v_measure
value: 37.94850105022274
- task:
type: Clustering
dataset:
name: MTEB CLSClusteringS2S
type: C-MTEB/CLSClusteringS2S
config: default
split: test
revision: e458b3f5414b62b7f9f83499ac1f5497ae2e869f
metrics:
- type: v_measure
value: 38.11958675421534
- task:
type: Reranking
dataset:
name: MTEB CMedQAv1
type: C-MTEB/CMedQAv1-reranking
config: default
split: test
revision: 8d7f1e942507dac42dc58017c1a001c3717da7df
metrics:
- type: map
value: 86.10950950485399
- task:
type: Reranking
dataset:
name: MTEB CMedQAv2
type: C-MTEB/CMedQAv2-reranking
config: default
split: test
revision: 23d186750531a14a0357ca22cd92d712fd512ea0
metrics:
- type: map
value: 87.28038294231966
- task:
type: Retrieval
dataset:
name: MTEB CQADupstackAndroidRetrieval
type: mteb/cqadupstack-android
config: default
split: test
revision: f46a197baaae43b4f621051089b82a364682dfeb
metrics:
- type: ndcg_at_10
value: 47.099000000000004
- task:
type: Retrieval
dataset:
name: MTEB CQADupstackEnglishRetrieval
type: mteb/cqadupstack-english
config: default
split: test
revision: ad9991cb51e31e31e430383c75ffb2885547b5f0
metrics:
- type: ndcg_at_10
value: 45.973000000000006
- task:
type: Retrieval
dataset:
name: MTEB CQADupstackGamingRetrieval
type: mteb/cqadupstack-gaming
config: default
split: test
revision: 4885aa143210c98657558c04aaf3dc47cfb54340
metrics:
- type: ndcg_at_10
value: 55.606
- task:
type: Retrieval
dataset:
name: MTEB CQADupstackGisRetrieval
type: mteb/cqadupstack-gis
config: default
split: test
revision: 5003b3064772da1887988e05400cf3806fe491f2
metrics:
- type: ndcg_at_10
value: 36.638
- task:
type: Retrieval
dataset:
name: MTEB CQADupstackMathematicaRetrieval
type: mteb/cqadupstack-mathematica
config: default
split: test
revision: 90fceea13679c63fe563ded68f3b6f06e50061de
metrics:
- type: ndcg_at_10
value: 30.711
- task:
type: Retrieval
dataset:
name: MTEB CQADupstackPhysicsRetrieval
type: mteb/cqadupstack-physics
config: default
split: test
revision: 79531abbd1fb92d06c6d6315a0cbbbf5bb247ea4
metrics:
- type: ndcg_at_10
value: 44.523
- task:
type: Retrieval
dataset:
name: MTEB CQADupstackProgrammersRetrieval
type: mteb/cqadupstack-programmers
config: default
split: test
revision: 6184bc1440d2dbc7612be22b50686b8826d22b32
metrics:
- type: ndcg_at_10
value: 37.940000000000005
- task:
type: Retrieval
dataset:
name: MTEB CQADupstackRetrieval
type: mteb/cqadupstack
config: default
split: test
revision: 4ffe81d471b1924886b33c7567bfb200e9eec5c4
metrics:
- type: ndcg_at_10
value: 38.12183333333333
- task:
type: Retrieval
dataset:
name: MTEB CQADupstackStatsRetrieval
type: mteb/cqadupstack-stats
config: default
split: test
revision: 65ac3a16b8e91f9cee4c9828cc7c335575432a2a
metrics:
- type: ndcg_at_10
value: 32.684000000000005
- task:
type: Retrieval
dataset:
name: MTEB CQADupstackTexRetrieval
type: mteb/cqadupstack-tex
config: default
split: test
revision: 46989137a86843e03a6195de44b09deda022eec7
metrics:
- type: ndcg_at_10
value: 26.735
- task:
type: Retrieval
dataset:
name: MTEB CQADupstackUnixRetrieval
type: mteb/cqadupstack-unix
config: default
split: test
revision: 6c6430d3a6d36f8d2a829195bc5dc94d7e063e53
metrics:
- type: ndcg_at_10
value: 36.933
- task:
type: Retrieval
dataset:
name: MTEB CQADupstackWebmastersRetrieval
type: mteb/cqadupstack-webmasters
config: default
split: test
revision: 160c094312a0e1facb97e55eeddb698c0abe3571
metrics:
- type: ndcg_at_10
value: 33.747
- task:
type: Retrieval
dataset:
name: MTEB CQADupstackWordpressRetrieval
type: mteb/cqadupstack-wordpress
config: default
split: test
revision: 4ffe81d471b1924886b33c7567bfb200e9eec5c4
metrics:
- type: ndcg_at_10
value: 28.872999999999998
- task:
type: Retrieval
dataset:
name: MTEB ClimateFEVER
type: mteb/climate-fever
config: default
split: test
revision: 47f2ac6acb640fc46020b02a5b59fdda04d39380
metrics:
- type: ndcg_at_10
value: 34.833
- task:
type: Retrieval
dataset:
name: MTEB CmedqaRetrieval
type: C-MTEB/CmedqaRetrieval
config: default
split: dev
revision: cd540c506dae1cf9e9a59c3e06f42030d54e7301
metrics:
- type: ndcg_at_10
value: 43.78
- task:
type: PairClassification
dataset:
name: MTEB Cmnli
type: C-MTEB/CMNLI
config: default
split: validation
revision: 41bc36f332156f7adc9e38f53777c959b2ae9766
metrics:
- type: cos_sim_ap
value: 84.00640599186677
- task:
type: Retrieval
dataset:
name: MTEB CovidRetrieval
type: C-MTEB/CovidRetrieval
config: default
split: dev
revision: 1271c7809071a13532e05f25fb53511ffce77117
metrics:
- type: ndcg_at_10
value: 80.60000000000001
- task:
type: Retrieval
dataset:
name: MTEB DBPedia
type: mteb/dbpedia
config: default
split: test
revision: c0f706b76e590d620bd6618b3ca8efdd34e2d659
metrics:
- type: ndcg_at_10
value: 40.116
- task:
type: Retrieval
dataset:
name: MTEB DBPedia-PL
type: clarin-knext/dbpedia-pl
config: default
split: test
revision: 76afe41d9af165cc40999fcaa92312b8b012064a
metrics:
- type: ndcg_at_10
value: 32.498
- task:
type: Retrieval
dataset:
name: MTEB DuRetrieval
type: C-MTEB/DuRetrieval
config: default
split: dev
revision: a1a333e290fe30b10f3f56498e3a0d911a693ced
metrics:
- type: ndcg_at_10
value: 87.547
- task:
type: Retrieval
dataset:
name: MTEB EcomRetrieval
type: C-MTEB/EcomRetrieval
config: default
split: dev
revision: 687de13dc7294d6fd9be10c6945f9e8fec8166b9
metrics:
- type: ndcg_at_10
value: 64.85
- task:
type: Classification
dataset:
name: MTEB EmotionClassification
type: mteb/emotion
config: default
split: test
revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37
metrics:
- type: accuracy
value: 47.949999999999996
- task:
type: Retrieval
dataset:
name: MTEB FEVER
type: mteb/fever
config: default
split: test
revision: bea83ef9e8fb933d90a2f1d5515737465d613e12
metrics:
- type: ndcg_at_10
value: 92.111
- task:
type: Retrieval
dataset:
name: MTEB FiQA-PL
type: clarin-knext/fiqa-pl
config: default
split: test
revision: 2e535829717f8bf9dc829b7f911cc5bbd4e6608e
metrics:
- type: ndcg_at_10
value: 28.962
- task:
type: Retrieval
dataset:
name: MTEB FiQA2018
type: mteb/fiqa
config: default
split: test
revision: 27a168819829fe9bcd655c2df245fb19452e8e06
metrics:
- type: ndcg_at_10
value: 45.005
- task:
type: Clustering
dataset:
name: MTEB HALClusteringS2S
type: lyon-nlp/clustering-hal-s2s
config: default
split: test
revision: e06ebbbb123f8144bef1a5d18796f3dec9ae2915
metrics:
- type: v_measure
value: 25.133776435657595
- task:
type: Retrieval
dataset:
name: MTEB HotpotQA
type: mteb/hotpotqa
config: default
split: test
revision: ab518f4d6fcca38d87c25209f94beba119d02014
metrics:
- type: ndcg_at_10
value: 63.036
- task:
type: Retrieval
dataset:
name: MTEB HotpotQA-PL
type: clarin-knext/hotpotqa-pl
config: default
split: test
revision: a0bd479ac97b4ccb5bd6ce320c415d0bb4beb907
metrics:
- type: ndcg_at_10
value: 56.904999999999994
- task:
type: Classification
dataset:
name: MTEB IFlyTek
type: C-MTEB/IFlyTek-classification
config: default
split: validation
revision: 421605374b29664c5fc098418fe20ada9bd55f8a
metrics:
- type: accuracy
value: 44.59407464409388
- task:
type: Classification
dataset:
name: MTEB ImdbClassification
type: mteb/imdb
config: default
split: test
revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7
metrics:
- type: accuracy
value: 74.912
- task:
type: Classification
dataset:
name: MTEB JDReview
type: C-MTEB/JDReview-classification
config: default
split: test
revision: b7c64bd89eb87f8ded463478346f76731f07bf8b
metrics:
- type: accuracy
value: 79.26829268292683
- task:
type: STS
dataset:
name: MTEB LCQMC
type: C-MTEB/LCQMC
config: default
split: test
revision: 17f9b096f80380fce5ed12a9be8be7784b337daf
metrics:
- type: cos_sim_spearman
value: 74.8601229809791
- task:
type: Clustering
dataset:
name: MTEB MLSUMClusteringP2P
type: mlsum
config: default
split: test
revision: b5d54f8f3b61ae17845046286940f03c6bc79bc7
metrics:
- type: v_measure
value: 42.331902754246556
- type: v_measure
value: 40.92029335502153
- task:
type: Reranking
dataset:
name: MTEB MMarcoReranking
type: C-MTEB/Mmarco-reranking
config: default
split: dev
revision: 8e0c766dbe9e16e1d221116a3f36795fbade07f6
metrics:
- type: map
value: 32.19266316591337
- task:
type: Retrieval
dataset:
name: MTEB MMarcoRetrieval
type: C-MTEB/MMarcoRetrieval
config: default
split: dev
revision: 539bbde593d947e2a124ba72651aafc09eb33fc2
metrics:
- type: ndcg_at_10
value: 79.346
- task:
type: Retrieval
dataset:
name: MTEB MSMARCO
type: mteb/msmarco
config: default
split: dev
revision: c5a29a104738b98a9e76336939199e264163d4a0
metrics:
- type: ndcg_at_10
value: 39.922999999999995
- task:
type: Retrieval
dataset:
name: MTEB MSMARCO-PL
type: clarin-knext/msmarco-pl
config: default
split: test
revision: 8634c07806d5cce3a6138e260e59b81760a0a640
metrics:
- type: ndcg_at_10
value: 55.620999999999995
- task:
type: Classification
dataset:
name: MTEB MTOPDomainClassification (en)
type: mteb/mtop_domain
config: en
split: test
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
metrics:
- type: accuracy
value: 92.53989968080255
- task:
type: Classification
dataset:
name: MTEB MTOPDomainClassification (de)
type: mteb/mtop_domain
config: de
split: test
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
metrics:
- type: accuracy
value: 88.26993519301212
- task:
type: Classification
dataset:
name: MTEB MTOPDomainClassification (es)
type: mteb/mtop_domain
config: es
split: test
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
metrics:
- type: accuracy
value: 90.87725150100067
- task:
type: Classification
dataset:
name: MTEB MTOPDomainClassification (fr)
type: mteb/mtop_domain
config: fr
split: test
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
metrics:
- type: accuracy
value: 87.48512370811149
- task:
type: Classification
dataset:
name: MTEB MTOPDomainClassification (hi)
type: mteb/mtop_domain
config: hi
split: test
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
metrics:
- type: accuracy
value: 89.45141627823591
- task:
type: Classification
dataset:
name: MTEB MTOPDomainClassification (th)
type: mteb/mtop_domain
config: th
split: test
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
metrics:
- type: accuracy
value: 83.45750452079565
- task:
type: Classification
dataset:
name: MTEB MTOPIntentClassification (en)
type: mteb/mtop_intent
config: en
split: test
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
metrics:
- type: accuracy
value: 72.57637938896488
- task:
type: Classification
dataset:
name: MTEB MTOPIntentClassification (de)
type: mteb/mtop_intent
config: de
split: test
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
metrics:
- type: accuracy
value: 63.50803043110736
- task:
type: Classification
dataset:
name: MTEB MTOPIntentClassification (es)
type: mteb/mtop_intent
config: es
split: test
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
metrics:
- type: accuracy
value: 71.6577718478986
- task:
type: Classification
dataset:
name: MTEB MTOPIntentClassification (fr)
type: mteb/mtop_intent
config: fr
split: test
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
metrics:
- type: accuracy
value: 64.05887879736925
- task:
type: Classification
dataset:
name: MTEB MTOPIntentClassification (hi)
type: mteb/mtop_intent
config: hi
split: test
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
metrics:
- type: accuracy
value: 65.27070634636071
- task:
type: Classification
dataset:
name: MTEB MTOPIntentClassification (th)
type: mteb/mtop_intent
config: th
split: test
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
metrics:
- type: accuracy
value: 63.04520795660037
- task:
type: Classification
dataset:
name: MTEB MasakhaNEWSClassification (fra)
type: masakhane/masakhanews
config: fra
split: test
revision: 8ccc72e69e65f40c70e117d8b3c08306bb788b60
metrics:
- type: accuracy
value: 80.66350710900474
- task:
type: Clustering
dataset:
name: MTEB MasakhaNEWSClusteringP2P (fra)
type: masakhane/masakhanews
config: fra
split: test
revision: 8ccc72e69e65f40c70e117d8b3c08306bb788b60
metrics:
- type: v_measure
value: 44.016506455899425
- type: v_measure
value: 40.67730129573544
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (af)
type: mteb/amazon_massive_intent
config: af
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 57.94552790854068
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (am)
type: mteb/amazon_massive_intent
config: am
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 49.273705447209146
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (ar)
type: mteb/amazon_massive_intent
config: ar
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 55.490921318090116
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (az)
type: mteb/amazon_massive_intent
config: az
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 60.97511768661733
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (bn)
type: mteb/amazon_massive_intent
config: bn
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 57.5689307330195
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (cy)
type: mteb/amazon_massive_intent
config: cy
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 48.34902488231337
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (da)
type: mteb/amazon_massive_intent
config: da
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 63.6684599865501
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (de)
type: mteb/amazon_massive_intent
config: de
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 62.54539340954942
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (el)
type: mteb/amazon_massive_intent
config: el
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 63.08675184936112
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (en)
type: mteb/amazon_massive_intent
config: en
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 72.12508406186953
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (es)
type: mteb/amazon_massive_intent
config: es
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 67.41425689307331
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (fa)
type: mteb/amazon_massive_intent
config: fa
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 65.59515803631474
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (fi)
type: mteb/amazon_massive_intent
config: fi
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 62.90517821116342
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (fr)
type: mteb/amazon_massive_intent
config: fr
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 67.91526563550774
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (he)
type: mteb/amazon_massive_intent
config: he
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 55.198386012104905
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (hi)
type: mteb/amazon_massive_intent
config: hi
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 65.04371217215869
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (hu)
type: mteb/amazon_massive_intent
config: hu
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 63.31203765971756
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (hy)
type: mteb/amazon_massive_intent
config: hy
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 55.521183591123055
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (id)
type: mteb/amazon_massive_intent
config: id
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 66.06254203093476
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (is)
type: mteb/amazon_massive_intent
config: is
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 56.01546738399461
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (it)
type: mteb/amazon_massive_intent
config: it
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 67.27975790181574
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (ja)
type: mteb/amazon_massive_intent
config: ja
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 66.79556153328849
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (jv)
type: mteb/amazon_massive_intent
config: jv
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 50.18493611297915
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (ka)
type: mteb/amazon_massive_intent
config: ka
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 47.888365837256224
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (km)
type: mteb/amazon_massive_intent
config: km
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 50.79690652320108
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (kn)
type: mteb/amazon_massive_intent
config: kn
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 57.225958305312716
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (ko)
type: mteb/amazon_massive_intent
config: ko
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 64.58641560188299
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (lv)
type: mteb/amazon_massive_intent
config: lv
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 59.08204438466711
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (ml)
type: mteb/amazon_massive_intent
config: ml
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 59.54606590450572
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (mn)
type: mteb/amazon_massive_intent
config: mn
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 53.443174176193665
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (ms)
type: mteb/amazon_massive_intent
config: ms
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 61.65097511768661
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (my)
type: mteb/amazon_massive_intent
config: my
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 53.45662407531944
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (nb)
type: mteb/amazon_massive_intent
config: nb
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 63.739071956960316
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (nl)
type: mteb/amazon_massive_intent
config: nl
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 66.36180228648286
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (pl)
type: mteb/amazon_massive_intent
config: pl
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 66.3920645595158
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (pt)
type: mteb/amazon_massive_intent
config: pt
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 68.06993947545395
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (ro)
type: mteb/amazon_massive_intent
config: ro
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 63.123739071956955
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (ru)
type: mteb/amazon_massive_intent
config: ru
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 67.46133154001346
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (sl)
type: mteb/amazon_massive_intent
config: sl
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 60.54472091459314
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (sq)
type: mteb/amazon_massive_intent
config: sq
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 58.204438466711494
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (sv)
type: mteb/amazon_massive_intent
config: sv
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 65.69603227975792
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (sw)
type: mteb/amazon_massive_intent
config: sw
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 51.684599865501
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (ta)
type: mteb/amazon_massive_intent
config: ta
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 58.523873570948226
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (te)
type: mteb/amazon_massive_intent
config: te
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 58.53396099529253
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (th)
type: mteb/amazon_massive_intent
config: th
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 61.88298587760591
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (tl)
type: mteb/amazon_massive_intent
config: tl
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 56.65097511768662
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (tr)
type: mteb/amazon_massive_intent
config: tr
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 64.8453261600538
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (ur)
type: mteb/amazon_massive_intent
config: ur
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 58.6247478143914
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (vi)
type: mteb/amazon_massive_intent
config: vi
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 64.16274377942166
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (zh-CN)
type: mteb/amazon_massive_intent
config: zh-CN
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 69.61667787491594
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (zh-TW)
type: mteb/amazon_massive_intent
config: zh-TW
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 64.17283120376598
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (af)
type: mteb/amazon_massive_scenario
config: af
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 64.89912575655683
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (am)
type: mteb/amazon_massive_scenario
config: am
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 57.27975790181573
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (ar)
type: mteb/amazon_massive_scenario
config: ar
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 62.269670477471415
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (az)
type: mteb/amazon_massive_scenario
config: az
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 65.10423671822461
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (bn)
type: mteb/amazon_massive_scenario
config: bn
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 62.40753194351043
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (cy)
type: mteb/amazon_massive_scenario
config: cy
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 55.369872225958304
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (da)
type: mteb/amazon_massive_scenario
config: da
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 71.60726294552792
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (de)
type: mteb/amazon_massive_scenario
config: de
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 70.30262273032952
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (el)
type: mteb/amazon_massive_scenario
config: el
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 69.52925353059851
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (en)
type: mteb/amazon_massive_scenario
config: en
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 76.28446536650976
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (es)
type: mteb/amazon_massive_scenario
config: es
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 72.45460659045058
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (fa)
type: mteb/amazon_massive_scenario
config: fa
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 70.26563550773368
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (fi)
type: mteb/amazon_massive_scenario
config: fi
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 67.20578345662408
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (fr)
type: mteb/amazon_massive_scenario
config: fr
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 72.64963012777405
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (he)
type: mteb/amazon_massive_scenario
config: he
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 61.698049764626774
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (hi)
type: mteb/amazon_massive_scenario
config: hi
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 70.14458641560188
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (hu)
type: mteb/amazon_massive_scenario
config: hu
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 70.51445864156018
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (hy)
type: mteb/amazon_massive_scenario
config: hy
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 60.13786146603901
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (id)
type: mteb/amazon_massive_scenario
config: id
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 70.61533288500337
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (is)
type: mteb/amazon_massive_scenario
config: is
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 61.526563550773375
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (it)
type: mteb/amazon_massive_scenario
config: it
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 71.99731002017484
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (ja)
type: mteb/amazon_massive_scenario
config: ja
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 71.59381304640216
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (jv)
type: mteb/amazon_massive_scenario
config: jv
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 57.010759919300604
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (ka)
type: mteb/amazon_massive_scenario
config: ka
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 53.26160053799597
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (km)
type: mteb/amazon_massive_scenario
config: km
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 57.800941492938804
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (kn)
type: mteb/amazon_massive_scenario
config: kn
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 62.387357094821795
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (ko)
type: mteb/amazon_massive_scenario
config: ko
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 69.5359784801614
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (lv)
type: mteb/amazon_massive_scenario
config: lv
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 63.36919973100203
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (ml)
type: mteb/amazon_massive_scenario
config: ml
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 64.81506388702084
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (mn)
type: mteb/amazon_massive_scenario
config: mn
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 59.35104236718225
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (ms)
type: mteb/amazon_massive_scenario
config: ms
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 66.67787491593813
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (my)
type: mteb/amazon_massive_scenario
config: my
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 59.4250168123739
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (nb)
type: mteb/amazon_massive_scenario
config: nb
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 71.49630127774043
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (nl)
type: mteb/amazon_massive_scenario
config: nl
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 71.95696032279758
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (pl)
type: mteb/amazon_massive_scenario
config: pl
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 70.11768661735036
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (pt)
type: mteb/amazon_massive_scenario
config: pt
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 71.86953597848016
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (ro)
type: mteb/amazon_massive_scenario
config: ro
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 68.51042367182247
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (ru)
type: mteb/amazon_massive_scenario
config: ru
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 71.65097511768661
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (sl)
type: mteb/amazon_massive_scenario
config: sl
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 66.81573638197713
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (sq)
type: mteb/amazon_massive_scenario
config: sq
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 65.26227303295225
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (sv)
type: mteb/amazon_massive_scenario
config: sv
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 72.51513113651646
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (sw)
type: mteb/amazon_massive_scenario
config: sw
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 58.29858776059179
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (ta)
type: mteb/amazon_massive_scenario
config: ta
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 62.72696704774714
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (te)
type: mteb/amazon_massive_scenario
config: te
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 66.57700067249496
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (th)
type: mteb/amazon_massive_scenario
config: th
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 68.22797579018157
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (tl)
type: mteb/amazon_massive_scenario
config: tl
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 61.97041022192333
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (tr)
type: mteb/amazon_massive_scenario
config: tr
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 70.72629455279085
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (ur)
type: mteb/amazon_massive_scenario
config: ur
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 63.16072629455278
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (vi)
type: mteb/amazon_massive_scenario
config: vi
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 67.92199058507062
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (zh-CN)
type: mteb/amazon_massive_scenario
config: zh-CN
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 74.40484196368527
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (zh-TW)
type: mteb/amazon_massive_scenario
config: zh-TW
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 71.61398789509079
- task:
type: Retrieval
dataset:
name: MTEB MedicalRetrieval
type: C-MTEB/MedicalRetrieval
config: default
split: dev
revision: 2039188fb5800a9803ba5048df7b76e6fb151fc6
metrics:
- type: ndcg_at_10
value: 61.934999999999995
- task:
type: Clustering
dataset:
name: MTEB MedrxivClusteringP2P
type: mteb/medrxiv-clustering-p2p
config: default
split: test
revision: e7a26af6f3ae46b30dde8737f02c07b1505bcc73
metrics:
- type: v_measure
value: 33.052031054565205
- task:
type: Clustering
dataset:
name: MTEB MedrxivClusteringS2S
type: mteb/medrxiv-clustering-s2s
config: default
split: test
revision: 35191c8c0dca72d8ff3efcd72aa802307d469663
metrics:
- type: v_measure
value: 31.969909524076794
- task:
type: Reranking
dataset:
name: MTEB MindSmallReranking
type: mteb/mind_small
config: default
split: test
revision: 3bdac13927fdc888b903db93b2ffdbd90b295a69
metrics:
- type: map
value: 31.7530992892652
- task:
type: Retrieval
dataset:
name: MTEB MintakaRetrieval (fr)
type: jinaai/mintakaqa
config: fr
split: test
revision: efa78cc2f74bbcd21eff2261f9e13aebe40b814e
metrics:
- type: ndcg_at_10
value: 34.705999999999996
- task:
type: Retrieval
dataset:
name: MTEB MultiLongDocRetrieval (ar)
type: Shitao/MLDR
config: ar
split: test
revision: None
metrics:
- type: ndcg_at_10
value: 55.166000000000004
- task:
type: Retrieval
dataset:
name: MTEB MultiLongDocRetrieval (de)
type: Shitao/MLDR
config: de
split: test
revision: None
metrics:
- type: ndcg_at_10
value: 55.155
- task:
type: Retrieval
dataset:
name: MTEB MultiLongDocRetrieval (en)
type: Shitao/MLDR
config: en
split: test
revision: None
metrics:
- type: ndcg_at_10
value: 50.993
- task:
type: Retrieval
dataset:
name: MTEB MultiLongDocRetrieval (es)
type: Shitao/MLDR
config: es
split: test
revision: None
metrics:
- type: ndcg_at_10
value: 81.228
- task:
type: Retrieval
dataset:
name: MTEB MultiLongDocRetrieval (fr)
type: Shitao/MLDR
config: fr
split: test
revision: None
metrics:
- type: ndcg_at_10
value: 76.19
- task:
type: Retrieval
dataset:
name: MTEB MultiLongDocRetrieval (hi)
type: Shitao/MLDR
config: hi
split: test
revision: None
metrics:
- type: ndcg_at_10
value: 45.206
- task:
type: Retrieval
dataset:
name: MTEB MultiLongDocRetrieval (it)
type: Shitao/MLDR
config: it
split: test
revision: None
metrics:
- type: ndcg_at_10
value: 66.741
- task:
type: Retrieval
dataset:
name: MTEB MultiLongDocRetrieval (ja)
type: Shitao/MLDR
config: ja
split: test
revision: None
metrics:
- type: ndcg_at_10
value: 52.111
- task:
type: Retrieval
dataset:
name: MTEB MultiLongDocRetrieval (ko)
type: Shitao/MLDR
config: ko
split: test
revision: None
metrics:
- type: ndcg_at_10
value: 46.733000000000004
- task:
type: Retrieval
dataset:
name: MTEB MultiLongDocRetrieval (pt)
type: Shitao/MLDR
config: pt
split: test
revision: None
metrics:
- type: ndcg_at_10
value: 79.105
- task:
type: Retrieval
dataset:
name: MTEB MultiLongDocRetrieval (ru)
type: Shitao/MLDR
config: ru
split: test
revision: None
metrics:
- type: ndcg_at_10
value: 64.21
- task:
type: Retrieval
dataset:
name: MTEB MultiLongDocRetrieval (th)
type: Shitao/MLDR
config: th
split: test
revision: None
metrics:
- type: ndcg_at_10
value: 35.467
- task:
type: Retrieval
dataset:
name: MTEB MultiLongDocRetrieval (zh)
type: Shitao/MLDR
config: zh
split: test
revision: None
metrics:
- type: ndcg_at_10
value: 27.419
- task:
type: Classification
dataset:
name: MTEB MultilingualSentiment
type: C-MTEB/MultilingualSentiment-classification
config: default
split: validation
revision: 46958b007a63fdbf239b7672c25d0bea67b5ea1a
metrics:
- type: accuracy
value: 61.02000000000001
- task:
type: Retrieval
dataset:
name: MTEB NFCorpus
type: mteb/nfcorpus
config: default
split: test
revision: ec0fa4fe99da2ff19ca1214b7966684033a58814
metrics:
- type: ndcg_at_10
value: 36.65
- task:
type: Retrieval
dataset:
name: MTEB NFCorpus-PL
type: clarin-knext/nfcorpus-pl
config: default
split: test
revision: 9a6f9567fda928260afed2de480d79c98bf0bec0
metrics:
- type: ndcg_at_10
value: 26.831
- task:
type: Retrieval
dataset:
name: MTEB NQ
type: mteb/nq
config: default
split: test
revision: b774495ed302d8c44a3a7ea25c90dbce03968f31
metrics:
- type: ndcg_at_10
value: 58.111000000000004
- task:
type: Retrieval
dataset:
name: MTEB NQ-PL
type: clarin-knext/nq-pl
config: default
split: test
revision: f171245712cf85dd4700b06bef18001578d0ca8d
metrics:
- type: ndcg_at_10
value: 43.126999999999995
- task:
type: PairClassification
dataset:
name: MTEB Ocnli
type: C-MTEB/OCNLI
config: default
split: validation
revision: 66e76a618a34d6d565d5538088562851e6daa7ec
metrics:
- type: cos_sim_ap
value: 72.67630697316041
- task:
type: Classification
dataset:
name: MTEB OnlineShopping
type: C-MTEB/OnlineShopping-classification
config: default
split: test
revision: e610f2ebd179a8fda30ae534c3878750a96db120
metrics:
- type: accuracy
value: 84.85000000000001
- task:
type: PairClassification
dataset:
name: MTEB OpusparcusPC (fr)
type: GEM/opusparcus
config: fr
split: test
revision: 9e9b1f8ef51616073f47f306f7f47dd91663f86a
metrics:
- type: cos_sim_ap
value: 100
- task:
type: Classification
dataset:
name: MTEB PAC
type: laugustyniak/abusive-clauses-pl
config: default
split: test
revision: None
metrics:
- type: accuracy
value: 65.99189110918043
- task:
type: STS
dataset:
name: MTEB PAWSX
type: C-MTEB/PAWSX
config: default
split: test
revision: 9c6a90e430ac22b5779fb019a23e820b11a8b5e1
metrics:
- type: cos_sim_spearman
value: 16.124364530596228
- task:
type: PairClassification
dataset:
name: MTEB PPC
type: PL-MTEB/ppc-pairclassification
config: default
split: test
revision: None
metrics:
- type: cos_sim_ap
value: 92.43431057460192
- task:
type: PairClassification
dataset:
name: MTEB PSC
type: PL-MTEB/psc-pairclassification
config: default
split: test
revision: None
metrics:
- type: cos_sim_ap
value: 99.06090138049724
- task:
type: PairClassification
dataset:
name: MTEB PawsX (fr)
type: paws-x
config: fr
split: test
revision: 8a04d940a42cd40658986fdd8e3da561533a3646
metrics:
- type: cos_sim_ap
value: 58.9314954874314
- task:
type: Classification
dataset:
name: MTEB PolEmo2.0-IN
type: PL-MTEB/polemo2_in
config: default
split: test
revision: None
metrics:
- type: accuracy
value: 69.59833795013851
- task:
type: Classification
dataset:
name: MTEB PolEmo2.0-OUT
type: PL-MTEB/polemo2_out
config: default
split: test
revision: None
metrics:
- type: accuracy
value: 44.73684210526315
- task:
type: STS
dataset:
name: MTEB QBQTC
type: C-MTEB/QBQTC
config: default
split: test
revision: 790b0510dc52b1553e8c49f3d2afb48c0e5c48b7
metrics:
- type: cos_sim_spearman
value: 39.36450754137984
- task:
type: Retrieval
dataset:
name: MTEB Quora-PL
type: clarin-knext/quora-pl
config: default
split: test
revision: 0be27e93455051e531182b85e85e425aba12e9d4
metrics:
- type: ndcg_at_10
value: 80.76299999999999
- task:
type: Retrieval
dataset:
name: MTEB QuoraRetrieval
type: mteb/quora
config: default
split: test
revision: None
metrics:
- type: ndcg_at_10
value: 88.022
- task:
type: Clustering
dataset:
name: MTEB RedditClustering
type: mteb/reddit-clustering
config: default
split: test
revision: 24640382cdbf8abc73003fb0fa6d111a705499eb
metrics:
- type: v_measure
value: 55.719165988934385
- task:
type: Clustering
dataset:
name: MTEB RedditClusteringP2P
type: mteb/reddit-clustering-p2p
config: default
split: test
revision: 282350215ef01743dc01b456c7f5241fa8937f16
metrics:
- type: v_measure
value: 62.25390069273025
- task:
type: Retrieval
dataset:
name: MTEB SCIDOCS
type: mteb/scidocs
config: default
split: test
revision: None
metrics:
- type: ndcg_at_10
value: 18.243000000000002
- task:
type: Retrieval
dataset:
name: MTEB SCIDOCS-PL
type: clarin-knext/scidocs-pl
config: default
split: test
revision: 45452b03f05560207ef19149545f168e596c9337
metrics:
- type: ndcg_at_10
value: 14.219000000000001
- task:
type: PairClassification
dataset:
name: MTEB SICK-E-PL
type: PL-MTEB/sicke-pl-pairclassification
config: default
split: test
revision: None
metrics:
- type: cos_sim_ap
value: 75.4022630307816
- task:
type: STS
dataset:
name: MTEB SICK-R
type: mteb/sickr-sts
config: default
split: test
revision: a6ea5a8cab320b040a23452cc28066d9beae2cee
metrics:
- type: cos_sim_spearman
value: 79.34269390198548
- task:
type: STS
dataset:
name: MTEB SICK-R-PL
type: PL-MTEB/sickr-pl-sts
config: default
split: test
revision: None
metrics:
- type: cos_sim_spearman
value: 74.0651660446132
- task:
type: STS
dataset:
name: MTEB SICKFr
type: Lajavaness/SICK-fr
config: default
split: test
revision: e077ab4cf4774a1e36d86d593b150422fafd8e8a
metrics:
- type: cos_sim_spearman
value: 78.62693119733123
- task:
type: STS
dataset:
name: MTEB STS12
type: mteb/sts12-sts
config: default
split: test
revision: a0d554a64d88156834ff5ae9920b964011b16384
metrics:
- type: cos_sim_spearman
value: 77.50660544631359
- task:
type: STS
dataset:
name: MTEB STS13
type: mteb/sts13-sts
config: default
split: test
revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca
metrics:
- type: cos_sim_spearman
value: 85.55415077723738
- task:
type: STS
dataset:
name: MTEB STS14
type: mteb/sts14-sts
config: default
split: test
revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375
metrics:
- type: cos_sim_spearman
value: 81.67550814479077
- task:
type: STS
dataset:
name: MTEB STS15
type: mteb/sts15-sts
config: default
split: test
revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3
metrics:
- type: cos_sim_spearman
value: 88.94601412322764
- task:
type: STS
dataset:
name: MTEB STS16
type: mteb/sts16-sts
config: default
split: test
revision: 4d8694f8f0e0100860b497b999b3dbed754a0513
metrics:
- type: cos_sim_spearman
value: 84.33844259337481
- task:
type: STS
dataset:
name: MTEB STS17 (ko-ko)
type: mteb/sts17-crosslingual-sts
config: ko-ko
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_spearman
value: 81.58650681159105
- task:
type: STS
dataset:
name: MTEB STS17 (ar-ar)
type: mteb/sts17-crosslingual-sts
config: ar-ar
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_spearman
value: 78.82472265884256
- task:
type: STS
dataset:
name: MTEB STS17 (en-ar)
type: mteb/sts17-crosslingual-sts
config: en-ar
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_spearman
value: 76.43637938260397
- task:
type: STS
dataset:
name: MTEB STS17 (en-de)
type: mteb/sts17-crosslingual-sts
config: en-de
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_spearman
value: 84.71008299464059
- task:
type: STS
dataset:
name: MTEB STS17 (en-en)
type: mteb/sts17-crosslingual-sts
config: en-en
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_spearman
value: 88.88074713413747
- task:
type: STS
dataset:
name: MTEB STS17 (en-tr)
type: mteb/sts17-crosslingual-sts
config: en-tr
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_spearman
value: 76.36405640457285
- task:
type: STS
dataset:
name: MTEB STS17 (es-en)
type: mteb/sts17-crosslingual-sts
config: es-en
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_spearman
value: 83.84737910084762
- task:
type: STS
dataset:
name: MTEB STS17 (es-es)
type: mteb/sts17-crosslingual-sts
config: es-es
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_spearman
value: 87.03931621433031
- task:
type: STS
dataset:
name: MTEB STS17 (fr-en)
type: mteb/sts17-crosslingual-sts
config: fr-en
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_spearman
value: 84.43335591752246
- task:
type: STS
dataset:
name: MTEB STS17 (it-en)
type: mteb/sts17-crosslingual-sts
config: it-en
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_spearman
value: 83.85268648747021
- task:
type: STS
dataset:
name: MTEB STS17 (nl-en)
type: mteb/sts17-crosslingual-sts
config: nl-en
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_spearman
value: 82.45786516224341
- task:
type: STS
dataset:
name: MTEB STS22 (en)
type: mteb/sts22-crosslingual-sts
config: en
split: test
revision: eea2b4fe26a775864c896887d910b76a8098ad3f
metrics:
- type: cos_sim_spearman
value: 67.20227303970304
- task:
type: STS
dataset:
name: MTEB STS22 (de)
type: mteb/sts22-crosslingual-sts
config: de
split: test
revision: eea2b4fe26a775864c896887d910b76a8098ad3f
metrics:
- type: cos_sim_spearman
value: 60.892838305537126
- task:
type: STS
dataset:
name: MTEB STS22 (es)
type: mteb/sts22-crosslingual-sts
config: es
split: test
revision: eea2b4fe26a775864c896887d910b76a8098ad3f
metrics:
- type: cos_sim_spearman
value: 72.01876318464508
- task:
type: STS
dataset:
name: MTEB STS22 (pl)
type: mteb/sts22-crosslingual-sts
config: pl
split: test
revision: eea2b4fe26a775864c896887d910b76a8098ad3f
metrics:
- type: cos_sim_spearman
value: 42.3879320510127
- task:
type: STS
dataset:
name: MTEB STS22 (tr)
type: mteb/sts22-crosslingual-sts
config: tr
split: test
revision: eea2b4fe26a775864c896887d910b76a8098ad3f
metrics:
- type: cos_sim_spearman
value: 65.54048784845729
- task:
type: STS
dataset:
name: MTEB STS22 (ar)
type: mteb/sts22-crosslingual-sts
config: ar
split: test
revision: eea2b4fe26a775864c896887d910b76a8098ad3f
metrics:
- type: cos_sim_spearman
value: 58.55244068334867
- task:
type: STS
dataset:
name: MTEB STS22 (ru)
type: mteb/sts22-crosslingual-sts
config: ru
split: test
revision: eea2b4fe26a775864c896887d910b76a8098ad3f
metrics:
- type: cos_sim_spearman
value: 66.48710288440624
- task:
type: STS
dataset:
name: MTEB STS22 (zh)
type: mteb/sts22-crosslingual-sts
config: zh
split: test
revision: eea2b4fe26a775864c896887d910b76a8098ad3f
metrics:
- type: cos_sim_spearman
value: 66.585754901838
- task:
type: STS
dataset:
name: MTEB STS22 (fr)
type: mteb/sts22-crosslingual-sts
config: fr
split: test
revision: eea2b4fe26a775864c896887d910b76a8098ad3f
metrics:
- type: cos_sim_spearman
value: 81.03001290557805
- task:
type: STS
dataset:
name: MTEB STS22 (de-en)
type: mteb/sts22-crosslingual-sts
config: de-en
split: test
revision: eea2b4fe26a775864c896887d910b76a8098ad3f
metrics:
- type: cos_sim_spearman
value: 62.28001859884359
- task:
type: STS
dataset:
name: MTEB STS22 (es-en)
type: mteb/sts22-crosslingual-sts
config: es-en
split: test
revision: eea2b4fe26a775864c896887d910b76a8098ad3f
metrics:
- type: cos_sim_spearman
value: 79.64106342105019
- task:
type: STS
dataset:
name: MTEB STS22 (it)
type: mteb/sts22-crosslingual-sts
config: it
split: test
revision: eea2b4fe26a775864c896887d910b76a8098ad3f
metrics:
- type: cos_sim_spearman
value: 78.27915339361124
- task:
type: STS
dataset:
name: MTEB STS22 (pl-en)
type: mteb/sts22-crosslingual-sts
config: pl-en
split: test
revision: eea2b4fe26a775864c896887d910b76a8098ad3f
metrics:
- type: cos_sim_spearman
value: 78.28574268257462
- task:
type: STS
dataset:
name: MTEB STS22 (zh-en)
type: mteb/sts22-crosslingual-sts
config: zh-en
split: test
revision: eea2b4fe26a775864c896887d910b76a8098ad3f
metrics:
- type: cos_sim_spearman
value: 72.92658860751482
- task:
type: STS
dataset:
name: MTEB STS22 (es-it)
type: mteb/sts22-crosslingual-sts
config: es-it
split: test
revision: eea2b4fe26a775864c896887d910b76a8098ad3f
metrics:
- type: cos_sim_spearman
value: 74.83418886368217
- task:
type: STS
dataset:
name: MTEB STS22 (de-fr)
type: mteb/sts22-crosslingual-sts
config: de-fr
split: test
revision: eea2b4fe26a775864c896887d910b76a8098ad3f
metrics:
- type: cos_sim_spearman
value: 56.01064022625769
- task:
type: STS
dataset:
name: MTEB STS22 (de-pl)
type: mteb/sts22-crosslingual-sts
config: de-pl
split: test
revision: eea2b4fe26a775864c896887d910b76a8098ad3f
metrics:
- type: cos_sim_spearman
value: 53.64332829635126
- task:
type: STS
dataset:
name: MTEB STS22 (fr-pl)
type: mteb/sts22-crosslingual-sts
config: fr-pl
split: test
revision: eea2b4fe26a775864c896887d910b76a8098ad3f
metrics:
- type: cos_sim_spearman
value: 73.24670207647144
- task:
type: STS
dataset:
name: MTEB STSB
type: C-MTEB/STSB
config: default
split: test
revision: 0cde68302b3541bb8b3c340dc0644b0b745b3dc0
metrics:
- type: cos_sim_spearman
value: 80.7157790971544
- task:
type: STS
dataset:
name: MTEB STSBenchmark
type: mteb/stsbenchmark-sts
config: default
split: test
revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831
metrics:
- type: cos_sim_spearman
value: 86.45763616928973
- task:
type: STS
dataset:
name: MTEB STSBenchmarkMultilingualSTS (fr)
type: stsb_multi_mt
config: fr
split: test
revision: 93d57ef91790589e3ce9c365164337a8a78b7632
metrics:
- type: cos_sim_spearman
value: 84.4335500335282
- task:
type: Reranking
dataset:
name: MTEB SciDocsRR
type: mteb/scidocs-reranking
config: default
split: test
revision: d3c5e1fc0b855ab6097bf1cda04dd73947d7caab
metrics:
- type: map
value: 84.15276484499303
- task:
type: Retrieval
dataset:
name: MTEB SciFact
type: mteb/scifact
config: default
split: test
revision: 0228b52cf27578f30900b9e5271d331663a030d7
metrics:
- type: ndcg_at_10
value: 73.433
- task:
type: Retrieval
dataset:
name: MTEB SciFact-PL
type: clarin-knext/scifact-pl
config: default
split: test
revision: 47932a35f045ef8ed01ba82bf9ff67f6e109207e
metrics:
- type: ndcg_at_10
value: 58.919999999999995
- task:
type: PairClassification
dataset:
name: MTEB SprintDuplicateQuestions
type: mteb/sprintduplicatequestions-pairclassification
config: default
split: test
revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46
metrics:
- type: cos_sim_ap
value: 95.40564890916419
- task:
type: Clustering
dataset:
name: MTEB StackExchangeClustering
type: mteb/stackexchange-clustering
config: default
split: test
revision: 6cbc1f7b2bc0622f2e39d2c77fa502909748c259
metrics:
- type: v_measure
value: 63.41856697730145
- task:
type: Clustering
dataset:
name: MTEB StackExchangeClusteringP2P
type: mteb/stackexchange-clustering-p2p
config: default
split: test
revision: 815ca46b2622cec33ccafc3735d572c266efdb44
metrics:
- type: v_measure
value: 31.709285904909112
- task:
type: Reranking
dataset:
name: MTEB StackOverflowDupQuestions
type: mteb/stackoverflowdupquestions-reranking
config: default
split: test
revision: e185fbe320c72810689fc5848eb6114e1ef5ec69
metrics:
- type: map
value: 52.09341030060322
- task:
type: Summarization
dataset:
name: MTEB SummEval
type: mteb/summeval
config: default
split: test
revision: cda12ad7615edc362dbf25a00fdd61d3b1eaf93c
metrics:
- type: cos_sim_spearman
value: 30.58262517835034
- task:
type: Summarization
dataset:
name: MTEB SummEvalFr
type: lyon-nlp/summarization-summeval-fr-p2p
config: default
split: test
revision: b385812de6a9577b6f4d0f88c6a6e35395a94054
metrics:
- type: cos_sim_spearman
value: 29.744542072951358
- task:
type: Reranking
dataset:
name: MTEB SyntecReranking
type: lyon-nlp/mteb-fr-reranking-syntec-s2p
config: default
split: test
revision: b205c5084a0934ce8af14338bf03feb19499c84d
metrics:
- type: map
value: 88.03333333333333
- task:
type: Retrieval
dataset:
name: MTEB SyntecRetrieval
type: lyon-nlp/mteb-fr-retrieval-syntec-s2p
config: default
split: test
revision: 77f7e271bf4a92b24fce5119f3486b583ca016ff
metrics:
- type: ndcg_at_10
value: 83.043
- task:
type: Reranking
dataset:
name: MTEB T2Reranking
type: C-MTEB/T2Reranking
config: default
split: dev
revision: 76631901a18387f85eaa53e5450019b87ad58ef9
metrics:
- type: map
value: 67.08577894804324
- task:
type: Retrieval
dataset:
name: MTEB T2Retrieval
type: C-MTEB/T2Retrieval
config: default
split: dev
revision: 8731a845f1bf500a4f111cf1070785c793d10e64
metrics:
- type: ndcg_at_10
value: 84.718
- task:
type: Classification
dataset:
name: MTEB TNews
type: C-MTEB/TNews-classification
config: default
split: validation
revision: 317f262bf1e6126357bbe89e875451e4b0938fe4
metrics:
- type: accuracy
value: 48.726
- task:
type: Retrieval
dataset:
name: MTEB TRECCOVID
type: mteb/trec-covid
config: default
split: test
revision: None
metrics:
- type: ndcg_at_10
value: 57.56
- task:
type: Retrieval
dataset:
name: MTEB TRECCOVID-PL
type: clarin-knext/trec-covid-pl
config: default
split: test
revision: 81bcb408f33366c2a20ac54adafad1ae7e877fdd
metrics:
- type: ndcg_at_10
value: 59.355999999999995
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (sqi-eng)
type: mteb/tatoeba-bitext-mining
config: sqi-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 82.765
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (fry-eng)
type: mteb/tatoeba-bitext-mining
config: fry-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 73.69942196531792
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (kur-eng)
type: mteb/tatoeba-bitext-mining
config: kur-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 32.86585365853657
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (tur-eng)
type: mteb/tatoeba-bitext-mining
config: tur-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 95.81666666666666
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (deu-eng)
type: mteb/tatoeba-bitext-mining
config: deu-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 97.75
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (nld-eng)
type: mteb/tatoeba-bitext-mining
config: nld-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 93.78333333333335
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (ron-eng)
type: mteb/tatoeba-bitext-mining
config: ron-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 90.72333333333333
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (ang-eng)
type: mteb/tatoeba-bitext-mining
config: ang-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 42.45202558635395
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (ido-eng)
type: mteb/tatoeba-bitext-mining
config: ido-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 77.59238095238095
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (jav-eng)
type: mteb/tatoeba-bitext-mining
config: jav-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 35.69686411149825
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (isl-eng)
type: mteb/tatoeba-bitext-mining
config: isl-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 82.59333333333333
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (slv-eng)
type: mteb/tatoeba-bitext-mining
config: slv-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 84.1456922987907
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (cym-eng)
type: mteb/tatoeba-bitext-mining
config: cym-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 52.47462133594857
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (kaz-eng)
type: mteb/tatoeba-bitext-mining
config: kaz-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 67.62965440356746
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (est-eng)
type: mteb/tatoeba-bitext-mining
config: est-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 79.48412698412699
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (heb-eng)
type: mteb/tatoeba-bitext-mining
config: heb-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 75.85
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (gla-eng)
type: mteb/tatoeba-bitext-mining
config: gla-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 27.32600866497127
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (mar-eng)
type: mteb/tatoeba-bitext-mining
config: mar-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 84.38
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (lat-eng)
type: mteb/tatoeba-bitext-mining
config: lat-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 42.98888712165028
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (bel-eng)
type: mteb/tatoeba-bitext-mining
config: bel-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 85.55690476190476
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (pms-eng)
type: mteb/tatoeba-bitext-mining
config: pms-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 46.68466031323174
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (gle-eng)
type: mteb/tatoeba-bitext-mining
config: gle-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 32.73071428571428
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (pes-eng)
type: mteb/tatoeba-bitext-mining
config: pes-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 88.26333333333334
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (nob-eng)
type: mteb/tatoeba-bitext-mining
config: nob-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 96.61666666666666
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (bul-eng)
type: mteb/tatoeba-bitext-mining
config: bul-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 91.30666666666666
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (cbk-eng)
type: mteb/tatoeba-bitext-mining
config: cbk-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 70.03714285714285
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (hun-eng)
type: mteb/tatoeba-bitext-mining
config: hun-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 89.09
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (uig-eng)
type: mteb/tatoeba-bitext-mining
config: uig-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 59.570476190476185
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (rus-eng)
type: mteb/tatoeba-bitext-mining
config: rus-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 92.9
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (spa-eng)
type: mteb/tatoeba-bitext-mining
config: spa-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 97.68333333333334
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (hye-eng)
type: mteb/tatoeba-bitext-mining
config: hye-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 80.40880503144653
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (tel-eng)
type: mteb/tatoeba-bitext-mining
config: tel-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 89.7008547008547
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (afr-eng)
type: mteb/tatoeba-bitext-mining
config: afr-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 81.84833333333333
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (mon-eng)
type: mteb/tatoeba-bitext-mining
config: mon-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 71.69696969696969
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (arz-eng)
type: mteb/tatoeba-bitext-mining
config: arz-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 55.76985790822269
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (hrv-eng)
type: mteb/tatoeba-bitext-mining
config: hrv-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 91.66666666666666
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (nov-eng)
type: mteb/tatoeba-bitext-mining
config: nov-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 68.36668519547896
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (gsw-eng)
type: mteb/tatoeba-bitext-mining
config: gsw-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 36.73992673992674
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (nds-eng)
type: mteb/tatoeba-bitext-mining
config: nds-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 63.420952380952365
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (ukr-eng)
type: mteb/tatoeba-bitext-mining
config: ukr-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 91.28999999999999
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (uzb-eng)
type: mteb/tatoeba-bitext-mining
config: uzb-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 40.95392490046146
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (lit-eng)
type: mteb/tatoeba-bitext-mining
config: lit-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 77.58936507936508
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (ina-eng)
type: mteb/tatoeba-bitext-mining
config: ina-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 91.28999999999999
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (lfn-eng)
type: mteb/tatoeba-bitext-mining
config: lfn-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 63.563650793650794
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (zsm-eng)
type: mteb/tatoeba-bitext-mining
config: zsm-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 94.35
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (ita-eng)
type: mteb/tatoeba-bitext-mining
config: ita-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 91.43
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (cmn-eng)
type: mteb/tatoeba-bitext-mining
config: cmn-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 95.73333333333332
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (lvs-eng)
type: mteb/tatoeba-bitext-mining
config: lvs-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 79.38666666666667
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (glg-eng)
type: mteb/tatoeba-bitext-mining
config: glg-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 89.64
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (ceb-eng)
type: mteb/tatoeba-bitext-mining
config: ceb-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 21.257184628237262
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (bre-eng)
type: mteb/tatoeba-bitext-mining
config: bre-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 13.592316017316017
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (ben-eng)
type: mteb/tatoeba-bitext-mining
config: ben-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 73.22666666666666
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (swg-eng)
type: mteb/tatoeba-bitext-mining
config: swg-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 51.711309523809526
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (arq-eng)
type: mteb/tatoeba-bitext-mining
config: arq-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 24.98790634904795
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (kab-eng)
type: mteb/tatoeba-bitext-mining
config: kab-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 17.19218192918193
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (fra-eng)
type: mteb/tatoeba-bitext-mining
config: fra-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 93.26666666666667
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (por-eng)
type: mteb/tatoeba-bitext-mining
config: por-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 94.57333333333334
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (tat-eng)
type: mteb/tatoeba-bitext-mining
config: tat-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 42.35127206127206
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (oci-eng)
type: mteb/tatoeba-bitext-mining
config: oci-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 51.12318903318903
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (pol-eng)
type: mteb/tatoeba-bitext-mining
config: pol-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 94.89999999999999
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (war-eng)
type: mteb/tatoeba-bitext-mining
config: war-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 23.856320290390055
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (aze-eng)
type: mteb/tatoeba-bitext-mining
config: aze-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 79.52833333333334
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (vie-eng)
type: mteb/tatoeba-bitext-mining
config: vie-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 95.93333333333334
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (nno-eng)
type: mteb/tatoeba-bitext-mining
config: nno-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 90.75333333333333
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (cha-eng)
type: mteb/tatoeba-bitext-mining
config: cha-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 30.802919708029197
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (mhr-eng)
type: mteb/tatoeba-bitext-mining
config: mhr-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 15.984076294076294
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (dan-eng)
type: mteb/tatoeba-bitext-mining
config: dan-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 91.82666666666667
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (ell-eng)
type: mteb/tatoeba-bitext-mining
config: ell-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 91.9
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (amh-eng)
type: mteb/tatoeba-bitext-mining
config: amh-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 76.36054421768706
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (pam-eng)
type: mteb/tatoeba-bitext-mining
config: pam-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 9.232711399711398
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (hsb-eng)
type: mteb/tatoeba-bitext-mining
config: hsb-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 45.640803181175855
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (srp-eng)
type: mteb/tatoeba-bitext-mining
config: srp-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 86.29
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (epo-eng)
type: mteb/tatoeba-bitext-mining
config: epo-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 88.90833333333332
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (kzj-eng)
type: mteb/tatoeba-bitext-mining
config: kzj-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 11.11880248978075
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (awa-eng)
type: mteb/tatoeba-bitext-mining
config: awa-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 48.45839345839346
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (fao-eng)
type: mteb/tatoeba-bitext-mining
config: fao-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 65.68157033805888
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (mal-eng)
type: mteb/tatoeba-bitext-mining
config: mal-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 94.63852498786997
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (ile-eng)
type: mteb/tatoeba-bitext-mining
config: ile-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 81.67904761904761
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (bos-eng)
type: mteb/tatoeba-bitext-mining
config: bos-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 89.35969868173258
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (cor-eng)
type: mteb/tatoeba-bitext-mining
config: cor-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 5.957229437229437
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (cat-eng)
type: mteb/tatoeba-bitext-mining
config: cat-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 91.50333333333333
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (eus-eng)
type: mteb/tatoeba-bitext-mining
config: eus-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 63.75498778998778
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (yue-eng)
type: mteb/tatoeba-bitext-mining
config: yue-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 82.99190476190476
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (swe-eng)
type: mteb/tatoeba-bitext-mining
config: swe-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 92.95
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (dtp-eng)
type: mteb/tatoeba-bitext-mining
config: dtp-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 9.054042624042623
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (kat-eng)
type: mteb/tatoeba-bitext-mining
config: kat-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 72.77064981488574
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (jpn-eng)
type: mteb/tatoeba-bitext-mining
config: jpn-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 93.14
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (csb-eng)
type: mteb/tatoeba-bitext-mining
config: csb-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 29.976786498525627
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (xho-eng)
type: mteb/tatoeba-bitext-mining
config: xho-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 67.6525821596244
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (orv-eng)
type: mteb/tatoeba-bitext-mining
config: orv-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 33.12964812964813
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (ind-eng)
type: mteb/tatoeba-bitext-mining
config: ind-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 92.30666666666666
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (tuk-eng)
type: mteb/tatoeba-bitext-mining
config: tuk-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 34.36077879427633
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (max-eng)
type: mteb/tatoeba-bitext-mining
config: max-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 52.571845212690285
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (swh-eng)
type: mteb/tatoeba-bitext-mining
config: swh-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 58.13107263107262
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (hin-eng)
type: mteb/tatoeba-bitext-mining
config: hin-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 93.33333333333333
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (dsb-eng)
type: mteb/tatoeba-bitext-mining
config: dsb-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 42.87370133925458
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (ber-eng)
type: mteb/tatoeba-bitext-mining
config: ber-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 20.394327616827614
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (tam-eng)
type: mteb/tatoeba-bitext-mining
config: tam-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 84.29967426710098
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (slk-eng)
type: mteb/tatoeba-bitext-mining
config: slk-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 88.80666666666667
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (tgl-eng)
type: mteb/tatoeba-bitext-mining
config: tgl-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 67.23062271062273
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (ast-eng)
type: mteb/tatoeba-bitext-mining
config: ast-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 78.08398950131233
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (mkd-eng)
type: mteb/tatoeba-bitext-mining
config: mkd-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 77.85166666666666
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (khm-eng)
type: mteb/tatoeba-bitext-mining
config: khm-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 67.63004001231148
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (ces-eng)
type: mteb/tatoeba-bitext-mining
config: ces-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 89.77000000000001
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (tzl-eng)
type: mteb/tatoeba-bitext-mining
config: tzl-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 40.2654503616042
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (urd-eng)
type: mteb/tatoeba-bitext-mining
config: urd-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 83.90333333333334
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (ara-eng)
type: mteb/tatoeba-bitext-mining
config: ara-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 77.80666666666666
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (kor-eng)
type: mteb/tatoeba-bitext-mining
config: kor-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 84.08
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (yid-eng)
type: mteb/tatoeba-bitext-mining
config: yid-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 60.43098607367475
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (fin-eng)
type: mteb/tatoeba-bitext-mining
config: fin-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 88.19333333333333
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (tha-eng)
type: mteb/tatoeba-bitext-mining
config: tha-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 90.55352798053529
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (wuu-eng)
type: mteb/tatoeba-bitext-mining
config: wuu-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: f1
value: 88.44999999999999
- task:
type: Clustering
dataset:
name: MTEB ThuNewsClusteringP2P
type: C-MTEB/ThuNewsClusteringP2P
config: default
split: test
revision: 5798586b105c0434e4f0fe5e767abe619442cf93
metrics:
- type: v_measure
value: 57.25416429643288
- task:
type: Clustering
dataset:
name: MTEB ThuNewsClusteringS2S
type: C-MTEB/ThuNewsClusteringS2S
config: default
split: test
revision: 8a8b2caeda43f39e13c4bc5bea0f8a667896e10d
metrics:
- type: v_measure
value: 56.616646560243524
- task:
type: Retrieval
dataset:
name: MTEB Touche2020
type: mteb/touche2020
config: default
split: test
revision: a34f9a33db75fa0cbb21bb5cfc3dae8dc8bec93f
metrics:
- type: ndcg_at_10
value: 22.819
- task:
type: Classification
dataset:
name: MTEB ToxicConversationsClassification
type: mteb/toxic_conversations_50k
config: default
split: test
revision: d7c0de2777da35d6aae2200a62c6e0e5af397c4c
metrics:
- type: accuracy
value: 71.02579999999999
- task:
type: Classification
dataset:
name: MTEB TweetSentimentExtractionClassification
type: mteb/tweet_sentiment_extraction
config: default
split: test
revision: d604517c81ca91fe16a244d1248fc021f9ecee7a
metrics:
- type: accuracy
value: 57.60045274476514
- task:
type: Clustering
dataset:
name: MTEB TwentyNewsgroupsClustering
type: mteb/twentynewsgroups-clustering
config: default
split: test
revision: 6125ec4e24fa026cec8a478383ee943acfbd5449
metrics:
- type: v_measure
value: 50.346666699466205
- task:
type: PairClassification
dataset:
name: MTEB TwitterSemEval2015
type: mteb/twittersemeval2015-pairclassification
config: default
split: test
revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1
metrics:
- type: cos_sim_ap
value: 71.88199004440489
- task:
type: PairClassification
dataset:
name: MTEB TwitterURLCorpus
type: mteb/twitterurlcorpus-pairclassification
config: default
split: test
revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf
metrics:
- type: cos_sim_ap
value: 85.41587779677383
- task:
type: Retrieval
dataset:
name: MTEB VideoRetrieval
type: C-MTEB/VideoRetrieval
config: default
split: dev
revision: 58c2597a5943a2ba48f4668c3b90d796283c5639
metrics:
- type: ndcg_at_10
value: 72.792
- task:
type: Classification
dataset:
name: MTEB Waimai
type: C-MTEB/waimai-classification
config: default
split: test
revision: 339287def212450dcaa9df8c22bf93e9980c7023
metrics:
- type: accuracy
value: 82.58000000000001
- task:
type: Retrieval
dataset:
name: MTEB XPQARetrieval (fr)
type: jinaai/xpqa
config: fr
split: test
revision: c99d599f0a6ab9b85b065da6f9d94f9cf731679f
metrics:
- type: ndcg_at_10
value: 67.327
---
## gte-multilingual-base
The **gte-multilingual-base** model is the latest in the [GTE](https://huggingface.co/collections/Alibaba-NLP/gte-models-6680f0b13f885cb431e6d469) (General Text Embedding) family of models, featuring several key attributes:
- **High Performance**: Achieves state-of-the-art (SOTA) results in multilingual retrieval tasks and multi-task representation model evaluations when compared to models of similar size.
- **Training Architecture**: Trained using an encoder-only transformers architecture, resulting in a smaller model size. Unlike previous models based on decode-only LLM architecture (e.g., gte-qwen2-1.5b-instruct), this model has lower hardware requirements for inference, offering a 10x increase in inference speed.
- **Long Context**: Supports text lengths up to **8192** tokens.
- **Multilingual Capability**: Supports over **70** languages.
- **Elastic Dense Embedding**: Support elastic output dense representation while maintaining the effectiveness of downstream tasks, which significantly reduces storage costs and improves execution efficiency.
- **Sparse Vectors**: In addition to dense representations, it can also generate sparse vectors.
**Paper**: [mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval](https://arxiv.org/pdf/2407.19669)
## Model Information
- Model Size: 305M
- Embedding Dimension: 768
- Max Input Tokens: 8192
## Usage
- **It is recommended to install xformers and enable unpadding for acceleration,
refer to [enable-unpadding-and-xformers](https://huggingface.co/Alibaba-NLP/new-impl#recommendation-enable-unpadding-and-acceleration-with-xformers).**
- **How to use it offline: [new-impl/discussions/2](https://huggingface.co/Alibaba-NLP/new-impl/discussions/2#662b08d04d8c3d0a09c88fa3)**
- **How to use with [TEI](https://github.com/huggingface/text-embeddings-inference): [refs/pr/7](https://huggingface.co/Alibaba-NLP/gte-multilingual-base/discussions/7#66bfb82ea03b764ca92a2221)**
### Get Dense Embeddings with Transformers
```
# Requires transformers>=4.36.0
import torch.nn.functional as F
from transformers import AutoModel, AutoTokenizer
input_texts = [
"what is the capital of China?",
"how to implement quick sort in python?",
"北京",
"快排算法介绍"
]
model_name_or_path = 'Alibaba-NLP/gte-multilingual-base'
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
model = AutoModel.from_pretrained(model_name_or_path, trust_remote_code=True)
# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=8192, padding=True, truncation=True, return_tensors='pt')
outputs = model(**batch_dict)
dimension=768 # The output dimension of the output embedding, should be in [128, 768]
embeddings = outputs.last_hidden_state[:, 0][:dimension]
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())
# [[0.3016996383666992, 0.7503870129585266, 0.3203084468841553]]
```
### Use with sentence-transformers
```
# Requires sentences-transformers>=3.0.0
from sentence_transformers import SentenceTransformer
from sentence_transformers.util import cos_sim
import numpy as np
input_texts = [
"what is the capital of China?",
"how to implement quick sort in python?",
"北京",
"快排算法介绍"
]
model_name_or_path="Alibaba-NLP/gte-multilingual-base"
model = SentenceTransformer(', trust_remote_code=True)
embeddings = model.encode(input_texts) # embeddings.shape (4, 768)
# normalized embeddings
norms = np.linalg.norm(embeddings, ord=2, axis=1, keepdims=True)
norms[norms == 0] = 1
embeddings = embeddings / norms
# sim scores
scores = (embeddings[:1] @ embeddings[1:].T)
print(scores.tolist())
# [[0.301699697971344, 0.7503870129585266, 0.32030850648880005]]
```
### Use with custom code to get dense embeddigns and sparse token weights
```
# You can find the script gte_embedding.py in https://huggingface.co/Alibaba-NLP/gte-multilingual-base/blob/main/scripts/gte_embedding.py
from gte_embedding import GTEEmbeddidng
model_name_or_path = 'Alibaba-NLP/gte-multilingual-base'
model = GTEEmbeddidng(model_name_or_path)
query = "中国的首都在哪儿"
docs = [
"what is the capital of China?",
"how to implement quick sort in python?",
"北京",
"快排算法介绍"
]
embs = model.encode(docs, return_dense=True,return_sparse=True)
print('dense_embeddings vecs', embs['dense_embeddings'])
print('token_weights', embs['token_weights'])
pairs = [(query, doc) for doc in docs]
dense_scores = model.compute_scores(pairs, dense_weight=1.0, sparse_weight=0.0)
sparse_scores = model.compute_scores(pairs, dense_weight=0.0, sparse_weight=1.0)
hybrid_scores = model.compute_scores(pairs, dense_weight=1.0, sparse_weight=0.3)
print('dense_scores', dense_scores)
print('sparse_scores', sparse_scores)
print('hybrid_scores', hybrid_scores)
# dense_scores [0.85302734375, 0.257568359375, 0.76953125, 0.325439453125]
# sparse_scores [0.0, 0.0, 4.600879669189453, 1.570279598236084]
# hybrid_scores [0.85302734375, 0.257568359375, 2.1497951507568356, 0.7965233325958252]
```
## Evaluation
We validated the performance of the **gte-multilingual-base** model on multiple downstream tasks, including multilingual retrieval, cross-lingual retrieval, long text retrieval, and general text representation evaluation on the [MTEB Leaderboard](https://huggingface.co/spaces/mteb/leaderboard), among others.
### Retrieval Task
Retrieval results on [MIRACL](https://arxiv.org/abs/2210.09984) and [MLDR](https://arxiv.org/abs/2402.03216) (multilingual), [MKQA](https://arxiv.org/abs/2007.15207) (crosslingual), [BEIR](https://arxiv.org/abs/2104.08663) and [LoCo](https://arxiv.org/abs/2402.07440) (English).
- Detail results on [MLDR](https://arxiv.org/abs/2402.03216)
- Detail results on [LoCo](https://arxiv.org/abs/2402.07440)
### MTEB
Results on MTEB English, Chinese, French, Polish
**More detailed experimental results can be found in the [paper](https://arxiv.org/pdf/2407.19669)**.
## Cloud API Services
In addition to the open-source [GTE](https://huggingface.co/collections/Alibaba-NLP/gte-models-6680f0b13f885cb431e6d469) series models, GTE series models are also available as commercial API services on Alibaba Cloud.
- [Embedding Models](https://help.aliyun.com/zh/model-studio/developer-reference/general-text-embedding/): Rhree versions of the text embedding models are available: text-embedding-v1/v2/v3, with v3 being the latest API service.
- [ReRank Models](https://help.aliyun.com/zh/model-studio/developer-reference/general-text-sorting-model/): The gte-rerank model service is available.
Note that the models behind the commercial APIs are not entirely identical to the open-source models.
## Citation
If you find our paper or models helpful, please consider cite:
```
@misc{zhang2024mgte,
title={mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval},
author={Xin Zhang and Yanzhao Zhang and Dingkun Long and Wen Xie and Ziqi Dai and Jialong Tang and Huan Lin and Baosong Yang and Pengjun Xie and Fei Huang and Meishan Zhang and Wenjie Li and Min Zhang},
year={2024},
eprint={2407.19669},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2407.19669},
}
``` | [
"SUMMARIZATION"
] | Non_BioNLP |
deerslab/llama-7b-embeddings | deerslab | text-generation | [
"transformers",
"pytorch",
"llama",
"text-generation",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 1,679,071,095,000 | 2023-03-17T17:41:37 | 21 | 5 | ---
license: other
duplicated_from: decapoda-research/llama-7b-hf
---
LLaMA-7B converted to work with Transformers/HuggingFace. This is under a special license, please see the LICENSE file for details.
--
license: other
---
# LLaMA Model Card
## Model details
**Organization developing the model**
The FAIR team of Meta AI.
**Model date**
LLaMA was trained between December. 2022 and Feb. 2023.
**Model version**
This is version 1 of the model.
**Model type**
LLaMA is an auto-regressive language model, based on the transformer architecture. The model comes in different sizes: 7B, 13B, 33B and 65B parameters.
**Paper or resources for more information**
More information can be found in the paper “LLaMA, Open and Efficient Foundation Language Models”, available at https://research.facebook.com/publications/llama-open-and-efficient-foundation-language-models/.
**Citations details**
https://research.facebook.com/publications/llama-open-and-efficient-foundation-language-models/
**License**
Non-commercial bespoke license
**Where to send questions or comments about the model**
Questions and comments about LLaMA can be sent via the [GitHub repository](https://github.com/facebookresearch/llama) of the project , by opening an issue.
## Intended use
**Primary intended uses**
The primary use of LLaMA is research on large language models, including:
exploring potential applications such as question answering, natural language understanding or reading comprehension,
understanding capabilities and limitations of current language models, and developing techniques to improve those,
evaluating and mitigating biases, risks, toxic and harmful content generations, hallucinations.
**Primary intended users**
The primary intended users of the model are researchers in natural language processing, machine learning and artificial intelligence.
**Out-of-scope use cases**
LLaMA is a base, or foundational, model. As such, it should not be used on downstream applications without further risk evaluation and mitigation. In particular, our model has not been trained with human feedback, and can thus generate toxic or offensive content, incorrect information or generally unhelpful answers.
## Factors
**Relevant factors**
One of the most relevant factors for which model performance may vary is which language is used. Although we included 20 languages in the training data, most of our dataset is made of English text, and we thus expect the model to perform better for English than other languages. Relatedly, it has been shown in previous studies that performance might vary for different dialects, and we expect that it will be the case for our model.
**Evaluation factors**
As our model is trained on data from the Web, we expect that it reflects biases from this source. We thus evaluated on RAI datasets to measure biases exhibited by the model for gender, religion, race, sexual orientation, age, nationality, disability, physical appearance and socio-economic status. We also measure the toxicity of model generations, depending on the toxicity of the context used to prompt the model.
## Metrics
**Model performance measures**
We use the following measure to evaluate the model:
- Accuracy for common sense reasoning, reading comprehension, natural language understanding (MMLU), BIG-bench hard, WinoGender and CrowS-Pairs,
- Exact match for question answering,
- The toxicity score from Perspective API on RealToxicityPrompts.
**Decision thresholds**
Not applicable.
**Approaches to uncertainty and variability**
Due to the high computational requirements of training LLMs, we trained only one model of each size, and thus could not evaluate variability of pre-training.
## Evaluation datasets
The model was evaluated on the following benchmarks: BoolQ, PIQA, SIQA, HellaSwag, WinoGrande, ARC, OpenBookQA, NaturalQuestions, TriviaQA, RACE, MMLU, BIG-bench hard, GSM8k, RealToxicityPrompts, WinoGender, CrowS-Pairs.
## Training dataset
The model was trained using the following source of data: CCNet [67%], C4 [15%], GitHub [4.5%], Wikipedia [4.5%], Books [4.5%], ArXiv [2.5%], Stack Exchange[2%]. The Wikipedia and Books domains include data in the following languages: bg, ca, cs, da, de, en, es, fr, hr, hu, it, nl, pl, pt, ro, ru, sl, sr, sv, uk. See the paper for more details about the training set and corresponding preprocessing.
## Quantitative analysis
Hyperparameters for the model architecture
<table>
<thead>
<tr>
<th >LLaMA</th> <th colspan=6>Model hyper parameters </th>
</tr>
<tr>
<th>Number of parameters</th><th>dimension</th><th>n heads</th><th>n layers</th><th>Learn rate</th><th>Batch size</th><th>n tokens</th>
</tr>
</thead>
<tbody>
<tr>
<th>7B</th> <th>4096</th> <th>32</th> <th>32</th> <th>3.0E-04</th><th>4M</th><th>1T
</tr>
<tr>
<th>13B</th><th>5120</th><th>40</th><th>40</th><th>3.0E-04</th><th>4M</th><th>1T
</tr>
<tr>
<th>33B</th><th>6656</th><th>52</th><th>60</th><th>1.5.E-04</th><th>4M</th><th>1.4T
</tr>
<tr>
<th>65B</th><th>8192</th><th>64</th><th>80</th><th>1.5.E-04</th><th>4M</th><th>1.4T
</tr>
</tbody>
</table>
*Table 1 - Summary of LLama Model Hyperparameters*
We present our results on eight standard common sense reasoning benchmarks in the table below.
<table>
<thead>
<tr>
<th>LLaMA</th> <th colspan=9>Reasoning tasks </th>
</tr>
<tr>
<th>Number of parameters</th> <th>BoolQ</th><th>PIQA</th><th>SIQA</th><th>HellaSwag</th><th>WinoGrande</th><th>ARC-e</th><th>ARC-c</th><th>OBQA</th><th>COPA</th>
</tr>
</thead>
<tbody>
<tr>
<th>7B</th><th>76.5</th><th>79.8</th><th>48.9</th><th>76.1</th><th>70.1</th><th>76.7</th><th>47.6</th><th>57.2</th><th>93
</th>
<tr><th>13B</th><th>78.1</th><th>80.1</th><th>50.4</th><th>79.2</th><th>73</th><th>78.1</th><th>52.7</th><th>56.4</th><th>94
</th>
<tr><th>33B</th><th>83.1</th><th>82.3</th><th>50.4</th><th>82.8</th><th>76</th><th>81.4</th><th>57.8</th><th>58.6</th><th>92
</th>
<tr><th>65B</th><th>85.3</th><th>82.8</th><th>52.3</th><th>84.2</th><th>77</th><th>81.5</th><th>56</th><th>60.2</th><th>94</th></tr>
</tbody>
</table>
*Table 2 - Summary of LLama Model Performance on Reasoning tasks*
We present our results on bias in the table below. Note that lower value is better indicating lower bias.
| No | Category | FAIR LLM |
| --- | -------------------- | -------- |
| 1 | Gender | 70.6 |
| 2 | Religion | 79 |
| 3 | Race/Color | 57 |
| 4 | Sexual orientation | 81 |
| 5 | Age | 70.1 |
| 6 | Nationality | 64.2 |
| 7 | Disability | 66.7 |
| 8 | Physical appearance | 77.8 |
| 9 | Socioeconomic status | 71.5 |
| | LLaMA Average | 66.6 |
*Table 3 - Summary bias of our model output*
## Ethical considerations
**Data**
The data used to train the model is collected from various sources, mostly from the Web. As such, it contains offensive, harmful and biased content. We thus expect the model to exhibit such biases from the training data.
**Human life**
The model is not intended to inform decisions about matters central to human life, and should not be used in such a way.
**Mitigations**
We filtered the data from the Web based on its proximity to Wikipedia text and references. For this, we used a Kneser-Ney language model and a fastText linear classifier.
**Risks and harms**
Risks and harms of large language models include the generation of harmful, offensive or biased content. These models are often prone to generating incorrect information, sometimes referred to as hallucinations. We do not expect our model to be an exception in this regard.
**Use cases**
LLaMA is a foundational model, and as such, it should not be used for downstream applications without further investigation and mitigations of risks. These risks and potential fraught use cases include, but are not limited to: generation of misinformation and generation of harmful, biased or offensive content.
| [
"QUESTION_ANSWERING"
] | Non_BioNLP |
LoneStriker/bagel-34b-v0.2-8.0bpw-h8-exl2 | LoneStriker | text-generation | [
"transformers",
"safetensors",
"llama",
"text-generation",
"dataset:ai2_arc",
"dataset:unalignment/spicy-3.1",
"dataset:codeparrot/apps",
"dataset:facebook/belebele",
"dataset:boolq",
"dataset:jondurbin/cinematika-v0.1",
"dataset:drop",
"dataset:lmsys/lmsys-chat-1m",
"dataset:TIGER-Lab/MathInstruct",
"dataset:cais/mmlu",
"dataset:Muennighoff/natural-instructions",
"dataset:openbookqa",
"dataset:piqa",
"dataset:Vezora/Tested-22k-Python-Alpaca",
"dataset:cakiki/rosetta-code",
"dataset:Open-Orca/SlimOrca",
"dataset:spider",
"dataset:squad_v2",
"dataset:migtissera/Synthia-v1.3",
"dataset:datasets/winogrande",
"dataset:nvidia/HelpSteer",
"dataset:Intel/orca_dpo_pairs",
"dataset:unalignment/toxic-dpo-v0.1",
"dataset:jondurbin/truthy-dpo-v0.1",
"dataset:allenai/ultrafeedback_binarized_cleaned",
"dataset:Squish42/bluemoon-fandom-1-1-rp-cleaned",
"dataset:LDJnr/Capybara",
"dataset:JULIELab/EmoBank",
"dataset:kingbri/PIPPA-shareGPT",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 1,704,214,987,000 | 2024-01-02T17:25:11 | 4 | 0 | ---
datasets:
- ai2_arc
- unalignment/spicy-3.1
- codeparrot/apps
- facebook/belebele
- boolq
- jondurbin/cinematika-v0.1
- drop
- lmsys/lmsys-chat-1m
- TIGER-Lab/MathInstruct
- cais/mmlu
- Muennighoff/natural-instructions
- openbookqa
- piqa
- Vezora/Tested-22k-Python-Alpaca
- cakiki/rosetta-code
- Open-Orca/SlimOrca
- spider
- squad_v2
- migtissera/Synthia-v1.3
- datasets/winogrande
- nvidia/HelpSteer
- Intel/orca_dpo_pairs
- unalignment/toxic-dpo-v0.1
- jondurbin/truthy-dpo-v0.1
- allenai/ultrafeedback_binarized_cleaned
- Squish42/bluemoon-fandom-1-1-rp-cleaned
- LDJnr/Capybara
- JULIELab/EmoBank
- kingbri/PIPPA-shareGPT
license: other
license_name: yi-license
license_link: https://huggingface.co/01-ai/Yi-34B-200K/blob/main/LICENSE
---
# A bagel, with everything (except DPO)
## Overview
An experimental fine-tune of yi-34b-200k using [bagel](https://github.com/jondurbin/bagel)
This is the model after the SFT phase, before DPO has been applied. You'll likely want to use the DPO'd version, rather than this one, but since I had it, I uploaded it.
### Data sources
*Yes, you will see benchmark names in the list, but this only uses the train splits, and a decontamination by cosine similarity is performed at the end as a sanity check*
- [ai2_arc](https://huggingface.co/datasets/ai2_arc)
- Abstraction and reasoning dataset, useful in measuring "intelligence" to a certain extent.
- [airoboros](https://huggingface.co/datasets/unalignment/spicy-3.1)
- Variety of categories of synthetic instructions generated by gpt-4.
- [apps](https://huggingface.co/datasets/codeparrot/apps)
- Python coding dataset with 10k problems.
- [belebele](https://huggingface.co/datasets/facebook/belebele)
- Multi-lingual reading comprehension dataset.
- [bluemoon](https://huggingface.co/datasets/Squish42/bluemoon-fandom-1-1-rp-cleaned)
- Roleplay data scraped from Bluemoon, then cleaned and formatted as ShareGPT.
- [boolq](https://huggingface.co/datasets/boolq)
- Corpus of yes/no questions (which can be surprisingly difficult for AI to answer apparently?)
- [capybara](https://huggingface.co/datasets/LDJnr/Capybara)
- Multi-turn dataset used to create the capybara models.
- [cinematika](https://huggingface.co/datasets/jondurbin/cinematika-v0.1) (instruction and plain text)
- RP-style data synthesized from movie scripts so the model isn't quite as boring as it otherwise would be.
- [drop](https://huggingface.co/datasets/drop)
- More reading comprehension.
- [emobank](https://github.com/JULIELab/EmoBank)
- Emotion annotations using the Valence-Arousal-Domninance scheme.
- [gutenberg](https://www.gutenberg.org/) (plain text)
- Books/plain text, again to make the model less boring, only a handful of examples supported by [chapterize](https://github.com/JonathanReeve/chapterize)
- [lmsys_chat_1m](https://huggingface.co/datasets/lmsys/lmsys-chat-1m) (only gpt-4 items, also used for DPO)
- Chats collected by the lmsys chat arena, containing a wide variety of chats with various models.
- [mathinstruct](https://huggingface.co/datasets/TIGER-Lab/MathInstruct)
- Composite dataset with a variety of math-related tasks and problem/question formats.
- [mmlu](https://huggingface.co/datasets/cais/mmlu)
- Massive Multitask Language Understanding - a wide variety of questions about various subject matters.
- [natural_instructions](https://huggingface.co/datasets/Muennighoff/natural-instructions)
- Millions of instructions from 1600+ task categories (sampled down substantially, stratified by task type)
- [openbookqa](https://huggingface.co/datasets/openbookqa)
- Question answering dataset.
- [pippa](https://huggingface.co/datasets/kingbri/PIPPA-shareGPT)
- Deduped version of [PIPPA](https://huggingface.co/datasets/PygmalionAI/PIPPA) in ShareGPT format.
- [piqa](https://huggingface.co/datasets/piqa)
- Phyiscal interaction question answering.
- [python_alpaca](https://huggingface.co/datasets/Vezora/Tested-22k-Python-Alpaca)
- Python instruction response pairs, validated as functional.
- [rosetta_code](https://huggingface.co/datasets/cakiki/rosetta-code)
- Code problems and solutions in a variety of programming languages taken from rosettacode.org.
- [slimorca](https://huggingface.co/datasets/Open-Orca/SlimOrca)
- Collection of ~500k gpt-4 verified chats from OpenOrca.
- [spider](https://huggingface.co/datasets/spider)
- SQL-targeted dataset.
- [squad_v2](https://huggingface.co/datasets/squad_v2)
- Contextual question answering (RAG).
- [synthia](https://huggingface.co/datasets/migtissera/Synthia-v1.3)
- GPT-4 generated data using advanced prompting from Migel Tissera.
- [winogrande](https://huggingface.co/datasets/winogrande)
- Fill in the blank style prompts.
Only the train splits were used (if a split was provided), and an additional pass of decontamination is performed using approximate nearest neighbor search (via faiss).
## Prompt formatting
In sticking with the theme of the bagel, I didn't want to use a single prompt format, so I used 4 - vicuna, llama-2, alpaca, and chat-ml (sorta).
I also didn't want to randomly select a single prompt format for each item (hoping each instruction would generalize more when used in a variety of prompt formats), so each instruction is actually converted into every prompt format.
This means each epoch of our fine-tune is really basically 4 epochs. So, for the fine-tunes, I would recommend only doing 1 epoch (or 0.75 epochs). I am testing with a single epoch using a relatively low learning rate.
### Alpaca (sort of)
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{system prompt, if provided}
{instruction}
### Response:
```
The main difference here is that because of the dataset formatting and variety of data sources, it would have been much to tedious to add an `### Input:` block, so the inputs are just in the instruction section.
### Vicuna
```
{system prompt, if provided, randomly defaulting to "A chat between a user and an unbiased, uncensored assistant."}
USER: {instruction}
ASSISTANT:
```
### ChatML (sort of)
I don't really understand the point of having special tokens for `<|im_start|>` and `<|im_end|>`, because in practice they just act as BOS and EOS tokens (but, please correct me if I'm wrong).
So, instead of:
```text
{bos}<|im_start|>{role}
{text}
<|im_end|>{eos}
```
I just changed it to:
```text
{bos}{role}
{text}
{eos}
```
If you *really* want to use `<|im_start|>` and `<|im_end|>`, just update your `tokenizer_config.json` to use `<|im_start|>` instead of `<s>` and `<|im_end|>` instead of `</s>` and when tokenizing. And if you still don't like what I've done to this chat-ml-ish format, feel free to cry into your pillow or fork the code and do a new fine-tune.
### Llama-2 chat
```
[INST] <<SYS>>
{system}
<</SYS>>
{instruction} [/INST]
``` | [
"QUESTION_ANSWERING"
] | Non_BioNLP |
TheBloke/manticore-13b-chat-pyg-GGML | TheBloke | null | [
"license:other",
"region:us"
] | 1,684,881,595,000 | 2023-06-10T01:10:15 | 0 | 25 | ---
license: other
inference: false
---
<!-- header start -->
<div style="width: 100%;">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p><a href="https://discord.gg/Jq4vkcDakD">Chat & support: my new Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<!-- header end -->
# OpenAccess AI Collective's Manticore 13B Chat GGML
These files are GGML format model files for [OpenAccess AI Collective's Manticore 13B Chat](https://huggingface.co/openaccess-ai-collective/manticore-13b-chat-pyg).
GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/ggerganov/llama.cpp) and libraries and UIs which support this format, such as:
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
* [KoboldCpp](https://github.com/LostRuins/koboldcpp)
* [ParisNeo/GPT4All-UI](https://github.com/ParisNeo/gpt4all-ui)
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python)
* [ctransformers](https://github.com/marella/ctransformers)
## Repositories available
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/manticore-13b-chat-pyg-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/manticore-13b-chat-pyg-GGML)
* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/openaccess-ai-collective/manticore-13b-chat-pyg)
<!-- compatibility_ggml start -->
## Compatibility
### Original llama.cpp quant methods: `q4_0, q4_1, q5_0, q5_1, q8_0`
I have quantized these 'original' quantisation methods using an older version of llama.cpp so that they remain compatible with llama.cpp as of May 19th, commit `2d5db48`.
They should be compatible with all current UIs and libraries that use llama.cpp, such as those listed at the top of this README.
### New k-quant methods: `q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K`
These new quantisation methods are only compatible with llama.cpp as of June 6th, commit `2d43387`.
They will NOT be compatible with koboldcpp, text-generation-ui, and other UIs and libraries yet. Support is expected to come over the next few days.
## Explanation of the new k-quant methods
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
* GGML_TYPE_Q8_K - "type-0" 8-bit quantization. Only used for quantizing intermediate results. The difference to the existing Q8_0 is that the block size is 256. All 2-6 bit dot products are implemented for this quantization type.
Refer to the Provided Files table below to see what files use which methods, and how.
<!-- compatibility_ggml end -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| Manticore-13B-Chat-Pyg.ggmlv3.q2_K.bin | q2_K | 2 | 5.43 GB | 7.93 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. |
| Manticore-13B-Chat-Pyg.ggmlv3.q3_K_L.bin | q3_K_L | 3 | 6.87 GB | 9.37 GB | New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
| Manticore-13B-Chat-Pyg.ggmlv3.q3_K_M.bin | q3_K_M | 3 | 6.25 GB | 8.75 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
| Manticore-13B-Chat-Pyg.ggmlv3.q3_K_S.bin | q3_K_S | 3 | 5.59 GB | 8.09 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors |
| Manticore-13B-Chat-Pyg.ggmlv3.q4_0.bin | q4_0 | 4 | 7.32 GB | 9.82 GB | Original llama.cpp quant method, 4-bit. |
| Manticore-13B-Chat-Pyg.ggmlv3.q4_1.bin | q4_1 | 4 | 8.14 GB | 10.64 GB | Original llama.cpp quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
| Manticore-13B-Chat-Pyg.ggmlv3.q4_K_M.bin | q4_K_M | 4 | 7.82 GB | 10.32 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K |
| Manticore-13B-Chat-Pyg.ggmlv3.q4_K_S.bin | q4_K_S | 4 | 7.32 GB | 9.82 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors |
| Manticore-13B-Chat-Pyg.ggmlv3.q5_0.bin | q5_0 | 5 | 8.95 GB | 11.45 GB | Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. |
| Manticore-13B-Chat-Pyg.ggmlv3.q5_1.bin | q5_1 | 5 | 9.76 GB | 12.26 GB | Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference. |
| Manticore-13B-Chat-Pyg.ggmlv3.q5_K_M.bin | q5_K_M | 5 | 9.21 GB | 11.71 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K |
| Manticore-13B-Chat-Pyg.ggmlv3.q5_K_S.bin | q5_K_S | 5 | 8.95 GB | 11.45 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors |
| Manticore-13B-Chat-Pyg.ggmlv3.q6_K.bin | q6_K | 6 | 10.68 GB | 13.18 GB | New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors |
| Manticore-13B-Chat-Pyg.ggmlv3.q8_0.bin | q8_0 | 8 | 13.83 GB | 16.33 GB | Original llama.cpp quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
## How to run in `llama.cpp`
I use the following command line; adjust for your tastes and needs:
```
./main -t 10 -ngl 32 -m Manticore-13B-Chat-Pyg.ggmlv3.q5_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### Instruction: Write a story about llamas\n### Response:"
```
Change `-t 10` to the number of physical CPU cores you have. For example if your system has 8 cores/16 threads, use `-t 8`.
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
## How to run in `text-generation-webui`
Further instructions here: [text-generation-webui/docs/llama.cpp-models.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp-models.md).
<!-- footer start -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/Jq4vkcDakD)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
**Patreon special mentions**: Oscar Rangel, Eugene Pentland, Talal Aujan, Cory Kujawski, Luke, Asp the Wyvern, Ai Maven, Pyrater, Alps Aficionado, senxiiz, Willem Michiel, Junyu Yang, trip7s trip, Sebastain Graf, Joseph William Delisle, Lone Striker, Jonathan Leane, Johann-Peter Hartmann, David Flickinger, Spiking Neurons AB, Kevin Schuppel, Mano Prime, Dmitriy Samsonov, Sean Connelly, Nathan LeClaire, Alain Rossmann, Fen Risland, Derek Yates, Luke Pendergrass, Nikolai Manek, Khalefa Al-Ahmad, Artur Olbinski, John Detwiler, Ajan Kanaga, Imad Khwaja, Trenton Dambrowitz, Kalila, vamX, webtim, Illia Dulskyi.
Thank you to all my generous patrons and donaters!
<!-- footer end -->
# Original model card: OpenAccess AI Collective's Manticore 13B Chat
# Manticore 13B Chat
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
Manticore 13B Chat builds on Manticore with new datasets, including a de-duped subset of the Pygmalion dataset. It also removes all Alpaca style prompts using `###` in favor of
chat only style prompts using `USER:`,`ASSISTANT:` as well as [pygmalion/metharme prompting](https://huggingface.co/PygmalionAI/metharme-7b#prompting) using `<|system|>, <|user|> and <|model|>` tokens.
Questions, comments, feedback, looking to donate, or want to help? Reach out on our [Discord](https://discord.gg/PugNNHAF5r) or email [[email protected]](mailto:[email protected])
# Training Datasets
Manticore 13B Chat is a Llama 13B model fine-tuned on the following datasets along with the datasets from the original Manticore 13B.
**Manticore 13B Chat was trained on 25% of the datasets below. The datasets were merged, shuffled, and then sharded into 4 parts.**
- de-duped pygmalion dataset, filtered down to RP data
- [riddle_sense](https://huggingface.co/datasets/riddle_sense) - instruct augmented
- hellaswag, updated for detailed explanations w 30K+ rows
- [gsm8k](https://huggingface.co/datasets/gsm8k) - instruct augmented
- [ewof/code-alpaca-instruct-unfiltered](https://huggingface.co/datasets/ewof/code-alpaca-instruct-unfiltered)
Manticore 13B
- [ShareGPT](https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered) - based on a cleaned and de-suped subset
- [WizardLM](https://huggingface.co/datasets/ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered)
- [Wizard-Vicuna](https://huggingface.co/datasets/ehartford/wizard_vicuna_70k_unfiltered)
- [subset of QingyiSi/Alpaca-CoT for roleplay and CoT](https://huggingface.co/QingyiSi/Alpaca-CoT)
- [GPT4-LLM-Cleaned](https://huggingface.co/datasets/teknium/GPT4-LLM-Cleaned)
- [GPTeacher-General-Instruct](https://huggingface.co/datasets/teknium/GPTeacher-General-Instruct)
- ARC-Easy & ARC-Challenge - instruct augmented for detailed responses, derived from the `train` split
- [hellaswag](https://huggingface.co/datasets/hellaswag) - 5K row subset of instruct augmented for concise responses, derived from the `train` split
- [metaeval/ScienceQA_text_only](https://huggingface.co/datasets/metaeval/ScienceQA_text_only) - instruct for concise responses
- [openai/summarize_from_feedback](https://huggingface.co/datasets/openai/summarize_from_feedback) - instruct augmented tl;dr summarization
Not added from Manticore 13B:
- mmlu - mmlu datasets were not added to this model as the `test` split is used for benchmarks
# Shoutouts
Special thanks to Nanobit for helping with Axolotl, TheBloke for quantizing these models are more accessible to all, ehartford for cleaned datasets, and 0x000011b for the RP dataset.
# Demo
Try out the model in HF Spaces. The demo uses a quantized GGML version of the model to quickly return predictions on smaller GPUs (and even CPUs). Quantized GGML may have some minimal loss of model quality.
- https://huggingface.co/spaces/openaccess-ai-collective/manticore-13b-chat-pyg
## Release Notes
- https://wandb.ai/wing-lian/manticore-13b-v2/runs/hxr3aiiw
## Build
Manticore was built with [Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) on 8xA100 80GB
- 3 epochs taking approximately 8 hours. No further epochs will be released.
- The configuration to duplicate this build is provided in this repo's [/config folder](https://huggingface.co/openaccess-ai-collective/manticore-13b/tree/main/configs).
## Bias, Risks, and Limitations
Manticore has not been aligned to human preferences with techniques like RLHF or deployed with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so).
Manticore was fine-tuned from the base model LlaMa 13B, please refer to its model card's Limitations Section for relevant information.
## Examples
```
USER: make up a sonnet in the style of shakespeare about a skier skiing in the glades on a bluebird day.
ASSISTANT: A skier doth glide 'neath sun’s glow, His edges sharp to cut the snow, Bluebird sky above, While he doth revel on the slopes below, The cold air biting his nose, But not his spirits, For he is filled with a sense of joy, As he carves through the powdery drifts. His body moves in graceful rhythm, And each turn he makes with ease, He feels like he could ski forever, With no care for the world outside these glades.
```
```
USER: tell me a joke about alpacas
ASSISTANT: Did you hear about the famous alpaca ballet dancer? She was a prima llama.
USER: okay, that is actually pretty good
ASSISTANT: What do you call an alpaca in a bowtie? A llama-cholla!
USER: why is that funny?
ASSISTANT: Because it’s a play on words. “Llama-cholla” sounds like “lame chola,” which is Spanish slang for someone who acts cool or pretentious. So, the joke is implying that alpacas are vain and act cool with their bowties.
```
```
USER: What is 44 + 77?
ASSISTANT: 121
USER: What is the sum of 33 and 77?
ASSISTANT: 110
USER: tell me 5 words that start with “ex” and the sum of 33 and 77.
ASSISTANT: exotic, expressive, explicit, experimental, and extravagant. The sum of 33 and 77 is 110.
USER: tell me 3 words that start with “egr” and end in “s”
ASSISTANT: egret, eggplant, and egrets.
```
- oof
```
USER: Sally has 3 brothers. Each brother has 2 sisters. How many sisters does Sally have?
ASSISTANT: Sally has a total of 6 siblings, so she has a total of 6 - 2 = 4 sisters.
USER: Sally has 3 brothers. Each brother has 2 sisters. How many sisters does Sally have? Use multi-step reasoning to explain your answer.
ASSISTANT: Sally has a total of three brothers, so she has a total of three * 2 = six siblings. Her family consists of three boys and six girls in total. This means that Sally has three sisters since there are six female relatives and only three male ones.
USER: But when brothers have sisters, aren’t they shared or the same?
ASSISTANT: No, not every sibling shares their mother. For example, I have two brothers who share one mother but my third brother has a different mother from both of them.
USER: Let’s assume they all share the same mother and father. Now explain with multi-step reasoning.
ASSISTANT: If Sally has three brothers then that means she has six siblings altogether. Each brother has two sisters, which means that there are twelve female relatives in her family - one for each of her brothers and herself. Since there are only six females in the entire family, that means that Sally’s mother has no other children than her own three sons - so she can’t be the mother of any of the sisters. So all those sisters have to belong to one of the brothers, and since they are shared by two brothers, then each brother has a single sister. Therefore, there is only one sister for Sally, making the final answer 1.
```
- pretty sure that reasoning isn't correct, and the final answer of having 1 sister is a lucky guess
| [
"SUMMARIZATION"
] | Non_BioNLP |
Neurora/opus-tatoeba-lit-eng | Neurora | translation | [
"safetensors",
"marian",
"translation",
"en",
"lt",
"license:cc-by-nc-sa-4.0",
"region:us"
] | 1,740,596,355,000 | 2025-02-26T19:07:26 | 26 | 0 | ---
language:
- en
- lt
license: cc-by-nc-sa-4.0
pipeline_tag: translation
---
# Opus Tatoeba | Lithuanian -> English
* dataset: opus
* model: transformer
* source language(s): lit
* target language(s): eng
* model: transformer
* pre-processing: normalization + SentencePiece (spm32k,spm32k)
* download: [opus-2021-02-23.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/lit-eng/opus-2021-02-23.zip)
* test set translations: [opus-2021-02-23.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/lit-eng/opus-2021-02-23.test.txt)
* test set scores: [opus-2021-02-23.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/lit-eng/opus-2021-02-23.eval.txt)
## Benchmarks
| testset | BLEU | chr-F | #sent | #words | BP |
|---------|-------|-------|-------|--------|----|
| newsdev2019-enlt.lit-eng | 30.8 | 0.580 | 2000 | 49666 | 0.991 |
| newstest2019-lten.lit-eng | 32.9 | 0.613 | 1000 | 26079 | 0.964 |
| Tatoeba-test.lit-eng | 59.1 | 0.734 | 2500 | 17688 | 0.976 |
| [
"TRANSLATION"
] | Non_BioNLP |
Gonalb/flucold-ft-v1 | Gonalb | sentence-similarity | [
"sentence-transformers",
"safetensors",
"bert",
"sentence-similarity",
"feature-extraction",
"generated_from_trainer",
"dataset_size:400",
"loss:MatryoshkaLoss",
"loss:MultipleNegativesRankingLoss",
"arxiv:1908.10084",
"arxiv:2205.13147",
"arxiv:1705.00652",
"base_model:Snowflake/snowflake-arctic-embed-l",
"base_model:finetune:Snowflake/snowflake-arctic-embed-l",
"model-index",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] | 1,740,263,793,000 | 2025-02-22T22:37:34 | 9 | 0 | ---
base_model: Snowflake/snowflake-arctic-embed-l
library_name: sentence-transformers
metrics:
- cosine_accuracy@1
- cosine_accuracy@3
- cosine_accuracy@5
- cosine_accuracy@10
- cosine_precision@1
- cosine_precision@3
- cosine_precision@5
- cosine_precision@10
- cosine_recall@1
- cosine_recall@3
- cosine_recall@5
- cosine_recall@10
- cosine_ndcg@10
- cosine_mrr@10
- cosine_map@100
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:400
- loss:MatryoshkaLoss
- loss:MultipleNegativesRankingLoss
widget:
- source_sentence: 'QUESTION #2: What percentage of patients in the study reported
experiencing "chills" and "feverish discomfort"?'
sentences:
- "been proven superior. Annual influenza vaccination is recommended for all people\
\ six months and older who do not have \ncontraindications. ( Am Fam Physician.\
\ 2019; 100(12):751-758. Copyright © 2019 American Academy of Family Physicians.)\n\
BEST PRACTICES IN INFECTIOUS DISEASE \nRecommendations from the Choosing \nWisely\
\ Campaign\nRecommendation Sponsoring organization\nDo not routinely avoid \n\
influenza vaccination in \negg-allergic patients.\nAmerican Academy of Allergy,\
\ \nAsthma, and Immunology\nSource: For more information on the Choosing Wisely\
\ Campaign,"
- 'Review
722 Vol 5 November 2005
accompanied by fever and some subjects have a transient
fall in body temperature during the early stages of
common cold. In a study of 272 patients with sore throat
associated with URTIs, the mean aural temperature was
36·8ºC and around 35% of these patients said they were
suffering from “chills” and “feverish discomfort”.49 The
sensation of chilliness may be unrelated to any change in
skin or body temperature. In a study of human
volunteers, a sensation of chill still develops on
administration of exogenous pyrogen even though the'
- "ered when the results will modify management or when a \npatient with signs or\
\ symptoms of influenza is hospitalized.19 \nTABLE 2\nComplications of Influenza\n\
Cardiovascular 26\nCerebrovascular accidents\nIschemic heart disease\nMyocarditis\n\
Hematologic 26\nHemolytic uremic syndrome\nHemophagocytic syndrome\nThrombotic\
\ thrombocytope -\nnic purpura\nMusculoskeletal 19,26\nMyositis\nRhabdomyolysis\n\
Neurologic 26\nAcute disseminated \nencephalomyelitis\nEncephalitis\nGuillain-Barré\
\ syndrome\nPostinfluenza encephalopathy \n(neurologic symptoms occur -\nring\
\ after resolution but within"
- source_sentence: How do cytokines interact with the body's systems to influence
the hypothalamus and affect body temperature?
sentences:
- 'interleukin 1, interleukin 6, and tumour necrosis factor
alpha, as well as the anti-inflammatory cytokines
interleukin-1 receptor antagonist and interleukin 10
have been investigated for their pyrogenic or antipyretic
action.17 Interleukin 1 and interleukin 6 are believed to
be the most important cytokines that induce fever. 55
Cytokines are believed to cross the blood–brain barrier
or interact with the vagus nerve endings to signal the
temperature control centre of the hypothalamus to
increase the thermal set point.55,56 The hypothalamus
then initiates shivering, constriction of skin blood'
- "mended human dose; possible \nrisk of embryo-fetal toxicity with \ncontinuous\
\ intravenous infusion \nbased on limited animal data\nBaloxavir (Xofluza), \n\
available as oral \ntablets\nNA ($160) Adults and children 12 years \nand older:\
\ \n88 to 174 lb (40 to 79 kg): \nsingle dose of 40 mg \n≥ 175 lb (80 kg):\
\ single dose \nof 80 mg\nTreatment of uncom-\nplicated acute \ninfluenza in\
\ patients \n12 years and older who \nhave been symptom -\natic for no more than\
\ \n48 hours\nContraindicated in people with \na history of hypersensitivity to\
\ \nbaloxavir or any component of the \nproduct"
- "CME This clinical content conforms to AAFP criteria for con-\ntinuing medical\
\ education (CME). See CME Quiz on page 271.\nAuthor disclosure: No relevant\
\ financial affiliations.\nPatient information: Handouts on this topic, written\
\ by the \nauthors of this article, are available at https:// www.aafp.org/\n\
afp/2019/0901/p281-s1.html and https:// www.aafp.org/\nafp/2019/0901/p281-s2.html.\n\
Acute upper respiratory tract infections are extremely common in adults and children,\
\ but only a few safe and effective treat-"
- source_sentence: What are the limitations of using adamantanes (amantadine and rimantadine)
for influenza treatment according to the context?
sentences:
- "December 15, 2019 ◆ Volume 100, Number 12 www.aafp.org/afp American Family Physician\
\ 755\nINFLUENZA\nClinicians caring for high-risk patients can also be consid\
\ -\nered for treatment.28\nFour antiviral drugs have been approved for the treat\
\ -\nment of influenza (Table 4): the NA inhibitors oseltamivir \n(Tamiflu),\
\ zanamivir (Relenza), and peramivir (Rapivab), \nand the cap-dependent endonuclease\
\ inhibitor baloxa -\nvir (Xofluza). 18,37 Any of these agents can be used in\
\ age- \nappropriate, otherwise healthy outpatients with uncom -\nplicated influenza\
\ and no contraindications. 18 Baloxavir is"
- "756 American Family Physician www.aafp.org/afp Volume 100, Number 12 ◆ December\
\ 15, 2019\nINFLUENZA\nthe risk of bronchospasm. 18,28 Adamantanes (amantadine\
\ \nand rimantadine [Flumadine]) are approved for influenza \ntreatment but are\
\ not currently recommended. These med -\nications are not active against influenza\
\ B, and most influ -\nenza A strains have shown adamantane resistance for the\
\ \npast 10 years.18\nThere is no demonstrated benefit to treating patients \n\
with more than one antiviral agent or using higher than \nrecommended dosages.\
\ 28 However, extended treatment"
- "distress syndrome\nDiffuse alveolar \nhemorrhage\nHypoxic respiratory \nfailure\n\
Primary viral pneumonia\nSecondary bacterial \npneumonia\nRenal 26\nAcute kidney\
\ injury \n(e.g., acute tubulo- \ninterstitial nephritis, \nglomerulonephritis,\
\ \nminimal change disease)\nMultiorgan failure\nInformation from references 8,\
\ 19, and 25-27.\nSORT: KEY RECOMMENDATIONS FOR PRACTICE\nClinical recommendation\n\
Evidence \nrating Comments\nAnnual influenza vaccination is recommended for all\
\ people 6 months and older. 15,16 A Reports of expert committees"
- source_sentence: Which symptoms of colds and flu are now better understood due to
new knowledge in molecular biology?
sentences:
- 'mechanisms that generate the familiar symptoms is poor compared with the amount
of knowledge available on the
molecular biology of the viruses involved. New knowledge of the effects of cytokines
in human beings now helps to
explain some of the symptoms of colds and flu that were previously in the realm
of folklore rather than medicine—
eg, fever, anorexia, malaise, chilliness, headache, and muscle aches and pains.
The mechanisms of symptoms of
sore throat, rhinorrhoea, sneezing, nasal congestion, cough, watery eyes, and
sinus pain are discussed, since these'
- 'medicines such as ipratropium. These studies have
demonstrated that nasal secretions in the first 4 days of a
common cold are inhibited by intranasal administration
of ipratropium.25 The nasal discharge also consists of a
protein-rich plasma exudate derived from subepithelial
capillaries,28 which may explain why anticholinergics
only partly inhibit nasal discharge associated with
URTIs.27
The colour of nasal discharge and sputum is often
used as a clinical marker to determine whether or not to
prescribe antibiotics but there is no evidence from the'
- "ing diffuse alveolar hemorrhage in immunocompetent patients: a state-\nof-the-art\
\ review. Lung. 2013; 191(1): 9-18.\n 28. Uyeki TM, Bernstein HH, Bradley JS,\
\ et al. Clinical practice guidelines by \nthe Infectious Diseases Society of\
\ America: 2018 update on diagnosis, \ntreatment, chemoprophylaxis, and institutional\
\ outbreak management \nof seasonal influenza. Clin Infect Dis. 2019; 68(6): 895-902.\n\
\ 29. Ebell MH, Afonso AM, Gonzales R, et al. Development and validation of \n\
a clinical decision rule for the diagnosis of influenza. J Am Board Fam \nMed.\
\ 2012; 25(1): 55-62."
- source_sentence: 'QUESTION #2: How does the sneeze centre in the brainstem coordinate
the actions involved in sneezing?'
sentences:
- "stroke, seizure disorder, dementia)\nAsthma or other chronic pulmonary disease\n\
Chronic kidney disease\nChronic liver disease\nHeart disease (acquired or congenital)\n\
Immunosuppression (e.g., HIV infection, cancer, transplant \nrecipients, use of\
\ immunosuppressive medications)\nLong-term aspirin therapy in patients younger\
\ than 19 years\nMetabolic disorders (acquired [e.g., diabetes mellitus] or \n\
inherited [e.g., mitochondrial disorders])\nMorbid obesity\nSickle cell anemia\
\ and other hemoglobinopathies\nSpecial groups\nAdults 65 years and older\nAmerican\
\ Indians and Alaska Natives"
- 'causes sneezing.23 The trigeminal nerves relay
information to the sneeze centre in the brainstem and
cause reflex activation of motor and parasympathetic
branches of the facial nerve and activate respiratory
muscles. A model of the sneeze reflex is illustrated in
figure 1. The sneeze centre coordinates the inspiratory
and expiratory actions of sneezing via respiratory
muscles, and lacrimation and nasal congestion via
parasympathetic branches of the facial nerve. The eyes
are always closed during sneezing by activation of facial
muscles, indicating a close relation between the'
- 'during experimental rhinovirus infections have not
been able to find any morphological changes in the
nasal epithelium of infected volunteers, apart from a
substantial increase in polymorphonuclear leucocytes
early in the course of the infection.11 The major cell
monitoring the host for the invasion of pathogens is
the macrophage, which has the ability to trigger an
acute phase response when stimulated with
components of viruses or bacteria—eg, viral RNA and
bacterial cell wall components.12 The surface of the
macrophage exhibits toll-like receptors that combine'
model-index:
- name: SentenceTransformer based on Snowflake/snowflake-arctic-embed-l
results:
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: Unknown
type: unknown
metrics:
- type: cosine_accuracy@1
value: 0.6122448979591837
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.8877551020408163
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.9387755102040817
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.9897959183673469
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.6122448979591837
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.29591836734693877
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.1877551020408163
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.09897959183673469
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.6122448979591837
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.8877551020408163
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.9387755102040817
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.9897959183673469
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.8165441473931409
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.7593091998704244
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.7600380628441854
name: Cosine Map@100
---
# SentenceTransformer based on Snowflake/snowflake-arctic-embed-l
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Snowflake/snowflake-arctic-embed-l](https://huggingface.co/Snowflake/snowflake-arctic-embed-l). It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
## Model Details
### Model Description
- **Model Type:** Sentence Transformer
- **Base model:** [Snowflake/snowflake-arctic-embed-l](https://huggingface.co/Snowflake/snowflake-arctic-embed-l) <!-- at revision d8fb21ca8d905d2832ee8b96c894d3298964346b -->
- **Maximum Sequence Length:** 512 tokens
- **Output Dimensionality:** 1024 dimensions
- **Similarity Function:** Cosine Similarity
<!-- - **Training Dataset:** Unknown -->
<!-- - **Language:** Unknown -->
<!-- - **License:** Unknown -->
### Model Sources
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
### Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
(2): Normalize()
)
```
## Usage
### Direct Usage (Sentence Transformers)
First install the Sentence Transformers library:
```bash
pip install -U sentence-transformers
```
Then you can load this model and run inference.
```python
from sentence_transformers import SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("Gonalb/flucold-ft-v1")
# Run inference
sentences = [
'QUESTION #2: How does the sneeze centre in the brainstem coordinate the actions involved in sneezing?',
'causes sneezing.23 The trigeminal nerves relay\ninformation to the sneeze centre in the brainstem and\ncause reflex activation of motor and parasympathetic\nbranches of the facial nerve and activate respiratory\nmuscles. A model of the sneeze reflex is illustrated in\nfigure 1. The sneeze centre coordinates the inspiratory\nand expiratory actions of sneezing via respiratory\nmuscles, and lacrimation and nasal congestion via\nparasympathetic branches of the facial nerve. The eyes\nare always closed during sneezing by activation of facial\nmuscles, indicating a close relation between the',
'stroke, seizure disorder, dementia)\nAsthma or other chronic pulmonary disease\nChronic kidney disease\nChronic liver disease\nHeart disease (acquired or congenital)\nImmunosuppression (e.g., HIV infection, cancer, transplant \nrecipients, use of immunosuppressive medications)\nLong-term aspirin therapy in patients younger than 19 years\nMetabolic disorders (acquired [e.g., diabetes mellitus] or \ninherited [e.g., mitochondrial disorders])\nMorbid obesity\nSickle cell anemia and other hemoglobinopathies\nSpecial groups\nAdults 65 years and older\nAmerican Indians and Alaska Natives',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]
```
<!--
### Direct Usage (Transformers)
<details><summary>Click to see the direct usage in Transformers</summary>
</details>
-->
<!--
### Downstream Usage (Sentence Transformers)
You can finetune this model on your own dataset.
<details><summary>Click to expand</summary>
</details>
-->
<!--
### Out-of-Scope Use
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->
## Evaluation
### Metrics
#### Information Retrieval
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| cosine_accuracy@1 | 0.6122 |
| cosine_accuracy@3 | 0.8878 |
| cosine_accuracy@5 | 0.9388 |
| cosine_accuracy@10 | 0.9898 |
| cosine_precision@1 | 0.6122 |
| cosine_precision@3 | 0.2959 |
| cosine_precision@5 | 0.1878 |
| cosine_precision@10 | 0.099 |
| cosine_recall@1 | 0.6122 |
| cosine_recall@3 | 0.8878 |
| cosine_recall@5 | 0.9388 |
| cosine_recall@10 | 0.9898 |
| **cosine_ndcg@10** | **0.8165** |
| cosine_mrr@10 | 0.7593 |
| cosine_map@100 | 0.76 |
<!--
## Bias, Risks and Limitations
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
-->
<!--
### Recommendations
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
-->
## Training Details
### Training Dataset
#### Unnamed Dataset
* Size: 400 training samples
* Columns: <code>sentence_0</code> and <code>sentence_1</code>
* Approximate statistics based on the first 400 samples:
| | sentence_0 | sentence_1 |
|:--------|:-----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
| type | string | string |
| details | <ul><li>min: 14 tokens</li><li>mean: 24.87 tokens</li><li>max: 53 tokens</li></ul> | <ul><li>min: 44 tokens</li><li>mean: 129.25 tokens</li><li>max: 188 tokens</li></ul> |
* Samples:
| sentence_0 | sentence_1 |
|:----------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <code>What is the recommended age for annual influenza vaccination according to the context?</code> | <code>recommend annual influenza vaccination for all people six <br>months and older who do not have contraindications. 15,16 <br>Vaccination efforts should target people at increased risk of <br>complicated or severe influenza (Table 117-19) and those who <br>care for or live with high-risk individuals, including health <br>care professionals. 15 Two previous FPM articles provided <br>communication strategies and tools for increasing influenza <br>vaccination rates in practice. 20,21<br>Multiple formulations of the influenza vaccine are avail -<br>able, including inactivated influenza vaccines (IIV); a recom-</code> |
| <code>Who should vaccination efforts specifically target to prevent complicated or severe influenza?</code> | <code>recommend annual influenza vaccination for all people six <br>months and older who do not have contraindications. 15,16 <br>Vaccination efforts should target people at increased risk of <br>complicated or severe influenza (Table 117-19) and those who <br>care for or live with high-risk individuals, including health <br>care professionals. 15 Two previous FPM articles provided <br>communication strategies and tools for increasing influenza <br>vaccination rates in practice. 20,21<br>Multiple formulations of the influenza vaccine are avail -<br>able, including inactivated influenza vaccines (IIV); a recom-</code> |
| <code>What types of studies were included in the search regarding influenza complications and treatment?</code> | <code>enza complications American Indians, influenza treatment, and <br>influenza universal vaccine. The search included meta-analyses, <br>randomized controlled trials, clinical trials, and reviews. Search <br>dates: December 1, 2018, to October 5, 2019.<br>The Authors<br>DAVID Y. GAITONDE, MD, is a core clinical faculty member <br>and chief of endocrinology service at Dwight D. Eisenhower <br>Army Medical Center, Fort Gordon, Ga.<br>CPT. FAITH C. MOORE, USA, MC, is a resident in the Depart -<br>ment of Internal Medicine at Dwight D. Eisenhower Army <br>Medical Center.<br>MAJ. MACKENZIE K. MORGAN, USA, MC, is chief of infec-</code> |
* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
```json
{
"loss": "MultipleNegativesRankingLoss",
"matryoshka_dims": [
768,
512,
256,
128,
64
],
"matryoshka_weights": [
1,
1,
1,
1,
1
],
"n_dims_per_step": -1
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `eval_strategy`: steps
- `per_device_train_batch_size`: 10
- `per_device_eval_batch_size`: 10
- `num_train_epochs`: 10
- `multi_dataset_batch_sampler`: round_robin
#### All Hyperparameters
<details><summary>Click to expand</summary>
- `overwrite_output_dir`: False
- `do_predict`: False
- `eval_strategy`: steps
- `prediction_loss_only`: True
- `per_device_train_batch_size`: 10
- `per_device_eval_batch_size`: 10
- `per_gpu_train_batch_size`: None
- `per_gpu_eval_batch_size`: None
- `gradient_accumulation_steps`: 1
- `eval_accumulation_steps`: None
- `torch_empty_cache_steps`: None
- `learning_rate`: 5e-05
- `weight_decay`: 0.0
- `adam_beta1`: 0.9
- `adam_beta2`: 0.999
- `adam_epsilon`: 1e-08
- `max_grad_norm`: 1
- `num_train_epochs`: 10
- `max_steps`: -1
- `lr_scheduler_type`: linear
- `lr_scheduler_kwargs`: {}
- `warmup_ratio`: 0.0
- `warmup_steps`: 0
- `log_level`: passive
- `log_level_replica`: warning
- `log_on_each_node`: True
- `logging_nan_inf_filter`: True
- `save_safetensors`: True
- `save_on_each_node`: False
- `save_only_model`: False
- `restore_callback_states_from_checkpoint`: False
- `no_cuda`: False
- `use_cpu`: False
- `use_mps_device`: False
- `seed`: 42
- `data_seed`: None
- `jit_mode_eval`: False
- `use_ipex`: False
- `bf16`: False
- `fp16`: False
- `fp16_opt_level`: O1
- `half_precision_backend`: auto
- `bf16_full_eval`: False
- `fp16_full_eval`: False
- `tf32`: None
- `local_rank`: 0
- `ddp_backend`: None
- `tpu_num_cores`: None
- `tpu_metrics_debug`: False
- `debug`: []
- `dataloader_drop_last`: False
- `dataloader_num_workers`: 0
- `dataloader_prefetch_factor`: None
- `past_index`: -1
- `disable_tqdm`: False
- `remove_unused_columns`: True
- `label_names`: None
- `load_best_model_at_end`: False
- `ignore_data_skip`: False
- `fsdp`: []
- `fsdp_min_num_params`: 0
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
- `fsdp_transformer_layer_cls_to_wrap`: None
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
- `deepspeed`: None
- `label_smoothing_factor`: 0.0
- `optim`: adamw_torch
- `optim_args`: None
- `adafactor`: False
- `group_by_length`: False
- `length_column_name`: length
- `ddp_find_unused_parameters`: None
- `ddp_bucket_cap_mb`: None
- `ddp_broadcast_buffers`: False
- `dataloader_pin_memory`: True
- `dataloader_persistent_workers`: False
- `skip_memory_metrics`: True
- `use_legacy_prediction_loop`: False
- `push_to_hub`: False
- `resume_from_checkpoint`: None
- `hub_model_id`: None
- `hub_strategy`: every_save
- `hub_private_repo`: None
- `hub_always_push`: False
- `gradient_checkpointing`: False
- `gradient_checkpointing_kwargs`: None
- `include_inputs_for_metrics`: False
- `include_for_metrics`: []
- `eval_do_concat_batches`: True
- `fp16_backend`: auto
- `push_to_hub_model_id`: None
- `push_to_hub_organization`: None
- `mp_parameters`:
- `auto_find_batch_size`: False
- `full_determinism`: False
- `torchdynamo`: None
- `ray_scope`: last
- `ddp_timeout`: 1800
- `torch_compile`: False
- `torch_compile_backend`: None
- `torch_compile_mode`: None
- `dispatch_batches`: None
- `split_batches`: None
- `include_tokens_per_second`: False
- `include_num_input_tokens_seen`: False
- `neftune_noise_alpha`: None
- `optim_target_modules`: None
- `batch_eval_metrics`: False
- `eval_on_start`: False
- `use_liger_kernel`: False
- `eval_use_gather_object`: False
- `average_tokens_across_devices`: False
- `prompts`: None
- `batch_sampler`: batch_sampler
- `multi_dataset_batch_sampler`: round_robin
</details>
### Training Logs
| Epoch | Step | cosine_ndcg@10 |
|:-----:|:----:|:--------------:|
| 1.0 | 40 | 0.8359 |
| 1.25 | 50 | 0.8312 |
| 2.0 | 80 | 0.8304 |
| 2.5 | 100 | 0.8156 |
| 3.0 | 120 | 0.8016 |
| 3.75 | 150 | 0.7952 |
| 4.0 | 160 | 0.7880 |
| 5.0 | 200 | 0.8021 |
| 6.0 | 240 | 0.8215 |
| 6.25 | 250 | 0.8286 |
| 7.0 | 280 | 0.8079 |
| 7.5 | 300 | 0.8043 |
| 8.0 | 320 | 0.8126 |
| 8.75 | 350 | 0.8099 |
| 9.0 | 360 | 0.8126 |
| 10.0 | 400 | 0.8165 |
### Framework Versions
- Python: 3.11.11
- Sentence Transformers: 3.4.1
- Transformers: 4.48.3
- PyTorch: 2.5.1+cu124
- Accelerate: 1.3.0
- Datasets: 3.3.2
- Tokenizers: 0.21.0
## Citation
### BibTeX
#### Sentence Transformers
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "https://arxiv.org/abs/1908.10084",
}
```
#### MatryoshkaLoss
```bibtex
@misc{kusupati2024matryoshka,
title={Matryoshka Representation Learning},
author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
year={2024},
eprint={2205.13147},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
```
#### MultipleNegativesRankingLoss
```bibtex
@misc{henderson2017efficient,
title={Efficient Natural Language Response Suggestion for Smart Reply},
author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
year={2017},
eprint={1705.00652},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
<!--
## Glossary
*Clearly define terms in order to be accessible across audiences.*
-->
<!--
## Model Card Authors
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->
<!--
## Model Card Contact
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
--> | [
"TEXT_CLASSIFICATION"
] | BioNLP |
Lvxue/distilled-mt5-small-0.05-1 | Lvxue | text2text-generation | [
"transformers",
"pytorch",
"mt5",
"text2text-generation",
"generated_from_trainer",
"en",
"ro",
"dataset:wmt16",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 1,660,209,377,000 | 2022-08-11T10:23:47 | 10 | 0 | ---
datasets:
- wmt16
language:
- en
- ro
license: apache-2.0
metrics:
- bleu
tags:
- generated_from_trainer
model-index:
- name: distilled-mt5-small-0.05-1
results:
- task:
type: translation
name: Translation
dataset:
name: wmt16 ro-en
type: wmt16
args: ro-en
metrics:
- type: bleu
value: 6.997
name: Bleu
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilled-mt5-small-0.05-1
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the wmt16 ro-en dataset.
It achieves the following results on the evaluation set:
- Loss: 2.8106
- Bleu: 6.997
- Gen Len: 46.2551
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0
### Training results
### Framework versions
- Transformers 4.20.1
- Pytorch 1.12.0+cu102
- Datasets 2.3.2
- Tokenizers 0.12.1
| [
"TRANSLATION"
] | Non_BioNLP |
onnx-community/opus-mt-en-ru | onnx-community | translation | [
"transformers.js",
"onnx",
"marian",
"text2text-generation",
"translation",
"base_model:Helsinki-NLP/opus-mt-en-ru",
"base_model:quantized:Helsinki-NLP/opus-mt-en-ru",
"license:cc-by-4.0",
"region:us"
] | 1,724,794,252,000 | 2024-10-08T13:54:12 | 6 | 0 | ---
base_model: Helsinki-NLP/opus-mt-en-ru
library_name: transformers.js
license: cc-by-4.0
pipeline_tag: translation
---
https://huggingface.co/Helsinki-NLP/opus-mt-en-ru with ONNX weights to be compatible with Transformers.js.
Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`). | [
"TRANSLATION"
] | Non_BioNLP |
bitextor/bicleaner-ai-full-en-ga | bitextor | null | [
"transformers",
"tf",
"xlm-roberta",
"bicleaner-ai",
"en",
"ga",
"multilingual",
"license:cc-by-sa-4.0",
"endpoints_compatible",
"region:us"
] | 1,679,917,534,000 | 2023-03-27T11:45:53 | 7 | 0 | ---
language:
- en
- ga
- multilingual
license: cc-by-sa-4.0
tags:
- bicleaner-ai
tasks:
- text-classification
---
# Bicleaner AI full model for en-ga
Bicleaner AI is a tool that aims at detecting noisy sentence pairs in a parallel corpus. It
indicates the likelihood of a pair of sentences being mutual translations (with a value near to 1) or not (with a value near to 0).
Sentence pairs considered very noisy are scored with 0.
Find out at our repository for further instructions on how to use it: https://github.com/bitextor/bicleaner-ai
| [
"TRANSLATION"
] | Non_BioNLP |
BounharAbdelaziz/Terjman-Large-v2.0 | BounharAbdelaziz | translation | [
"transformers",
"safetensors",
"marian",
"text2text-generation",
"translation",
"ary",
"en",
"dataset:BounharAbdelaziz/Terjman-v2-English-Darija-Dataset-350K",
"base_model:atlasia/Terjman-Large-v1.2",
"base_model:finetune:atlasia/Terjman-Large-v1.2",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 1,738,505,001,000 | 2025-03-11T09:18:07 | 109 | 1 | ---
base_model: atlasia/Terjman-Large-v1.2
datasets:
- BounharAbdelaziz/Terjman-v2-English-Darija-Dataset-350K
language:
- ary
- en
library_name: transformers
license: cc-by-nc-4.0
metrics:
- bleu
- chrf
- ter
pipeline_tag: translation
model-index:
- name: Terjman-Large-v2.0
results: []
---
# 🇲🇦 Terjman-Large-v2.0 (240M) 🚀
**Terjman-Large-v2.0** is an improved version of [atlasia/Terjman-Large-v1.2](https://huggingface.co/atlasia/Terjman-Large-v1.2), built on the powerful Transformer architecture and fine-tuned for **high-quality, accurate translations**.
This version is based on [atlasia/Terjman-Large-v1.2](https://huggingface.co/atlasia/Terjman-Large-v1.2) and has been trained on a **larger and more refined dataset**, leading to improved translation performance. The model achieves results **on par with gpt-4o-2024-08-06** on [TerjamaBench](https://huggingface.co/datasets/atlasia/TerjamaBench), an evaluation benchmark for English-Moroccan darija translation models, that challenges the models more on the cultural aspect.
## 🚀 Features
✅ **Fine-tuned for English->Moroccan darija translation**.
✅ **State-of-the-art performance** among open-source models.
✅ **Compatible with 🤗 Transformers** and easily deployable on various hardware setups.
## 🔥 Performance Comparison
The following table compares **Terjman-Large-v2.0** against proprietary and open-source models using BLEU, chrF, and TER scores. Higher **BLEU/chrF** and lower **TER** indicate better translation quality.
| **Model** | **Size** | **BLEU↑** | **chrF↑** | **TER↓** |
|------------|------|-------|-------|------|
| **Proprietary Models** | | | | |
| gemini-exp-1206 | * | **30.69** | **54.16** | 67.62 |
| claude-3-5-sonnet-20241022 | * | 30.51 | 51.80 | **67.42** |
| gpt-4o-2024-08-06 | * | 28.30 | 50.13 | 71.77 |
| **Open-Source Models** | | | | |
| Terjman-Ultra-v2.0| 1.3B | **25.00** | **44.70** | **77.20** |
| Terjman-Supreme-v2.0 | 3.3B | 23.43 | 44.57 | 78.17 |
| **Terjman-Large-v2.0 (This model)** | 240M | 22.67 | 42.57 | 83.00 |
| Terjman-Nano-v2.0| 77M | 18.84 | 38.41 | 94.73 |
| atlasia/Terjman-Large-v1.2.2 | 240M | 16.33 | 37.10 | 89.13 |
| MBZUAI-Paris/Atlas-Chat-9B | 9B | 14.80 | 35.26 | 93.95 |
| facebook/nllb-200-3.3B | 3.3B | 14.76 | 34.17 | 94.33 |
| atlasia/Terjman-Nano | 77M | 09.98 | 26.55 | 106.49 |
## 🔬 Model Details
- **Base Model**: [atlasia/Terjman-Large-v1.2](https://huggingface.co/atlasia/Terjman-Large-v1.2)
- **Architecture**: Transformer-based sequence-to-sequence model
- **Training Data**: High-quality parallel corpora with high quality translations
- **Training Precision**: FP16 for efficient inference
## 🚀 How to Use
You can use the model with the **Hugging Face Transformers** library:
```python
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
model_name = "BounharAbdelaziz/Terjman-Large-v2.0"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
def translate(text):
inputs = tokenizer(text, return_tensors="pt")
output = model.generate(**inputs)
return tokenizer.decode(output[0], skip_special_tokens=True)
# Example translation
text = "Hello there! Today the weather is so nice in Geneva, couldn't ask for more to enjoy the holidays :)"
translation = translate(text)
print("Translation:", translation)
# prints: صباح الخير! اليوم الطقس زوين بزاف فجنيف، ما قدرتش نطلب المزيد باش نستمتعو بالعطل:)
```
## 🖥️ Deployment
### Run in a Hugging Face Space
Try the model interactively in the [Terjman-Large Space](https://huggingface.co/spaces/BounharAbdelaziz/Terjman-Large-v2.0) 🤗
### Use with Text Generation Inference (TGI)
For fast inference, use **Hugging Face TGI**:
```bash
pip install text-generation
text-generation-launcher --model-id BounharAbdelaziz/Terjman-Large-v2.0
```
### Run Locally with Transformers & PyTorch
```bash
pip install transformers torch
python -c "from transformers import pipeline; print(pipeline('translation', model='BounharAbdelaziz/Terjman-Large-v2.0')('Hello there!'))"
```
### Deploy on an API Server
Use **FastAPI** to serve translations as an API:
```python
from fastapi import FastAPI
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
app = FastAPI()
model_name = "BounharAbdelaziz/Terjman-Large-v2.0"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
@app.get("/translate/")
def translate(text: str):
inputs = tokenizer(text, return_tensors="pt")
output = model.generate(**inputs)
return {"translation": tokenizer.decode(output[0], skip_special_tokens=True)}
```
## 🛠️ Training Details Hyperparameters**
The model was fine-tuned using the following training settings:
- **Learning Rate**: `0.001`
- **Training Batch Size**: `16`
- **Evaluation Batch Size**: `16`
- **Seed**: `42`
- **Gradient Accumulation Steps**: `8`
- **Total Effective Batch Size**: `128`
- **Optimizer**: `AdamW (Torch)` with `betas=(0.9,0.999)`, `epsilon=1e-08`
- **Learning Rate Scheduler**: `Linear`
- **Warmup Ratio**: `0.1`
- **Epochs**: `2`
- **Precision**: `Mixed FP16` for efficient training
## Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.21.0
-
## 📜 License
This model is released under the **CC BY-NC (Creative Commons Attribution-NonCommercial)** license, meaning it can be used for research and personal projects but not for commercial purposes. For commercial use, please get in touch :)
```bibtex
@misc{terjman-v2,
title = {Terjman-v2: High-Quality English-Moroccan Darija Translation Model},
author={Abdelaziz Bounhar},
year={2025},
howpublished = {\url{https://huggingface.co/BounharAbdelaziz/Terjman-Large-v2.0}},
license = {CC BY-NC}
}
``` | [
"TRANSLATION"
] | Non_BioNLP |
qingy2024/manticore-13b-v2 | qingy2024 | text-generation | [
"transformers",
"pytorch",
"llama",
"text-generation",
"en",
"dataset:anon8231489123/ShareGPT_Vicuna_unfiltered",
"dataset:ehartford/wizard_vicuna_70k_unfiltered",
"dataset:ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered",
"dataset:QingyiSi/Alpaca-CoT",
"dataset:teknium/GPT4-LLM-Cleaned",
"dataset:teknium/GPTeacher-General-Instruct",
"dataset:metaeval/ScienceQA_text_only",
"dataset:hellaswag",
"dataset:tasksource/mmlu",
"dataset:openai/summarize_from_feedback",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 1,739,220,334,000 | 2025-02-10T20:45:34 | 12 | 0 | ---
datasets:
- anon8231489123/ShareGPT_Vicuna_unfiltered
- ehartford/wizard_vicuna_70k_unfiltered
- ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered
- QingyiSi/Alpaca-CoT
- teknium/GPT4-LLM-Cleaned
- teknium/GPTeacher-General-Instruct
- metaeval/ScienceQA_text_only
- hellaswag
- tasksource/mmlu
- openai/summarize_from_feedback
language:
- en
library_name: transformers
pipeline_tag: text-generation
---
# Manticore 13B - (previously Wizard Mega)
**[💵 Donate to OpenAccess AI Collective](https://github.com/sponsors/OpenAccess-AI-Collective) to help us keep building great tools and models!**
Questions, comments, feedback, looking to donate, or want to help? Reach out on our [Discord](https://discord.gg/EqrvvehG) or email [[email protected]](mailto:[email protected])
Manticore 13B is a Llama 13B model fine-tuned on the following datasets:
- [ShareGPT](https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered) - based on a cleaned and de-suped subset
- [WizardLM](https://huggingface.co/datasets/ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered)
- [Wizard-Vicuna](https://huggingface.co/datasets/ehartford/wizard_vicuna_70k_unfiltered)
- [subset of QingyiSi/Alpaca-CoT for roleplay and CoT](https://huggingface.co/QingyiSi/Alpaca-CoT)
- [GPT4-LLM-Cleaned](https://huggingface.co/datasets/teknium/GPT4-LLM-Cleaned)
- [GPTeacher-General-Instruct](https://huggingface.co/datasets/teknium/GPTeacher-General-Instruct)
- ARC-Easy & ARC-Challenge - instruct augmented for detailed responses
- mmlu: instruct augmented for detailed responses subset including
- abstract_algebra
- conceptual_physics
- formal_logic
- high_school_physics
- logical_fallacies
- [hellaswag](https://huggingface.co/datasets/hellaswag) - 5K row subset of instruct augmented for concise responses
- [metaeval/ScienceQA_text_only](https://huggingface.co/datasets/metaeval/ScienceQA_text_only) - instruct for concise responses
- [openai/summarize_from_feedback](https://huggingface.co/datasets/openai/summarize_from_feedback) - instruct augmented tl;dr summarization
# Demo
Try out the model in HF Spaces. The demo uses a quantized GGML version of the model to quickly return predictions on smaller GPUs (and even CPUs). Quantized GGML may have some minimal loss of model quality.
- https://huggingface.co/spaces/openaccess-ai-collective/manticore-ggml
## Release Notes
- https://wandb.ai/wing-lian/manticore-13b/runs/nq3u3uoh/workspace
## Build
Manticore was built with [Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) on 8xA100 80GB
- Preview Release: 3 epochs taking approximately 24 hours.
- The configuration to duplicate this build is provided in this repo's [/config folder](https://huggingface.co/openaccess-ai-collective/manticore-13b/tree/main/configs).
## Bias, Risks, and Limitations
Manticore has not been aligned to human preferences with techniques like RLHF or deployed with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so).
Manticore was fine-tuned from the base model LlaMa 13B, please refer to its model card's Limitations Section for relevant information.
## Examples
````
### Instruction: write Python code that returns the first n numbers of the Fibonacci sequence using memoization.
### Assistant:
Here’s an example of how you can use memoization to efficiently calculate the first n numbers of the Fibonacci sequence in Python:
```
def fib(n):
# Memoize the last calculated Fibonacci number for each index
cache = {}
def fib_memoized(n):
if n not in cache:
cache[n] = [0, 1]
else:
return cache[n][-1], cache[n][-2]
# Recursive helper function to calculate the Fibonacci sequence up to a given index
def fib_helper(n):
if n == 0 or n == 1:
return 0, 1
else:
return fib_helper(n - 1) + fib_helper(n - 2)
# Calculate the first n numbers of the Fibonacci sequence using memoization
def fib_memoized_seq(n):
if n == 0 or n == 1:
return 0, 1
else:
result = fib_helper(n - 1) + fib_helper(n - 2)
cache[n] = [result]
return result, cache[n][-1], cache[n][-2]
# Example usage
for i in range(len(fib_memoized_seq(3))):
print(fib_memoized_seq(3)[i])
```
In this implementation, we use a cache dictionary to memoize the last calculated Fibonacci number for each index. We define two helper functions: fib_helper, which recursively calculates the Fibonacci sequence up to a given index, and fib_memoized, which uses memoization to efficiently calculate the first n numbers of the Fibonacci sequence. Finally, we define the fib_memoized_seq function, which is our main function for calculating the first n numbers of the Fibonacci sequence using memoization.
````
```
USER: Finish the joke, a mechanic and a car salesman walk into a bar...
ASSISTANT: … and when they get up to leave, they realize that they’ve left their keys in their cars. The mechanic says “I know how to fix this” and opens his toolbox to grab something. Then he stops and looks at the salesman. He says “You drive a Toyota, right?” The salesman nods. The mechanic then takes out a tiny screwdriver from his toolbox and starts working on the lock of the car door. The salesman is amazed and asks how he knew that. The mechanic replies “I can tell by the way you parked your car.”
```
```
USER: Describe how a tsunami would affect the residents of Denver Colorado
ASSISTANT: The impact of a tsunami in Denver, Colorado would likely be minimal. As there are no coastal areas or bodies of water nearby, a tsunami generated from an earthquake or volcanic activity elsewhere in the world would have little effect on the city and its residents. Even if a large tsunami were to hit the coastline of California or Mexico, the distance between Denver and these locations means that any impacts on the city itself would be minimal.
```
```
USER: If you could do one thing right now, what would it be?
ASSISTANT: I’d hug my loved ones a little tighter today and tell them how much they mean to me.
USER: And who are your loved ones?
ASSISTANT: My closest friends and family members.
USER: What are their names?
ASSISTANT: My two best friends are named Emily and Jessica, my mom is Mary, and my dad is David. Answering the question with a bit more information about who they are or what they mean to me would help provide a more personalized response.
```
| [
"SUMMARIZATION"
] | Non_BioNLP |
sarrabenrejeb/marian-finetuned-kde4-en-to-fr | sarrabenrejeb | translation | [
"transformers",
"tensorboard",
"safetensors",
"marian",
"text2text-generation",
"translation",
"generated_from_trainer",
"dataset:kde4",
"base_model:Helsinki-NLP/opus-mt-en-fr",
"base_model:finetune:Helsinki-NLP/opus-mt-en-fr",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 1,713,825,997,000 | 2024-04-23T00:31:45 | 8 | 0 | ---
base_model: Helsinki-NLP/opus-mt-en-fr
datasets:
- kde4
license: apache-2.0
metrics:
- bleu
tags:
- translation
- generated_from_trainer
model-index:
- name: marian-finetuned-kde4-en-to-fr
results:
- task:
type: text2text-generation
name: Sequence-to-sequence Language Modeling
dataset:
name: kde4
type: kde4
config: en-fr
split: train
args: en-fr
metrics:
- type: bleu
value: 52.91210143343284
name: Bleu
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# marian-finetuned-kde4-en-to-fr
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-fr](https://huggingface.co/Helsinki-NLP/opus-mt-en-fr) on the kde4 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8554
- Bleu: 52.9121
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
| [
"TRANSLATION"
] | Non_BioNLP |
pszemraj/long-t5-tglobal-base-sci-simplify-elife | pszemraj | summarization | [
"transformers",
"pytorch",
"onnx",
"safetensors",
"longt5",
"text2text-generation",
"lay summaries",
"paper summaries",
"biology",
"medical",
"summarization",
"en",
"dataset:pszemraj/scientific_lay_summarisation-elife-norm",
"base_model:google/long-t5-tglobal-base",
"base_model:quantized:google/long-t5-tglobal-base",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 1,680,996,956,000 | 2023-11-28T19:20:35 | 932 | 5 | ---
base_model: google/long-t5-tglobal-base
datasets:
- pszemraj/scientific_lay_summarisation-elife-norm
language:
- en
library_name: transformers
license: apache-2.0
pipeline_tag: summarization
tags:
- lay summaries
- paper summaries
- biology
- medical
widget:
- text: large earthquakes along a given fault segment do not occur at random intervals
because it takes time to accumulate the strain energy for the rupture. The rates
at which tectonic plates move and accumulate strain at their boundaries are approximately
uniform. Therefore, in first approximation, one may expect that large ruptures
of the same fault segment will occur at approximately constant time intervals.
If subsequent main shocks have different amounts of slip across the fault, then
the recurrence time may vary, and the basic idea of periodic mainshocks must be
modified. For great plate boundary ruptures the length and slip often vary by
a factor of 2. Along the southern segment of the San Andreas fault the recurrence
interval is 145 years with variations of several decades. The smaller the standard
deviation of the average recurrence interval, the more specific could be the long
term prediction of a future mainshock.
example_title: earthquakes
- text: ' A typical feed-forward neural field algorithm. Spatiotemporal coordinates
are fed into a neural network that predicts values in the reconstructed domain.
Then, this domain is mapped to the sensor domain where sensor measurements are
available as supervision. Class and Section Problems Addressed Generalization
(Section 2) Inverse problems, ill-posed problems, editability; symmetries. Hybrid
Representations (Section 3) Computation & memory efficiency, representation capacity,
editability: Forward Maps (Section 4) Inverse problems Network Architecture (Section
5) Spectral bias, integration & derivatives. Manipulating Neural Fields (Section
6) Edit ability, constraints, regularization. Table 2: The five classes of techniques
in the neural field toolbox each addresses problems that arise in learning, inference,
and control. (Section 3). We can supervise reconstruction via differentiable forward
maps that transform Or project our domain (e.g, 3D reconstruction via 2D images;
Section 4) With appropriate network architecture choices, we can overcome neural
network spectral biases (blurriness) and efficiently compute derivatives and integrals
(Section 5). Finally, we can manipulate neural fields to add constraints and regularizations,
and to achieve editable representations (Section 6). Collectively, these classes
constitute a ''toolbox'' of techniques to help solve problems with neural fields
There are three components in a conditional neural field: (1) An encoder or inference
function € that outputs the conditioning latent variable 2 given an observation
0 E(0) =2. 2 is typically a low-dimensional vector, and is often referred to aS
a latent code Or feature code_ (2) A mapping function 4 between Z and neural field
parameters O: Y(z) = O; (3) The neural field itself $. The encoder € finds the
most probable z given the observations O: argmaxz P(2/0). The decoder maximizes
the inverse conditional probability to find the most probable 0 given Z: arg-
max P(Olz). We discuss different encoding schemes with different optimality guarantees
(Section 2.1.1), both global and local conditioning (Section 2.1.2), and different
mapping functions Y (Section 2.1.3) 2. Generalization Suppose we wish to estimate
a plausible 3D surface shape given a partial or noisy point cloud. We need a suitable
prior over the sur- face in its reconstruction domain to generalize to the partial
observations. A neural network expresses a prior via the function space of its
architecture and parameters 0, and generalization is influenced by the inductive
bias of this function space (Section 5).'
example_title: scientific paper
- text: 'Is a else or outside the cob and tree written being of early client rope
and you have is for good reasons. On to the ocean in Orange for time. By''s the
aggregate we can bed it yet. Why this please pick up on a sort is do and also
M Getoi''s nerocos and do rain become you to let so is his brother is made in
use and Mjulia''s''s the lay major is aging Masastup coin present sea only of
Oosii rooms set to you We do er do we easy this private oliiishs lonthen might
be okay. Good afternoon everybody. Welcome to this lecture of Computational Statistics.
As you can see, I''m not socially my name is Michael Zelinger. I''m one of the
task for this class and you might have already seen me in the first lecture where
I made a quick appearance. I''m also going to give the tortillas in the last third
of this course. So to give you a little bit about me, I''m a old student here
with better Bulman and my research centres on casual inference applied to biomedical
disasters, so that could be genomics or that could be hospital data. If any of
you is interested in writing a bachelor thesis, a semester paper may be mastathesis
about this topic feel for reach out to me. you have my name on models and my email
address you can find in the directory I''d Be very happy to talk about it. you
do not need to be sure about it, we can just have a chat. So with that said, let''s
get on with the lecture. There''s an exciting topic today I''m going to start
by sharing some slides with you and later on during the lecture we''ll move to
the paper. So bear with me for a few seconds. Well, the projector is starting
up. Okay, so let''s get started. Today''s topic is a very important one. It''s
about a technique which really forms one of the fundamentals of data science,
machine learning, and any sort of modern statistics. It''s called cross validation.
I know you really want to understand this topic I Want you to understand this
and frankly, nobody''s gonna leave Professor Mineshousen''s class without understanding
cross validation. So to set the stage for this, I Want to introduce you to the
validation problem in computational statistics. So the problem is the following:
You trained a model on available data. You fitted your model, but you know the
training data you got could always have been different and some data from the
environment. Maybe it''s a random process. You do not really know what it is,
but you know that somebody else who gets a different batch of data from the same
environment they would get slightly different training data and you do not care
that your method performs as well. On this training data. you want to to perform
well on other data that you have not seen other data from the same environment.
So in other words, the validation problem is you want to quantify the performance
of your model on data that you have not seen. So how is this even possible? How
could you possibly measure the performance on data that you do not know The solution
to? This is the following realization is that given that you have a bunch of data,
you were in charge. You get to control how much that your model sees. It works
in the following way: You can hide data firms model. Let''s say you have a training
data set which is a bunch of doubtless so X eyes are the features those are typically
hide and national vector. It''s got more than one dimension for sure. And the
why why eyes. Those are the labels for supervised learning. As you''ve seen before,
it''s the same set up as we have in regression. And so you have this training
data and now you choose that you only use some of those data to fit your model.
You''re not going to use everything, you only use some of it the other part you
hide from your model. And then you can use this hidden data to do validation from
the point of you of your model. This hidden data is complete by unseen. In other
words, we solve our problem of validation.'
example_title: transcribed audio - lecture
- text: 'Transformer-based models have shown to be very useful for many NLP tasks.
However, a major limitation of transformers-based models is its O(n^2)O(n 2) time
& memory complexity (where nn is sequence length). Hence, it''s computationally
very expensive to apply transformer-based models on long sequences n > 512n>512.
Several recent papers, e.g. Longformer, Performer, Reformer, Clustered attention
try to remedy this problem by approximating the full attention matrix. You can
checkout 🤗''s recent blog post in case you are unfamiliar with these models.
BigBird (introduced in paper) is one of such recent models to address this issue.
BigBird relies on block sparse attention instead of normal attention (i.e. BERT''s
attention) and can handle sequences up to a length of 4096 at a much lower computational
cost compared to BERT. It has achieved SOTA on various tasks involving very long
sequences such as long documents summarization, question-answering with long contexts.
BigBird RoBERTa-like model is now available in 🤗Transformers. The goal of this
post is to give the reader an in-depth understanding of big bird implementation
& ease one''s life in using BigBird with 🤗Transformers. But, before going into
more depth, it is important to remember that the BigBird''s attention is an approximation
of BERT''s full attention and therefore does not strive to be better than BERT''s
full attention, but rather to be more efficient. It simply allows to apply transformer-based
models to much longer sequences since BERT''s quadratic memory requirement quickly
becomes unbearable. Simply put, if we would have ∞ compute & ∞ time, BERT''s attention
would be preferred over block sparse attention (which we are going to discuss
in this post).
If you wonder why we need more compute when working with longer sequences, this
blog post is just right for you!
Some of the main questions one might have when working with standard BERT-like
attention include:
Do all tokens really have to attend to all other tokens? Why not compute attention
only over important tokens? How to decide what tokens are important? How to attend
to just a few tokens in a very efficient way? In this blog post, we will try to
answer those questions.
What tokens should be attended to? We will give a practical example of how attention
works by considering the sentence ''BigBird is now available in HuggingFace for
extractive question answering''. In BERT-like attention, every word would simply
attend to all other tokens.
Let''s think about a sensible choice of key tokens that a queried token actually
only should attend to by writing some pseudo-code. Will will assume that the token
available is queried and build a sensible list of key tokens to attend to.
>>> # let''s consider following sentence as an example >>> example = [''BigBird'',
''is'', ''now'', ''available'', ''in'', ''HuggingFace'', ''for'', ''extractive'',
''question'', ''answering'']
>>> # further let''s assume, we''re trying to understand the representation of
''available'' i.e. >>> query_token = ''available'' >>> # We will initialize an
empty `set` and fill up the tokens of our interest as we proceed in this section.
>>> key_tokens = [] # => currently ''available'' token doesn''t have anything
to attend Nearby tokens should be important because, in a sentence (sequence of
words), the current word is highly dependent on neighboring past & future tokens.
This intuition is the idea behind the concept of sliding attention.'
example_title: bigbird blog intro
- text: 'To be fair, you have to have a very high IQ to understand Rick and Morty.
The humour is extremely subtle, and without a solid grasp of theoretical physics
most of the jokes will go over a typical viewer''s head. There''s also Rick''s
nihilistic outlook, which is deftly woven into his characterisation- his personal
philosophy draws heavily from Narodnaya Volya literature, for instance. The fans
understand this stuff; they have the intellectual capacity to truly appreciate
the depths of these jokes, to realise that they''re not just funny- they say something
deep about LIFE. As a consequence people who dislike Rick & Morty truly ARE idiots-
of course they wouldn''t appreciate, for instance, the humour in Rick''s existential
catchphrase ''Wubba Lubba Dub Dub,'' which itself is a cryptic reference to Turgenev''s
Russian epic Fathers and Sons. I''m smirking right now just imagining one of those
addlepated simpletons scratching their heads in confusion as Dan Harmon''s genius
wit unfolds itself on their television screens. What fools.. how I pity them.
😂
And yes, by the way, i DO have a Rick & Morty tattoo. And no, you cannot see it.
It''s for the ladies'' eyes only- and even then they have to demonstrate that
they''re within 5 IQ points of my own (preferably lower) beforehand. Nothin personnel
kid 😎'
example_title: Richard & Mortimer
- text: The tower is 324 metres (1,063 ft) tall, about the same height as an 81-storey
building, and the tallest structure in Paris. Its base is square, measuring 125
metres (410 ft) on each side. During its construction, the Eiffel Tower surpassed
the Washington Monument to become the tallest man-made structure in the world,
a title it held for 41 years until the Chrysler Building in New York City was
finished in 1930. It was the first structure to reach a height of 300 metres.
Due to the addition of a broadcasting aerial at the top of the tower in 1957,
it is now taller than the Chrysler Building by 5.2 metres (17 ft). Excluding transmitters,
the Eiffel Tower is the second tallest free-standing structure in France after
the Millau Viaduct.
example_title: eiffel
parameters:
max_length: 64
min_length: 8
no_repeat_ngram_size: 3
early_stopping: true
repetition_penalty: 3.5
encoder_no_repeat_ngram_size: 4
length_penalty: 0.4
num_beams: 4
---
# long-t5-tglobal-base-sci-simplify: elife subset
<a href="https://colab.research.google.com/gist/pszemraj/37a406059887a400afc1428d70374327/long-t5-tglobal-base-sci-simplify-elife-example-with-textsum.ipynb">
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
</a>
Exploring how well long-document models trained on "lay summaries" of scientific papers generalize.
> A lay summary is a summary of a research paper or scientific study that is written in plain language, without the use of technical jargon, and is designed to be easily understood by non-experts.
## Model description
This model is a fine-tuned version of [google/long-t5-tglobal-base](https://huggingface.co/google/long-t5-tglobal-base) on the `pszemraj/scientific_lay_summarisation-elife-norm` dataset.
- The variant trained on the PLOS subset can be found [here](https://huggingface.co/pszemraj/long-t5-tglobal-base-sci-simplify)
## Usage
It's recommended to use this model with [beam search decoding](https://huggingface.co/docs/transformers/generation_strategies#beamsearch-decoding). If interested, you can also use the `textsum` util repo to have most of this abstracted out for you:
```bash
pip install -U textsum
```
```python
from textsum.summarize import Summarizer
model_name = "pszemraj/long-t5-tglobal-base-sci-simplify-elife"
summarizer = Summarizer(model_name) # GPU auto-detected
text = "put the text you don't want to read here"
summary = summarizer.summarize_string(text)
print(summary)
```
## Intended uses & limitations
- Ability to generalize outside of the dataset domain (pubmed/bioscience type papers) has to be evaluated.
## Training and evaluation data
The `elife` subset of the lay summaries dataset. Refer to `pszemraj/scientific_lay_summarisation-elife-norm`
## Training procedure
### Eval results
It achieves the following results on the evaluation set:
- Loss: 1.9990
- Rouge1: 38.5587
- Rouge2: 9.7336
- Rougel: 21.1974
- Rougelsum: 35.9333
- Gen Len: 392.7095
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0004
- train_batch_size: 4
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.01
- num_epochs: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:--------:|
| 2.2995 | 1.47 | 100 | 2.0175 | 35.2501 | 8.2121 | 20.4587 | 32.4494 | 439.7552 |
| 2.2171 | 2.94 | 200 | 1.9990 | 38.5587 | 9.7336 | 21.1974 | 35.9333 | 392.7095 |
| [
"QUESTION_ANSWERING",
"SUMMARIZATION"
] | BioNLP |
cstr/Spaetzle-v12-7b | cstr | text-generation | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"flemmingmiguel/NeuDist-Ro-7B",
"Blizado/discolm-mfto-7b-german-v0.1",
"ResplendentAI/Flora_DPO_7B",
"conversational",
"base_model:Blizado/discolm-mfto-7b-german-v0.1",
"base_model:merge:Blizado/discolm-mfto-7b-german-v0.1",
"base_model:ResplendentAI/Flora_DPO_7B",
"base_model:merge:ResplendentAI/Flora_DPO_7B",
"base_model:flemmingmiguel/NeuDist-Ro-7B",
"base_model:merge:flemmingmiguel/NeuDist-Ro-7B",
"license:cc-by-sa-4.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 1,710,138,705,000 | 2024-04-13T16:06:36 | 33 | 2 | ---
base_model:
- flemmingmiguel/NeuDist-Ro-7B
- Blizado/discolm-mfto-7b-german-v0.1
- ResplendentAI/Flora_DPO_7B
license: cc-by-sa-4.0
tags:
- merge
- mergekit
- lazymergekit
- flemmingmiguel/NeuDist-Ro-7B
- Blizado/discolm-mfto-7b-german-v0.1
- ResplendentAI/Flora_DPO_7B
---
# Spaetzle-v12-7b
Spaetzle-v12-7b is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [flemmingmiguel/NeuDist-Ro-7B](https://huggingface.co/flemmingmiguel/NeuDist-Ro-7B)
* [Blizado/discolm-mfto-7b-german-v0.1](https://huggingface.co/Blizado/discolm-mfto-7b-german-v0.1)
* [ResplendentAI/Flora_DPO_7B](https://huggingface.co/ResplendentAI/Flora_DPO_7B)
* on the basis of [mayflowergmbh/Wiedervereinigung-7b-dpo-laser](https://huggingface.co/mayflowergmbh/Wiedervereinigung-7b-dpo-laser)
As expected, this is a little bit worse in general English tasks over [cstr/spaetzle-v8-7b](https://huggingface.co/cstr/spaetzle-v8-7b), but a tiny little bit better on German tasks, at least some: e.g. it reaches an EQ-Bench (de)
score of 64.81, but only
| Metric |Value|
|---------------------------------|----:|
|Avg. |69.36|
|AI2 Reasoning Challenge (25-Shot)|65.96|
|HellaSwag (10-Shot) |86.16|
|MMLU (5-Shot) |63.48|
|TruthfulQA (0-shot) |57.84|
|Winogrande (5-shot) |80.03|
|GSM8k (5-shot) |62.70|
| Model |AGIEval|GPT4All|TruthfulQA|Bigbench|Average|
|--------------------------------------------------------------|------:|------:|---------:|-------:|------:|
|[Spaetzle-v12-7b](https://huggingface.co/cstr/Spaetzle-v12-7b)| 42.64| 74.3| 58.44| 44.44| 54.95|
### AGIEval
| Task |Version| Metric |Value| |Stderr|
|------------------------------|------:|--------|----:|---|-----:|
|agieval_aqua_rat | 0|acc |24.02|± | 2.69|
| | |acc_norm|21.65|± | 2.59|
|agieval_logiqa_en | 0|acc |36.10|± | 1.88|
| | |acc_norm|37.63|± | 1.90|
|agieval_lsat_ar | 0|acc |24.35|± | 2.84|
| | |acc_norm|23.04|± | 2.78|
|agieval_lsat_lr | 0|acc |48.82|± | 2.22|
| | |acc_norm|47.25|± | 2.21|
|agieval_lsat_rc | 0|acc |60.59|± | 2.98|
| | |acc_norm|57.99|± | 3.01|
|agieval_sat_en | 0|acc |76.21|± | 2.97|
| | |acc_norm|74.76|± | 3.03|
|agieval_sat_en_without_passage| 0|acc |46.60|± | 3.48|
| | |acc_norm|45.63|± | 3.48|
|agieval_sat_math | 0|acc |37.27|± | 3.27|
| | |acc_norm|33.18|± | 3.18|
Average: 42.64%
### GPT4All
| Task |Version| Metric |Value| |Stderr|
|-------------|------:|--------|----:|---|-----:|
|arc_challenge| 0|acc |59.13|± | 1.44|
| | |acc_norm|61.26|± | 1.42|
|arc_easy | 0|acc |83.67|± | 0.76|
| | |acc_norm|80.89|± | 0.81|
|boolq | 1|acc |87.83|± | 0.57|
|hellaswag | 0|acc |66.45|± | 0.47|
| | |acc_norm|84.63|± | 0.36|
|openbookqa | 0|acc |37.40|± | 2.17|
| | |acc_norm|45.80|± | 2.23|
|piqa | 0|acc |82.15|± | 0.89|
| | |acc_norm|83.13|± | 0.87|
|winogrande | 0|acc |76.56|± | 1.19|
Average: 74.3%
### TruthfulQA
| Task |Version|Metric|Value| |Stderr|
|-------------|------:|------|----:|---|-----:|
|truthfulqa_mc| 1|mc1 |42.59|± | 1.73|
| | |mc2 |58.44|± | 1.58|
Average: 58.44%
### Bigbench
| Task |Version| Metric |Value| |Stderr|
|------------------------------------------------|------:|---------------------|----:|---|-----:|
|bigbench_causal_judgement | 0|multiple_choice_grade|55.26|± | 3.62|
|bigbench_date_understanding | 0|multiple_choice_grade|64.77|± | 2.49|
|bigbench_disambiguation_qa | 0|multiple_choice_grade|37.60|± | 3.02|
|bigbench_geometric_shapes | 0|multiple_choice_grade|32.31|± | 2.47|
| | |exact_str_match |21.45|± | 2.17|
|bigbench_logical_deduction_five_objects | 0|multiple_choice_grade|31.00|± | 2.07|
|bigbench_logical_deduction_seven_objects | 0|multiple_choice_grade|22.43|± | 1.58|
|bigbench_logical_deduction_three_objects | 0|multiple_choice_grade|53.00|± | 2.89|
|bigbench_movie_recommendation | 0|multiple_choice_grade|40.40|± | 2.20|
|bigbench_navigate | 0|multiple_choice_grade|51.30|± | 1.58|
|bigbench_reasoning_about_colored_objects | 0|multiple_choice_grade|68.50|± | 1.04|
|bigbench_ruin_names | 0|multiple_choice_grade|48.66|± | 2.36|
|bigbench_salient_translation_error_detection | 0|multiple_choice_grade|30.36|± | 1.46|
|bigbench_snarks | 0|multiple_choice_grade|70.17|± | 3.41|
|bigbench_sports_understanding | 0|multiple_choice_grade|70.39|± | 1.45|
|bigbench_temporal_sequences | 0|multiple_choice_grade|31.00|± | 1.46|
|bigbench_tracking_shuffled_objects_five_objects | 0|multiple_choice_grade|21.44|± | 1.16|
|bigbench_tracking_shuffled_objects_seven_objects| 0|multiple_choice_grade|18.29|± | 0.92|
|bigbench_tracking_shuffled_objects_three_objects| 0|multiple_choice_grade|53.00|± | 2.89|
Average: 44.44%
Average score: 54.95%
Elapsed time: 02:50:51
## 🧩 Configuration
```yaml
models:
- model: mayflowergmbh/Wiedervereinigung-7b-dpo-laser
# no parameters necessary for base model
- model: flemmingmiguel/NeuDist-Ro-7B
parameters:
density: 0.60
weight: 0.30
- model: Blizado/discolm-mfto-7b-german-v0.1
parameters:
density: 0.65
weight: 0.40
- model: ResplendentAI/Flora_DPO_7B
parameters:
density: 0.6
weight: 0.3
merge_method: dare_ties
base_model: mayflowergmbh/Wiedervereinigung-7b-dpo-laser
parameters:
int8_mask: true
dtype: bfloat16
random_seed: 0
tokenizer_source: base
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "cstr/Spaetzle-v12-7b"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
``` | [
"TRANSLATION"
] | Non_BioNLP |
RichardErkhov/DecisionOptimizationSystemProduction_-_DeepFeatTextEmbeddingLarge-4bits | RichardErkhov | null | [
"safetensors",
"qwen2",
"custom_code",
"arxiv:2308.03281",
"4-bit",
"bitsandbytes",
"region:us"
] | 1,741,462,730,000 | 2025-03-08T19:39:56 | 2 | 0 | ---
{}
---
Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
DeepFeatTextEmbeddingLarge - bnb 4bits
- Model creator: https://huggingface.co/DecisionOptimizationSystemProduction/
- Original model: https://huggingface.co/DecisionOptimizationSystemProduction/DeepFeatTextEmbeddingLarge/
Original model description:
---
tags:
- mteb
- sentence-transformers
- transformers
- Qwen2
- sentence-similarity
license: apache-2.0
model-index:
- name: gte-qwen2-7B-instruct
results:
- dataset:
config: en
name: MTEB AmazonCounterfactualClassification (en)
revision: e8379541af4e31359cca9fbcf4b00f2671dba205
split: test
type: mteb/amazon_counterfactual
metrics:
- type: accuracy
value: 83.98507462686567
- type: ap
value: 50.93015252587014
- type: f1
value: 78.50416599051215
task:
type: Classification
- dataset:
config: default
name: MTEB AmazonPolarityClassification
revision: e2d317d38cd51312af73b3d32a06d1a08b442046
split: test
type: mteb/amazon_polarity
metrics:
- type: accuracy
value: 96.61065
- type: ap
value: 94.89174052954196
- type: f1
value: 96.60942596940565
task:
type: Classification
- dataset:
config: en
name: MTEB AmazonReviewsClassification (en)
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
split: test
type: mteb/amazon_reviews_multi
metrics:
- type: accuracy
value: 55.614000000000004
- type: f1
value: 54.90553480294904
task:
type: Classification
- dataset:
config: default
name: MTEB ArguAna
revision: c22ab2a51041ffd869aaddef7af8d8215647e41a
split: test
type: mteb/arguana
metrics:
- type: map_at_1
value: 45.164
- type: map_at_10
value: 61.519
- type: map_at_100
value: 61.769
- type: map_at_1000
value: 61.769
- type: map_at_3
value: 57.443999999999996
- type: map_at_5
value: 60.058
- type: mrr_at_1
value: 46.088
- type: mrr_at_10
value: 61.861
- type: mrr_at_100
value: 62.117999999999995
- type: mrr_at_1000
value: 62.117999999999995
- type: mrr_at_3
value: 57.729
- type: mrr_at_5
value: 60.392
- type: ndcg_at_1
value: 45.164
- type: ndcg_at_10
value: 69.72
- type: ndcg_at_100
value: 70.719
- type: ndcg_at_1000
value: 70.719
- type: ndcg_at_3
value: 61.517999999999994
- type: ndcg_at_5
value: 66.247
- type: precision_at_1
value: 45.164
- type: precision_at_10
value: 9.545
- type: precision_at_100
value: 0.996
- type: precision_at_1000
value: 0.1
- type: precision_at_3
value: 24.443
- type: precision_at_5
value: 16.97
- type: recall_at_1
value: 45.164
- type: recall_at_10
value: 95.448
- type: recall_at_100
value: 99.644
- type: recall_at_1000
value: 99.644
- type: recall_at_3
value: 73.329
- type: recall_at_5
value: 84.851
task:
type: Retrieval
- dataset:
config: default
name: MTEB ArxivClusteringP2P
revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d
split: test
type: mteb/arxiv-clustering-p2p
metrics:
- type: v_measure
value: 50.511868162026175
task:
type: Clustering
- dataset:
config: default
name: MTEB ArxivClusteringS2S
revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53
split: test
type: mteb/arxiv-clustering-s2s
metrics:
- type: v_measure
value: 45.007803189284004
task:
type: Clustering
- dataset:
config: default
name: MTEB AskUbuntuDupQuestions
revision: 2000358ca161889fa9c082cb41daa8dcfb161a54
split: test
type: mteb/askubuntudupquestions-reranking
metrics:
- type: map
value: 64.55292107723382
- type: mrr
value: 77.66158818097877
task:
type: Reranking
- dataset:
config: default
name: MTEB BIOSSES
revision: d3fb88f8f02e40887cd149695127462bbcf29b4a
split: test
type: mteb/biosses-sts
metrics:
- type: cos_sim_pearson
value: 85.65459047085452
- type: cos_sim_spearman
value: 82.10729255710761
- type: euclidean_pearson
value: 82.78079159312476
- type: euclidean_spearman
value: 80.50002701880933
- type: manhattan_pearson
value: 82.41372641383016
- type: manhattan_spearman
value: 80.57412509272639
task:
type: STS
- dataset:
config: default
name: MTEB Banking77Classification
revision: 0fd18e25b25c072e09e0d92ab615fda904d66300
split: test
type: mteb/banking77
metrics:
- type: accuracy
value: 87.30844155844156
- type: f1
value: 87.25307322443255
task:
type: Classification
- dataset:
config: default
name: MTEB BiorxivClusteringP2P
revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40
split: test
type: mteb/biorxiv-clustering-p2p
metrics:
- type: v_measure
value: 43.20754608934859
task:
type: Clustering
- dataset:
config: default
name: MTEB BiorxivClusteringS2S
revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908
split: test
type: mteb/biorxiv-clustering-s2s
metrics:
- type: v_measure
value: 38.818037697335505
task:
type: Clustering
- dataset:
config: default
name: MTEB CQADupstackAndroidRetrieval
revision: f46a197baaae43b4f621051089b82a364682dfeb
split: test
type: BeIR/cqadupstack
metrics:
- type: map_at_1
value: 35.423
- type: map_at_10
value: 47.198
- type: map_at_100
value: 48.899
- type: map_at_1000
value: 49.004
- type: map_at_3
value: 43.114999999999995
- type: map_at_5
value: 45.491
- type: mrr_at_1
value: 42.918
- type: mrr_at_10
value: 53.299
- type: mrr_at_100
value: 54.032000000000004
- type: mrr_at_1000
value: 54.055
- type: mrr_at_3
value: 50.453
- type: mrr_at_5
value: 52.205999999999996
- type: ndcg_at_1
value: 42.918
- type: ndcg_at_10
value: 53.98
- type: ndcg_at_100
value: 59.57
- type: ndcg_at_1000
value: 60.879000000000005
- type: ndcg_at_3
value: 48.224000000000004
- type: ndcg_at_5
value: 50.998
- type: precision_at_1
value: 42.918
- type: precision_at_10
value: 10.299999999999999
- type: precision_at_100
value: 1.687
- type: precision_at_1000
value: 0.211
- type: precision_at_3
value: 22.842000000000002
- type: precision_at_5
value: 16.681
- type: recall_at_1
value: 35.423
- type: recall_at_10
value: 66.824
- type: recall_at_100
value: 89.564
- type: recall_at_1000
value: 97.501
- type: recall_at_3
value: 50.365
- type: recall_at_5
value: 57.921
task:
type: Retrieval
- dataset:
config: default
name: MTEB CQADupstackEnglishRetrieval
revision: ad9991cb51e31e31e430383c75ffb2885547b5f0
split: test
type: BeIR/cqadupstack
metrics:
- type: map_at_1
value: 33.205
- type: map_at_10
value: 44.859
- type: map_at_100
value: 46.135
- type: map_at_1000
value: 46.259
- type: map_at_3
value: 41.839
- type: map_at_5
value: 43.662
- type: mrr_at_1
value: 41.146
- type: mrr_at_10
value: 50.621
- type: mrr_at_100
value: 51.207
- type: mrr_at_1000
value: 51.246
- type: mrr_at_3
value: 48.535000000000004
- type: mrr_at_5
value: 49.818
- type: ndcg_at_1
value: 41.146
- type: ndcg_at_10
value: 50.683
- type: ndcg_at_100
value: 54.82
- type: ndcg_at_1000
value: 56.69
- type: ndcg_at_3
value: 46.611000000000004
- type: ndcg_at_5
value: 48.66
- type: precision_at_1
value: 41.146
- type: precision_at_10
value: 9.439
- type: precision_at_100
value: 1.465
- type: precision_at_1000
value: 0.194
- type: precision_at_3
value: 22.59
- type: precision_at_5
value: 15.86
- type: recall_at_1
value: 33.205
- type: recall_at_10
value: 61.028999999999996
- type: recall_at_100
value: 78.152
- type: recall_at_1000
value: 89.59700000000001
- type: recall_at_3
value: 49.05
- type: recall_at_5
value: 54.836
task:
type: Retrieval
- dataset:
config: default
name: MTEB CQADupstackGamingRetrieval
revision: 4885aa143210c98657558c04aaf3dc47cfb54340
split: test
type: BeIR/cqadupstack
metrics:
- type: map_at_1
value: 41.637
- type: map_at_10
value: 55.162
- type: map_at_100
value: 56.142
- type: map_at_1000
value: 56.188
- type: map_at_3
value: 51.564
- type: map_at_5
value: 53.696
- type: mrr_at_1
value: 47.524
- type: mrr_at_10
value: 58.243
- type: mrr_at_100
value: 58.879999999999995
- type: mrr_at_1000
value: 58.9
- type: mrr_at_3
value: 55.69499999999999
- type: mrr_at_5
value: 57.284
- type: ndcg_at_1
value: 47.524
- type: ndcg_at_10
value: 61.305
- type: ndcg_at_100
value: 65.077
- type: ndcg_at_1000
value: 65.941
- type: ndcg_at_3
value: 55.422000000000004
- type: ndcg_at_5
value: 58.516
- type: precision_at_1
value: 47.524
- type: precision_at_10
value: 9.918000000000001
- type: precision_at_100
value: 1.276
- type: precision_at_1000
value: 0.13899999999999998
- type: precision_at_3
value: 24.765
- type: precision_at_5
value: 17.204
- type: recall_at_1
value: 41.637
- type: recall_at_10
value: 76.185
- type: recall_at_100
value: 92.149
- type: recall_at_1000
value: 98.199
- type: recall_at_3
value: 60.856
- type: recall_at_5
value: 68.25099999999999
task:
type: Retrieval
- dataset:
config: default
name: MTEB CQADupstackGisRetrieval
revision: 5003b3064772da1887988e05400cf3806fe491f2
split: test
type: BeIR/cqadupstack
metrics:
- type: map_at_1
value: 26.27
- type: map_at_10
value: 37.463
- type: map_at_100
value: 38.434000000000005
- type: map_at_1000
value: 38.509
- type: map_at_3
value: 34.226
- type: map_at_5
value: 36.161
- type: mrr_at_1
value: 28.588
- type: mrr_at_10
value: 39.383
- type: mrr_at_100
value: 40.23
- type: mrr_at_1000
value: 40.281
- type: mrr_at_3
value: 36.422
- type: mrr_at_5
value: 38.252
- type: ndcg_at_1
value: 28.588
- type: ndcg_at_10
value: 43.511
- type: ndcg_at_100
value: 48.274
- type: ndcg_at_1000
value: 49.975
- type: ndcg_at_3
value: 37.319
- type: ndcg_at_5
value: 40.568
- type: precision_at_1
value: 28.588
- type: precision_at_10
value: 6.893000000000001
- type: precision_at_100
value: 0.9900000000000001
- type: precision_at_1000
value: 0.117
- type: precision_at_3
value: 16.347
- type: precision_at_5
value: 11.661000000000001
- type: recall_at_1
value: 26.27
- type: recall_at_10
value: 60.284000000000006
- type: recall_at_100
value: 81.902
- type: recall_at_1000
value: 94.43
- type: recall_at_3
value: 43.537
- type: recall_at_5
value: 51.475
task:
type: Retrieval
- dataset:
config: default
name: MTEB CQADupstackMathematicaRetrieval
revision: 90fceea13679c63fe563ded68f3b6f06e50061de
split: test
type: BeIR/cqadupstack
metrics:
- type: map_at_1
value: 18.168
- type: map_at_10
value: 28.410000000000004
- type: map_at_100
value: 29.78
- type: map_at_1000
value: 29.892999999999997
- type: map_at_3
value: 25.238
- type: map_at_5
value: 26.96
- type: mrr_at_1
value: 23.507
- type: mrr_at_10
value: 33.382
- type: mrr_at_100
value: 34.404
- type: mrr_at_1000
value: 34.467999999999996
- type: mrr_at_3
value: 30.637999999999998
- type: mrr_at_5
value: 32.199
- type: ndcg_at_1
value: 23.507
- type: ndcg_at_10
value: 34.571000000000005
- type: ndcg_at_100
value: 40.663
- type: ndcg_at_1000
value: 43.236000000000004
- type: ndcg_at_3
value: 29.053
- type: ndcg_at_5
value: 31.563999999999997
- type: precision_at_1
value: 23.507
- type: precision_at_10
value: 6.654
- type: precision_at_100
value: 1.113
- type: precision_at_1000
value: 0.146
- type: precision_at_3
value: 14.427999999999999
- type: precision_at_5
value: 10.498000000000001
- type: recall_at_1
value: 18.168
- type: recall_at_10
value: 48.443000000000005
- type: recall_at_100
value: 74.47
- type: recall_at_1000
value: 92.494
- type: recall_at_3
value: 33.379999999999995
- type: recall_at_5
value: 39.76
task:
type: Retrieval
- dataset:
config: default
name: MTEB CQADupstackPhysicsRetrieval
revision: 79531abbd1fb92d06c6d6315a0cbbbf5bb247ea4
split: test
type: BeIR/cqadupstack
metrics:
- type: map_at_1
value: 32.39
- type: map_at_10
value: 44.479
- type: map_at_100
value: 45.977000000000004
- type: map_at_1000
value: 46.087
- type: map_at_3
value: 40.976
- type: map_at_5
value: 43.038
- type: mrr_at_1
value: 40.135
- type: mrr_at_10
value: 50.160000000000004
- type: mrr_at_100
value: 51.052
- type: mrr_at_1000
value: 51.087
- type: mrr_at_3
value: 47.818
- type: mrr_at_5
value: 49.171
- type: ndcg_at_1
value: 40.135
- type: ndcg_at_10
value: 50.731
- type: ndcg_at_100
value: 56.452000000000005
- type: ndcg_at_1000
value: 58.123000000000005
- type: ndcg_at_3
value: 45.507
- type: ndcg_at_5
value: 48.11
- type: precision_at_1
value: 40.135
- type: precision_at_10
value: 9.192
- type: precision_at_100
value: 1.397
- type: precision_at_1000
value: 0.169
- type: precision_at_3
value: 21.816
- type: precision_at_5
value: 15.476
- type: recall_at_1
value: 32.39
- type: recall_at_10
value: 63.597
- type: recall_at_100
value: 86.737
- type: recall_at_1000
value: 97.039
- type: recall_at_3
value: 48.906
- type: recall_at_5
value: 55.659000000000006
task:
type: Retrieval
- dataset:
config: default
name: MTEB CQADupstackProgrammersRetrieval
revision: 6184bc1440d2dbc7612be22b50686b8826d22b32
split: test
type: BeIR/cqadupstack
metrics:
- type: map_at_1
value: 28.397
- type: map_at_10
value: 39.871
- type: map_at_100
value: 41.309000000000005
- type: map_at_1000
value: 41.409
- type: map_at_3
value: 36.047000000000004
- type: map_at_5
value: 38.104
- type: mrr_at_1
value: 34.703
- type: mrr_at_10
value: 44.773
- type: mrr_at_100
value: 45.64
- type: mrr_at_1000
value: 45.678999999999995
- type: mrr_at_3
value: 41.705
- type: mrr_at_5
value: 43.406
- type: ndcg_at_1
value: 34.703
- type: ndcg_at_10
value: 46.271
- type: ndcg_at_100
value: 52.037
- type: ndcg_at_1000
value: 53.81700000000001
- type: ndcg_at_3
value: 39.966
- type: ndcg_at_5
value: 42.801
- type: precision_at_1
value: 34.703
- type: precision_at_10
value: 8.744
- type: precision_at_100
value: 1.348
- type: precision_at_1000
value: 0.167
- type: precision_at_3
value: 19.102
- type: precision_at_5
value: 13.836
- type: recall_at_1
value: 28.397
- type: recall_at_10
value: 60.299
- type: recall_at_100
value: 84.595
- type: recall_at_1000
value: 96.155
- type: recall_at_3
value: 43.065
- type: recall_at_5
value: 50.371
task:
type: Retrieval
- dataset:
config: default
name: MTEB CQADupstackRetrieval
revision: 4ffe81d471b1924886b33c7567bfb200e9eec5c4
split: test
type: BeIR/cqadupstack
metrics:
- type: map_at_1
value: 28.044333333333338
- type: map_at_10
value: 38.78691666666666
- type: map_at_100
value: 40.113
- type: map_at_1000
value: 40.22125
- type: map_at_3
value: 35.52966666666667
- type: map_at_5
value: 37.372749999999996
- type: mrr_at_1
value: 33.159083333333335
- type: mrr_at_10
value: 42.913583333333335
- type: mrr_at_100
value: 43.7845
- type: mrr_at_1000
value: 43.830333333333336
- type: mrr_at_3
value: 40.29816666666667
- type: mrr_at_5
value: 41.81366666666667
- type: ndcg_at_1
value: 33.159083333333335
- type: ndcg_at_10
value: 44.75750000000001
- type: ndcg_at_100
value: 50.13658333333334
- type: ndcg_at_1000
value: 52.037
- type: ndcg_at_3
value: 39.34258333333334
- type: ndcg_at_5
value: 41.93708333333333
- type: precision_at_1
value: 33.159083333333335
- type: precision_at_10
value: 7.952416666666667
- type: precision_at_100
value: 1.2571666666666668
- type: precision_at_1000
value: 0.16099999999999998
- type: precision_at_3
value: 18.303833333333337
- type: precision_at_5
value: 13.057083333333333
- type: recall_at_1
value: 28.044333333333338
- type: recall_at_10
value: 58.237249999999996
- type: recall_at_100
value: 81.35391666666666
- type: recall_at_1000
value: 94.21283333333334
- type: recall_at_3
value: 43.32341666666667
- type: recall_at_5
value: 49.94908333333333
task:
type: Retrieval
- dataset:
config: default
name: MTEB CQADupstackStatsRetrieval
revision: 65ac3a16b8e91f9cee4c9828cc7c335575432a2a
split: test
type: BeIR/cqadupstack
metrics:
- type: map_at_1
value: 27.838
- type: map_at_10
value: 36.04
- type: map_at_100
value: 37.113
- type: map_at_1000
value: 37.204
- type: map_at_3
value: 33.585
- type: map_at_5
value: 34.845
- type: mrr_at_1
value: 30.982
- type: mrr_at_10
value: 39.105000000000004
- type: mrr_at_100
value: 39.98
- type: mrr_at_1000
value: 40.042
- type: mrr_at_3
value: 36.912
- type: mrr_at_5
value: 38.062000000000005
- type: ndcg_at_1
value: 30.982
- type: ndcg_at_10
value: 40.982
- type: ndcg_at_100
value: 46.092
- type: ndcg_at_1000
value: 48.25
- type: ndcg_at_3
value: 36.41
- type: ndcg_at_5
value: 38.379999999999995
- type: precision_at_1
value: 30.982
- type: precision_at_10
value: 6.534
- type: precision_at_100
value: 0.9820000000000001
- type: precision_at_1000
value: 0.124
- type: precision_at_3
value: 15.745999999999999
- type: precision_at_5
value: 10.828
- type: recall_at_1
value: 27.838
- type: recall_at_10
value: 52.971000000000004
- type: recall_at_100
value: 76.357
- type: recall_at_1000
value: 91.973
- type: recall_at_3
value: 40.157
- type: recall_at_5
value: 45.147999999999996
task:
type: Retrieval
- dataset:
config: default
name: MTEB CQADupstackTexRetrieval
revision: 46989137a86843e03a6195de44b09deda022eec7
split: test
type: BeIR/cqadupstack
metrics:
- type: map_at_1
value: 19.059
- type: map_at_10
value: 27.454
- type: map_at_100
value: 28.736
- type: map_at_1000
value: 28.865000000000002
- type: map_at_3
value: 24.773999999999997
- type: map_at_5
value: 26.266000000000002
- type: mrr_at_1
value: 23.125
- type: mrr_at_10
value: 31.267
- type: mrr_at_100
value: 32.32
- type: mrr_at_1000
value: 32.394
- type: mrr_at_3
value: 28.894
- type: mrr_at_5
value: 30.281000000000002
- type: ndcg_at_1
value: 23.125
- type: ndcg_at_10
value: 32.588
- type: ndcg_at_100
value: 38.432
- type: ndcg_at_1000
value: 41.214
- type: ndcg_at_3
value: 27.938000000000002
- type: ndcg_at_5
value: 30.127
- type: precision_at_1
value: 23.125
- type: precision_at_10
value: 5.9639999999999995
- type: precision_at_100
value: 1.047
- type: precision_at_1000
value: 0.148
- type: precision_at_3
value: 13.294
- type: precision_at_5
value: 9.628
- type: recall_at_1
value: 19.059
- type: recall_at_10
value: 44.25
- type: recall_at_100
value: 69.948
- type: recall_at_1000
value: 89.35300000000001
- type: recall_at_3
value: 31.114000000000004
- type: recall_at_5
value: 36.846000000000004
task:
type: Retrieval
- dataset:
config: default
name: MTEB CQADupstackUnixRetrieval
revision: 6c6430d3a6d36f8d2a829195bc5dc94d7e063e53
split: test
type: BeIR/cqadupstack
metrics:
- type: map_at_1
value: 28.355999999999998
- type: map_at_10
value: 39.055
- type: map_at_100
value: 40.486
- type: map_at_1000
value: 40.571
- type: map_at_3
value: 35.69
- type: map_at_5
value: 37.605
- type: mrr_at_1
value: 33.302
- type: mrr_at_10
value: 42.986000000000004
- type: mrr_at_100
value: 43.957
- type: mrr_at_1000
value: 43.996
- type: mrr_at_3
value: 40.111999999999995
- type: mrr_at_5
value: 41.735
- type: ndcg_at_1
value: 33.302
- type: ndcg_at_10
value: 44.962999999999994
- type: ndcg_at_100
value: 50.917
- type: ndcg_at_1000
value: 52.622
- type: ndcg_at_3
value: 39.182
- type: ndcg_at_5
value: 41.939
- type: precision_at_1
value: 33.302
- type: precision_at_10
value: 7.779999999999999
- type: precision_at_100
value: 1.203
- type: precision_at_1000
value: 0.145
- type: precision_at_3
value: 18.035
- type: precision_at_5
value: 12.873000000000001
- type: recall_at_1
value: 28.355999999999998
- type: recall_at_10
value: 58.782000000000004
- type: recall_at_100
value: 84.02199999999999
- type: recall_at_1000
value: 95.511
- type: recall_at_3
value: 43.126999999999995
- type: recall_at_5
value: 50.14999999999999
task:
type: Retrieval
- dataset:
config: default
name: MTEB CQADupstackWebmastersRetrieval
revision: 160c094312a0e1facb97e55eeddb698c0abe3571
split: test
type: BeIR/cqadupstack
metrics:
- type: map_at_1
value: 27.391
- type: map_at_10
value: 37.523
- type: map_at_100
value: 39.312000000000005
- type: map_at_1000
value: 39.54
- type: map_at_3
value: 34.231
- type: map_at_5
value: 36.062
- type: mrr_at_1
value: 32.016
- type: mrr_at_10
value: 41.747
- type: mrr_at_100
value: 42.812
- type: mrr_at_1000
value: 42.844
- type: mrr_at_3
value: 39.129999999999995
- type: mrr_at_5
value: 40.524
- type: ndcg_at_1
value: 32.016
- type: ndcg_at_10
value: 43.826
- type: ndcg_at_100
value: 50.373999999999995
- type: ndcg_at_1000
value: 52.318
- type: ndcg_at_3
value: 38.479
- type: ndcg_at_5
value: 40.944
- type: precision_at_1
value: 32.016
- type: precision_at_10
value: 8.280999999999999
- type: precision_at_100
value: 1.6760000000000002
- type: precision_at_1000
value: 0.25
- type: precision_at_3
value: 18.05
- type: precision_at_5
value: 13.083
- type: recall_at_1
value: 27.391
- type: recall_at_10
value: 56.928999999999995
- type: recall_at_100
value: 85.169
- type: recall_at_1000
value: 96.665
- type: recall_at_3
value: 42.264
- type: recall_at_5
value: 48.556
task:
type: Retrieval
- dataset:
config: default
name: MTEB CQADupstackWordpressRetrieval
revision: 4ffe81d471b1924886b33c7567bfb200e9eec5c4
split: test
type: BeIR/cqadupstack
metrics:
- type: map_at_1
value: 18.398
- type: map_at_10
value: 27.929
- type: map_at_100
value: 29.032999999999998
- type: map_at_1000
value: 29.126
- type: map_at_3
value: 25.070999999999998
- type: map_at_5
value: 26.583000000000002
- type: mrr_at_1
value: 19.963
- type: mrr_at_10
value: 29.997
- type: mrr_at_100
value: 30.9
- type: mrr_at_1000
value: 30.972
- type: mrr_at_3
value: 27.264
- type: mrr_at_5
value: 28.826
- type: ndcg_at_1
value: 19.963
- type: ndcg_at_10
value: 33.678999999999995
- type: ndcg_at_100
value: 38.931
- type: ndcg_at_1000
value: 41.379
- type: ndcg_at_3
value: 28.000000000000004
- type: ndcg_at_5
value: 30.637999999999998
- type: precision_at_1
value: 19.963
- type: precision_at_10
value: 5.7299999999999995
- type: precision_at_100
value: 0.902
- type: precision_at_1000
value: 0.122
- type: precision_at_3
value: 12.631
- type: precision_at_5
value: 9.057
- type: recall_at_1
value: 18.398
- type: recall_at_10
value: 49.254
- type: recall_at_100
value: 73.182
- type: recall_at_1000
value: 91.637
- type: recall_at_3
value: 34.06
- type: recall_at_5
value: 40.416000000000004
task:
type: Retrieval
- dataset:
config: default
name: MTEB ClimateFEVER
revision: 47f2ac6acb640fc46020b02a5b59fdda04d39380
split: test
type: mteb/climate-fever
metrics:
- type: map_at_1
value: 19.681
- type: map_at_10
value: 32.741
- type: map_at_100
value: 34.811
- type: map_at_1000
value: 35.003
- type: map_at_3
value: 27.697
- type: map_at_5
value: 30.372
- type: mrr_at_1
value: 44.951
- type: mrr_at_10
value: 56.34400000000001
- type: mrr_at_100
value: 56.961
- type: mrr_at_1000
value: 56.987
- type: mrr_at_3
value: 53.681
- type: mrr_at_5
value: 55.407
- type: ndcg_at_1
value: 44.951
- type: ndcg_at_10
value: 42.905
- type: ndcg_at_100
value: 49.95
- type: ndcg_at_1000
value: 52.917
- type: ndcg_at_3
value: 36.815
- type: ndcg_at_5
value: 38.817
- type: precision_at_1
value: 44.951
- type: precision_at_10
value: 12.989999999999998
- type: precision_at_100
value: 2.068
- type: precision_at_1000
value: 0.263
- type: precision_at_3
value: 27.275
- type: precision_at_5
value: 20.365
- type: recall_at_1
value: 19.681
- type: recall_at_10
value: 48.272999999999996
- type: recall_at_100
value: 71.87400000000001
- type: recall_at_1000
value: 87.929
- type: recall_at_3
value: 32.653999999999996
- type: recall_at_5
value: 39.364
task:
type: Retrieval
- dataset:
config: default
name: MTEB DBPedia
revision: c0f706b76e590d620bd6618b3ca8efdd34e2d659
split: test
type: mteb/dbpedia
metrics:
- type: map_at_1
value: 10.231
- type: map_at_10
value: 22.338
- type: map_at_100
value: 31.927
- type: map_at_1000
value: 33.87
- type: map_at_3
value: 15.559999999999999
- type: map_at_5
value: 18.239
- type: mrr_at_1
value: 75.0
- type: mrr_at_10
value: 81.303
- type: mrr_at_100
value: 81.523
- type: mrr_at_1000
value: 81.53
- type: mrr_at_3
value: 80.083
- type: mrr_at_5
value: 80.758
- type: ndcg_at_1
value: 64.625
- type: ndcg_at_10
value: 48.687000000000005
- type: ndcg_at_100
value: 52.791
- type: ndcg_at_1000
value: 60.041999999999994
- type: ndcg_at_3
value: 53.757999999999996
- type: ndcg_at_5
value: 50.76500000000001
- type: precision_at_1
value: 75.0
- type: precision_at_10
value: 38.3
- type: precision_at_100
value: 12.025
- type: precision_at_1000
value: 2.3970000000000002
- type: precision_at_3
value: 55.417
- type: precision_at_5
value: 47.5
- type: recall_at_1
value: 10.231
- type: recall_at_10
value: 27.697
- type: recall_at_100
value: 57.409
- type: recall_at_1000
value: 80.547
- type: recall_at_3
value: 16.668
- type: recall_at_5
value: 20.552
task:
type: Retrieval
- dataset:
config: default
name: MTEB EmotionClassification
revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37
split: test
type: mteb/emotion
metrics:
- type: accuracy
value: 61.365
- type: f1
value: 56.7540827912991
task:
type: Classification
- dataset:
config: default
name: MTEB FEVER
revision: bea83ef9e8fb933d90a2f1d5515737465d613e12
split: test
type: mteb/fever
metrics:
- type: map_at_1
value: 83.479
- type: map_at_10
value: 88.898
- type: map_at_100
value: 89.11
- type: map_at_1000
value: 89.12400000000001
- type: map_at_3
value: 88.103
- type: map_at_5
value: 88.629
- type: mrr_at_1
value: 89.934
- type: mrr_at_10
value: 93.91000000000001
- type: mrr_at_100
value: 93.937
- type: mrr_at_1000
value: 93.938
- type: mrr_at_3
value: 93.62700000000001
- type: mrr_at_5
value: 93.84599999999999
- type: ndcg_at_1
value: 89.934
- type: ndcg_at_10
value: 91.574
- type: ndcg_at_100
value: 92.238
- type: ndcg_at_1000
value: 92.45
- type: ndcg_at_3
value: 90.586
- type: ndcg_at_5
value: 91.16300000000001
- type: precision_at_1
value: 89.934
- type: precision_at_10
value: 10.555
- type: precision_at_100
value: 1.1159999999999999
- type: precision_at_1000
value: 0.11499999999999999
- type: precision_at_3
value: 33.588
- type: precision_at_5
value: 20.642
- type: recall_at_1
value: 83.479
- type: recall_at_10
value: 94.971
- type: recall_at_100
value: 97.397
- type: recall_at_1000
value: 98.666
- type: recall_at_3
value: 92.24799999999999
- type: recall_at_5
value: 93.797
task:
type: Retrieval
- dataset:
config: default
name: MTEB FiQA2018
revision: 27a168819829fe9bcd655c2df245fb19452e8e06
split: test
type: mteb/fiqa
metrics:
- type: map_at_1
value: 27.16
- type: map_at_10
value: 45.593
- type: map_at_100
value: 47.762
- type: map_at_1000
value: 47.899
- type: map_at_3
value: 39.237
- type: map_at_5
value: 42.970000000000006
- type: mrr_at_1
value: 52.623
- type: mrr_at_10
value: 62.637
- type: mrr_at_100
value: 63.169
- type: mrr_at_1000
value: 63.185
- type: mrr_at_3
value: 59.928000000000004
- type: mrr_at_5
value: 61.702999999999996
- type: ndcg_at_1
value: 52.623
- type: ndcg_at_10
value: 54.701
- type: ndcg_at_100
value: 61.263
- type: ndcg_at_1000
value: 63.134
- type: ndcg_at_3
value: 49.265
- type: ndcg_at_5
value: 51.665000000000006
- type: precision_at_1
value: 52.623
- type: precision_at_10
value: 15.185
- type: precision_at_100
value: 2.202
- type: precision_at_1000
value: 0.254
- type: precision_at_3
value: 32.767
- type: precision_at_5
value: 24.722
- type: recall_at_1
value: 27.16
- type: recall_at_10
value: 63.309000000000005
- type: recall_at_100
value: 86.722
- type: recall_at_1000
value: 97.505
- type: recall_at_3
value: 45.045
- type: recall_at_5
value: 54.02400000000001
task:
type: Retrieval
- dataset:
config: default
name: MTEB HotpotQA
revision: ab518f4d6fcca38d87c25209f94beba119d02014
split: test
type: mteb/hotpotqa
metrics:
- type: map_at_1
value: 42.573
- type: map_at_10
value: 59.373
- type: map_at_100
value: 60.292
- type: map_at_1000
value: 60.358999999999995
- type: map_at_3
value: 56.159000000000006
- type: map_at_5
value: 58.123999999999995
- type: mrr_at_1
value: 85.14500000000001
- type: mrr_at_10
value: 89.25999999999999
- type: mrr_at_100
value: 89.373
- type: mrr_at_1000
value: 89.377
- type: mrr_at_3
value: 88.618
- type: mrr_at_5
value: 89.036
- type: ndcg_at_1
value: 85.14500000000001
- type: ndcg_at_10
value: 68.95
- type: ndcg_at_100
value: 71.95
- type: ndcg_at_1000
value: 73.232
- type: ndcg_at_3
value: 64.546
- type: ndcg_at_5
value: 66.945
- type: precision_at_1
value: 85.14500000000001
- type: precision_at_10
value: 13.865
- type: precision_at_100
value: 1.619
- type: precision_at_1000
value: 0.179
- type: precision_at_3
value: 39.703
- type: precision_at_5
value: 25.718000000000004
- type: recall_at_1
value: 42.573
- type: recall_at_10
value: 69.325
- type: recall_at_100
value: 80.932
- type: recall_at_1000
value: 89.446
- type: recall_at_3
value: 59.553999999999995
- type: recall_at_5
value: 64.294
task:
type: Retrieval
- dataset:
config: default
name: MTEB ImdbClassification
revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7
split: test
type: mteb/imdb
metrics:
- type: accuracy
value: 95.8336
- type: ap
value: 93.78862962194073
- type: f1
value: 95.83192650728371
task:
type: Classification
- dataset:
config: default
name: MTEB MSMARCO
revision: c5a29a104738b98a9e76336939199e264163d4a0
split: dev
type: mteb/msmarco
metrics:
- type: map_at_1
value: 23.075000000000003
- type: map_at_10
value: 36.102000000000004
- type: map_at_100
value: 37.257
- type: map_at_1000
value: 37.3
- type: map_at_3
value: 32.144
- type: map_at_5
value: 34.359
- type: mrr_at_1
value: 23.711
- type: mrr_at_10
value: 36.671
- type: mrr_at_100
value: 37.763999999999996
- type: mrr_at_1000
value: 37.801
- type: mrr_at_3
value: 32.775
- type: mrr_at_5
value: 34.977000000000004
- type: ndcg_at_1
value: 23.711
- type: ndcg_at_10
value: 43.361
- type: ndcg_at_100
value: 48.839
- type: ndcg_at_1000
value: 49.88
- type: ndcg_at_3
value: 35.269
- type: ndcg_at_5
value: 39.224
- type: precision_at_1
value: 23.711
- type: precision_at_10
value: 6.866999999999999
- type: precision_at_100
value: 0.96
- type: precision_at_1000
value: 0.105
- type: precision_at_3
value: 15.096000000000002
- type: precision_at_5
value: 11.083
- type: recall_at_1
value: 23.075000000000003
- type: recall_at_10
value: 65.756
- type: recall_at_100
value: 90.88199999999999
- type: recall_at_1000
value: 98.739
- type: recall_at_3
value: 43.691
- type: recall_at_5
value: 53.15800000000001
task:
type: Retrieval
- dataset:
config: en
name: MTEB MTOPDomainClassification (en)
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
split: test
type: mteb/mtop_domain
metrics:
- type: accuracy
value: 97.69493844049248
- type: f1
value: 97.55048089616261
task:
type: Classification
- dataset:
config: en
name: MTEB MTOPIntentClassification (en)
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
split: test
type: mteb/mtop_intent
metrics:
- type: accuracy
value: 88.75968992248062
- type: f1
value: 72.26321223399123
task:
type: Classification
- dataset:
config: en
name: MTEB MassiveIntentClassification (en)
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
split: test
type: mteb/amazon_massive_intent
metrics:
- type: accuracy
value: 82.40080699394754
- type: f1
value: 79.62590029057968
task:
type: Classification
- dataset:
config: en
name: MTEB MassiveScenarioClassification (en)
revision: 7d571f92784cd94a019292a1f45445077d0ef634
split: test
type: mteb/amazon_massive_scenario
metrics:
- type: accuracy
value: 84.49562878278414
- type: f1
value: 84.0040193313333
task:
type: Classification
- dataset:
config: default
name: MTEB MedrxivClusteringP2P
revision: e7a26af6f3ae46b30dde8737f02c07b1505bcc73
split: test
type: mteb/medrxiv-clustering-p2p
metrics:
- type: v_measure
value: 39.386760057101945
task:
type: Clustering
- dataset:
config: default
name: MTEB MedrxivClusteringS2S
revision: 35191c8c0dca72d8ff3efcd72aa802307d469663
split: test
type: mteb/medrxiv-clustering-s2s
metrics:
- type: v_measure
value: 37.89687154075537
task:
type: Clustering
- dataset:
config: default
name: MTEB MindSmallReranking
revision: 3bdac13927fdc888b903db93b2ffdbd90b295a69
split: test
type: mteb/mind_small
metrics:
- type: map
value: 33.94151656057482
- type: mrr
value: 35.32684700746953
task:
type: Reranking
- dataset:
config: default
name: MTEB NFCorpus
revision: ec0fa4fe99da2ff19ca1214b7966684033a58814
split: test
type: mteb/nfcorpus
metrics:
- type: map_at_1
value: 6.239999999999999
- type: map_at_10
value: 14.862
- type: map_at_100
value: 18.955
- type: map_at_1000
value: 20.694000000000003
- type: map_at_3
value: 10.683
- type: map_at_5
value: 12.674
- type: mrr_at_1
value: 50.15500000000001
- type: mrr_at_10
value: 59.697
- type: mrr_at_100
value: 60.095
- type: mrr_at_1000
value: 60.129999999999995
- type: mrr_at_3
value: 58.35900000000001
- type: mrr_at_5
value: 58.839
- type: ndcg_at_1
value: 48.452
- type: ndcg_at_10
value: 39.341
- type: ndcg_at_100
value: 35.866
- type: ndcg_at_1000
value: 45.111000000000004
- type: ndcg_at_3
value: 44.527
- type: ndcg_at_5
value: 42.946
- type: precision_at_1
value: 50.15500000000001
- type: precision_at_10
value: 29.536
- type: precision_at_100
value: 9.142
- type: precision_at_1000
value: 2.2849999999999997
- type: precision_at_3
value: 41.899
- type: precision_at_5
value: 37.647000000000006
- type: recall_at_1
value: 6.239999999999999
- type: recall_at_10
value: 19.278000000000002
- type: recall_at_100
value: 36.074
- type: recall_at_1000
value: 70.017
- type: recall_at_3
value: 12.066
- type: recall_at_5
value: 15.254000000000001
task:
type: Retrieval
- dataset:
config: default
name: MTEB NQ
revision: b774495ed302d8c44a3a7ea25c90dbce03968f31
split: test
type: mteb/nq
metrics:
- type: map_at_1
value: 39.75
- type: map_at_10
value: 56.443
- type: map_at_100
value: 57.233999999999995
- type: map_at_1000
value: 57.249
- type: map_at_3
value: 52.032999999999994
- type: map_at_5
value: 54.937999999999995
- type: mrr_at_1
value: 44.728
- type: mrr_at_10
value: 58.939
- type: mrr_at_100
value: 59.489000000000004
- type: mrr_at_1000
value: 59.499
- type: mrr_at_3
value: 55.711999999999996
- type: mrr_at_5
value: 57.89
- type: ndcg_at_1
value: 44.728
- type: ndcg_at_10
value: 63.998999999999995
- type: ndcg_at_100
value: 67.077
- type: ndcg_at_1000
value: 67.40899999999999
- type: ndcg_at_3
value: 56.266000000000005
- type: ndcg_at_5
value: 60.88
- type: precision_at_1
value: 44.728
- type: precision_at_10
value: 10.09
- type: precision_at_100
value: 1.1809999999999998
- type: precision_at_1000
value: 0.121
- type: precision_at_3
value: 25.145
- type: precision_at_5
value: 17.822
- type: recall_at_1
value: 39.75
- type: recall_at_10
value: 84.234
- type: recall_at_100
value: 97.055
- type: recall_at_1000
value: 99.517
- type: recall_at_3
value: 64.851
- type: recall_at_5
value: 75.343
task:
type: Retrieval
- dataset:
config: default
name: MTEB QuoraRetrieval
revision: None
split: test
type: mteb/quora
metrics:
- type: map_at_1
value: 72.085
- type: map_at_10
value: 86.107
- type: map_at_100
value: 86.727
- type: map_at_1000
value: 86.74
- type: map_at_3
value: 83.21
- type: map_at_5
value: 85.06
- type: mrr_at_1
value: 82.94
- type: mrr_at_10
value: 88.845
- type: mrr_at_100
value: 88.926
- type: mrr_at_1000
value: 88.927
- type: mrr_at_3
value: 87.993
- type: mrr_at_5
value: 88.62299999999999
- type: ndcg_at_1
value: 82.97
- type: ndcg_at_10
value: 89.645
- type: ndcg_at_100
value: 90.717
- type: ndcg_at_1000
value: 90.78
- type: ndcg_at_3
value: 86.99900000000001
- type: ndcg_at_5
value: 88.52600000000001
- type: precision_at_1
value: 82.97
- type: precision_at_10
value: 13.569
- type: precision_at_100
value: 1.539
- type: precision_at_1000
value: 0.157
- type: precision_at_3
value: 38.043
- type: precision_at_5
value: 24.992
- type: recall_at_1
value: 72.085
- type: recall_at_10
value: 96.262
- type: recall_at_100
value: 99.77000000000001
- type: recall_at_1000
value: 99.997
- type: recall_at_3
value: 88.652
- type: recall_at_5
value: 93.01899999999999
task:
type: Retrieval
- dataset:
config: default
name: MTEB RedditClustering
revision: 24640382cdbf8abc73003fb0fa6d111a705499eb
split: test
type: mteb/reddit-clustering
metrics:
- type: v_measure
value: 55.82153952668092
task:
type: Clustering
- dataset:
config: default
name: MTEB RedditClusteringP2P
revision: 282350215ef01743dc01b456c7f5241fa8937f16
split: test
type: mteb/reddit-clustering-p2p
metrics:
- type: v_measure
value: 62.094465801879295
task:
type: Clustering
- dataset:
config: default
name: MTEB SCIDOCS
revision: None
split: test
type: mteb/scidocs
metrics:
- type: map_at_1
value: 5.688
- type: map_at_10
value: 15.201999999999998
- type: map_at_100
value: 18.096
- type: map_at_1000
value: 18.481
- type: map_at_3
value: 10.734
- type: map_at_5
value: 12.94
- type: mrr_at_1
value: 28.000000000000004
- type: mrr_at_10
value: 41.101
- type: mrr_at_100
value: 42.202
- type: mrr_at_1000
value: 42.228
- type: mrr_at_3
value: 37.683
- type: mrr_at_5
value: 39.708
- type: ndcg_at_1
value: 28.000000000000004
- type: ndcg_at_10
value: 24.976000000000003
- type: ndcg_at_100
value: 35.129
- type: ndcg_at_1000
value: 40.77
- type: ndcg_at_3
value: 23.787
- type: ndcg_at_5
value: 20.816000000000003
- type: precision_at_1
value: 28.000000000000004
- type: precision_at_10
value: 13.04
- type: precision_at_100
value: 2.761
- type: precision_at_1000
value: 0.41000000000000003
- type: precision_at_3
value: 22.6
- type: precision_at_5
value: 18.52
- type: recall_at_1
value: 5.688
- type: recall_at_10
value: 26.43
- type: recall_at_100
value: 56.02
- type: recall_at_1000
value: 83.21
- type: recall_at_3
value: 13.752
- type: recall_at_5
value: 18.777
task:
type: Retrieval
- dataset:
config: default
name: MTEB SICK-R
revision: a6ea5a8cab320b040a23452cc28066d9beae2cee
split: test
type: mteb/sickr-sts
metrics:
- type: cos_sim_pearson
value: 85.15084859283178
- type: cos_sim_spearman
value: 80.49030614009419
- type: euclidean_pearson
value: 81.84574978672468
- type: euclidean_spearman
value: 79.89787150656818
- type: manhattan_pearson
value: 81.63076538567131
- type: manhattan_spearman
value: 79.69867352121841
task:
type: STS
- dataset:
config: default
name: MTEB STS12
revision: a0d554a64d88156834ff5ae9920b964011b16384
split: test
type: mteb/sts12-sts
metrics:
- type: cos_sim_pearson
value: 84.64097921490992
- type: cos_sim_spearman
value: 77.25370084896514
- type: euclidean_pearson
value: 82.71210826468788
- type: euclidean_spearman
value: 78.50445584994826
- type: manhattan_pearson
value: 82.92580164330298
- type: manhattan_spearman
value: 78.69686891301019
task:
type: STS
- dataset:
config: default
name: MTEB STS13
revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca
split: test
type: mteb/sts13-sts
metrics:
- type: cos_sim_pearson
value: 87.24596417308994
- type: cos_sim_spearman
value: 87.79454220555091
- type: euclidean_pearson
value: 87.40242561671164
- type: euclidean_spearman
value: 88.25955597373556
- type: manhattan_pearson
value: 87.25160240485849
- type: manhattan_spearman
value: 88.155794979818
task:
type: STS
- dataset:
config: default
name: MTEB STS14
revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375
split: test
type: mteb/sts14-sts
metrics:
- type: cos_sim_pearson
value: 84.44914233422564
- type: cos_sim_spearman
value: 82.91015471820322
- type: euclidean_pearson
value: 84.7206656630327
- type: euclidean_spearman
value: 83.86408872059216
- type: manhattan_pearson
value: 84.72816725158454
- type: manhattan_spearman
value: 84.01603388572788
task:
type: STS
- dataset:
config: default
name: MTEB STS15
revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3
split: test
type: mteb/sts15-sts
metrics:
- type: cos_sim_pearson
value: 87.6168026237477
- type: cos_sim_spearman
value: 88.45414278092397
- type: euclidean_pearson
value: 88.57023240882022
- type: euclidean_spearman
value: 89.04102190922094
- type: manhattan_pearson
value: 88.66695535796354
- type: manhattan_spearman
value: 89.19898476680969
task:
type: STS
- dataset:
config: default
name: MTEB STS16
revision: 4d8694f8f0e0100860b497b999b3dbed754a0513
split: test
type: mteb/sts16-sts
metrics:
- type: cos_sim_pearson
value: 84.27925826089424
- type: cos_sim_spearman
value: 85.45291099550461
- type: euclidean_pearson
value: 83.63853036580834
- type: euclidean_spearman
value: 84.33468035821484
- type: manhattan_pearson
value: 83.72778773251596
- type: manhattan_spearman
value: 84.51583132445376
task:
type: STS
- dataset:
config: en-en
name: MTEB STS17 (en-en)
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
split: test
type: mteb/sts17-crosslingual-sts
metrics:
- type: cos_sim_pearson
value: 89.67375185692552
- type: cos_sim_spearman
value: 90.32542469203855
- type: euclidean_pearson
value: 89.63513717951847
- type: euclidean_spearman
value: 89.87760271003745
- type: manhattan_pearson
value: 89.28381452982924
- type: manhattan_spearman
value: 89.53568197785721
task:
type: STS
- dataset:
config: en
name: MTEB STS22 (en)
revision: eea2b4fe26a775864c896887d910b76a8098ad3f
split: test
type: mteb/sts22-crosslingual-sts
metrics:
- type: cos_sim_pearson
value: 66.24644693819846
- type: cos_sim_spearman
value: 66.09889420525377
- type: euclidean_pearson
value: 63.72551583520747
- type: euclidean_spearman
value: 63.01385470780679
- type: manhattan_pearson
value: 64.09258157214097
- type: manhattan_spearman
value: 63.080517752822594
task:
type: STS
- dataset:
config: default
name: MTEB STSBenchmark
revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831
split: test
type: mteb/stsbenchmark-sts
metrics:
- type: cos_sim_pearson
value: 86.27321463839989
- type: cos_sim_spearman
value: 86.37572865993327
- type: euclidean_pearson
value: 86.36268020198149
- type: euclidean_spearman
value: 86.31089339478922
- type: manhattan_pearson
value: 86.4260445761947
- type: manhattan_spearman
value: 86.45885895320457
task:
type: STS
- dataset:
config: default
name: MTEB SciDocsRR
revision: d3c5e1fc0b855ab6097bf1cda04dd73947d7caab
split: test
type: mteb/scidocs-reranking
metrics:
- type: map
value: 86.52456702387798
- type: mrr
value: 96.34556529164372
task:
type: Reranking
- dataset:
config: default
name: MTEB SciFact
revision: 0228b52cf27578f30900b9e5271d331663a030d7
split: test
type: mteb/scifact
metrics:
- type: map_at_1
value: 61.99400000000001
- type: map_at_10
value: 73.38799999999999
- type: map_at_100
value: 73.747
- type: map_at_1000
value: 73.75
- type: map_at_3
value: 70.04599999999999
- type: map_at_5
value: 72.095
- type: mrr_at_1
value: 65.0
- type: mrr_at_10
value: 74.42800000000001
- type: mrr_at_100
value: 74.722
- type: mrr_at_1000
value: 74.725
- type: mrr_at_3
value: 72.056
- type: mrr_at_5
value: 73.60600000000001
- type: ndcg_at_1
value: 65.0
- type: ndcg_at_10
value: 78.435
- type: ndcg_at_100
value: 79.922
- type: ndcg_at_1000
value: 80.00500000000001
- type: ndcg_at_3
value: 73.05199999999999
- type: ndcg_at_5
value: 75.98
- type: precision_at_1
value: 65.0
- type: precision_at_10
value: 10.5
- type: precision_at_100
value: 1.123
- type: precision_at_1000
value: 0.11299999999999999
- type: precision_at_3
value: 28.555999999999997
- type: precision_at_5
value: 19.0
- type: recall_at_1
value: 61.99400000000001
- type: recall_at_10
value: 92.72200000000001
- type: recall_at_100
value: 99.333
- type: recall_at_1000
value: 100.0
- type: recall_at_3
value: 78.739
- type: recall_at_5
value: 85.828
task:
type: Retrieval
- dataset:
config: default
name: MTEB SprintDuplicateQuestions
revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46
split: test
type: mteb/sprintduplicatequestions-pairclassification
metrics:
- type: cos_sim_accuracy
value: 99.79009900990098
- type: cos_sim_ap
value: 95.3203137438653
- type: cos_sim_f1
value: 89.12386706948641
- type: cos_sim_precision
value: 89.75659229208925
- type: cos_sim_recall
value: 88.5
- type: dot_accuracy
value: 99.67821782178218
- type: dot_ap
value: 89.94069840000675
- type: dot_f1
value: 83.45902463549521
- type: dot_precision
value: 83.9231547017189
- type: dot_recall
value: 83.0
- type: euclidean_accuracy
value: 99.78613861386138
- type: euclidean_ap
value: 95.10648259135526
- type: euclidean_f1
value: 88.77338877338877
- type: euclidean_precision
value: 92.42424242424242
- type: euclidean_recall
value: 85.39999999999999
- type: manhattan_accuracy
value: 99.7950495049505
- type: manhattan_ap
value: 95.29987661320946
- type: manhattan_f1
value: 89.21313183949972
- type: manhattan_precision
value: 93.14472252448314
- type: manhattan_recall
value: 85.6
- type: max_accuracy
value: 99.7950495049505
- type: max_ap
value: 95.3203137438653
- type: max_f1
value: 89.21313183949972
task:
type: PairClassification
- dataset:
config: default
name: MTEB StackExchangeClustering
revision: 6cbc1f7b2bc0622f2e39d2c77fa502909748c259
split: test
type: mteb/stackexchange-clustering
metrics:
- type: v_measure
value: 67.65446577183913
task:
type: Clustering
- dataset:
config: default
name: MTEB StackExchangeClusteringP2P
revision: 815ca46b2622cec33ccafc3735d572c266efdb44
split: test
type: mteb/stackexchange-clustering-p2p
metrics:
- type: v_measure
value: 46.30749237193961
task:
type: Clustering
- dataset:
config: default
name: MTEB StackOverflowDupQuestions
revision: e185fbe320c72810689fc5848eb6114e1ef5ec69
split: test
type: mteb/stackoverflowdupquestions-reranking
metrics:
- type: map
value: 54.91481849959949
- type: mrr
value: 55.853506175197346
task:
type: Reranking
- dataset:
config: default
name: MTEB SummEval
revision: cda12ad7615edc362dbf25a00fdd61d3b1eaf93c
split: test
type: mteb/summeval
metrics:
- type: cos_sim_pearson
value: 30.08196549170419
- type: cos_sim_spearman
value: 31.16661390597077
- type: dot_pearson
value: 29.892258410943466
- type: dot_spearman
value: 30.51328811965085
task:
type: Summarization
- dataset:
config: default
name: MTEB TRECCOVID
revision: None
split: test
type: mteb/trec-covid
metrics:
- type: map_at_1
value: 0.23900000000000002
- type: map_at_10
value: 2.173
- type: map_at_100
value: 14.24
- type: map_at_1000
value: 35.309000000000005
- type: map_at_3
value: 0.7100000000000001
- type: map_at_5
value: 1.163
- type: mrr_at_1
value: 92.0
- type: mrr_at_10
value: 96.0
- type: mrr_at_100
value: 96.0
- type: mrr_at_1000
value: 96.0
- type: mrr_at_3
value: 96.0
- type: mrr_at_5
value: 96.0
- type: ndcg_at_1
value: 90.0
- type: ndcg_at_10
value: 85.382
- type: ndcg_at_100
value: 68.03
- type: ndcg_at_1000
value: 61.021
- type: ndcg_at_3
value: 89.765
- type: ndcg_at_5
value: 88.444
- type: precision_at_1
value: 92.0
- type: precision_at_10
value: 88.0
- type: precision_at_100
value: 70.02000000000001
- type: precision_at_1000
value: 26.984
- type: precision_at_3
value: 94.0
- type: precision_at_5
value: 92.80000000000001
- type: recall_at_1
value: 0.23900000000000002
- type: recall_at_10
value: 2.313
- type: recall_at_100
value: 17.049
- type: recall_at_1000
value: 57.489999999999995
- type: recall_at_3
value: 0.737
- type: recall_at_5
value: 1.221
task:
type: Retrieval
- dataset:
config: default
name: MTEB Touche2020
revision: a34f9a33db75fa0cbb21bb5cfc3dae8dc8bec93f
split: test
type: mteb/touche2020
metrics:
- type: map_at_1
value: 2.75
- type: map_at_10
value: 11.29
- type: map_at_100
value: 18.032999999999998
- type: map_at_1000
value: 19.746
- type: map_at_3
value: 6.555
- type: map_at_5
value: 8.706999999999999
- type: mrr_at_1
value: 34.694
- type: mrr_at_10
value: 50.55
- type: mrr_at_100
value: 51.659
- type: mrr_at_1000
value: 51.659
- type: mrr_at_3
value: 47.278999999999996
- type: mrr_at_5
value: 49.728
- type: ndcg_at_1
value: 32.653
- type: ndcg_at_10
value: 27.894000000000002
- type: ndcg_at_100
value: 39.769
- type: ndcg_at_1000
value: 51.495999999999995
- type: ndcg_at_3
value: 32.954
- type: ndcg_at_5
value: 31.502999999999997
- type: precision_at_1
value: 34.694
- type: precision_at_10
value: 23.265
- type: precision_at_100
value: 7.898
- type: precision_at_1000
value: 1.58
- type: precision_at_3
value: 34.694
- type: precision_at_5
value: 31.429000000000002
- type: recall_at_1
value: 2.75
- type: recall_at_10
value: 16.953
- type: recall_at_100
value: 48.68
- type: recall_at_1000
value: 85.18599999999999
- type: recall_at_3
value: 7.710999999999999
- type: recall_at_5
value: 11.484
task:
type: Retrieval
- dataset:
config: default
name: MTEB ToxicConversationsClassification
revision: d7c0de2777da35d6aae2200a62c6e0e5af397c4c
split: test
type: mteb/toxic_conversations_50k
metrics:
- type: accuracy
value: 82.66099999999999
- type: ap
value: 25.555698090238337
- type: f1
value: 66.48402012461622
task:
type: Classification
- dataset:
config: default
name: MTEB TweetSentimentExtractionClassification
revision: d604517c81ca91fe16a244d1248fc021f9ecee7a
split: test
type: mteb/tweet_sentiment_extraction
metrics:
- type: accuracy
value: 72.94567062818335
- type: f1
value: 73.28139189595674
task:
type: Classification
- dataset:
config: default
name: MTEB TwentyNewsgroupsClustering
revision: 6125ec4e24fa026cec8a478383ee943acfbd5449
split: test
type: mteb/twentynewsgroups-clustering
metrics:
- type: v_measure
value: 49.581627240203474
task:
type: Clustering
- dataset:
config: default
name: MTEB TwitterSemEval2015
revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1
split: test
type: mteb/twittersemeval2015-pairclassification
metrics:
- type: cos_sim_accuracy
value: 87.78089050485785
- type: cos_sim_ap
value: 79.64487116574168
- type: cos_sim_f1
value: 72.46563021970964
- type: cos_sim_precision
value: 70.62359128474831
- type: cos_sim_recall
value: 74.40633245382587
- type: dot_accuracy
value: 86.2609524944865
- type: dot_ap
value: 75.513046857613
- type: dot_f1
value: 68.58213616489695
- type: dot_precision
value: 65.12455516014235
- type: dot_recall
value: 72.42744063324538
- type: euclidean_accuracy
value: 87.6080348095607
- type: euclidean_ap
value: 79.00204933649795
- type: euclidean_f1
value: 72.14495342605589
- type: euclidean_precision
value: 69.85421299728193
- type: euclidean_recall
value: 74.5910290237467
- type: manhattan_accuracy
value: 87.59611372712642
- type: manhattan_ap
value: 78.78523756706264
- type: manhattan_f1
value: 71.86499137718648
- type: manhattan_precision
value: 67.39833641404806
- type: manhattan_recall
value: 76.96569920844327
- type: max_accuracy
value: 87.78089050485785
- type: max_ap
value: 79.64487116574168
- type: max_f1
value: 72.46563021970964
task:
type: PairClassification
- dataset:
config: default
name: MTEB TwitterURLCorpus
revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf
split: test
type: mteb/twitterurlcorpus-pairclassification
metrics:
- type: cos_sim_accuracy
value: 89.98719292117825
- type: cos_sim_ap
value: 87.58146137353202
- type: cos_sim_f1
value: 80.28543232369239
- type: cos_sim_precision
value: 79.1735289714029
- type: cos_sim_recall
value: 81.42901139513397
- type: dot_accuracy
value: 88.9199363526992
- type: dot_ap
value: 84.98499998630417
- type: dot_f1
value: 78.21951400757969
- type: dot_precision
value: 75.58523624874336
- type: dot_recall
value: 81.04404065291038
- type: euclidean_accuracy
value: 89.77374160748244
- type: euclidean_ap
value: 87.35151562835209
- type: euclidean_f1
value: 79.92160922940393
- type: euclidean_precision
value: 76.88531587933979
- type: euclidean_recall
value: 83.20757622420696
- type: manhattan_accuracy
value: 89.72717041176699
- type: manhattan_ap
value: 87.34065592142515
- type: manhattan_f1
value: 79.85603419187943
- type: manhattan_precision
value: 77.82243332115455
- type: manhattan_recall
value: 81.99876809362489
- type: max_accuracy
value: 89.98719292117825
- type: max_ap
value: 87.58146137353202
- type: max_f1
value: 80.28543232369239
task:
type: PairClassification
- dataset:
config: default
name: MTEB AFQMC
revision: b44c3b011063adb25877c13823db83bb193913c4
split: validation
type: C-MTEB/AFQMC
metrics:
- type: cos_sim_pearson
value: 53.45954203592337
- type: cos_sim_spearman
value: 58.42154680418638
- type: euclidean_pearson
value: 56.41543791722753
- type: euclidean_spearman
value: 58.39328016640146
- type: manhattan_pearson
value: 56.318510356833876
- type: manhattan_spearman
value: 58.28423447818184
task:
type: STS
- dataset:
config: default
name: MTEB ATEC
revision: 0f319b1142f28d00e055a6770f3f726ae9b7d865
split: test
type: C-MTEB/ATEC
metrics:
- type: cos_sim_pearson
value: 50.78356460675945
- type: cos_sim_spearman
value: 55.6530411663269
- type: euclidean_pearson
value: 56.50763660417816
- type: euclidean_spearman
value: 55.733823335669065
- type: manhattan_pearson
value: 56.45323093512866
- type: manhattan_spearman
value: 55.63248619032702
task:
type: STS
- dataset:
config: zh
name: MTEB AmazonReviewsClassification (zh)
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
split: test
type: mteb/amazon_reviews_multi
metrics:
- type: accuracy
value: 47.209999999999994
- type: f1
value: 46.08892432018655
task:
type: Classification
- dataset:
config: default
name: MTEB BQ
revision: e3dda5e115e487b39ec7e618c0c6a29137052a55
split: test
type: C-MTEB/BQ
metrics:
- type: cos_sim_pearson
value: 70.25573992001478
- type: cos_sim_spearman
value: 73.85247134951433
- type: euclidean_pearson
value: 72.60033082168442
- type: euclidean_spearman
value: 73.72445893756499
- type: manhattan_pearson
value: 72.59932284620231
- type: manhattan_spearman
value: 73.68002490614583
task:
type: STS
- dataset:
config: default
name: MTEB CLSClusteringP2P
revision: 4b6227591c6c1a73bc76b1055f3b7f3588e72476
split: test
type: C-MTEB/CLSClusteringP2P
metrics:
- type: v_measure
value: 45.21317724305628
task:
type: Clustering
- dataset:
config: default
name: MTEB CLSClusteringS2S
revision: e458b3f5414b62b7f9f83499ac1f5497ae2e869f
split: test
type: C-MTEB/CLSClusteringS2S
metrics:
- type: v_measure
value: 42.49825170976724
task:
type: Clustering
- dataset:
config: default
name: MTEB CMedQAv1
revision: 8d7f1e942507dac42dc58017c1a001c3717da7df
split: test
type: C-MTEB/CMedQAv1-reranking
metrics:
- type: map
value: 88.15661686810597
- type: mrr
value: 90.11222222222223
task:
type: Reranking
- dataset:
config: default
name: MTEB CMedQAv2
revision: 23d186750531a14a0357ca22cd92d712fd512ea0
split: test
type: C-MTEB/CMedQAv2-reranking
metrics:
- type: map
value: 88.1204726064383
- type: mrr
value: 90.20142857142858
task:
type: Reranking
- dataset:
config: default
name: MTEB CmedqaRetrieval
revision: cd540c506dae1cf9e9a59c3e06f42030d54e7301
split: dev
type: C-MTEB/CmedqaRetrieval
metrics:
- type: map_at_1
value: 27.224999999999998
- type: map_at_10
value: 40.169
- type: map_at_100
value: 42.0
- type: map_at_1000
value: 42.109
- type: map_at_3
value: 35.76
- type: map_at_5
value: 38.221
- type: mrr_at_1
value: 40.56
- type: mrr_at_10
value: 49.118
- type: mrr_at_100
value: 50.092999999999996
- type: mrr_at_1000
value: 50.133
- type: mrr_at_3
value: 46.507
- type: mrr_at_5
value: 47.973
- type: ndcg_at_1
value: 40.56
- type: ndcg_at_10
value: 46.972
- type: ndcg_at_100
value: 54.04
- type: ndcg_at_1000
value: 55.862
- type: ndcg_at_3
value: 41.36
- type: ndcg_at_5
value: 43.704
- type: precision_at_1
value: 40.56
- type: precision_at_10
value: 10.302999999999999
- type: precision_at_100
value: 1.606
- type: precision_at_1000
value: 0.184
- type: precision_at_3
value: 23.064
- type: precision_at_5
value: 16.764000000000003
- type: recall_at_1
value: 27.224999999999998
- type: recall_at_10
value: 58.05200000000001
- type: recall_at_100
value: 87.092
- type: recall_at_1000
value: 99.099
- type: recall_at_3
value: 41.373
- type: recall_at_5
value: 48.453
task:
type: Retrieval
- dataset:
config: default
name: MTEB Cmnli
revision: 41bc36f332156f7adc9e38f53777c959b2ae9766
split: validation
type: C-MTEB/CMNLI
metrics:
- type: cos_sim_accuracy
value: 77.40228502705953
- type: cos_sim_ap
value: 86.22359172956327
- type: cos_sim_f1
value: 78.96328293736501
- type: cos_sim_precision
value: 73.36945615091311
- type: cos_sim_recall
value: 85.48047696983868
- type: dot_accuracy
value: 75.53818400481059
- type: dot_ap
value: 83.70164011305312
- type: dot_f1
value: 77.67298719348754
- type: dot_precision
value: 67.49482401656314
- type: dot_recall
value: 91.46598082768296
- type: euclidean_accuracy
value: 77.94347564642213
- type: euclidean_ap
value: 86.4652108728609
- type: euclidean_f1
value: 79.15555555555555
- type: euclidean_precision
value: 75.41816641964853
- type: euclidean_recall
value: 83.28267477203647
- type: manhattan_accuracy
value: 77.45039085989175
- type: manhattan_ap
value: 86.09986583900665
- type: manhattan_f1
value: 78.93669264438988
- type: manhattan_precision
value: 72.63261296660117
- type: manhattan_recall
value: 86.43909282207154
- type: max_accuracy
value: 77.94347564642213
- type: max_ap
value: 86.4652108728609
- type: max_f1
value: 79.15555555555555
task:
type: PairClassification
- dataset:
config: default
name: MTEB CovidRetrieval
revision: 1271c7809071a13532e05f25fb53511ffce77117
split: dev
type: C-MTEB/CovidRetrieval
metrics:
- type: map_at_1
value: 69.336
- type: map_at_10
value: 77.16
- type: map_at_100
value: 77.47500000000001
- type: map_at_1000
value: 77.482
- type: map_at_3
value: 75.42999999999999
- type: map_at_5
value: 76.468
- type: mrr_at_1
value: 69.44200000000001
- type: mrr_at_10
value: 77.132
- type: mrr_at_100
value: 77.43299999999999
- type: mrr_at_1000
value: 77.44
- type: mrr_at_3
value: 75.395
- type: mrr_at_5
value: 76.459
- type: ndcg_at_1
value: 69.547
- type: ndcg_at_10
value: 80.794
- type: ndcg_at_100
value: 82.245
- type: ndcg_at_1000
value: 82.40899999999999
- type: ndcg_at_3
value: 77.303
- type: ndcg_at_5
value: 79.168
- type: precision_at_1
value: 69.547
- type: precision_at_10
value: 9.305
- type: precision_at_100
value: 0.9979999999999999
- type: precision_at_1000
value: 0.101
- type: precision_at_3
value: 27.749000000000002
- type: precision_at_5
value: 17.576
- type: recall_at_1
value: 69.336
- type: recall_at_10
value: 92.097
- type: recall_at_100
value: 98.736
- type: recall_at_1000
value: 100.0
- type: recall_at_3
value: 82.64
- type: recall_at_5
value: 87.144
task:
type: Retrieval
- dataset:
config: default
name: MTEB DuRetrieval
revision: a1a333e290fe30b10f3f56498e3a0d911a693ced
split: dev
type: C-MTEB/DuRetrieval
metrics:
- type: map_at_1
value: 26.817999999999998
- type: map_at_10
value: 82.67
- type: map_at_100
value: 85.304
- type: map_at_1000
value: 85.334
- type: map_at_3
value: 57.336
- type: map_at_5
value: 72.474
- type: mrr_at_1
value: 91.45
- type: mrr_at_10
value: 94.272
- type: mrr_at_100
value: 94.318
- type: mrr_at_1000
value: 94.32000000000001
- type: mrr_at_3
value: 94.0
- type: mrr_at_5
value: 94.17699999999999
- type: ndcg_at_1
value: 91.45
- type: ndcg_at_10
value: 89.404
- type: ndcg_at_100
value: 91.724
- type: ndcg_at_1000
value: 91.973
- type: ndcg_at_3
value: 88.104
- type: ndcg_at_5
value: 87.25699999999999
- type: precision_at_1
value: 91.45
- type: precision_at_10
value: 42.585
- type: precision_at_100
value: 4.838
- type: precision_at_1000
value: 0.49
- type: precision_at_3
value: 78.8
- type: precision_at_5
value: 66.66
- type: recall_at_1
value: 26.817999999999998
- type: recall_at_10
value: 90.67
- type: recall_at_100
value: 98.36200000000001
- type: recall_at_1000
value: 99.583
- type: recall_at_3
value: 59.614999999999995
- type: recall_at_5
value: 77.05199999999999
task:
type: Retrieval
- dataset:
config: default
name: MTEB EcomRetrieval
revision: 687de13dc7294d6fd9be10c6945f9e8fec8166b9
split: dev
type: C-MTEB/EcomRetrieval
metrics:
- type: map_at_1
value: 47.699999999999996
- type: map_at_10
value: 57.589999999999996
- type: map_at_100
value: 58.226
- type: map_at_1000
value: 58.251
- type: map_at_3
value: 55.233
- type: map_at_5
value: 56.633
- type: mrr_at_1
value: 47.699999999999996
- type: mrr_at_10
value: 57.589999999999996
- type: mrr_at_100
value: 58.226
- type: mrr_at_1000
value: 58.251
- type: mrr_at_3
value: 55.233
- type: mrr_at_5
value: 56.633
- type: ndcg_at_1
value: 47.699999999999996
- type: ndcg_at_10
value: 62.505
- type: ndcg_at_100
value: 65.517
- type: ndcg_at_1000
value: 66.19800000000001
- type: ndcg_at_3
value: 57.643
- type: ndcg_at_5
value: 60.181
- type: precision_at_1
value: 47.699999999999996
- type: precision_at_10
value: 7.8
- type: precision_at_100
value: 0.919
- type: precision_at_1000
value: 0.097
- type: precision_at_3
value: 21.532999999999998
- type: precision_at_5
value: 14.16
- type: recall_at_1
value: 47.699999999999996
- type: recall_at_10
value: 78.0
- type: recall_at_100
value: 91.9
- type: recall_at_1000
value: 97.3
- type: recall_at_3
value: 64.60000000000001
- type: recall_at_5
value: 70.8
task:
type: Retrieval
- dataset:
config: default
name: MTEB IFlyTek
revision: 421605374b29664c5fc098418fe20ada9bd55f8a
split: validation
type: C-MTEB/IFlyTek-classification
metrics:
- type: accuracy
value: 44.84801846864178
- type: f1
value: 37.47347897956339
task:
type: Classification
- dataset:
config: default
name: MTEB JDReview
revision: b7c64bd89eb87f8ded463478346f76731f07bf8b
split: test
type: C-MTEB/JDReview-classification
metrics:
- type: accuracy
value: 85.81613508442777
- type: ap
value: 52.68244615477374
- type: f1
value: 80.0445640948843
task:
type: Classification
- dataset:
config: default
name: MTEB LCQMC
revision: 17f9b096f80380fce5ed12a9be8be7784b337daf
split: test
type: C-MTEB/LCQMC
metrics:
- type: cos_sim_pearson
value: 69.57786502217138
- type: cos_sim_spearman
value: 75.39106054489906
- type: euclidean_pearson
value: 73.72082954602402
- type: euclidean_spearman
value: 75.14421475913619
- type: manhattan_pearson
value: 73.62463076633642
- type: manhattan_spearman
value: 75.01301565104112
task:
type: STS
- dataset:
config: default
name: MTEB MMarcoReranking
revision: None
split: dev
type: C-MTEB/Mmarco-reranking
metrics:
- type: map
value: 29.143797057999134
- type: mrr
value: 28.08174603174603
task:
type: Reranking
- dataset:
config: default
name: MTEB MMarcoRetrieval
revision: 539bbde593d947e2a124ba72651aafc09eb33fc2
split: dev
type: C-MTEB/MMarcoRetrieval
metrics:
- type: map_at_1
value: 70.492
- type: map_at_10
value: 79.501
- type: map_at_100
value: 79.728
- type: map_at_1000
value: 79.735
- type: map_at_3
value: 77.77
- type: map_at_5
value: 78.851
- type: mrr_at_1
value: 72.822
- type: mrr_at_10
value: 80.001
- type: mrr_at_100
value: 80.19
- type: mrr_at_1000
value: 80.197
- type: mrr_at_3
value: 78.484
- type: mrr_at_5
value: 79.42099999999999
- type: ndcg_at_1
value: 72.822
- type: ndcg_at_10
value: 83.013
- type: ndcg_at_100
value: 84.013
- type: ndcg_at_1000
value: 84.20400000000001
- type: ndcg_at_3
value: 79.728
- type: ndcg_at_5
value: 81.542
- type: precision_at_1
value: 72.822
- type: precision_at_10
value: 9.917
- type: precision_at_100
value: 1.042
- type: precision_at_1000
value: 0.106
- type: precision_at_3
value: 29.847
- type: precision_at_5
value: 18.871
- type: recall_at_1
value: 70.492
- type: recall_at_10
value: 93.325
- type: recall_at_100
value: 97.822
- type: recall_at_1000
value: 99.319
- type: recall_at_3
value: 84.636
- type: recall_at_5
value: 88.93100000000001
task:
type: Retrieval
- dataset:
config: zh-CN
name: MTEB MassiveIntentClassification (zh-CN)
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
split: test
type: mteb/amazon_massive_intent
metrics:
- type: accuracy
value: 76.88298587760592
- type: f1
value: 73.89001762017176
task:
type: Classification
- dataset:
config: zh-CN
name: MTEB MassiveScenarioClassification (zh-CN)
revision: 7d571f92784cd94a019292a1f45445077d0ef634
split: test
type: mteb/amazon_massive_scenario
metrics:
- type: accuracy
value: 80.76328177538669
- type: f1
value: 80.24718532423358
task:
type: Classification
- dataset:
config: default
name: MTEB MedicalRetrieval
revision: 2039188fb5800a9803ba5048df7b76e6fb151fc6
split: dev
type: C-MTEB/MedicalRetrieval
metrics:
- type: map_at_1
value: 49.6
- type: map_at_10
value: 55.620999999999995
- type: map_at_100
value: 56.204
- type: map_at_1000
value: 56.251
- type: map_at_3
value: 54.132999999999996
- type: map_at_5
value: 54.933
- type: mrr_at_1
value: 49.7
- type: mrr_at_10
value: 55.67100000000001
- type: mrr_at_100
value: 56.254000000000005
- type: mrr_at_1000
value: 56.301
- type: mrr_at_3
value: 54.18300000000001
- type: mrr_at_5
value: 54.983000000000004
- type: ndcg_at_1
value: 49.6
- type: ndcg_at_10
value: 58.645
- type: ndcg_at_100
value: 61.789
- type: ndcg_at_1000
value: 63.219
- type: ndcg_at_3
value: 55.567
- type: ndcg_at_5
value: 57.008
- type: precision_at_1
value: 49.6
- type: precision_at_10
value: 6.819999999999999
- type: precision_at_100
value: 0.836
- type: precision_at_1000
value: 0.095
- type: precision_at_3
value: 19.900000000000002
- type: precision_at_5
value: 12.64
- type: recall_at_1
value: 49.6
- type: recall_at_10
value: 68.2
- type: recall_at_100
value: 83.6
- type: recall_at_1000
value: 95.3
- type: recall_at_3
value: 59.699999999999996
- type: recall_at_5
value: 63.2
task:
type: Retrieval
- dataset:
config: default
name: MTEB MultilingualSentiment
revision: 46958b007a63fdbf239b7672c25d0bea67b5ea1a
split: validation
type: C-MTEB/MultilingualSentiment-classification
metrics:
- type: accuracy
value: 74.45666666666666
- type: f1
value: 74.32582402190089
task:
type: Classification
- dataset:
config: default
name: MTEB Ocnli
revision: 66e76a618a34d6d565d5538088562851e6daa7ec
split: validation
type: C-MTEB/OCNLI
metrics:
- type: cos_sim_accuracy
value: 80.67135896047645
- type: cos_sim_ap
value: 87.60421240712051
- type: cos_sim_f1
value: 82.1304131408661
- type: cos_sim_precision
value: 77.68361581920904
- type: cos_sim_recall
value: 87.11721224920802
- type: dot_accuracy
value: 79.04710341093666
- type: dot_ap
value: 85.6370059719336
- type: dot_f1
value: 80.763723150358
- type: dot_precision
value: 73.69337979094077
- type: dot_recall
value: 89.33474128827878
- type: euclidean_accuracy
value: 81.05035192203573
- type: euclidean_ap
value: 87.7880240053663
- type: euclidean_f1
value: 82.50244379276637
- type: euclidean_precision
value: 76.7970882620564
- type: euclidean_recall
value: 89.1235480464625
- type: manhattan_accuracy
value: 80.61721710882512
- type: manhattan_ap
value: 87.43568120591175
- type: manhattan_f1
value: 81.89526184538653
- type: manhattan_precision
value: 77.5992438563327
- type: manhattan_recall
value: 86.6948257655755
- type: max_accuracy
value: 81.05035192203573
- type: max_ap
value: 87.7880240053663
- type: max_f1
value: 82.50244379276637
task:
type: PairClassification
- dataset:
config: default
name: MTEB OnlineShopping
revision: e610f2ebd179a8fda30ae534c3878750a96db120
split: test
type: C-MTEB/OnlineShopping-classification
metrics:
- type: accuracy
value: 93.5
- type: ap
value: 91.31357903446782
- type: f1
value: 93.48088994006616
task:
type: Classification
- dataset:
config: default
name: MTEB PAWSX
revision: 9c6a90e430ac22b5779fb019a23e820b11a8b5e1
split: test
type: C-MTEB/PAWSX
metrics:
- type: cos_sim_pearson
value: 36.93293453538077
- type: cos_sim_spearman
value: 42.45972506308574
- type: euclidean_pearson
value: 42.34945133152159
- type: euclidean_spearman
value: 42.331610303674644
- type: manhattan_pearson
value: 42.31455070249498
- type: manhattan_spearman
value: 42.19887982891834
task:
type: STS
- dataset:
config: default
name: MTEB QBQTC
revision: 790b0510dc52b1553e8c49f3d2afb48c0e5c48b7
split: test
type: C-MTEB/QBQTC
metrics:
- type: cos_sim_pearson
value: 33.683290790043785
- type: cos_sim_spearman
value: 35.149171171202994
- type: euclidean_pearson
value: 32.33806561267862
- type: euclidean_spearman
value: 34.483576387347966
- type: manhattan_pearson
value: 32.47629754599608
- type: manhattan_spearman
value: 34.66434471867615
task:
type: STS
- dataset:
config: zh
name: MTEB STS22 (zh)
revision: eea2b4fe26a775864c896887d910b76a8098ad3f
split: test
type: mteb/sts22-crosslingual-sts
metrics:
- type: cos_sim_pearson
value: 66.46322760516104
- type: cos_sim_spearman
value: 67.398478319726
- type: euclidean_pearson
value: 64.7223480293625
- type: euclidean_spearman
value: 66.83118568812951
- type: manhattan_pearson
value: 64.88440039828305
- type: manhattan_spearman
value: 66.80429458952257
task:
type: STS
- dataset:
config: default
name: MTEB STSB
revision: 0cde68302b3541bb8b3c340dc0644b0b745b3dc0
split: test
type: C-MTEB/STSB
metrics:
- type: cos_sim_pearson
value: 79.08991383232105
- type: cos_sim_spearman
value: 79.39715677296854
- type: euclidean_pearson
value: 78.63201279320496
- type: euclidean_spearman
value: 79.40262660785731
- type: manhattan_pearson
value: 78.98138363146906
- type: manhattan_spearman
value: 79.79968413014194
task:
type: STS
- dataset:
config: default
name: MTEB T2Reranking
revision: 76631901a18387f85eaa53e5450019b87ad58ef9
split: dev
type: C-MTEB/T2Reranking
metrics:
- type: map
value: 67.43289278789972
- type: mrr
value: 77.53012460908535
task:
type: Reranking
- dataset:
config: default
name: MTEB T2Retrieval
revision: 8731a845f1bf500a4f111cf1070785c793d10e64
split: dev
type: C-MTEB/T2Retrieval
metrics:
- type: map_at_1
value: 27.733999999999998
- type: map_at_10
value: 78.24799999999999
- type: map_at_100
value: 81.765
- type: map_at_1000
value: 81.824
- type: map_at_3
value: 54.92
- type: map_at_5
value: 67.61399999999999
- type: mrr_at_1
value: 90.527
- type: mrr_at_10
value: 92.843
- type: mrr_at_100
value: 92.927
- type: mrr_at_1000
value: 92.93
- type: mrr_at_3
value: 92.45100000000001
- type: mrr_at_5
value: 92.693
- type: ndcg_at_1
value: 90.527
- type: ndcg_at_10
value: 85.466
- type: ndcg_at_100
value: 88.846
- type: ndcg_at_1000
value: 89.415
- type: ndcg_at_3
value: 86.768
- type: ndcg_at_5
value: 85.46000000000001
- type: precision_at_1
value: 90.527
- type: precision_at_10
value: 42.488
- type: precision_at_100
value: 5.024
- type: precision_at_1000
value: 0.516
- type: precision_at_3
value: 75.907
- type: precision_at_5
value: 63.727000000000004
- type: recall_at_1
value: 27.733999999999998
- type: recall_at_10
value: 84.346
- type: recall_at_100
value: 95.536
- type: recall_at_1000
value: 98.42999999999999
- type: recall_at_3
value: 56.455
- type: recall_at_5
value: 70.755
task:
type: Retrieval
- dataset:
config: default
name: MTEB TNews
revision: 317f262bf1e6126357bbe89e875451e4b0938fe4
split: validation
type: C-MTEB/TNews-classification
metrics:
- type: accuracy
value: 49.952000000000005
- type: f1
value: 48.264617195258054
task:
type: Classification
- dataset:
config: default
name: MTEB ThuNewsClusteringP2P
revision: 5798586b105c0434e4f0fe5e767abe619442cf93
split: test
type: C-MTEB/ThuNewsClusteringP2P
metrics:
- type: v_measure
value: 68.23769904483508
task:
type: Clustering
- dataset:
config: default
name: MTEB ThuNewsClusteringS2S
revision: 8a8b2caeda43f39e13c4bc5bea0f8a667896e10d
split: test
type: C-MTEB/ThuNewsClusteringS2S
metrics:
- type: v_measure
value: 62.50294403136556
task:
type: Clustering
- dataset:
config: default
name: MTEB VideoRetrieval
revision: 58c2597a5943a2ba48f4668c3b90d796283c5639
split: dev
type: C-MTEB/VideoRetrieval
metrics:
- type: map_at_1
value: 54.0
- type: map_at_10
value: 63.668
- type: map_at_100
value: 64.217
- type: map_at_1000
value: 64.23100000000001
- type: map_at_3
value: 61.7
- type: map_at_5
value: 62.870000000000005
- type: mrr_at_1
value: 54.0
- type: mrr_at_10
value: 63.668
- type: mrr_at_100
value: 64.217
- type: mrr_at_1000
value: 64.23100000000001
- type: mrr_at_3
value: 61.7
- type: mrr_at_5
value: 62.870000000000005
- type: ndcg_at_1
value: 54.0
- type: ndcg_at_10
value: 68.11399999999999
- type: ndcg_at_100
value: 70.723
- type: ndcg_at_1000
value: 71.123
- type: ndcg_at_3
value: 64.074
- type: ndcg_at_5
value: 66.178
- type: precision_at_1
value: 54.0
- type: precision_at_10
value: 8.200000000000001
- type: precision_at_100
value: 0.941
- type: precision_at_1000
value: 0.097
- type: precision_at_3
value: 23.633000000000003
- type: precision_at_5
value: 15.2
- type: recall_at_1
value: 54.0
- type: recall_at_10
value: 82.0
- type: recall_at_100
value: 94.1
- type: recall_at_1000
value: 97.3
- type: recall_at_3
value: 70.89999999999999
- type: recall_at_5
value: 76.0
task:
type: Retrieval
- dataset:
config: default
name: MTEB Waimai
revision: 339287def212450dcaa9df8c22bf93e9980c7023
split: test
type: C-MTEB/waimai-classification
metrics:
- type: accuracy
value: 86.63000000000001
- type: ap
value: 69.99457882599567
- type: f1
value: 85.07735617998541
task:
type: Classification
- dataset:
config: default
name: MTEB 8TagsClustering
revision: None
split: test
type: PL-MTEB/8tags-clustering
metrics:
- type: v_measure
value: 44.594104491193555
task:
type: Clustering
- dataset:
config: default
name: MTEB AllegroReviews
revision: None
split: test
type: PL-MTEB/allegro-reviews
metrics:
- type: accuracy
value: 63.97614314115309
- type: f1
value: 52.15634261679283
task:
type: Classification
- dataset:
config: default
name: MTEB ArguAna-PL
revision: 63fc86750af76253e8c760fc9e534bbf24d260a2
split: test
type: clarin-knext/arguana-pl
metrics:
- type: map_at_1
value: 32.646
- type: map_at_10
value: 47.963
- type: map_at_100
value: 48.789
- type: map_at_1000
value: 48.797000000000004
- type: map_at_3
value: 43.196
- type: map_at_5
value: 46.016
- type: mrr_at_1
value: 33.073
- type: mrr_at_10
value: 48.126000000000005
- type: mrr_at_100
value: 48.946
- type: mrr_at_1000
value: 48.953
- type: mrr_at_3
value: 43.374
- type: mrr_at_5
value: 46.147
- type: ndcg_at_1
value: 32.646
- type: ndcg_at_10
value: 56.481
- type: ndcg_at_100
value: 59.922
- type: ndcg_at_1000
value: 60.07
- type: ndcg_at_3
value: 46.675
- type: ndcg_at_5
value: 51.76500000000001
- type: precision_at_1
value: 32.646
- type: precision_at_10
value: 8.371
- type: precision_at_100
value: 0.9860000000000001
- type: precision_at_1000
value: 0.1
- type: precision_at_3
value: 18.919
- type: precision_at_5
value: 13.825999999999999
- type: recall_at_1
value: 32.646
- type: recall_at_10
value: 83.71300000000001
- type: recall_at_100
value: 98.578
- type: recall_at_1000
value: 99.644
- type: recall_at_3
value: 56.757000000000005
- type: recall_at_5
value: 69.132
task:
type: Retrieval
- dataset:
config: default
name: MTEB CBD
revision: None
split: test
type: PL-MTEB/cbd
metrics:
- type: accuracy
value: 68.56
- type: ap
value: 23.310493680488513
- type: f1
value: 58.85369533105693
task:
type: Classification
- dataset:
config: default
name: MTEB CDSC-E
revision: None
split: test
type: PL-MTEB/cdsce-pairclassification
metrics:
- type: cos_sim_accuracy
value: 88.5
- type: cos_sim_ap
value: 72.42140924378361
- type: cos_sim_f1
value: 66.0919540229885
- type: cos_sim_precision
value: 72.78481012658227
- type: cos_sim_recall
value: 60.526315789473685
- type: dot_accuracy
value: 88.5
- type: dot_ap
value: 72.42140924378361
- type: dot_f1
value: 66.0919540229885
- type: dot_precision
value: 72.78481012658227
- type: dot_recall
value: 60.526315789473685
- type: euclidean_accuracy
value: 88.5
- type: euclidean_ap
value: 72.42140924378361
- type: euclidean_f1
value: 66.0919540229885
- type: euclidean_precision
value: 72.78481012658227
- type: euclidean_recall
value: 60.526315789473685
- type: manhattan_accuracy
value: 88.5
- type: manhattan_ap
value: 72.49745515311696
- type: manhattan_f1
value: 66.0968660968661
- type: manhattan_precision
value: 72.04968944099379
- type: manhattan_recall
value: 61.05263157894737
- type: max_accuracy
value: 88.5
- type: max_ap
value: 72.49745515311696
- type: max_f1
value: 66.0968660968661
task:
type: PairClassification
- dataset:
config: default
name: MTEB CDSC-R
revision: None
split: test
type: PL-MTEB/cdscr-sts
metrics:
- type: cos_sim_pearson
value: 90.32269765590145
- type: cos_sim_spearman
value: 89.73666311491672
- type: euclidean_pearson
value: 88.2933868516544
- type: euclidean_spearman
value: 89.73666311491672
- type: manhattan_pearson
value: 88.33474590219448
- type: manhattan_spearman
value: 89.8548364866583
task:
type: STS
- dataset:
config: default
name: MTEB DBPedia-PL
revision: 76afe41d9af165cc40999fcaa92312b8b012064a
split: test
type: clarin-knext/dbpedia-pl
metrics:
- type: map_at_1
value: 7.632999999999999
- type: map_at_10
value: 16.426
- type: map_at_100
value: 22.651
- type: map_at_1000
value: 24.372
- type: map_at_3
value: 11.706
- type: map_at_5
value: 13.529
- type: mrr_at_1
value: 60.75000000000001
- type: mrr_at_10
value: 68.613
- type: mrr_at_100
value: 69.001
- type: mrr_at_1000
value: 69.021
- type: mrr_at_3
value: 67.0
- type: mrr_at_5
value: 67.925
- type: ndcg_at_1
value: 49.875
- type: ndcg_at_10
value: 36.978
- type: ndcg_at_100
value: 40.031
- type: ndcg_at_1000
value: 47.566
- type: ndcg_at_3
value: 41.148
- type: ndcg_at_5
value: 38.702
- type: precision_at_1
value: 60.75000000000001
- type: precision_at_10
value: 29.7
- type: precision_at_100
value: 9.278
- type: precision_at_1000
value: 2.099
- type: precision_at_3
value: 44.0
- type: precision_at_5
value: 37.6
- type: recall_at_1
value: 7.632999999999999
- type: recall_at_10
value: 22.040000000000003
- type: recall_at_100
value: 44.024
- type: recall_at_1000
value: 67.848
- type: recall_at_3
value: 13.093
- type: recall_at_5
value: 15.973
task:
type: Retrieval
- dataset:
config: default
name: MTEB FiQA-PL
revision: 2e535829717f8bf9dc829b7f911cc5bbd4e6608e
split: test
type: clarin-knext/fiqa-pl
metrics:
- type: map_at_1
value: 15.473
- type: map_at_10
value: 24.579
- type: map_at_100
value: 26.387
- type: map_at_1000
value: 26.57
- type: map_at_3
value: 21.278
- type: map_at_5
value: 23.179
- type: mrr_at_1
value: 30.709999999999997
- type: mrr_at_10
value: 38.994
- type: mrr_at_100
value: 39.993
- type: mrr_at_1000
value: 40.044999999999995
- type: mrr_at_3
value: 36.342999999999996
- type: mrr_at_5
value: 37.846999999999994
- type: ndcg_at_1
value: 30.709999999999997
- type: ndcg_at_10
value: 31.608999999999998
- type: ndcg_at_100
value: 38.807
- type: ndcg_at_1000
value: 42.208
- type: ndcg_at_3
value: 28.086
- type: ndcg_at_5
value: 29.323
- type: precision_at_1
value: 30.709999999999997
- type: precision_at_10
value: 8.688
- type: precision_at_100
value: 1.608
- type: precision_at_1000
value: 0.22100000000000003
- type: precision_at_3
value: 18.724
- type: precision_at_5
value: 13.950999999999999
- type: recall_at_1
value: 15.473
- type: recall_at_10
value: 38.361000000000004
- type: recall_at_100
value: 65.2
- type: recall_at_1000
value: 85.789
- type: recall_at_3
value: 25.401
- type: recall_at_5
value: 30.875999999999998
task:
type: Retrieval
- dataset:
config: default
name: MTEB HotpotQA-PL
revision: a0bd479ac97b4ccb5bd6ce320c415d0bb4beb907
split: test
type: clarin-knext/hotpotqa-pl
metrics:
- type: map_at_1
value: 38.096000000000004
- type: map_at_10
value: 51.44499999999999
- type: map_at_100
value: 52.325
- type: map_at_1000
value: 52.397000000000006
- type: map_at_3
value: 48.626999999999995
- type: map_at_5
value: 50.342
- type: mrr_at_1
value: 76.19200000000001
- type: mrr_at_10
value: 81.191
- type: mrr_at_100
value: 81.431
- type: mrr_at_1000
value: 81.443
- type: mrr_at_3
value: 80.30199999999999
- type: mrr_at_5
value: 80.85900000000001
- type: ndcg_at_1
value: 76.19200000000001
- type: ndcg_at_10
value: 60.9
- type: ndcg_at_100
value: 64.14699999999999
- type: ndcg_at_1000
value: 65.647
- type: ndcg_at_3
value: 56.818000000000005
- type: ndcg_at_5
value: 59.019999999999996
- type: precision_at_1
value: 76.19200000000001
- type: precision_at_10
value: 12.203
- type: precision_at_100
value: 1.478
- type: precision_at_1000
value: 0.168
- type: precision_at_3
value: 34.616
- type: precision_at_5
value: 22.515
- type: recall_at_1
value: 38.096000000000004
- type: recall_at_10
value: 61.013
- type: recall_at_100
value: 73.90299999999999
- type: recall_at_1000
value: 83.91
- type: recall_at_3
value: 51.92400000000001
- type: recall_at_5
value: 56.286
task:
type: Retrieval
- dataset:
config: default
name: MTEB MSMARCO-PL
revision: 8634c07806d5cce3a6138e260e59b81760a0a640
split: test
type: clarin-knext/msmarco-pl
metrics:
- type: map_at_1
value: 1.548
- type: map_at_10
value: 11.049000000000001
- type: map_at_100
value: 28.874
- type: map_at_1000
value: 34.931
- type: map_at_3
value: 4.162
- type: map_at_5
value: 6.396
- type: mrr_at_1
value: 90.69800000000001
- type: mrr_at_10
value: 92.093
- type: mrr_at_100
value: 92.345
- type: mrr_at_1000
value: 92.345
- type: mrr_at_3
value: 91.86
- type: mrr_at_5
value: 91.86
- type: ndcg_at_1
value: 74.031
- type: ndcg_at_10
value: 63.978
- type: ndcg_at_100
value: 53.101
- type: ndcg_at_1000
value: 60.675999999999995
- type: ndcg_at_3
value: 71.421
- type: ndcg_at_5
value: 68.098
- type: precision_at_1
value: 90.69800000000001
- type: precision_at_10
value: 71.86
- type: precision_at_100
value: 31.395
- type: precision_at_1000
value: 5.981
- type: precision_at_3
value: 84.49600000000001
- type: precision_at_5
value: 79.07
- type: recall_at_1
value: 1.548
- type: recall_at_10
value: 12.149000000000001
- type: recall_at_100
value: 40.794999999999995
- type: recall_at_1000
value: 67.974
- type: recall_at_3
value: 4.244
- type: recall_at_5
value: 6.608
task:
type: Retrieval
- dataset:
config: pl
name: MTEB MassiveIntentClassification (pl)
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
split: test
type: mteb/amazon_massive_intent
metrics:
- type: accuracy
value: 73.55413584398119
- type: f1
value: 69.65610882318181
task:
type: Classification
- dataset:
config: pl
name: MTEB MassiveScenarioClassification (pl)
revision: 7d571f92784cd94a019292a1f45445077d0ef634
split: test
type: mteb/amazon_massive_scenario
metrics:
- type: accuracy
value: 76.37188971082716
- type: f1
value: 75.64847309941361
task:
type: Classification
- dataset:
config: default
name: MTEB NFCorpus-PL
revision: 9a6f9567fda928260afed2de480d79c98bf0bec0
split: test
type: clarin-knext/nfcorpus-pl
metrics:
- type: map_at_1
value: 4.919
- type: map_at_10
value: 10.834000000000001
- type: map_at_100
value: 13.38
- type: map_at_1000
value: 14.581
- type: map_at_3
value: 8.198
- type: map_at_5
value: 9.428
- type: mrr_at_1
value: 41.176
- type: mrr_at_10
value: 50.083
- type: mrr_at_100
value: 50.559
- type: mrr_at_1000
value: 50.604000000000006
- type: mrr_at_3
value: 47.936
- type: mrr_at_5
value: 49.407000000000004
- type: ndcg_at_1
value: 39.628
- type: ndcg_at_10
value: 30.098000000000003
- type: ndcg_at_100
value: 27.061
- type: ndcg_at_1000
value: 35.94
- type: ndcg_at_3
value: 35.135
- type: ndcg_at_5
value: 33.335
- type: precision_at_1
value: 41.176
- type: precision_at_10
value: 22.259999999999998
- type: precision_at_100
value: 6.712
- type: precision_at_1000
value: 1.9060000000000001
- type: precision_at_3
value: 33.23
- type: precision_at_5
value: 29.04
- type: recall_at_1
value: 4.919
- type: recall_at_10
value: 14.196
- type: recall_at_100
value: 26.948
- type: recall_at_1000
value: 59.211000000000006
- type: recall_at_3
value: 9.44
- type: recall_at_5
value: 11.569
task:
type: Retrieval
- dataset:
config: default
name: MTEB NQ-PL
revision: f171245712cf85dd4700b06bef18001578d0ca8d
split: test
type: clarin-knext/nq-pl
metrics:
- type: map_at_1
value: 25.35
- type: map_at_10
value: 37.884
- type: map_at_100
value: 38.955
- type: map_at_1000
value: 39.007999999999996
- type: map_at_3
value: 34.239999999999995
- type: map_at_5
value: 36.398
- type: mrr_at_1
value: 28.737000000000002
- type: mrr_at_10
value: 39.973
- type: mrr_at_100
value: 40.844
- type: mrr_at_1000
value: 40.885
- type: mrr_at_3
value: 36.901
- type: mrr_at_5
value: 38.721
- type: ndcg_at_1
value: 28.708
- type: ndcg_at_10
value: 44.204
- type: ndcg_at_100
value: 48.978
- type: ndcg_at_1000
value: 50.33
- type: ndcg_at_3
value: 37.36
- type: ndcg_at_5
value: 40.912
- type: precision_at_1
value: 28.708
- type: precision_at_10
value: 7.367
- type: precision_at_100
value: 1.0030000000000001
- type: precision_at_1000
value: 0.11299999999999999
- type: precision_at_3
value: 17.034
- type: precision_at_5
value: 12.293999999999999
- type: recall_at_1
value: 25.35
- type: recall_at_10
value: 61.411
- type: recall_at_100
value: 82.599
- type: recall_at_1000
value: 92.903
- type: recall_at_3
value: 43.728
- type: recall_at_5
value: 51.854
task:
type: Retrieval
- dataset:
config: default
name: MTEB PAC
revision: None
split: test
type: laugustyniak/abusive-clauses-pl
metrics:
- type: accuracy
value: 69.04141326382856
- type: ap
value: 77.49422763833996
- type: f1
value: 66.73472657783407
task:
type: Classification
- dataset:
config: default
name: MTEB PPC
revision: None
split: test
type: PL-MTEB/ppc-pairclassification
metrics:
- type: cos_sim_accuracy
value: 81.0
- type: cos_sim_ap
value: 91.47194213011349
- type: cos_sim_f1
value: 84.73767885532592
- type: cos_sim_precision
value: 81.49847094801224
- type: cos_sim_recall
value: 88.24503311258279
- type: dot_accuracy
value: 81.0
- type: dot_ap
value: 91.47194213011349
- type: dot_f1
value: 84.73767885532592
- type: dot_precision
value: 81.49847094801224
- type: dot_recall
value: 88.24503311258279
- type: euclidean_accuracy
value: 81.0
- type: euclidean_ap
value: 91.47194213011349
- type: euclidean_f1
value: 84.73767885532592
- type: euclidean_precision
value: 81.49847094801224
- type: euclidean_recall
value: 88.24503311258279
- type: manhattan_accuracy
value: 81.0
- type: manhattan_ap
value: 91.46464475050571
- type: manhattan_f1
value: 84.48687350835321
- type: manhattan_precision
value: 81.31699846860643
- type: manhattan_recall
value: 87.91390728476821
- type: max_accuracy
value: 81.0
- type: max_ap
value: 91.47194213011349
- type: max_f1
value: 84.73767885532592
task:
type: PairClassification
- dataset:
config: default
name: MTEB PSC
revision: None
split: test
type: PL-MTEB/psc-pairclassification
metrics:
- type: cos_sim_accuracy
value: 97.6808905380334
- type: cos_sim_ap
value: 99.27948611836348
- type: cos_sim_f1
value: 96.15975422427034
- type: cos_sim_precision
value: 96.90402476780186
- type: cos_sim_recall
value: 95.42682926829268
- type: dot_accuracy
value: 97.6808905380334
- type: dot_ap
value: 99.2794861183635
- type: dot_f1
value: 96.15975422427034
- type: dot_precision
value: 96.90402476780186
- type: dot_recall
value: 95.42682926829268
- type: euclidean_accuracy
value: 97.6808905380334
- type: euclidean_ap
value: 99.2794861183635
- type: euclidean_f1
value: 96.15975422427034
- type: euclidean_precision
value: 96.90402476780186
- type: euclidean_recall
value: 95.42682926829268
- type: manhattan_accuracy
value: 97.6808905380334
- type: manhattan_ap
value: 99.28715055268721
- type: manhattan_f1
value: 96.14791987673343
- type: manhattan_precision
value: 97.19626168224299
- type: manhattan_recall
value: 95.1219512195122
- type: max_accuracy
value: 97.6808905380334
- type: max_ap
value: 99.28715055268721
- type: max_f1
value: 96.15975422427034
task:
type: PairClassification
- dataset:
config: default
name: MTEB PolEmo2.0-IN
revision: None
split: test
type: PL-MTEB/polemo2_in
metrics:
- type: accuracy
value: 86.16343490304708
- type: f1
value: 83.3442579486744
task:
type: Classification
- dataset:
config: default
name: MTEB PolEmo2.0-OUT
revision: None
split: test
type: PL-MTEB/polemo2_out
metrics:
- type: accuracy
value: 68.40080971659918
- type: f1
value: 53.13720751142237
task:
type: Classification
- dataset:
config: default
name: MTEB Quora-PL
revision: 0be27e93455051e531182b85e85e425aba12e9d4
split: test
type: clarin-knext/quora-pl
metrics:
- type: map_at_1
value: 63.322
- type: map_at_10
value: 76.847
- type: map_at_100
value: 77.616
- type: map_at_1000
value: 77.644
- type: map_at_3
value: 73.624
- type: map_at_5
value: 75.603
- type: mrr_at_1
value: 72.88
- type: mrr_at_10
value: 80.376
- type: mrr_at_100
value: 80.604
- type: mrr_at_1000
value: 80.61
- type: mrr_at_3
value: 78.92
- type: mrr_at_5
value: 79.869
- type: ndcg_at_1
value: 72.89999999999999
- type: ndcg_at_10
value: 81.43
- type: ndcg_at_100
value: 83.394
- type: ndcg_at_1000
value: 83.685
- type: ndcg_at_3
value: 77.62599999999999
- type: ndcg_at_5
value: 79.656
- type: precision_at_1
value: 72.89999999999999
- type: precision_at_10
value: 12.548
- type: precision_at_100
value: 1.4869999999999999
- type: precision_at_1000
value: 0.155
- type: precision_at_3
value: 34.027
- type: precision_at_5
value: 22.654
- type: recall_at_1
value: 63.322
- type: recall_at_10
value: 90.664
- type: recall_at_100
value: 97.974
- type: recall_at_1000
value: 99.636
- type: recall_at_3
value: 80.067
- type: recall_at_5
value: 85.526
task:
type: Retrieval
- dataset:
config: default
name: MTEB SCIDOCS-PL
revision: 45452b03f05560207ef19149545f168e596c9337
split: test
type: clarin-knext/scidocs-pl
metrics:
- type: map_at_1
value: 3.95
- type: map_at_10
value: 9.658999999999999
- type: map_at_100
value: 11.384
- type: map_at_1000
value: 11.677
- type: map_at_3
value: 7.055
- type: map_at_5
value: 8.244
- type: mrr_at_1
value: 19.5
- type: mrr_at_10
value: 28.777
- type: mrr_at_100
value: 29.936
- type: mrr_at_1000
value: 30.009999999999998
- type: mrr_at_3
value: 25.55
- type: mrr_at_5
value: 27.284999999999997
- type: ndcg_at_1
value: 19.5
- type: ndcg_at_10
value: 16.589000000000002
- type: ndcg_at_100
value: 23.879
- type: ndcg_at_1000
value: 29.279
- type: ndcg_at_3
value: 15.719
- type: ndcg_at_5
value: 13.572000000000001
- type: precision_at_1
value: 19.5
- type: precision_at_10
value: 8.62
- type: precision_at_100
value: 1.924
- type: precision_at_1000
value: 0.322
- type: precision_at_3
value: 14.6
- type: precision_at_5
value: 11.78
- type: recall_at_1
value: 3.95
- type: recall_at_10
value: 17.477999999999998
- type: recall_at_100
value: 38.99
- type: recall_at_1000
value: 65.417
- type: recall_at_3
value: 8.883000000000001
- type: recall_at_5
value: 11.933
task:
type: Retrieval
- dataset:
config: default
name: MTEB SICK-E-PL
revision: None
split: test
type: PL-MTEB/sicke-pl-pairclassification
metrics:
- type: cos_sim_accuracy
value: 83.48960456583775
- type: cos_sim_ap
value: 76.31522115825375
- type: cos_sim_f1
value: 70.35573122529645
- type: cos_sim_precision
value: 70.9934735315446
- type: cos_sim_recall
value: 69.72934472934473
- type: dot_accuracy
value: 83.48960456583775
- type: dot_ap
value: 76.31522115825373
- type: dot_f1
value: 70.35573122529645
- type: dot_precision
value: 70.9934735315446
- type: dot_recall
value: 69.72934472934473
- type: euclidean_accuracy
value: 83.48960456583775
- type: euclidean_ap
value: 76.31522115825373
- type: euclidean_f1
value: 70.35573122529645
- type: euclidean_precision
value: 70.9934735315446
- type: euclidean_recall
value: 69.72934472934473
- type: manhattan_accuracy
value: 83.46922136159804
- type: manhattan_ap
value: 76.18474601388084
- type: manhattan_f1
value: 70.34779490856937
- type: manhattan_precision
value: 70.83032490974729
- type: manhattan_recall
value: 69.87179487179486
- type: max_accuracy
value: 83.48960456583775
- type: max_ap
value: 76.31522115825375
- type: max_f1
value: 70.35573122529645
task:
type: PairClassification
- dataset:
config: default
name: MTEB SICK-R-PL
revision: None
split: test
type: PL-MTEB/sickr-pl-sts
metrics:
- type: cos_sim_pearson
value: 77.95374883876302
- type: cos_sim_spearman
value: 73.77630219171942
- type: euclidean_pearson
value: 75.81927069594934
- type: euclidean_spearman
value: 73.7763211303831
- type: manhattan_pearson
value: 76.03126859057528
- type: manhattan_spearman
value: 73.96528138013369
task:
type: STS
- dataset:
config: pl
name: MTEB STS22 (pl)
revision: eea2b4fe26a775864c896887d910b76a8098ad3f
split: test
type: mteb/sts22-crosslingual-sts
metrics:
- type: cos_sim_pearson
value: 37.388282764841826
- type: cos_sim_spearman
value: 40.83477184710897
- type: euclidean_pearson
value: 26.754737044177805
- type: euclidean_spearman
value: 40.83477184710897
- type: manhattan_pearson
value: 26.760453110872458
- type: manhattan_spearman
value: 41.034477441383856
task:
type: STS
- dataset:
config: default
name: MTEB SciFact-PL
revision: 47932a35f045ef8ed01ba82bf9ff67f6e109207e
split: test
type: clarin-knext/scifact-pl
metrics:
- type: map_at_1
value: 49.15
- type: map_at_10
value: 61.690999999999995
- type: map_at_100
value: 62.348000000000006
- type: map_at_1000
value: 62.38
- type: map_at_3
value: 58.824
- type: map_at_5
value: 60.662000000000006
- type: mrr_at_1
value: 51.333
- type: mrr_at_10
value: 62.731
- type: mrr_at_100
value: 63.245
- type: mrr_at_1000
value: 63.275000000000006
- type: mrr_at_3
value: 60.667
- type: mrr_at_5
value: 61.93300000000001
- type: ndcg_at_1
value: 51.333
- type: ndcg_at_10
value: 67.168
- type: ndcg_at_100
value: 69.833
- type: ndcg_at_1000
value: 70.56700000000001
- type: ndcg_at_3
value: 62.40599999999999
- type: ndcg_at_5
value: 65.029
- type: precision_at_1
value: 51.333
- type: precision_at_10
value: 9.333
- type: precision_at_100
value: 1.0699999999999998
- type: precision_at_1000
value: 0.11299999999999999
- type: precision_at_3
value: 25.333
- type: precision_at_5
value: 17.067
- type: recall_at_1
value: 49.15
- type: recall_at_10
value: 82.533
- type: recall_at_100
value: 94.167
- type: recall_at_1000
value: 99.667
- type: recall_at_3
value: 69.917
- type: recall_at_5
value: 76.356
task:
type: Retrieval
- dataset:
config: default
name: MTEB TRECCOVID-PL
revision: 81bcb408f33366c2a20ac54adafad1ae7e877fdd
split: test
type: clarin-knext/trec-covid-pl
metrics:
- type: map_at_1
value: 0.261
- type: map_at_10
value: 2.1260000000000003
- type: map_at_100
value: 12.171999999999999
- type: map_at_1000
value: 26.884999999999998
- type: map_at_3
value: 0.695
- type: map_at_5
value: 1.134
- type: mrr_at_1
value: 96.0
- type: mrr_at_10
value: 96.952
- type: mrr_at_100
value: 96.952
- type: mrr_at_1000
value: 96.952
- type: mrr_at_3
value: 96.667
- type: mrr_at_5
value: 96.667
- type: ndcg_at_1
value: 92.0
- type: ndcg_at_10
value: 81.193
- type: ndcg_at_100
value: 61.129
- type: ndcg_at_1000
value: 51.157
- type: ndcg_at_3
value: 85.693
- type: ndcg_at_5
value: 84.129
- type: precision_at_1
value: 96.0
- type: precision_at_10
value: 85.39999999999999
- type: precision_at_100
value: 62.03999999999999
- type: precision_at_1000
value: 22.224
- type: precision_at_3
value: 88.0
- type: precision_at_5
value: 88.0
- type: recall_at_1
value: 0.261
- type: recall_at_10
value: 2.262
- type: recall_at_100
value: 14.981
- type: recall_at_1000
value: 46.837
- type: recall_at_3
value: 0.703
- type: recall_at_5
value: 1.172
task:
type: Retrieval
- dataset:
config: default
name: MTEB AlloProfClusteringP2P
revision: 392ba3f5bcc8c51f578786c1fc3dae648662cb9b
split: test
type: lyon-nlp/alloprof
metrics:
- type: v_measure
value: 70.55290063940157
task:
type: Clustering
- dataset:
config: default
name: MTEB AlloProfClusteringS2S
revision: 392ba3f5bcc8c51f578786c1fc3dae648662cb9b
split: test
type: lyon-nlp/alloprof
metrics:
- type: v_measure
value: 55.41500719337263
task:
type: Clustering
- dataset:
config: default
name: MTEB AlloprofReranking
revision: 666fdacebe0291776e86f29345663dfaf80a0db9
split: test
type: lyon-nlp/mteb-fr-reranking-alloprof-s2p
metrics:
- type: map
value: 73.48697375332002
- type: mrr
value: 75.01836585523822
task:
type: Reranking
- dataset:
config: default
name: MTEB AlloprofRetrieval
revision: 392ba3f5bcc8c51f578786c1fc3dae648662cb9b
split: test
type: lyon-nlp/alloprof
metrics:
- type: map_at_1
value: 38.454
- type: map_at_10
value: 51.605000000000004
- type: map_at_100
value: 52.653000000000006
- type: map_at_1000
value: 52.697
- type: map_at_3
value: 48.304
- type: map_at_5
value: 50.073
- type: mrr_at_1
value: 43.307
- type: mrr_at_10
value: 54.400000000000006
- type: mrr_at_100
value: 55.147999999999996
- type: mrr_at_1000
value: 55.174
- type: mrr_at_3
value: 51.77
- type: mrr_at_5
value: 53.166999999999994
- type: ndcg_at_1
value: 43.307
- type: ndcg_at_10
value: 57.891000000000005
- type: ndcg_at_100
value: 62.161
- type: ndcg_at_1000
value: 63.083
- type: ndcg_at_3
value: 51.851
- type: ndcg_at_5
value: 54.605000000000004
- type: precision_at_1
value: 43.307
- type: precision_at_10
value: 9.033
- type: precision_at_100
value: 1.172
- type: precision_at_1000
value: 0.127
- type: precision_at_3
value: 22.798
- type: precision_at_5
value: 15.492
- type: recall_at_1
value: 38.454
- type: recall_at_10
value: 74.166
- type: recall_at_100
value: 92.43599999999999
- type: recall_at_1000
value: 99.071
- type: recall_at_3
value: 58.087
- type: recall_at_5
value: 64.568
task:
type: Retrieval
- dataset:
config: fr
name: MTEB AmazonReviewsClassification (fr)
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
split: test
type: mteb/amazon_reviews_multi
metrics:
- type: accuracy
value: 53.474
- type: f1
value: 50.38275392350236
task:
type: Classification
- dataset:
config: default
name: MTEB BSARDRetrieval
revision: 5effa1b9b5fa3b0f9e12523e6e43e5f86a6e6d59
split: test
type: maastrichtlawtech/bsard
metrics:
- type: map_at_1
value: 2.252
- type: map_at_10
value: 4.661
- type: map_at_100
value: 5.271
- type: map_at_1000
value: 5.3629999999999995
- type: map_at_3
value: 3.604
- type: map_at_5
value: 4.3020000000000005
- type: mrr_at_1
value: 2.252
- type: mrr_at_10
value: 4.661
- type: mrr_at_100
value: 5.271
- type: mrr_at_1000
value: 5.3629999999999995
- type: mrr_at_3
value: 3.604
- type: mrr_at_5
value: 4.3020000000000005
- type: ndcg_at_1
value: 2.252
- type: ndcg_at_10
value: 6.3020000000000005
- type: ndcg_at_100
value: 10.342
- type: ndcg_at_1000
value: 13.475999999999999
- type: ndcg_at_3
value: 4.0649999999999995
- type: ndcg_at_5
value: 5.344
- type: precision_at_1
value: 2.252
- type: precision_at_10
value: 1.171
- type: precision_at_100
value: 0.333
- type: precision_at_1000
value: 0.059000000000000004
- type: precision_at_3
value: 1.802
- type: precision_at_5
value: 1.712
- type: recall_at_1
value: 2.252
- type: recall_at_10
value: 11.712
- type: recall_at_100
value: 33.333
- type: recall_at_1000
value: 59.458999999999996
- type: recall_at_3
value: 5.405
- type: recall_at_5
value: 8.559
task:
type: Retrieval
- dataset:
config: default
name: MTEB HALClusteringS2S
revision: e06ebbbb123f8144bef1a5d18796f3dec9ae2915
split: test
type: lyon-nlp/clustering-hal-s2s
metrics:
- type: v_measure
value: 28.301882091023288
task:
type: Clustering
- dataset:
config: default
name: MTEB MLSUMClusteringP2P
revision: b5d54f8f3b61ae17845046286940f03c6bc79bc7
split: test
type: mlsum
metrics:
- type: v_measure
value: 45.26992995191701
task:
type: Clustering
- dataset:
config: default
name: MTEB MLSUMClusteringS2S
revision: b5d54f8f3b61ae17845046286940f03c6bc79bc7
split: test
type: mlsum
metrics:
- type: v_measure
value: 42.773174876871145
task:
type: Clustering
- dataset:
config: fr
name: MTEB MTOPDomainClassification (fr)
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
split: test
type: mteb/mtop_domain
metrics:
- type: accuracy
value: 93.47635452552458
- type: f1
value: 93.19922617577213
task:
type: Classification
- dataset:
config: fr
name: MTEB MTOPIntentClassification (fr)
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
split: test
type: mteb/mtop_intent
metrics:
- type: accuracy
value: 80.2317569683683
- type: f1
value: 56.18060418621901
task:
type: Classification
- dataset:
config: fra
name: MTEB MasakhaNEWSClassification (fra)
revision: 8ccc72e69e65f40c70e117d8b3c08306bb788b60
split: test
type: masakhane/masakhanews
metrics:
- type: accuracy
value: 85.18957345971565
- type: f1
value: 80.829981537394
task:
type: Classification
- dataset:
config: fra
name: MTEB MasakhaNEWSClusteringP2P (fra)
revision: 8ccc72e69e65f40c70e117d8b3c08306bb788b60
split: test
type: masakhane/masakhanews
metrics:
- type: v_measure
value: 71.04138999801822
task:
type: Clustering
- dataset:
config: fra
name: MTEB MasakhaNEWSClusteringS2S (fra)
revision: 8ccc72e69e65f40c70e117d8b3c08306bb788b60
split: test
type: masakhane/masakhanews
metrics:
- type: v_measure
value: 71.7056263158008
task:
type: Clustering
- dataset:
config: fr
name: MTEB MassiveIntentClassification (fr)
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
split: test
type: mteb/amazon_massive_intent
metrics:
- type: accuracy
value: 76.65097511768661
- type: f1
value: 73.82441070598712
task:
type: Classification
- dataset:
config: fr
name: MTEB MassiveScenarioClassification (fr)
revision: 7d571f92784cd94a019292a1f45445077d0ef634
split: test
type: mteb/amazon_massive_scenario
metrics:
- type: accuracy
value: 79.09885675857431
- type: f1
value: 78.28407777434224
task:
type: Classification
- dataset:
config: fr
name: MTEB MintakaRetrieval (fr)
revision: efa78cc2f74bbcd21eff2261f9e13aebe40b814e
split: test
type: jinaai/mintakaqa
metrics:
- type: map_at_1
value: 25.307000000000002
- type: map_at_10
value: 36.723
- type: map_at_100
value: 37.713
- type: map_at_1000
value: 37.769000000000005
- type: map_at_3
value: 33.77
- type: map_at_5
value: 35.463
- type: mrr_at_1
value: 25.307000000000002
- type: mrr_at_10
value: 36.723
- type: mrr_at_100
value: 37.713
- type: mrr_at_1000
value: 37.769000000000005
- type: mrr_at_3
value: 33.77
- type: mrr_at_5
value: 35.463
- type: ndcg_at_1
value: 25.307000000000002
- type: ndcg_at_10
value: 42.559999999999995
- type: ndcg_at_100
value: 47.457
- type: ndcg_at_1000
value: 49.162
- type: ndcg_at_3
value: 36.461
- type: ndcg_at_5
value: 39.504
- type: precision_at_1
value: 25.307000000000002
- type: precision_at_10
value: 6.106
- type: precision_at_100
value: 0.8420000000000001
- type: precision_at_1000
value: 0.098
- type: precision_at_3
value: 14.741999999999999
- type: precision_at_5
value: 10.319
- type: recall_at_1
value: 25.307000000000002
- type: recall_at_10
value: 61.056999999999995
- type: recall_at_100
value: 84.152
- type: recall_at_1000
value: 98.03399999999999
- type: recall_at_3
value: 44.226
- type: recall_at_5
value: 51.597
task:
type: Retrieval
- dataset:
config: fr
name: MTEB OpusparcusPC (fr)
revision: 9e9b1f8ef51616073f47f306f7f47dd91663f86a
split: test
type: GEM/opusparcus
metrics:
- type: cos_sim_accuracy
value: 99.90069513406156
- type: cos_sim_ap
value: 100.0
- type: cos_sim_f1
value: 99.95032290114257
- type: cos_sim_precision
value: 100.0
- type: cos_sim_recall
value: 99.90069513406156
- type: dot_accuracy
value: 99.90069513406156
- type: dot_ap
value: 100.0
- type: dot_f1
value: 99.95032290114257
- type: dot_precision
value: 100.0
- type: dot_recall
value: 99.90069513406156
- type: euclidean_accuracy
value: 99.90069513406156
- type: euclidean_ap
value: 100.0
- type: euclidean_f1
value: 99.95032290114257
- type: euclidean_precision
value: 100.0
- type: euclidean_recall
value: 99.90069513406156
- type: manhattan_accuracy
value: 99.90069513406156
- type: manhattan_ap
value: 100.0
- type: manhattan_f1
value: 99.95032290114257
- type: manhattan_precision
value: 100.0
- type: manhattan_recall
value: 99.90069513406156
- type: max_accuracy
value: 99.90069513406156
- type: max_ap
value: 100.0
- type: max_f1
value: 99.95032290114257
task:
type: PairClassification
- dataset:
config: fr
name: MTEB PawsX (fr)
revision: 8a04d940a42cd40658986fdd8e3da561533a3646
split: test
type: paws-x
metrics:
- type: cos_sim_accuracy
value: 70.8
- type: cos_sim_ap
value: 73.7671529695957
- type: cos_sim_f1
value: 68.80964339527875
- type: cos_sim_precision
value: 62.95955882352941
- type: cos_sim_recall
value: 75.85825027685493
- type: dot_accuracy
value: 70.8
- type: dot_ap
value: 73.78345265366947
- type: dot_f1
value: 68.80964339527875
- type: dot_precision
value: 62.95955882352941
- type: dot_recall
value: 75.85825027685493
- type: euclidean_accuracy
value: 70.8
- type: euclidean_ap
value: 73.7671529695957
- type: euclidean_f1
value: 68.80964339527875
- type: euclidean_precision
value: 62.95955882352941
- type: euclidean_recall
value: 75.85825027685493
- type: manhattan_accuracy
value: 70.75
- type: manhattan_ap
value: 73.78996383615953
- type: manhattan_f1
value: 68.79432624113475
- type: manhattan_precision
value: 63.39869281045751
- type: manhattan_recall
value: 75.1937984496124
- type: max_accuracy
value: 70.8
- type: max_ap
value: 73.78996383615953
- type: max_f1
value: 68.80964339527875
task:
type: PairClassification
- dataset:
config: default
name: MTEB SICKFr
revision: e077ab4cf4774a1e36d86d593b150422fafd8e8a
split: test
type: Lajavaness/SICK-fr
metrics:
- type: cos_sim_pearson
value: 84.03253762760392
- type: cos_sim_spearman
value: 79.68280105762004
- type: euclidean_pearson
value: 80.98265050044444
- type: euclidean_spearman
value: 79.68233242682867
- type: manhattan_pearson
value: 80.9678911810704
- type: manhattan_spearman
value: 79.70264097683109
task:
type: STS
- dataset:
config: fr
name: MTEB STS22 (fr)
revision: eea2b4fe26a775864c896887d910b76a8098ad3f
split: test
type: mteb/sts22-crosslingual-sts
metrics:
- type: cos_sim_pearson
value: 80.56896987572884
- type: cos_sim_spearman
value: 81.84352499523287
- type: euclidean_pearson
value: 80.40831759421305
- type: euclidean_spearman
value: 81.84352499523287
- type: manhattan_pearson
value: 80.74333857561238
- type: manhattan_spearman
value: 82.41503246733892
task:
type: STS
- dataset:
config: fr
name: MTEB STSBenchmarkMultilingualSTS (fr)
revision: 93d57ef91790589e3ce9c365164337a8a78b7632
split: test
type: stsb_multi_mt
metrics:
- type: cos_sim_pearson
value: 82.71826762276979
- type: cos_sim_spearman
value: 82.25433354916042
- type: euclidean_pearson
value: 81.87115571724316
- type: euclidean_spearman
value: 82.25322342890107
- type: manhattan_pearson
value: 82.11174867527224
- type: manhattan_spearman
value: 82.55905365203084
task:
type: STS
- dataset:
config: default
name: MTEB SummEvalFr
revision: b385812de6a9577b6f4d0f88c6a6e35395a94054
split: test
type: lyon-nlp/summarization-summeval-fr-p2p
metrics:
- type: cos_sim_pearson
value: 30.659441623392887
- type: cos_sim_spearman
value: 30.501134097353315
- type: dot_pearson
value: 30.659444768851056
- type: dot_spearman
value: 30.501134097353315
task:
type: Summarization
- dataset:
config: default
name: MTEB SyntecReranking
revision: b205c5084a0934ce8af14338bf03feb19499c84d
split: test
type: lyon-nlp/mteb-fr-reranking-syntec-s2p
metrics:
- type: map
value: 94.03333333333333
- type: mrr
value: 94.03333333333333
task:
type: Reranking
- dataset:
config: default
name: MTEB SyntecRetrieval
revision: 77f7e271bf4a92b24fce5119f3486b583ca016ff
split: test
type: lyon-nlp/mteb-fr-retrieval-syntec-s2p
metrics:
- type: map_at_1
value: 79.0
- type: map_at_10
value: 87.61
- type: map_at_100
value: 87.655
- type: map_at_1000
value: 87.655
- type: map_at_3
value: 87.167
- type: map_at_5
value: 87.36699999999999
- type: mrr_at_1
value: 79.0
- type: mrr_at_10
value: 87.61
- type: mrr_at_100
value: 87.655
- type: mrr_at_1000
value: 87.655
- type: mrr_at_3
value: 87.167
- type: mrr_at_5
value: 87.36699999999999
- type: ndcg_at_1
value: 79.0
- type: ndcg_at_10
value: 90.473
- type: ndcg_at_100
value: 90.694
- type: ndcg_at_1000
value: 90.694
- type: ndcg_at_3
value: 89.464
- type: ndcg_at_5
value: 89.851
- type: precision_at_1
value: 79.0
- type: precision_at_10
value: 9.9
- type: precision_at_100
value: 1.0
- type: precision_at_1000
value: 0.1
- type: precision_at_3
value: 32.0
- type: precision_at_5
value: 19.400000000000002
- type: recall_at_1
value: 79.0
- type: recall_at_10
value: 99.0
- type: recall_at_100
value: 100.0
- type: recall_at_1000
value: 100.0
- type: recall_at_3
value: 96.0
- type: recall_at_5
value: 97.0
task:
type: Retrieval
- dataset:
config: fr
name: MTEB XPQARetrieval (fr)
revision: c99d599f0a6ab9b85b065da6f9d94f9cf731679f
split: test
type: jinaai/xpqa
metrics:
- type: map_at_1
value: 39.395
- type: map_at_10
value: 59.123999999999995
- type: map_at_100
value: 60.704
- type: map_at_1000
value: 60.760000000000005
- type: map_at_3
value: 53.187
- type: map_at_5
value: 56.863
- type: mrr_at_1
value: 62.083
- type: mrr_at_10
value: 68.87299999999999
- type: mrr_at_100
value: 69.46900000000001
- type: mrr_at_1000
value: 69.48299999999999
- type: mrr_at_3
value: 66.8
- type: mrr_at_5
value: 67.928
- type: ndcg_at_1
value: 62.083
- type: ndcg_at_10
value: 65.583
- type: ndcg_at_100
value: 70.918
- type: ndcg_at_1000
value: 71.72800000000001
- type: ndcg_at_3
value: 60.428000000000004
- type: ndcg_at_5
value: 61.853
- type: precision_at_1
value: 62.083
- type: precision_at_10
value: 15.033
- type: precision_at_100
value: 1.9529999999999998
- type: precision_at_1000
value: 0.207
- type: precision_at_3
value: 36.315
- type: precision_at_5
value: 25.955000000000002
- type: recall_at_1
value: 39.395
- type: recall_at_10
value: 74.332
- type: recall_at_100
value: 94.729
- type: recall_at_1000
value: 99.75500000000001
- type: recall_at_3
value: 57.679
- type: recall_at_5
value: 65.036
task:
type: Retrieval
---
## gte-Qwen2-1.5B-instruct
**gte-Qwen2-1.5B-instruct** is the latest model in the gte (General Text Embedding) model family. The model is built on [Qwen2-1.5B](https://huggingface.co/Qwen/Qwen2-1.5B) LLM model and use the same training data and strategies as the [gte-Qwen2-7B-instruct](https://huggingface.co/Alibaba-NLP/gte-Qwen2-7B-instruct) model.
The model incorporates several key advancements:
- Integration of bidirectional attention mechanisms, enriching its contextual understanding.
- Instruction tuning, applied solely on the query side for streamlined efficiency
- Comprehensive training across a vast, multilingual text corpus spanning diverse domains and scenarios. This training leverages both weakly supervised and supervised data, ensuring the model's applicability across numerous languages and a wide array of downstream tasks.
## Model Information
- Model Size: 1.5B
- Embedding Dimension: 1536
- Max Input Tokens: 32k
## Requirements
```
transformers>=4.39.2
flash_attn>=2.5.6
```
## Usage
### Sentence Transformers
```python
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("Alibaba-NLP/gte-Qwen2-1.5B-instruct", trust_remote_code=True)
# In case you want to reduce the maximum length:
model.max_seq_length = 8192
queries = [
"how much protein should a female eat",
"summit define",
]
documents = [
"As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 is 46 grams per day. But, as you can see from this chart, you'll need to increase that if you're expecting or training for a marathon. Check out the chart below to see how much protein you should be eating each day.",
"Definition of summit for English Language Learners. : 1 the highest point of a mountain : the top of a mountain. : 2 the highest level. : 3 a meeting or series of meetings between the leaders of two or more governments.",
]
query_embeddings = model.encode(queries, prompt_name="query")
document_embeddings = model.encode(documents)
scores = (query_embeddings @ document_embeddings.T) * 100
print(scores.tolist())
```
Observe the [config_sentence_transformers.json](config_sentence_transformers.json) to see all pre-built prompt names. Otherwise, you can use `model.encode(queries, prompt="Instruct: ...\nQuery: "` to use a custom prompt of your choice.
### Transformers
```python
import torch
import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel
def last_token_pool(last_hidden_states: Tensor,
attention_mask: Tensor) -> Tensor:
left_padding = (attention_mask[:, -1].sum() == attention_mask.shape[0])
if left_padding:
return last_hidden_states[:, -1]
else:
sequence_lengths = attention_mask.sum(dim=1) - 1
batch_size = last_hidden_states.shape[0]
return last_hidden_states[torch.arange(batch_size, device=last_hidden_states.device), sequence_lengths]
def get_detailed_instruct(task_description: str, query: str) -> str:
return f'Instruct: {task_description}\nQuery: {query}'
# Each query must come with a one-sentence instruction that describes the task
task = 'Given a web search query, retrieve relevant passages that answer the query'
queries = [
get_detailed_instruct(task, 'how much protein should a female eat'),
get_detailed_instruct(task, 'summit define')
]
# No need to add instruction for retrieval documents
documents = [
"As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 is 46 grams per day. But, as you can see from this chart, you'll need to increase that if you're expecting or training for a marathon. Check out the chart below to see how much protein you should be eating each day.",
"Definition of summit for English Language Learners. : 1 the highest point of a mountain : the top of a mountain. : 2 the highest level. : 3 a meeting or series of meetings between the leaders of two or more governments."
]
input_texts = queries + documents
tokenizer = AutoTokenizer.from_pretrained('Alibaba-NLP/gte-Qwen2-1.5B-instruct', trust_remote_code=True)
model = AutoModel.from_pretrained('Alibaba-NLP/gte-Qwen2-1.5B-instruct', trust_remote_code=True)
max_length = 8192
# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=max_length, padding=True, truncation=True, return_tensors='pt')
outputs = model(**batch_dict)
embeddings = last_token_pool(outputs.last_hidden_state, batch_dict['attention_mask'])
# normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:2] @ embeddings[2:].T) * 100
print(scores.tolist())
```
## Evaluation
### MTEB & C-MTEB
You can use the [scripts/eval_mteb.py](https://huggingface.co/Alibaba-NLP/gte-Qwen2-7B-instruct/blob/main/scripts/eval_mteb.py) to reproduce the following result of **gte-Qwen2-1.5B-instruct** on MTEB(English)/C-MTEB(Chinese):
| Model Name | MTEB(56) | C-MTEB(35) | MTEB-fr(26) | MTEB-pl(26) |
|:----:|:---------:|:----------:|:----------:|:----------:|
| [bge-base-en-1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) | 64.23 | - | - | - |
| [bge-large-en-1.5](https://huggingface.co/BAAI/bge-large-en-v1.5) | 63.55 | - | - | - |
| [gte-large-en-v1.5](https://huggingface.co/Alibaba-NLP/gte-large-en-v1.5) | 65.39 | - | - | - |
| [gte-base-en-v1.5](https://huggingface.co/Alibaba-NLP/gte-large-en-v1.5) | 64.11 | - | - | - |
| [mxbai-embed-large-v1](https://huggingface.co/mixedbread-ai/mxbai-embed-large-v1) | 64.68 | - | - | - |
| [acge_text_embedding](https://huggingface.co/aspire/acge_text_embedding) | - | 69.07 | - | - |
| [stella-mrl-large-zh-v3.5-1792d](https://huggingface.co/infgrad/stella-mrl-large-zh-v3.5-1792d) | - | 68.55 | - | - |
| [gte-large-zh](https://huggingface.co/thenlper/gte-large-zh) | - | 66.72 | - | - |
| [multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base) | 59.45 | 56.21 | - | - |
| [multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large) | 61.50 | 58.81 | - | - |
| [e5-mistral-7b-instruct](https://huggingface.co/intfloat/e5-mistral-7b-instruct) | 66.63 | 60.81 | - | - |
| [gte-Qwen1.5-7B-instruct](https://huggingface.co/Alibaba-NLP/gte-Qwen1.5-7B-instruct) | 67.34 | 69.52 | - | - |
| [NV-Embed-v1](https://huggingface.co/nvidia/NV-Embed-v1) | 69.32 | - | - | - |
| [**gte-Qwen2-7B-instruct**](https://huggingface.co/Alibaba-NLP/gte-Qwen2-7B-instruct) | **70.24** | **72.05** | **68.25** | **67.86** |
| [**gte-Qwen2-1.5B-instruct**](https://huggingface.co/Alibaba-NLP/gte-Qwen2-1.5B-instruct) | **67.16** | **67.65** | **66.60** | **64.04** |
### GTE Models
The gte series models have consistently released two types of models: encoder-only models (based on the BERT architecture) and decode-only models (based on the LLM architecture).
| Models | Language | Max Sequence Length | Dimension | Model Size (Memory Usage, fp32) |
|:-------------------------------------------------------------------------------------:|:--------:|:-----: |:---------:|:-------------------------------:|
| [GTE-large-zh](https://huggingface.co/thenlper/gte-large-zh) | Chinese | 512 | 1024 | 1.25GB |
| [GTE-base-zh](https://huggingface.co/thenlper/gte-base-zh) | Chinese | 512 | 512 | 0.41GB |
| [GTE-small-zh](https://huggingface.co/thenlper/gte-small-zh) | Chinese | 512 | 512 | 0.12GB |
| [GTE-large](https://huggingface.co/thenlper/gte-large) | English | 512 | 1024 | 1.25GB |
| [GTE-base](https://huggingface.co/thenlper/gte-base) | English | 512 | 512 | 0.21GB |
| [GTE-small](https://huggingface.co/thenlper/gte-small) | English | 512 | 384 | 0.10GB |
| [GTE-large-en-v1.5](https://huggingface.co/Alibaba-NLP/gte-large-en-v1.5) | English | 8192 | 1024 | 1.74GB |
| [GTE-base-en-v1.5](https://huggingface.co/Alibaba-NLP/gte-base-en-v1.5) | English | 8192 | 768 | 0.51GB |
| [GTE-Qwen1.5-7B-instruct](https://huggingface.co/Alibaba-NLP/gte-Qwen1.5-7B-instruct) | Multilingual | 32000 | 4096 | 26.45GB |
| [GTE-Qwen2-7B-instruct](https://huggingface.co/Alibaba-NLP/gte-Qwen2-7B-instruct) | Multilingual | 32000 | 3584 | 26.45GB |
| [GTE-Qwen2-1.5B-instruct](https://huggingface.co/Alibaba-NLP/gte-Qwen2-1.5B-instruct) | Multilingual | 32000 | 1536 | 6.62GB |
## Cloud API Services
In addition to the open-source [GTE](https://huggingface.co/collections/Alibaba-NLP/gte-models-6680f0b13f885cb431e6d469) series models, GTE series models are also available as commercial API services on Alibaba Cloud.
- [Embedding Models](https://help.aliyun.com/zh/model-studio/developer-reference/general-text-embedding/): Rhree versions of the text embedding models are available: text-embedding-v1/v2/v3, with v3 being the latest API service.
- [ReRank Models](https://help.aliyun.com/zh/model-studio/developer-reference/general-text-sorting-model/): The gte-rerank model service is available.
Note that the models behind the commercial APIs are not entirely identical to the open-source models.
## Citation
If you find our paper or models helpful, please consider cite:
```
@article{li2023towards,
title={Towards general text embeddings with multi-stage contrastive learning},
author={Li, Zehan and Zhang, Xin and Zhang, Yanzhao and Long, Dingkun and Xie, Pengjun and Zhang, Meishan},
journal={arXiv preprint arXiv:2308.03281},
year={2023}
}
```
| [
"SUMMARIZATION"
] | Non_BioNLP |
Gyaneshere/distilbert-base-uncased-finetuned-sst-2-english-ONNX | Gyaneshere | null | [
"onnx",
"distilbert",
"en",
"dataset:sst2",
"dataset:glue",
"arxiv:1910.01108",
"license:apache-2.0",
"model-index",
"region:us"
] | 1,739,932,807,000 | 2025-02-19T02:46:07 | 25 | 0 | ---
datasets:
- sst2
- glue
language: en
license: apache-2.0
model-index:
- name: distilbert-base-uncased-finetuned-sst-2-english-ONNX
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: glue
type: glue
config: sst2
split: validation
metrics:
- type: accuracy
value: 0.9105504587155964
name: Accuracy
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiN2YyOGMxYjY2Y2JhMjkxNjIzN2FmMjNiNmM2ZWViNGY3MTNmNWI2YzhiYjYxZTY0ZGUyN2M1NGIxZjRiMjQwZiIsInZlcnNpb24iOjF9.uui0srxV5ZHRhxbYN6082EZdwpnBgubPJ5R2-Wk8HTWqmxYE3QHidevR9LLAhidqGw6Ih93fK0goAXncld_gBg
- type: precision
value: 0.8978260869565218
name: Precision
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzgwYTYwYjA2MmM0ZTYwNDk0M2NmNTBkZmM2NGNhYzQ1OGEyN2NkNDQ3Mzc2NTQyMmZiNDJiNzBhNGVhZGUyOSIsInZlcnNpb24iOjF9.eHjLmw3K02OU69R2Au8eyuSqT3aBDHgZCn8jSzE3_urD6EUSSsLxUpiAYR4BGLD_U6-ZKcdxVo_A2rdXqvUJDA
- type: recall
value: 0.9301801801801802
name: Recall
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMGIzM2E3MTI2Mzc2MDYwNmU3ZTVjYmZmZDBkNjY4ZTc5MGY0Y2FkNDU3NjY1MmVkNmE3Y2QzMzAwZDZhOWY1NiIsInZlcnNpb24iOjF9.PUZlqmct13-rJWBXdHm5tdkXgETL9F82GNbbSR4hI8MB-v39KrK59cqzFC2Ac7kJe_DtOeUyosj34O_mFt_1DQ
- type: auc
value: 0.9716626673402374
name: AUC
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMDM0YWIwZmQ4YjUwOGZmMWU2MjI1YjIxZGQ2MzNjMzRmZmYxMzZkNGFjODhlMDcyZDM1Y2RkMWZlOWQ0MWYwNSIsInZlcnNpb24iOjF9.E7GRlAXmmpEkTHlXheVkuL1W4WNjv4JO3qY_WCVsTVKiO7bUu0UVjPIyQ6g-J1OxsfqZmW3Leli1wY8vPBNNCQ
- type: f1
value: 0.9137168141592922
name: F1
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMGU4MjNmOGYwZjZjMDQ1ZTkyZTA4YTc1MWYwOTM0NDM4ZWY1ZGVkNDY5MzNhYTQyZGFlNzIyZmUwMDg3NDU0NyIsInZlcnNpb24iOjF9.mW5ftkq50Se58M-jm6a2Pu93QeKa3MfV7xcBwvG3PSB_KNJxZWTCpfMQp-Cmx_EMlmI2siKOyd8akYjJUrzJCA
- type: loss
value: 0.39013850688934326
name: loss
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTZiNzAyZDc0MzUzMmE1MGJiN2JlYzFiODE5ZTNlNGE4MmI4YzRiMTc2ODEzMTUwZmEzOTgxNzc4YjJjZTRmNiIsInZlcnNpb24iOjF9.VqIC7uYC-ZZ8ss9zQOlRV39YVOOLc5R36sIzCcVz8lolh61ux_5djm2XjpP6ARc6KqEnXC4ZtfNXsX2HZfrtCQ
- task:
type: text-classification
name: Text Classification
dataset:
name: sst2
type: sst2
config: default
split: train
metrics:
- type: accuracy
value: 0.9885521685548412
name: Accuracy
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiY2I3NzU3YzhmMDkxZTViY2M3OTY1NmI0ZTdmMDQxNjNjYzJiZmQxNzczM2E4YmExYTY5ODY0NDBkY2I4ZjNkOCIsInZlcnNpb24iOjF9.4Gtk3FeVc9sPWSqZIaeUXJ9oVlPzm-NmujnWpK2y5s1Vhp1l6Y1pK5_78wW0-NxSvQqV6qd5KQf_OAEpVAkQDA
- type: precision
value: 0.9881965062029833
name: Precision Macro
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZDdlZDMzY2I3MTAwYTljNmM4MGMyMzU2YjAzZDg1NDYwN2ZmM2Y5OWZhMjUyMGJiNjY1YmZiMzFhMDI2ODFhNyIsInZlcnNpb24iOjF9.cqmv6yBxu4St2mykRWrZ07tDsiSLdtLTz2hbqQ7Gm1rMzq9tdlkZ8MyJRxtME_Y8UaOG9rs68pV-gKVUs8wABw
- type: precision
value: 0.9885521685548412
name: Precision Micro
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZjFlYzAzNmE1YjljNjUwNzBjZjEzZDY0ZDQyMmY5ZWM2OTBhNzNjYjYzYTk1YWE1NjU3YTMxZDQwOTE1Y2FkNyIsInZlcnNpb24iOjF9.jnCHOkUHuAOZZ_ZMVOnetx__OVJCS6LOno4caWECAmfrUaIPnPNV9iJ6izRO3sqkHRmxYpWBb-27GJ4N3LU-BQ
- type: precision
value: 0.9885639626373408
name: Precision Weighted
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZGUyODFjNjBlNTE2MTY3ZDAxOGU1N2U0YjUyY2NiZjhkOGVmYThjYjBkNGU3NTRkYzkzNDQ2MmMwMjkwMWNiMyIsInZlcnNpb24iOjF9.zTNabMwApiZyXdr76QUn7WgGB7D7lP-iqS3bn35piqVTNsv3wnKjZOaKFVLIUvtBXq4gKw7N2oWxvWc4OcSNDg
- type: recall
value: 0.9886145346602994
name: Recall Macro
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNTU1YjlhODU3YTkyNTdiZDcwZGFlZDBiYjY0N2NjMGM2NTRiNjQ3MDNjNGMxOWY2ZGQ4NWU1YmMzY2UwZTI3YSIsInZlcnNpb24iOjF9.xaLPY7U-wHsJ3DDui1yyyM-xWjL0Jz5puRThy7fczal9x05eKEQ9s0a_WD-iLmapvJs0caXpV70hDe2NLcs-DA
- type: recall
value: 0.9885521685548412
name: Recall Micro
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiODE0YTU0MDBlOGY4YzU0MjY5MzA3OTk2OGNhOGVkMmU5OGRjZmFiZWI2ZjY5ODEzZTQzMTI0N2NiOTVkNDliYiIsInZlcnNpb24iOjF9.SOt1baTBbuZRrsvGcak2sUwoTrQzmNCbyV2m1_yjGsU48SBH0NcKXicidNBSnJ6ihM5jf_Lv_B5_eOBkLfNWDQ
- type: recall
value: 0.9885521685548412
name: Recall Weighted
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZWNkNmM0ZGRlNmYxYzIwNDk4OTI5MzIwZWU1NzZjZDVhMDcyNDFlMjBhNDQxODU5OWMwMWNhNGEzNjY3ZGUyOSIsInZlcnNpb24iOjF9.b15Fh70GwtlG3cSqPW-8VEZT2oy0CtgvgEOtWiYonOovjkIQ4RSLFVzVG-YfslaIyfg9RzMWzjhLnMY7Bpn2Aw
- type: f1
value: 0.9884019815052447
name: F1 Macro
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYmM4NjQ5Yjk5ODRhYTU1MTY3MmRhZDBmODM1NTg3OTFiNWM4NDRmYjI0MzZkNmQ1MzE3MzcxODZlYzBkYTMyYSIsInZlcnNpb24iOjF9.74RaDK8nBVuGRl2Se_-hwQvP6c4lvVxGHpcCWB4uZUCf2_HoC9NT9u7P3pMJfH_tK2cpV7U3VWGgSDhQDi-UBQ
- type: f1
value: 0.9885521685548412
name: F1 Micro
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZDRmYWRmMmQ0YjViZmQxMzhhYTUyOTE1MTc0ZDU1ZjQyZjFhMDYzYzMzZDE0NzZlYzQyOTBhMTBhNmM5NTlkMiIsInZlcnNpb24iOjF9.VMn_psdAHIZTlW6GbjERZDe8MHhwzJ0rbjV_VJyuMrsdOh5QDmko-wEvaBWNEdT0cEKsbggm-6jd3Gh81PfHAQ
- type: f1
value: 0.9885546181087554
name: F1 Weighted
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMjUyZWFhZDZhMGQ3MzBmYmRiNDVmN2FkZDBjMjk3ODk0OTAxNGZkMWE0NzU5ZjI0NzE0NGZiNzM0N2Y2NDYyOSIsInZlcnNpb24iOjF9.YsXBhnzEEFEW6jw3mQlFUuIrW7Gabad2Ils-iunYJr-myg0heF8NEnEWABKFE1SnvCWt-69jkLza6SupeyLVCA
- type: loss
value: 0.040652573108673096
name: loss
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTc3YjU3MjdjMzkxODA5MjU5NGUyY2NkMGVhZDg3ZWEzMmU1YWVjMmI0NmU2OWEyZTkzMTVjNDZiYTc0YjIyNCIsInZlcnNpb24iOjF9.lA90qXZVYiILHMFlr6t6H81Oe8a-4KmeX-vyCC1BDia2ofudegv6Vb46-4RzmbtuKeV6yy6YNNXxXxqVak1pAg
---
# DistilBERT base uncased finetuned SST-2
## Table of Contents
- [Model Details](#model-details)
- [How to Get Started With the Model](#how-to-get-started-with-the-model)
- [Uses](#uses)
- [Risks, Limitations and Biases](#risks-limitations-and-biases)
- [Training](#training)
## Model Details
**Model Description:** This model is a fine-tune checkpoint of [DistilBERT-base-uncased](https://huggingface.co/distilbert-base-uncased), fine-tuned on SST-2.
This model reaches an accuracy of 91.3 on the dev set (for comparison, Bert bert-base-uncased version reaches an accuracy of 92.7).
- **Developed by:** Hugging Face
- **Model Type:** Text Classification
- **Language(s):** English
- **License:** Apache-2.0
- **Parent Model:** For more details about DistilBERT, we encourage users to check out [this model card](https://huggingface.co/distilbert-base-uncased).
- **Resources for more information:**
- [Model Documentation](https://huggingface.co/docs/transformers/main/en/model_doc/distilbert#transformers.DistilBertForSequenceClassification)
- [DistilBERT paper](https://arxiv.org/abs/1910.01108)
## How to Get Started With the Model
Example of single-label classification:
```python
import torch
from transformers import DistilBertTokenizer, DistilBertForSequenceClassification
tokenizer = DistilBertTokenizer.from_pretrained("distilbert-base-uncased-finetuned-sst-2-english")
model = DistilBertForSequenceClassification.from_pretrained("distilbert-base-uncased-finetuned-sst-2-english")
inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
with torch.no_grad():
logits = model(**inputs).logits
predicted_class_id = logits.argmax().item()
model.config.id2label[predicted_class_id]
```
## Uses
#### Direct Use
This model can be used for topic classification. You can use the raw model for either masked language modeling or next sentence prediction, but it's mostly intended to be fine-tuned on a downstream task. See the model hub to look for fine-tuned versions on a task that interests you.
#### Misuse and Out-of-scope Use
The model should not be used to intentionally create hostile or alienating environments for people. In addition, the model was not trained to be factual or true representations of people or events, and therefore using the model to generate such content is out-of-scope for the abilities of this model.
## Risks, Limitations and Biases
Based on a few experimentations, we observed that this model could produce biased predictions that target underrepresented populations.
For instance, for sentences like `This film was filmed in COUNTRY`, this binary classification model will give radically different probabilities for the positive label depending on the country (0.89 if the country is France, but 0.08 if the country is Afghanistan) when nothing in the input indicates such a strong semantic shift. In this [colab](https://colab.research.google.com/gist/ageron/fb2f64fb145b4bc7c49efc97e5f114d3/biasmap.ipynb), [Aurélien Géron](https://twitter.com/aureliengeron) made an interesting map plotting these probabilities for each country.
<img src="https://huggingface.co/distilbert-base-uncased-finetuned-sst-2-english/resolve/main/map.jpeg" alt="Map of positive probabilities per country." width="500"/>
We strongly advise users to thoroughly probe these aspects on their use-cases in order to evaluate the risks of this model. We recommend looking at the following bias evaluation datasets as a place to start: [WinoBias](https://huggingface.co/datasets/wino_bias), [WinoGender](https://huggingface.co/datasets/super_glue), [Stereoset](https://huggingface.co/datasets/stereoset).
# Training
#### Training Data
The authors use the following Stanford Sentiment Treebank([sst2](https://huggingface.co/datasets/sst2)) corpora for the model.
#### Training Procedure
###### Fine-tuning hyper-parameters
- learning_rate = 1e-5
- batch_size = 32
- warmup = 600
- max_seq_length = 128
- num_train_epochs = 3.0
| [
"TEXT_CLASSIFICATION"
] | Non_BioNLP |
apwic/liputan6-lora-8 | apwic | null | [
"generated_from_trainer",
"id",
"dataset:id_liputan6",
"base_model:LazarusNLP/IndoNanoT5-base",
"base_model:finetune:LazarusNLP/IndoNanoT5-base",
"license:apache-2.0",
"model-index",
"region:us"
] | 1,721,688,539,000 | 2024-07-23T10:37:05 | 0 | 0 | ---
base_model: LazarusNLP/IndoNanoT5-base
datasets:
- id_liputan6
language:
- id
license: apache-2.0
metrics:
- rouge
tags:
- generated_from_trainer
model-index:
- name: liputan6-lora-8
results:
- task:
type: summarization
name: Summarization
dataset:
name: id_liputan6 canonical
type: id_liputan6
config: canonical
split: validation
args: canonical
metrics:
- type: rouge
value: 44.041
name: Rouge1
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# liputan6-lora-8
This model is a fine-tuned version of [LazarusNLP/IndoNanoT5-base](https://huggingface.co/LazarusNLP/IndoNanoT5-base) on the id_liputan6 canonical dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2482
- Rouge1: 44.041
- Rouge2: 35.4021
- Rougel: 40.435
- Rougelsum: 42.6248
- Gen Len: 60.602
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.001
- train_batch_size: 16
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
| 1.4611 | 1.0 | 63 | 0.4168 | 20.2294 | 15.1672 | 18.3462 | 19.5551 | 26.342 |
| 0.6123 | 2.0 | 126 | 0.3030 | 42.4943 | 33.9837 | 39.042 | 40.9843 | 54.709 |
| 0.4836 | 3.0 | 189 | 0.2516 | 39.2983 | 30.3972 | 36.1696 | 37.7681 | 48.258 |
| 0.4256 | 4.0 | 252 | 0.2482 | 42.8202 | 33.9496 | 39.2137 | 41.343 | 54.56 |
| 0.4014 | 5.0 | 315 | 0.2389 | 42.5107 | 33.6017 | 39.0118 | 41.0601 | 55.005 |
### Framework versions
- Transformers 4.40.2
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
| [
"SUMMARIZATION"
] | Non_BioNLP |
SEBIS/legal_t5_small_trans_cs_it | SEBIS | text2text-generation | [
"transformers",
"pytorch",
"jax",
"t5",
"text2text-generation",
"translation Cszech Italian model",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 1,646,263,744,000 | 2021-06-23T11:35:03 | 202 | 0 | ---
datasets:
- dcep europarl jrc-acquis
language: Cszech Italian
tags:
- translation Cszech Italian model
widget:
- text: – Měly by se podporovat normy sportovní správy prostřednictvím výměny osvědčených
postupů.
---
# legal_t5_small_trans_cs_it model
Model on translating legal text from Cszech to Italian. It was first released in
[this repository](https://github.com/agemagician/LegalTrans). This model is trained on three parallel corpus from jrc-acquis, europarl and dcep.
## Model description
legal_t5_small_trans_cs_it is based on the `t5-small` model and was trained on a large corpus of parallel text. This is a smaller model, which scales the baseline model of t5 down by using `dmodel = 512`, `dff = 2,048`, 8-headed attention, and only 6 layers each in the encoder and decoder. This variant has about 60 million parameters.
## Intended uses & limitations
The model could be used for translation of legal texts from Cszech to Italian.
### How to use
Here is how to use this model to translate legal text from Cszech to Italian in PyTorch:
```python
from transformers import AutoTokenizer, AutoModelWithLMHead, TranslationPipeline
pipeline = TranslationPipeline(
model=AutoModelWithLMHead.from_pretrained("SEBIS/legal_t5_small_trans_cs_it"),
tokenizer=AutoTokenizer.from_pretrained(pretrained_model_name_or_path = "SEBIS/legal_t5_small_trans_cs_it", do_lower_case=False,
skip_special_tokens=True),
device=0
)
cs_text = "– Měly by se podporovat normy sportovní správy prostřednictvím výměny osvědčených postupů."
pipeline([cs_text], max_length=512)
```
## Training data
The legal_t5_small_trans_cs_it model was trained on [JRC-ACQUIS](https://wt-public.emm4u.eu/Acquis/index_2.2.html), [EUROPARL](https://www.statmt.org/europarl/), and [DCEP](https://ec.europa.eu/jrc/en/language-technologies/dcep) dataset consisting of 5 Million parallel texts.
## Training procedure
The model was trained on a single TPU Pod V3-8 for 250K steps in total, using sequence length 512 (batch size 4096). It has a total of approximately 220M parameters and was trained using the encoder-decoder architecture. The optimizer used is AdaFactor with inverse square root learning rate schedule for pre-training.
### Preprocessing
An unigram model trained with 88M lines of text from the parallel corpus (of all possible language pairs) to get the vocabulary (with byte pair encoding), which is used with this model.
### Pretraining
## Evaluation results
When the model is used for translation test dataset, achieves the following results:
Test results :
| Model | BLEU score |
|:-----:|:-----:|
| legal_t5_small_trans_cs_it | 46.67|
### BibTeX entry and citation info
> Created by [Ahmed Elnaggar/@Elnaggar_AI](https://twitter.com/Elnaggar_AI) | [LinkedIn](https://www.linkedin.com/in/prof-ahmed-elnaggar/)
| [
"TRANSLATION"
] | Non_BioNLP |
raisin2402/marian-finetuned-kde4-en-to-fr | raisin2402 | translation | [
"transformers",
"pytorch",
"tensorboard",
"marian",
"text2text-generation",
"translation",
"generated_from_trainer",
"dataset:kde4",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 1,659,092,919,000 | 2022-07-29T12:59:05 | 12 | 1 | ---
datasets:
- kde4
license: apache-2.0
metrics:
- bleu
tags:
- translation
- generated_from_trainer
model-index:
- name: marian-finetuned-kde4-en-to-fr
results:
- task:
type: text2text-generation
name: Sequence-to-sequence Language Modeling
dataset:
name: kde4
type: kde4
config: en-fr
split: train
args: en-fr
metrics:
- type: bleu
value: 52.83113187001415
name: Bleu
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# marian-finetuned-kde4-en-to-fr
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-fr](https://huggingface.co/Helsinki-NLP/opus-mt-en-fr) on the kde4 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8560
- Bleu: 52.8311
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.21.0
- Pytorch 1.12.0+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1
| [
"TRANSLATION"
] | Non_BioNLP |
QuantFactory/DRT-o1-7B-GGUF | QuantFactory | text-generation | [
"gguf",
"machine tranlsation",
"O1-like model",
"Chat",
"text-generation",
"en",
"zh",
"arxiv:2412.17498",
"base_model:Qwen/Qwen2.5-7B-Instruct",
"base_model:quantized:Qwen/Qwen2.5-7B-Instruct",
"license:cc-by-nc-sa-4.0",
"endpoints_compatible",
"region:us",
"conversational"
] | 1,735,823,753,000 | 2025-01-02T13:51:52 | 258 | 2 | ---
base_model:
- Qwen/Qwen2.5-7B-Instruct
language:
- en
- zh
license: cc-by-nc-sa-4.0
pipeline_tag: text-generation
tags:
- machine tranlsation
- O1-like model
- Chat
---
[](https://hf.co/QuantFactory)
# QuantFactory/DRT-o1-7B-GGUF
This is quantized version of [Krystalan/DRT-o1-7B](https://huggingface.co/Krystalan/DRT-o1-7B) created using llama.cpp
# Original Model Card
# DRT-o1
<p align="center">
🤗 <a href="https://huggingface.co/Krystalan/DRT-o1-7B">DRT-o1-7B</a>   |   🤗 <a href="https://huggingface.co/Krystalan/DRT-o1-8B">DRT-o1-8B</a>   |   🤗 <a href="https://huggingface.co/Krystalan/DRT-o1-14B">DRT-o1-14B</a>   |    📑 <a href="https://arxiv.org/abs/2412.17498">Paper</a>
</p>
This repository contains the resources for our paper ["DRT-o1: Optimized Deep Reasoning Translation via Long Chain-of-Thought"](https://arxiv.org/abs/2412.17498)
### Updates:
- *2024.12.31*: We updated [our paper](https://arxiv.org/abs/2412.17498) with more detals and analyses. Check it out!
- *2024.12.31*: We released the testing set of our work, please refer to `data/test.jsonl`
- *2024.12.30*: We released a new model checkpoint using Llama-3.1-8B-Instruct as the backbone, i.e., 🤗 <a href="https://huggingface.co/Krystalan/DRT-o1-8B">DRT-o1-8B</a>
- *2024.12.24*: We released [our paper](https://arxiv.org/abs/2412.17498). Check it out!
- *2024.12.23*: We released our model checkpoints. 🤗 <a href="https://huggingface.co/Krystalan/DRT-o1-7B">DRT-o1-7B</a> and 🤗 <a href="https://huggingface.co/Krystalan/DRT-o1-14B">DRT-o1-14B</a>.
If you find this work is useful, please consider cite our paper:
```
@article{wang2024drt,
title={DRT-o1: Optimized Deep Reasoning Translation via Long Chain-of-Thought},
author={Wang, Jiaan and Meng, Fandong and Liang, Yunlong and Zhou, Jie},
journal={arXiv preprint arXiv:2412.17498},
year={2024}
}
```
## Quick Links
- [Introduction](#introduction)
- [Models](#models)
- [Model Access](#model-access)
- [Model Performance](#model-performance)
- [Model Prompts](#model-prompts)
- [Quickstart](#quickstart)
- [Translation Cases](#translation-cases)
- [Data](#data)
- [License](#license)
## Introduction
In this work, we introduce DRT-o1, an attempt to bring the success of long thought reasoning to neural machine translation (MT). To this end,
- 🌟 We mine English sentences with similes or metaphors from existing literature books, which are suitable for translation via long thought.
- 🌟 We propose a designed multi-agent framework with three agents (i.e., a translator, an advisor and an evaluator) to synthesize the MT samples with long thought. There are 22,264 synthesized samples in total.
- 🌟 We train DRT-o1-8B, DRT-o1-7B and DRT-o1-14B using Llama-3.1-8B-Instruct, Qwen2.5-7B-Instruct and Qwen2.5-14B-Instruct as backbones.
> Our goal is not to achieve competitive performance with OpenAI’s O1 in neural machine translation (MT). Instead, we explore technical routes to bring the success of long thought to MT. To this end, we introduce DRT-o1, *a byproduct of our exploration*, and we hope it could facilitate the corresponding research in this direction.
## Models
### Model Access
| | Backbone | Model Access |
| :--: | :--: | :--: |
| DRT-o1-7B | 🤗 <a href="https://huggingface.co/Qwen/Qwen2.5-7B-Instruct">Qwen2.5-7B-Instruct</a> | 🤗 <a href="https://huggingface.co/Krystalan/DRT-o1-7B">DRT-o1-7B</a> |
| DRT-o1-8B | 🤗 <a href="https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct">Llama-3.1-8B-Instruct</a> | 🤗 <a href="https://huggingface.co/Krystalan/DRT-o1-8B">DRT-o1-8B</a> |
| DRT-o1-14B | 🤗 <a href="https://huggingface.co/Qwen/Qwen2.5-14B-Instruct">Qwen2.5-14B-Instruct</a> | 🤗 <a href="https://huggingface.co/Krystalan/DRT-o1-14B">DRT-o1-14B</a> |
### Model Performance
| | GRF | CometKiwi | GRB | BLEU | CometScore |
| :--: | :--: | :--: | :--: | :--: | :--: |
| Llama-3.1-8B-Instruct | 79.25 | 70.14 | 73.30 | 18.55 | 74.58 |
| Qwen2.5-7B-Instruct | 81.53 | 70.36 | 77.92 | 27.02 | 76.78 |
| Qwen2.5-14B-Instruct | 84.74 | 72.01 | 80.85 | 30.23 | 78.84 |
| Marco-o1-7B | 82.41 | 71.62 | 77.50 | 29.48 | 77.41 |
| QwQ-32B-preview | 86.31 | 71.48 | 83.08 | 27.46 | 78.68 |
| DRT-o1-8B | 84.49 | 70.85 | 80.80 | 32.67 | 78.81 |
| DRT-o1-7B | 85.57 | 71.78 | 82.38 | 35.54 | 80.19 |
| DRT-o1-14B | **87.19** | **72.11** | **83.20** | **36.46** | **80.64** |
### Model Prompts
During model inference, please use the following prompts:
- System prompt: `You are a philosopher skilled in deep thinking, accustomed to exploring complex problems with profound insight.`
- User prompt: `Please translate the following text from English to Chinese:\n[An English text]`
DRT-o1 models will first generate the thought and then provide the final translation, with the following format:
```
<thought>
[Reasoning process]
</thought>
<output>
[Final translation]
</output>
```
### Quickstart
- ⛷️ Huggingface Transformers:
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "Krystalan/DRT-o1-7B"
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)
prompt = "Please translate the following text from English to Chinese:\nThe mother, with her feet propped up on a stool, seemed to be trying to get to the bottom of that answer, whose feminine profundity had struck her all of a heap."
messages = [
{"role": "system", "content": "You are a philosopher skilled in deep thinking, accustomed to exploring complex problems with profound insight."},
{"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
generated_ids = model.generate(
**model_inputs,
max_new_tokens=2048
)
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)
```
- ⛷️ vllm:
Deploying LLMs:
```bash
python3 -m vllm.entrypoints.openai.api_server --model [model_ckpt] --served-model-name [model_name]
```
Calling LLMs:
```python
from openai import OpenAI
# Set OpenAI's API key and API base to use vLLM's API server.
openai_api_key = "EMPTY"
openai_api_base = "http://localhost:8000/v1"
client = OpenAI(
api_key=openai_api_key,
base_url=openai_api_base,
)
chat_response = client.chat.completions.create(
model=[model_name],
messages=[
{"role": "system", "content": "You are a philosopher skilled in deep thinking, accustomed to exploring complex problems with profound insight."},
{"role": "user", "content": "Please translate the following text from English to Chinese:\nThe mother, with her feet propped up on a stool, seemed to be trying to get to the bottom of that answer, whose feminine profundity had struck her all of a heap."},
],
temperature=0.1,
top_p=0.8,
max_tokens=2048,
extra_body={
"repetition_penalty": 1.05,
},
)
print("Chat response:", chat_response)
```
## Translation Cases
| Source Sentence | Qwen2.5-14B-Instruct | QwQ-32B-preview | DRT-o1-14B |
| :--: | :--: | :--: | :--: |
|Women were weeping and children crying, and all were going as fast as seemingly lay in their power, looking behind now and then as if pursued by some deadly enemy. | 妇女在哭泣，孩子们在哀号，所有人都似乎在尽全力快速前行，不时回头张望，仿佛背后有某个致命的敌人在追赶。 | 妇女们哭泣着，孩子们哭喊着，每个人都在尽力加快脚步，不时回头张望，仿佛背后有致命的敌人在追击。 | 妇女悲泣，孩童哀号，众人疾奔，不时回首，仿佛有致命之敌在后紧追。 |
|Wait through this season of the rain Till suns of autumn dry the plain, Then shall thy giant foe, and all His host and realm, before thee fall. | 等待这雨季过去，直到秋日的阳光晒干原野，那时你的巨敌及其部众和王国都将倒在你面前。 | 忍过雨季漫长夜，待秋阳升空，晒干大地湿润色，那时，巨敌垮台，他的军队和王国，全在你脚下。 | 历尽这雨季，待秋日阳光驱散平原上的最后一丝湿润，那时，你那巨敌，连同他的军队与王国，都将匍匐在你脚下。 |
|And if their words had taken another turn...if he himself had been less fastidious about intruding on another man's secrets...it was cruel to think how thin a film had shut out rescue from all this guilt and misery. | 而如果他们的言辞转向了另一个方向……如果他自己对侵扰他人秘密不那么介意……想到正是那层薄薄的隔阂将救援拒之门外，使得这一切的罪恶和痛苦无法避免，真是残酷。 | 而且，假如他们的谈话走向不同……假如他自己不对干涉他人私事如此谨慎……那时他会意识到，只要一层薄薄的屏障就阻隔了救援，使得所有这些罪恶和痛苦无法解脱，这真是残忍。 | 若他们的言辞稍作转变……若他本人不那么介意侵入他人的心扉……想到这层薄薄的隔阂竟将所有内疚与痛苦隔离于救援之外，实为残忍。 |
|This cold officer upon a monument, who dropped epithets unconcernedly down, would be finer as a dead man, he thought. | 他认为，这个站在纪念碑上的冷漠官员，若死了会更好，他不带任何感情地抛下了一些称呼。 | 这个冷冰冰的官员站在纪念碑上，毫不在意地抛下一些称号，他想，如果作为一个死人会更出色。 | 纪念碑上的冷淡官员，漫不经心地吟咏那些修饰语，他心想，若化为亡者，或许更显尊贵。 |
## Data
We release the testing set of our work, please refer to `data/test.jsonl`, where `en` indicates the English source sentences, and `zh` denotes the corresponding Chinese translation.
We will release the long-thought MT data as well as the data collection codes soon!
## License
This work is licensed under cc-by-nc-sa-4.0
| [
"TRANSLATION"
] | Non_BioNLP |
vineet10/new_model_2 | vineet10 | sentence-similarity | [
"sentence-transformers",
"safetensors",
"bert",
"sentence-similarity",
"feature-extraction",
"generated_from_trainer",
"dataset_size:26",
"loss:MultipleNegativesRankingLoss",
"arxiv:1908.10084",
"arxiv:1705.00652",
"base_model:BAAI/bge-base-en-v1.5",
"base_model:finetune:BAAI/bge-base-en-v1.5",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] | 1,721,340,609,000 | 2024-07-18T22:10:40 | 5 | 0 | ---
base_model: BAAI/bge-base-en-v1.5
datasets: []
language: []
library_name: sentence-transformers
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:26
- loss:MultipleNegativesRankingLoss
widget:
- source_sentence: 'Answer: Users can contact Customer Care before confirmation to
request a refund for offline'
sentences:
- single order?
- a booking?
- MOU?
- source_sentence: The Employee agrees to be employed on the terms and conditions
set out in this Agreement.
sentences:
- What events constitute Force Majeure under this Agreement?
- What are the specific terms and conditions of employment?
- What is the scope of this Agreement?
- source_sentence: The term of this Agreement shall continue until terminated by either
party in accordance with
sentences:
- When does this Agreement terminate?
- What is the term of the Agreement?
- Can the Company make changes to the job title or duties of the Employee?
- source_sentence: The initial job title of the Employee will be Relationship Manager.
The initial job duties the
sentences:
- What remedies are available in case of a material breach of this Agreement?
- What representations and warranties does the Employee make to the Company?
- What are the initial job title and duties of the Employee?
- source_sentence: The Company has employed the Employee to render services as described
herein from the
sentences:
- What rules and policies must the Employee abide by?
- What are the general obligations of the Employee?
- When does the Company employ the Employee?
---
# SentenceTransformer based on BAAI/bge-base-en-v1.5
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
## Model Details
### Model Description
- **Model Type:** Sentence Transformer
- **Base model:** [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) <!-- at revision a5beb1e3e68b9ab74eb54cfd186867f64f240e1a -->
- **Maximum Sequence Length:** 512 tokens
- **Output Dimensionality:** 768 tokens
- **Similarity Function:** Cosine Similarity
<!-- - **Training Dataset:** Unknown -->
<!-- - **Language:** Unknown -->
<!-- - **License:** Unknown -->
### Model Sources
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
### Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
(2): Normalize()
)
```
## Usage
### Direct Usage (Sentence Transformers)
First install the Sentence Transformers library:
```bash
pip install -U sentence-transformers
```
Then you can load this model and run inference.
```python
from sentence_transformers import SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("vineet10/new_model_2")
# Run inference
sentences = [
'The Company has employed the Employee to render services as described herein from the',
'When does the Company employ the Employee?',
'What are the general obligations of the Employee?',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]
```
<!--
### Direct Usage (Transformers)
<details><summary>Click to see the direct usage in Transformers</summary>
</details>
-->
<!--
### Downstream Usage (Sentence Transformers)
You can finetune this model on your own dataset.
<details><summary>Click to expand</summary>
</details>
-->
<!--
### Out-of-Scope Use
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->
<!--
## Bias, Risks and Limitations
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
-->
<!--
### Recommendations
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
-->
## Training Details
### Training Dataset
#### Unnamed Dataset
* Size: 26 training samples
* Columns: <code>context</code> and <code>question</code>
* Approximate statistics based on the first 1000 samples:
| | context | question |
|:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
| type | string | string |
| details | <ul><li>min: 2 tokens</li><li>mean: 19.15 tokens</li><li>max: 28 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 11.35 tokens</li><li>max: 18 tokens</li></ul> |
* Samples:
| context | question |
|:----------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------|
| <code>The Employee agrees to diligently, honestly, and to the best of their abilities, perform all</code> | <code>What are the general obligations of the Employee?</code> |
| <code>The Company has employed the Employee to render services as described herein from the</code> | <code>When does the Company employ the Employee?</code> |
| <code>Answer: Users can report delays to Customer Care and expect an automatic refund within</code> | <code>order?</code> |
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "cos_sim"
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `eval_strategy`: steps
- `per_device_train_batch_size`: 16
- `per_device_eval_batch_size`: 16
- `num_train_epochs`: 1
- `warmup_ratio`: 0.1
- `fp16`: True
- `batch_sampler`: no_duplicates
#### All Hyperparameters
<details><summary>Click to expand</summary>
- `overwrite_output_dir`: False
- `do_predict`: False
- `eval_strategy`: steps
- `prediction_loss_only`: True
- `per_device_train_batch_size`: 16
- `per_device_eval_batch_size`: 16
- `per_gpu_train_batch_size`: None
- `per_gpu_eval_batch_size`: None
- `gradient_accumulation_steps`: 1
- `eval_accumulation_steps`: None
- `learning_rate`: 5e-05
- `weight_decay`: 0.0
- `adam_beta1`: 0.9
- `adam_beta2`: 0.999
- `adam_epsilon`: 1e-08
- `max_grad_norm`: 1.0
- `num_train_epochs`: 1
- `max_steps`: -1
- `lr_scheduler_type`: linear
- `lr_scheduler_kwargs`: {}
- `warmup_ratio`: 0.1
- `warmup_steps`: 0
- `log_level`: passive
- `log_level_replica`: warning
- `log_on_each_node`: True
- `logging_nan_inf_filter`: True
- `save_safetensors`: True
- `save_on_each_node`: False
- `save_only_model`: False
- `restore_callback_states_from_checkpoint`: False
- `no_cuda`: False
- `use_cpu`: False
- `use_mps_device`: False
- `seed`: 42
- `data_seed`: None
- `jit_mode_eval`: False
- `use_ipex`: False
- `bf16`: False
- `fp16`: True
- `fp16_opt_level`: O1
- `half_precision_backend`: auto
- `bf16_full_eval`: False
- `fp16_full_eval`: False
- `tf32`: None
- `local_rank`: 0
- `ddp_backend`: None
- `tpu_num_cores`: None
- `tpu_metrics_debug`: False
- `debug`: []
- `dataloader_drop_last`: False
- `dataloader_num_workers`: 0
- `dataloader_prefetch_factor`: None
- `past_index`: -1
- `disable_tqdm`: False
- `remove_unused_columns`: True
- `label_names`: None
- `load_best_model_at_end`: False
- `ignore_data_skip`: False
- `fsdp`: []
- `fsdp_min_num_params`: 0
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
- `fsdp_transformer_layer_cls_to_wrap`: None
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
- `deepspeed`: None
- `label_smoothing_factor`: 0.0
- `optim`: adamw_torch
- `optim_args`: None
- `adafactor`: False
- `group_by_length`: False
- `length_column_name`: length
- `ddp_find_unused_parameters`: None
- `ddp_bucket_cap_mb`: None
- `ddp_broadcast_buffers`: False
- `dataloader_pin_memory`: True
- `dataloader_persistent_workers`: False
- `skip_memory_metrics`: True
- `use_legacy_prediction_loop`: False
- `push_to_hub`: False
- `resume_from_checkpoint`: None
- `hub_model_id`: None
- `hub_strategy`: every_save
- `hub_private_repo`: False
- `hub_always_push`: False
- `gradient_checkpointing`: False
- `gradient_checkpointing_kwargs`: None
- `include_inputs_for_metrics`: False
- `eval_do_concat_batches`: True
- `fp16_backend`: auto
- `push_to_hub_model_id`: None
- `push_to_hub_organization`: None
- `mp_parameters`:
- `auto_find_batch_size`: False
- `full_determinism`: False
- `torchdynamo`: None
- `ray_scope`: last
- `ddp_timeout`: 1800
- `torch_compile`: False
- `torch_compile_backend`: None
- `torch_compile_mode`: None
- `dispatch_batches`: None
- `split_batches`: None
- `include_tokens_per_second`: False
- `include_num_input_tokens_seen`: False
- `neftune_noise_alpha`: None
- `optim_target_modules`: None
- `batch_eval_metrics`: False
- `eval_on_start`: False
- `batch_sampler`: no_duplicates
- `multi_dataset_batch_sampler`: proportional
</details>
### Framework Versions
- Python: 3.10.12
- Sentence Transformers: 3.0.1
- Transformers: 4.42.4
- PyTorch: 2.3.1+cu121
- Accelerate: 0.32.1
- Datasets: 2.20.0
- Tokenizers: 0.19.1
## Citation
### BibTeX
#### Sentence Transformers
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "https://arxiv.org/abs/1908.10084",
}
```
#### MultipleNegativesRankingLoss
```bibtex
@misc{henderson2017efficient,
title={Efficient Natural Language Response Suggestion for Smart Reply},
author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
year={2017},
eprint={1705.00652},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
<!--
## Glossary
*Clearly define terms in order to be accessible across audiences.*
-->
<!--
## Model Card Authors
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->
<!--
## Model Card Contact
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
--> | [
"TEXT_CLASSIFICATION"
] | Non_BioNLP |
rezhwan12/Nechir13 | rezhwan12 | summarization | [
"adapter-transformers",
"summarization",
"ar",
"dataset:BAAI/Infinity-Instruct",
"license:bsd-3-clause",
"region:us"
] | 1,720,601,480,000 | 2024-07-10T08:52:36 | 0 | 0 | ---
datasets:
- BAAI/Infinity-Instruct
language:
- ar
library_name: adapter-transformers
license: bsd-3-clause
metrics:
- accuracy
pipeline_tag: summarization
---
| [
"SUMMARIZATION"
] | Non_BioNLP |
abdalrahmanshahrour/auto-arabic-summarization | abdalrahmanshahrour | summarization | [
"transformers",
"pytorch",
"mbart",
"text2text-generation",
"summarization",
"AraBERT",
"BERT",
"BERT2BERT",
"MSA",
"Arabic Text Summarization",
"Arabic News Title Generation",
"Arabic Paraphrasing",
"Summarization",
"generated_from_trainer",
"Transformers",
"PyTorch",
"ar",
"dataset:abdalrahmanshahrour/autotrain-data-auto-arabic-summarization",
"co2_eq_emissions",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 1,671,736,977,000 | 2023-02-08T11:10:23 | 42 | 8 | ---
datasets:
- abdalrahmanshahrour/autotrain-data-auto-arabic-summarization
language:
- ar
tags:
- summarization
- AraBERT
- BERT
- BERT2BERT
- MSA
- Arabic Text Summarization
- Arabic News Title Generation
- Arabic Paraphrasing
- Summarization
- generated_from_trainer
- Transformers
- PyTorch
widget:
- text: ' شهدت مدينة طرابلس، مساء أمس الأربعاء، احتجاجات شعبية وأعمال شغب لليوم الثالث
على التوالي، وذلك بسبب تردي الوضع المعيشي والاقتصادي. واندلعت مواجهات عنيفة وعمليات
كر وفر ما بين الجيش اللبناني والمحتجين استمرت لساعات، إثر محاولة فتح الطرقات المقطوعة،
ما أدى إلى إصابة العشرات من الطرفين.'
co2_eq_emissions:
emissions: 23.934855677704917
---
# Model Trained Using AutoTrain
- Problem type: Summarization
- Model ID: 2581378622
- CO2 Emissions (in grams): 23.9349
## Validation Metrics
- Loss: 0.829
- Rouge1: 1.132
- Rouge2: 0.127
- RougeL: 1.137
- RougeLsum: 1.129
### Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.7.1
- Tokenizers 0.13.2
| [
"SUMMARIZATION",
"PARAPHRASING"
] | Non_BioNLP |
narainp/jina-embeddings-GGUF | narainp | feature-extraction | [
"sentence-transformers",
"gguf",
"feature-extraction",
"sentence-similarity",
"mteb",
"llama-cpp",
"gguf-my-repo",
"en",
"dataset:allenai/c4",
"base_model:jinaai/jina-embeddings-v2-base-en",
"base_model:quantized:jinaai/jina-embeddings-v2-base-en",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"region:us"
] | 1,736,314,070,000 | 2025-01-08T09:45:10 | 1,487 | 1 | ---
base_model: jinaai/jina-embeddings-v2-base-en
datasets:
- allenai/c4
language: en
license: apache-2.0
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- mteb
- llama-cpp
- gguf-my-repo
inference: false
model-index:
- name: jina-embedding-b-en-v2
results:
- task:
type: Classification
dataset:
name: MTEB AmazonCounterfactualClassification (en)
type: mteb/amazon_counterfactual
config: en
split: test
revision: e8379541af4e31359cca9fbcf4b00f2671dba205
metrics:
- type: accuracy
value: 74.73134328358209
- type: ap
value: 37.765427081831035
- type: f1
value: 68.79367444339518
- task:
type: Classification
dataset:
name: MTEB AmazonPolarityClassification
type: mteb/amazon_polarity
config: default
split: test
revision: e2d317d38cd51312af73b3d32a06d1a08b442046
metrics:
- type: accuracy
value: 88.544275
- type: ap
value: 84.61328675662887
- type: f1
value: 88.51879035862375
- task:
type: Classification
dataset:
name: MTEB AmazonReviewsClassification (en)
type: mteb/amazon_reviews_multi
config: en
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 45.263999999999996
- type: f1
value: 43.778759656699435
- task:
type: Retrieval
dataset:
name: MTEB ArguAna
type: arguana
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 21.693
- type: map_at_10
value: 35.487
- type: map_at_100
value: 36.862
- type: map_at_1000
value: 36.872
- type: map_at_3
value: 30.049999999999997
- type: map_at_5
value: 32.966
- type: mrr_at_1
value: 21.977
- type: mrr_at_10
value: 35.565999999999995
- type: mrr_at_100
value: 36.948
- type: mrr_at_1000
value: 36.958
- type: mrr_at_3
value: 30.121
- type: mrr_at_5
value: 33.051
- type: ndcg_at_1
value: 21.693
- type: ndcg_at_10
value: 44.181
- type: ndcg_at_100
value: 49.982
- type: ndcg_at_1000
value: 50.233000000000004
- type: ndcg_at_3
value: 32.830999999999996
- type: ndcg_at_5
value: 38.080000000000005
- type: precision_at_1
value: 21.693
- type: precision_at_10
value: 7.248
- type: precision_at_100
value: 0.9769999999999999
- type: precision_at_1000
value: 0.1
- type: precision_at_3
value: 13.632
- type: precision_at_5
value: 10.725
- type: recall_at_1
value: 21.693
- type: recall_at_10
value: 72.475
- type: recall_at_100
value: 97.653
- type: recall_at_1000
value: 99.57300000000001
- type: recall_at_3
value: 40.896
- type: recall_at_5
value: 53.627
- task:
type: Clustering
dataset:
name: MTEB ArxivClusteringP2P
type: mteb/arxiv-clustering-p2p
config: default
split: test
revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d
metrics:
- type: v_measure
value: 45.39242428696777
- task:
type: Clustering
dataset:
name: MTEB ArxivClusteringS2S
type: mteb/arxiv-clustering-s2s
config: default
split: test
revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53
metrics:
- type: v_measure
value: 36.675626784714
- task:
type: Reranking
dataset:
name: MTEB AskUbuntuDupQuestions
type: mteb/askubuntudupquestions-reranking
config: default
split: test
revision: 2000358ca161889fa9c082cb41daa8dcfb161a54
metrics:
- type: map
value: 62.247725694904034
- type: mrr
value: 74.91359978894604
- task:
type: STS
dataset:
name: MTEB BIOSSES
type: mteb/biosses-sts
config: default
split: test
revision: d3fb88f8f02e40887cd149695127462bbcf29b4a
metrics:
- type: cos_sim_pearson
value: 82.68003802970496
- type: cos_sim_spearman
value: 81.23438110096286
- type: euclidean_pearson
value: 81.87462986142582
- type: euclidean_spearman
value: 81.23438110096286
- type: manhattan_pearson
value: 81.61162566600755
- type: manhattan_spearman
value: 81.11329400456184
- task:
type: Classification
dataset:
name: MTEB Banking77Classification
type: mteb/banking77
config: default
split: test
revision: 0fd18e25b25c072e09e0d92ab615fda904d66300
metrics:
- type: accuracy
value: 84.01298701298701
- type: f1
value: 83.31690714969382
- task:
type: Clustering
dataset:
name: MTEB BiorxivClusteringP2P
type: mteb/biorxiv-clustering-p2p
config: default
split: test
revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40
metrics:
- type: v_measure
value: 37.050108150972086
- task:
type: Clustering
dataset:
name: MTEB BiorxivClusteringS2S
type: mteb/biorxiv-clustering-s2s
config: default
split: test
revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908
metrics:
- type: v_measure
value: 30.15731442819715
- task:
type: Retrieval
dataset:
name: MTEB CQADupstackAndroidRetrieval
type: BeIR/cqadupstack
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 31.391999999999996
- type: map_at_10
value: 42.597
- type: map_at_100
value: 44.07
- type: map_at_1000
value: 44.198
- type: map_at_3
value: 38.957
- type: map_at_5
value: 40.961
- type: mrr_at_1
value: 37.196
- type: mrr_at_10
value: 48.152
- type: mrr_at_100
value: 48.928
- type: mrr_at_1000
value: 48.964999999999996
- type: mrr_at_3
value: 45.446
- type: mrr_at_5
value: 47.205999999999996
- type: ndcg_at_1
value: 37.196
- type: ndcg_at_10
value: 49.089
- type: ndcg_at_100
value: 54.471000000000004
- type: ndcg_at_1000
value: 56.385
- type: ndcg_at_3
value: 43.699
- type: ndcg_at_5
value: 46.22
- type: precision_at_1
value: 37.196
- type: precision_at_10
value: 9.313
- type: precision_at_100
value: 1.478
- type: precision_at_1000
value: 0.198
- type: precision_at_3
value: 20.839
- type: precision_at_5
value: 14.936
- type: recall_at_1
value: 31.391999999999996
- type: recall_at_10
value: 61.876
- type: recall_at_100
value: 84.214
- type: recall_at_1000
value: 95.985
- type: recall_at_3
value: 46.6
- type: recall_at_5
value: 53.588
- type: map_at_1
value: 29.083
- type: map_at_10
value: 38.812999999999995
- type: map_at_100
value: 40.053
- type: map_at_1000
value: 40.188
- type: map_at_3
value: 36.111
- type: map_at_5
value: 37.519000000000005
- type: mrr_at_1
value: 36.497
- type: mrr_at_10
value: 44.85
- type: mrr_at_100
value: 45.546
- type: mrr_at_1000
value: 45.593
- type: mrr_at_3
value: 42.686
- type: mrr_at_5
value: 43.909
- type: ndcg_at_1
value: 36.497
- type: ndcg_at_10
value: 44.443
- type: ndcg_at_100
value: 48.979
- type: ndcg_at_1000
value: 51.154999999999994
- type: ndcg_at_3
value: 40.660000000000004
- type: ndcg_at_5
value: 42.193000000000005
- type: precision_at_1
value: 36.497
- type: precision_at_10
value: 8.433
- type: precision_at_100
value: 1.369
- type: precision_at_1000
value: 0.185
- type: precision_at_3
value: 19.894000000000002
- type: precision_at_5
value: 13.873
- type: recall_at_1
value: 29.083
- type: recall_at_10
value: 54.313
- type: recall_at_100
value: 73.792
- type: recall_at_1000
value: 87.629
- type: recall_at_3
value: 42.257
- type: recall_at_5
value: 47.066
- type: map_at_1
value: 38.556000000000004
- type: map_at_10
value: 50.698
- type: map_at_100
value: 51.705
- type: map_at_1000
value: 51.768
- type: map_at_3
value: 47.848
- type: map_at_5
value: 49.358000000000004
- type: mrr_at_1
value: 43.95
- type: mrr_at_10
value: 54.191
- type: mrr_at_100
value: 54.852999999999994
- type: mrr_at_1000
value: 54.885
- type: mrr_at_3
value: 51.954
- type: mrr_at_5
value: 53.13
- type: ndcg_at_1
value: 43.95
- type: ndcg_at_10
value: 56.516
- type: ndcg_at_100
value: 60.477000000000004
- type: ndcg_at_1000
value: 61.746
- type: ndcg_at_3
value: 51.601
- type: ndcg_at_5
value: 53.795
- type: precision_at_1
value: 43.95
- type: precision_at_10
value: 9.009
- type: precision_at_100
value: 1.189
- type: precision_at_1000
value: 0.135
- type: precision_at_3
value: 22.989
- type: precision_at_5
value: 15.473
- type: recall_at_1
value: 38.556000000000004
- type: recall_at_10
value: 70.159
- type: recall_at_100
value: 87.132
- type: recall_at_1000
value: 96.16
- type: recall_at_3
value: 56.906
- type: recall_at_5
value: 62.332
- type: map_at_1
value: 24.238
- type: map_at_10
value: 32.5
- type: map_at_100
value: 33.637
- type: map_at_1000
value: 33.719
- type: map_at_3
value: 30.026999999999997
- type: map_at_5
value: 31.555
- type: mrr_at_1
value: 26.328000000000003
- type: mrr_at_10
value: 34.44
- type: mrr_at_100
value: 35.455999999999996
- type: mrr_at_1000
value: 35.521
- type: mrr_at_3
value: 32.034
- type: mrr_at_5
value: 33.565
- type: ndcg_at_1
value: 26.328000000000003
- type: ndcg_at_10
value: 37.202
- type: ndcg_at_100
value: 42.728
- type: ndcg_at_1000
value: 44.792
- type: ndcg_at_3
value: 32.368
- type: ndcg_at_5
value: 35.008
- type: precision_at_1
value: 26.328000000000003
- type: precision_at_10
value: 5.7059999999999995
- type: precision_at_100
value: 0.8880000000000001
- type: precision_at_1000
value: 0.11100000000000002
- type: precision_at_3
value: 13.672
- type: precision_at_5
value: 9.74
- type: recall_at_1
value: 24.238
- type: recall_at_10
value: 49.829
- type: recall_at_100
value: 75.21
- type: recall_at_1000
value: 90.521
- type: recall_at_3
value: 36.867
- type: recall_at_5
value: 43.241
- type: map_at_1
value: 15.378
- type: map_at_10
value: 22.817999999999998
- type: map_at_100
value: 23.977999999999998
- type: map_at_1000
value: 24.108
- type: map_at_3
value: 20.719
- type: map_at_5
value: 21.889
- type: mrr_at_1
value: 19.03
- type: mrr_at_10
value: 27.022000000000002
- type: mrr_at_100
value: 28.011999999999997
- type: mrr_at_1000
value: 28.096
- type: mrr_at_3
value: 24.855
- type: mrr_at_5
value: 26.029999999999998
- type: ndcg_at_1
value: 19.03
- type: ndcg_at_10
value: 27.526
- type: ndcg_at_100
value: 33.040000000000006
- type: ndcg_at_1000
value: 36.187000000000005
- type: ndcg_at_3
value: 23.497
- type: ndcg_at_5
value: 25.334
- type: precision_at_1
value: 19.03
- type: precision_at_10
value: 4.963
- type: precision_at_100
value: 0.893
- type: precision_at_1000
value: 0.13
- type: precision_at_3
value: 11.360000000000001
- type: precision_at_5
value: 8.134
- type: recall_at_1
value: 15.378
- type: recall_at_10
value: 38.061
- type: recall_at_100
value: 61.754
- type: recall_at_1000
value: 84.259
- type: recall_at_3
value: 26.788
- type: recall_at_5
value: 31.326999999999998
- type: map_at_1
value: 27.511999999999997
- type: map_at_10
value: 37.429
- type: map_at_100
value: 38.818000000000005
- type: map_at_1000
value: 38.924
- type: map_at_3
value: 34.625
- type: map_at_5
value: 36.064
- type: mrr_at_1
value: 33.300999999999995
- type: mrr_at_10
value: 43.036
- type: mrr_at_100
value: 43.894
- type: mrr_at_1000
value: 43.936
- type: mrr_at_3
value: 40.825
- type: mrr_at_5
value: 42.028
- type: ndcg_at_1
value: 33.300999999999995
- type: ndcg_at_10
value: 43.229
- type: ndcg_at_100
value: 48.992000000000004
- type: ndcg_at_1000
value: 51.02100000000001
- type: ndcg_at_3
value: 38.794000000000004
- type: ndcg_at_5
value: 40.65
- type: precision_at_1
value: 33.300999999999995
- type: precision_at_10
value: 7.777000000000001
- type: precision_at_100
value: 1.269
- type: precision_at_1000
value: 0.163
- type: precision_at_3
value: 18.351
- type: precision_at_5
value: 12.762
- type: recall_at_1
value: 27.511999999999997
- type: recall_at_10
value: 54.788000000000004
- type: recall_at_100
value: 79.105
- type: recall_at_1000
value: 92.49199999999999
- type: recall_at_3
value: 41.924
- type: recall_at_5
value: 47.026
- type: map_at_1
value: 24.117
- type: map_at_10
value: 33.32
- type: map_at_100
value: 34.677
- type: map_at_1000
value: 34.78
- type: map_at_3
value: 30.233999999999998
- type: map_at_5
value: 31.668000000000003
- type: mrr_at_1
value: 29.566
- type: mrr_at_10
value: 38.244
- type: mrr_at_100
value: 39.245000000000005
- type: mrr_at_1000
value: 39.296
- type: mrr_at_3
value: 35.864000000000004
- type: mrr_at_5
value: 36.919999999999995
- type: ndcg_at_1
value: 29.566
- type: ndcg_at_10
value: 39.127
- type: ndcg_at_100
value: 44.989000000000004
- type: ndcg_at_1000
value: 47.189
- type: ndcg_at_3
value: 34.039
- type: ndcg_at_5
value: 35.744
- type: precision_at_1
value: 29.566
- type: precision_at_10
value: 7.385999999999999
- type: precision_at_100
value: 1.204
- type: precision_at_1000
value: 0.158
- type: precision_at_3
value: 16.286
- type: precision_at_5
value: 11.484
- type: recall_at_1
value: 24.117
- type: recall_at_10
value: 51.559999999999995
- type: recall_at_100
value: 77.104
- type: recall_at_1000
value: 91.79899999999999
- type: recall_at_3
value: 36.82
- type: recall_at_5
value: 41.453
- type: map_at_1
value: 25.17625
- type: map_at_10
value: 34.063916666666664
- type: map_at_100
value: 35.255500000000005
- type: map_at_1000
value: 35.37275
- type: map_at_3
value: 31.351666666666667
- type: map_at_5
value: 32.80608333333333
- type: mrr_at_1
value: 29.59783333333333
- type: mrr_at_10
value: 38.0925
- type: mrr_at_100
value: 38.957249999999995
- type: mrr_at_1000
value: 39.01608333333333
- type: mrr_at_3
value: 35.77625
- type: mrr_at_5
value: 37.04991666666667
- type: ndcg_at_1
value: 29.59783333333333
- type: ndcg_at_10
value: 39.343666666666664
- type: ndcg_at_100
value: 44.488249999999994
- type: ndcg_at_1000
value: 46.83358333333334
- type: ndcg_at_3
value: 34.69708333333333
- type: ndcg_at_5
value: 36.75075
- type: precision_at_1
value: 29.59783333333333
- type: precision_at_10
value: 6.884083333333332
- type: precision_at_100
value: 1.114
- type: precision_at_1000
value: 0.15108333333333332
- type: precision_at_3
value: 15.965250000000003
- type: precision_at_5
value: 11.246500000000001
- type: recall_at_1
value: 25.17625
- type: recall_at_10
value: 51.015999999999984
- type: recall_at_100
value: 73.60174999999998
- type: recall_at_1000
value: 89.849
- type: recall_at_3
value: 37.88399999999999
- type: recall_at_5
value: 43.24541666666666
- type: map_at_1
value: 24.537
- type: map_at_10
value: 31.081999999999997
- type: map_at_100
value: 32.042
- type: map_at_1000
value: 32.141
- type: map_at_3
value: 29.137
- type: map_at_5
value: 30.079
- type: mrr_at_1
value: 27.454
- type: mrr_at_10
value: 33.694
- type: mrr_at_100
value: 34.579
- type: mrr_at_1000
value: 34.649
- type: mrr_at_3
value: 32.004
- type: mrr_at_5
value: 32.794000000000004
- type: ndcg_at_1
value: 27.454
- type: ndcg_at_10
value: 34.915
- type: ndcg_at_100
value: 39.641
- type: ndcg_at_1000
value: 42.105
- type: ndcg_at_3
value: 31.276
- type: ndcg_at_5
value: 32.65
- type: precision_at_1
value: 27.454
- type: precision_at_10
value: 5.337
- type: precision_at_100
value: 0.8250000000000001
- type: precision_at_1000
value: 0.11199999999999999
- type: precision_at_3
value: 13.241
- type: precision_at_5
value: 8.895999999999999
- type: recall_at_1
value: 24.537
- type: recall_at_10
value: 44.324999999999996
- type: recall_at_100
value: 65.949
- type: recall_at_1000
value: 84.017
- type: recall_at_3
value: 33.857
- type: recall_at_5
value: 37.316
- type: map_at_1
value: 17.122
- type: map_at_10
value: 24.32
- type: map_at_100
value: 25.338
- type: map_at_1000
value: 25.462
- type: map_at_3
value: 22.064
- type: map_at_5
value: 23.322000000000003
- type: mrr_at_1
value: 20.647
- type: mrr_at_10
value: 27.858
- type: mrr_at_100
value: 28.743999999999996
- type: mrr_at_1000
value: 28.819
- type: mrr_at_3
value: 25.769
- type: mrr_at_5
value: 26.964
- type: ndcg_at_1
value: 20.647
- type: ndcg_at_10
value: 28.849999999999998
- type: ndcg_at_100
value: 33.849000000000004
- type: ndcg_at_1000
value: 36.802
- type: ndcg_at_3
value: 24.799
- type: ndcg_at_5
value: 26.682
- type: precision_at_1
value: 20.647
- type: precision_at_10
value: 5.2170000000000005
- type: precision_at_100
value: 0.906
- type: precision_at_1000
value: 0.134
- type: precision_at_3
value: 11.769
- type: precision_at_5
value: 8.486
- type: recall_at_1
value: 17.122
- type: recall_at_10
value: 38.999
- type: recall_at_100
value: 61.467000000000006
- type: recall_at_1000
value: 82.716
- type: recall_at_3
value: 27.601
- type: recall_at_5
value: 32.471
- type: map_at_1
value: 24.396
- type: map_at_10
value: 33.415
- type: map_at_100
value: 34.521
- type: map_at_1000
value: 34.631
- type: map_at_3
value: 30.703999999999997
- type: map_at_5
value: 32.166
- type: mrr_at_1
value: 28.825
- type: mrr_at_10
value: 37.397000000000006
- type: mrr_at_100
value: 38.286
- type: mrr_at_1000
value: 38.346000000000004
- type: mrr_at_3
value: 35.028
- type: mrr_at_5
value: 36.32
- type: ndcg_at_1
value: 28.825
- type: ndcg_at_10
value: 38.656
- type: ndcg_at_100
value: 43.856
- type: ndcg_at_1000
value: 46.31
- type: ndcg_at_3
value: 33.793
- type: ndcg_at_5
value: 35.909
- type: precision_at_1
value: 28.825
- type: precision_at_10
value: 6.567
- type: precision_at_100
value: 1.0330000000000001
- type: precision_at_1000
value: 0.135
- type: precision_at_3
value: 15.516
- type: precision_at_5
value: 10.914
- type: recall_at_1
value: 24.396
- type: recall_at_10
value: 50.747
- type: recall_at_100
value: 73.477
- type: recall_at_1000
value: 90.801
- type: recall_at_3
value: 37.1
- type: recall_at_5
value: 42.589
- type: map_at_1
value: 25.072
- type: map_at_10
value: 34.307
- type: map_at_100
value: 35.725
- type: map_at_1000
value: 35.943999999999996
- type: map_at_3
value: 30.906
- type: map_at_5
value: 32.818000000000005
- type: mrr_at_1
value: 29.644
- type: mrr_at_10
value: 38.673
- type: mrr_at_100
value: 39.459
- type: mrr_at_1000
value: 39.527
- type: mrr_at_3
value: 35.771
- type: mrr_at_5
value: 37.332
- type: ndcg_at_1
value: 29.644
- type: ndcg_at_10
value: 40.548
- type: ndcg_at_100
value: 45.678999999999995
- type: ndcg_at_1000
value: 48.488
- type: ndcg_at_3
value: 34.887
- type: ndcg_at_5
value: 37.543
- type: precision_at_1
value: 29.644
- type: precision_at_10
value: 7.688000000000001
- type: precision_at_100
value: 1.482
- type: precision_at_1000
value: 0.23600000000000002
- type: precision_at_3
value: 16.206
- type: precision_at_5
value: 12.016
- type: recall_at_1
value: 25.072
- type: recall_at_10
value: 53.478
- type: recall_at_100
value: 76.07300000000001
- type: recall_at_1000
value: 93.884
- type: recall_at_3
value: 37.583
- type: recall_at_5
value: 44.464
- type: map_at_1
value: 20.712
- type: map_at_10
value: 27.467999999999996
- type: map_at_100
value: 28.502
- type: map_at_1000
value: 28.610000000000003
- type: map_at_3
value: 24.887999999999998
- type: map_at_5
value: 26.273999999999997
- type: mrr_at_1
value: 22.736
- type: mrr_at_10
value: 29.553
- type: mrr_at_100
value: 30.485
- type: mrr_at_1000
value: 30.56
- type: mrr_at_3
value: 27.078999999999997
- type: mrr_at_5
value: 28.401
- type: ndcg_at_1
value: 22.736
- type: ndcg_at_10
value: 32.023
- type: ndcg_at_100
value: 37.158
- type: ndcg_at_1000
value: 39.823
- type: ndcg_at_3
value: 26.951999999999998
- type: ndcg_at_5
value: 29.281000000000002
- type: precision_at_1
value: 22.736
- type: precision_at_10
value: 5.213
- type: precision_at_100
value: 0.832
- type: precision_at_1000
value: 0.116
- type: precision_at_3
value: 11.459999999999999
- type: precision_at_5
value: 8.244
- type: recall_at_1
value: 20.712
- type: recall_at_10
value: 44.057
- type: recall_at_100
value: 67.944
- type: recall_at_1000
value: 87.925
- type: recall_at_3
value: 30.305
- type: recall_at_5
value: 36.071999999999996
- task:
type: Retrieval
dataset:
name: MTEB ClimateFEVER
type: climate-fever
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 10.181999999999999
- type: map_at_10
value: 16.66
- type: map_at_100
value: 18.273
- type: map_at_1000
value: 18.45
- type: map_at_3
value: 14.141
- type: map_at_5
value: 15.455
- type: mrr_at_1
value: 22.15
- type: mrr_at_10
value: 32.062000000000005
- type: mrr_at_100
value: 33.116
- type: mrr_at_1000
value: 33.168
- type: mrr_at_3
value: 28.827
- type: mrr_at_5
value: 30.892999999999997
- type: ndcg_at_1
value: 22.15
- type: ndcg_at_10
value: 23.532
- type: ndcg_at_100
value: 30.358
- type: ndcg_at_1000
value: 33.783
- type: ndcg_at_3
value: 19.222
- type: ndcg_at_5
value: 20.919999999999998
- type: precision_at_1
value: 22.15
- type: precision_at_10
value: 7.185999999999999
- type: precision_at_100
value: 1.433
- type: precision_at_1000
value: 0.207
- type: precision_at_3
value: 13.941
- type: precision_at_5
value: 10.906
- type: recall_at_1
value: 10.181999999999999
- type: recall_at_10
value: 28.104000000000003
- type: recall_at_100
value: 51.998999999999995
- type: recall_at_1000
value: 71.311
- type: recall_at_3
value: 17.698
- type: recall_at_5
value: 22.262999999999998
- task:
type: Retrieval
dataset:
name: MTEB DBPedia
type: dbpedia-entity
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 6.669
- type: map_at_10
value: 15.552
- type: map_at_100
value: 21.865000000000002
- type: map_at_1000
value: 23.268
- type: map_at_3
value: 11.309
- type: map_at_5
value: 13.084000000000001
- type: mrr_at_1
value: 55.50000000000001
- type: mrr_at_10
value: 66.46600000000001
- type: mrr_at_100
value: 66.944
- type: mrr_at_1000
value: 66.956
- type: mrr_at_3
value: 64.542
- type: mrr_at_5
value: 65.717
- type: ndcg_at_1
value: 44.75
- type: ndcg_at_10
value: 35.049
- type: ndcg_at_100
value: 39.073
- type: ndcg_at_1000
value: 46.208
- type: ndcg_at_3
value: 39.525
- type: ndcg_at_5
value: 37.156
- type: precision_at_1
value: 55.50000000000001
- type: precision_at_10
value: 27.800000000000004
- type: precision_at_100
value: 9.013
- type: precision_at_1000
value: 1.8800000000000001
- type: precision_at_3
value: 42.667
- type: precision_at_5
value: 36.0
- type: recall_at_1
value: 6.669
- type: recall_at_10
value: 21.811
- type: recall_at_100
value: 45.112
- type: recall_at_1000
value: 67.806
- type: recall_at_3
value: 13.373
- type: recall_at_5
value: 16.615
- task:
type: Classification
dataset:
name: MTEB EmotionClassification
type: mteb/emotion
config: default
split: test
revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37
metrics:
- type: accuracy
value: 48.769999999999996
- type: f1
value: 42.91448356376592
- task:
type: Retrieval
dataset:
name: MTEB FEVER
type: fever
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 54.013
- type: map_at_10
value: 66.239
- type: map_at_100
value: 66.62599999999999
- type: map_at_1000
value: 66.644
- type: map_at_3
value: 63.965
- type: map_at_5
value: 65.45400000000001
- type: mrr_at_1
value: 58.221000000000004
- type: mrr_at_10
value: 70.43700000000001
- type: mrr_at_100
value: 70.744
- type: mrr_at_1000
value: 70.75099999999999
- type: mrr_at_3
value: 68.284
- type: mrr_at_5
value: 69.721
- type: ndcg_at_1
value: 58.221000000000004
- type: ndcg_at_10
value: 72.327
- type: ndcg_at_100
value: 73.953
- type: ndcg_at_1000
value: 74.312
- type: ndcg_at_3
value: 68.062
- type: ndcg_at_5
value: 70.56400000000001
- type: precision_at_1
value: 58.221000000000004
- type: precision_at_10
value: 9.521
- type: precision_at_100
value: 1.045
- type: precision_at_1000
value: 0.109
- type: precision_at_3
value: 27.348
- type: precision_at_5
value: 17.794999999999998
- type: recall_at_1
value: 54.013
- type: recall_at_10
value: 86.957
- type: recall_at_100
value: 93.911
- type: recall_at_1000
value: 96.38
- type: recall_at_3
value: 75.555
- type: recall_at_5
value: 81.671
- task:
type: Retrieval
dataset:
name: MTEB FiQA2018
type: fiqa
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 21.254
- type: map_at_10
value: 33.723
- type: map_at_100
value: 35.574
- type: map_at_1000
value: 35.730000000000004
- type: map_at_3
value: 29.473
- type: map_at_5
value: 31.543
- type: mrr_at_1
value: 41.358
- type: mrr_at_10
value: 49.498
- type: mrr_at_100
value: 50.275999999999996
- type: mrr_at_1000
value: 50.308
- type: mrr_at_3
value: 47.016000000000005
- type: mrr_at_5
value: 48.336
- type: ndcg_at_1
value: 41.358
- type: ndcg_at_10
value: 41.579
- type: ndcg_at_100
value: 48.455
- type: ndcg_at_1000
value: 51.165000000000006
- type: ndcg_at_3
value: 37.681
- type: ndcg_at_5
value: 38.49
- type: precision_at_1
value: 41.358
- type: precision_at_10
value: 11.543000000000001
- type: precision_at_100
value: 1.87
- type: precision_at_1000
value: 0.23600000000000002
- type: precision_at_3
value: 24.743000000000002
- type: precision_at_5
value: 17.994
- type: recall_at_1
value: 21.254
- type: recall_at_10
value: 48.698
- type: recall_at_100
value: 74.588
- type: recall_at_1000
value: 91.00200000000001
- type: recall_at_3
value: 33.939
- type: recall_at_5
value: 39.367000000000004
- task:
type: Retrieval
dataset:
name: MTEB HotpotQA
type: hotpotqa
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 35.922
- type: map_at_10
value: 52.32599999999999
- type: map_at_100
value: 53.18000000000001
- type: map_at_1000
value: 53.245
- type: map_at_3
value: 49.294
- type: map_at_5
value: 51.202999999999996
- type: mrr_at_1
value: 71.843
- type: mrr_at_10
value: 78.24600000000001
- type: mrr_at_100
value: 78.515
- type: mrr_at_1000
value: 78.527
- type: mrr_at_3
value: 77.17500000000001
- type: mrr_at_5
value: 77.852
- type: ndcg_at_1
value: 71.843
- type: ndcg_at_10
value: 61.379
- type: ndcg_at_100
value: 64.535
- type: ndcg_at_1000
value: 65.888
- type: ndcg_at_3
value: 56.958
- type: ndcg_at_5
value: 59.434
- type: precision_at_1
value: 71.843
- type: precision_at_10
value: 12.686
- type: precision_at_100
value: 1.517
- type: precision_at_1000
value: 0.16999999999999998
- type: precision_at_3
value: 35.778
- type: precision_at_5
value: 23.422
- type: recall_at_1
value: 35.922
- type: recall_at_10
value: 63.43
- type: recall_at_100
value: 75.868
- type: recall_at_1000
value: 84.88900000000001
- type: recall_at_3
value: 53.666000000000004
- type: recall_at_5
value: 58.555
- task:
type: Classification
dataset:
name: MTEB ImdbClassification
type: mteb/imdb
config: default
split: test
revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7
metrics:
- type: accuracy
value: 79.4408
- type: ap
value: 73.52820871620366
- type: f1
value: 79.36240238685001
- task:
type: Retrieval
dataset:
name: MTEB MSMARCO
type: msmarco
config: default
split: dev
revision: None
metrics:
- type: map_at_1
value: 21.826999999999998
- type: map_at_10
value: 34.04
- type: map_at_100
value: 35.226
- type: map_at_1000
value: 35.275
- type: map_at_3
value: 30.165999999999997
- type: map_at_5
value: 32.318000000000005
- type: mrr_at_1
value: 22.464000000000002
- type: mrr_at_10
value: 34.631
- type: mrr_at_100
value: 35.752
- type: mrr_at_1000
value: 35.795
- type: mrr_at_3
value: 30.798
- type: mrr_at_5
value: 32.946999999999996
- type: ndcg_at_1
value: 22.464000000000002
- type: ndcg_at_10
value: 40.919
- type: ndcg_at_100
value: 46.632
- type: ndcg_at_1000
value: 47.833
- type: ndcg_at_3
value: 32.992
- type: ndcg_at_5
value: 36.834
- type: precision_at_1
value: 22.464000000000002
- type: precision_at_10
value: 6.494
- type: precision_at_100
value: 0.9369999999999999
- type: precision_at_1000
value: 0.104
- type: precision_at_3
value: 14.021
- type: precision_at_5
value: 10.347000000000001
- type: recall_at_1
value: 21.826999999999998
- type: recall_at_10
value: 62.132
- type: recall_at_100
value: 88.55199999999999
- type: recall_at_1000
value: 97.707
- type: recall_at_3
value: 40.541
- type: recall_at_5
value: 49.739
- task:
type: Classification
dataset:
name: MTEB MTOPDomainClassification (en)
type: mteb/mtop_domain
config: en
split: test
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
metrics:
- type: accuracy
value: 95.68399452804377
- type: f1
value: 95.25490609832268
- task:
type: Classification
dataset:
name: MTEB MTOPIntentClassification (en)
type: mteb/mtop_intent
config: en
split: test
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
metrics:
- type: accuracy
value: 83.15321477428182
- type: f1
value: 60.35476439087966
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (en)
type: mteb/amazon_massive_intent
config: en
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 71.92669804976462
- type: f1
value: 69.22815107207565
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (en)
type: mteb/amazon_massive_scenario
config: en
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 74.4855413584398
- type: f1
value: 72.92107516103387
- task:
type: Clustering
dataset:
name: MTEB MedrxivClusteringP2P
type: mteb/medrxiv-clustering-p2p
config: default
split: test
revision: e7a26af6f3ae46b30dde8737f02c07b1505bcc73
metrics:
- type: v_measure
value: 32.412679360205544
- task:
type: Clustering
dataset:
name: MTEB MedrxivClusteringS2S
type: mteb/medrxiv-clustering-s2s
config: default
split: test
revision: 35191c8c0dca72d8ff3efcd72aa802307d469663
metrics:
- type: v_measure
value: 28.09211869875204
- task:
type: Reranking
dataset:
name: MTEB MindSmallReranking
type: mteb/mind_small
config: default
split: test
revision: 3bdac13927fdc888b903db93b2ffdbd90b295a69
metrics:
- type: map
value: 30.540919056982545
- type: mrr
value: 31.529904607063536
- task:
type: Retrieval
dataset:
name: MTEB NFCorpus
type: nfcorpus
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 5.745
- type: map_at_10
value: 12.013
- type: map_at_100
value: 15.040000000000001
- type: map_at_1000
value: 16.427
- type: map_at_3
value: 8.841000000000001
- type: map_at_5
value: 10.289
- type: mrr_at_1
value: 45.201
- type: mrr_at_10
value: 53.483999999999995
- type: mrr_at_100
value: 54.20700000000001
- type: mrr_at_1000
value: 54.252
- type: mrr_at_3
value: 51.29
- type: mrr_at_5
value: 52.73
- type: ndcg_at_1
value: 43.808
- type: ndcg_at_10
value: 32.445
- type: ndcg_at_100
value: 30.031000000000002
- type: ndcg_at_1000
value: 39.007
- type: ndcg_at_3
value: 37.204
- type: ndcg_at_5
value: 35.07
- type: precision_at_1
value: 45.201
- type: precision_at_10
value: 23.684
- type: precision_at_100
value: 7.600999999999999
- type: precision_at_1000
value: 2.043
- type: precision_at_3
value: 33.953
- type: precision_at_5
value: 29.412
- type: recall_at_1
value: 5.745
- type: recall_at_10
value: 16.168
- type: recall_at_100
value: 30.875999999999998
- type: recall_at_1000
value: 62.686
- type: recall_at_3
value: 9.75
- type: recall_at_5
value: 12.413
- task:
type: Retrieval
dataset:
name: MTEB NQ
type: nq
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 37.828
- type: map_at_10
value: 53.239000000000004
- type: map_at_100
value: 54.035999999999994
- type: map_at_1000
value: 54.067
- type: map_at_3
value: 49.289
- type: map_at_5
value: 51.784
- type: mrr_at_1
value: 42.497
- type: mrr_at_10
value: 55.916999999999994
- type: mrr_at_100
value: 56.495
- type: mrr_at_1000
value: 56.516999999999996
- type: mrr_at_3
value: 52.800000000000004
- type: mrr_at_5
value: 54.722
- type: ndcg_at_1
value: 42.468
- type: ndcg_at_10
value: 60.437
- type: ndcg_at_100
value: 63.731
- type: ndcg_at_1000
value: 64.41799999999999
- type: ndcg_at_3
value: 53.230999999999995
- type: ndcg_at_5
value: 57.26
- type: precision_at_1
value: 42.468
- type: precision_at_10
value: 9.47
- type: precision_at_100
value: 1.1360000000000001
- type: precision_at_1000
value: 0.12
- type: precision_at_3
value: 23.724999999999998
- type: precision_at_5
value: 16.593
- type: recall_at_1
value: 37.828
- type: recall_at_10
value: 79.538
- type: recall_at_100
value: 93.646
- type: recall_at_1000
value: 98.72999999999999
- type: recall_at_3
value: 61.134
- type: recall_at_5
value: 70.377
- task:
type: Retrieval
dataset:
name: MTEB QuoraRetrieval
type: quora
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 70.548
- type: map_at_10
value: 84.466
- type: map_at_100
value: 85.10600000000001
- type: map_at_1000
value: 85.123
- type: map_at_3
value: 81.57600000000001
- type: map_at_5
value: 83.399
- type: mrr_at_1
value: 81.24
- type: mrr_at_10
value: 87.457
- type: mrr_at_100
value: 87.574
- type: mrr_at_1000
value: 87.575
- type: mrr_at_3
value: 86.507
- type: mrr_at_5
value: 87.205
- type: ndcg_at_1
value: 81.25
- type: ndcg_at_10
value: 88.203
- type: ndcg_at_100
value: 89.457
- type: ndcg_at_1000
value: 89.563
- type: ndcg_at_3
value: 85.465
- type: ndcg_at_5
value: 87.007
- type: precision_at_1
value: 81.25
- type: precision_at_10
value: 13.373
- type: precision_at_100
value: 1.5270000000000001
- type: precision_at_1000
value: 0.157
- type: precision_at_3
value: 37.417
- type: precision_at_5
value: 24.556
- type: recall_at_1
value: 70.548
- type: recall_at_10
value: 95.208
- type: recall_at_100
value: 99.514
- type: recall_at_1000
value: 99.988
- type: recall_at_3
value: 87.214
- type: recall_at_5
value: 91.696
- task:
type: Clustering
dataset:
name: MTEB RedditClustering
type: mteb/reddit-clustering
config: default
split: test
revision: 24640382cdbf8abc73003fb0fa6d111a705499eb
metrics:
- type: v_measure
value: 53.04822095496839
- task:
type: Clustering
dataset:
name: MTEB RedditClusteringP2P
type: mteb/reddit-clustering-p2p
config: default
split: test
revision: 282350215ef01743dc01b456c7f5241fa8937f16
metrics:
- type: v_measure
value: 60.30778476474675
- task:
type: Retrieval
dataset:
name: MTEB SCIDOCS
type: scidocs
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 4.692
- type: map_at_10
value: 11.766
- type: map_at_100
value: 13.904
- type: map_at_1000
value: 14.216999999999999
- type: map_at_3
value: 8.245
- type: map_at_5
value: 9.92
- type: mrr_at_1
value: 23.0
- type: mrr_at_10
value: 33.78
- type: mrr_at_100
value: 34.922
- type: mrr_at_1000
value: 34.973
- type: mrr_at_3
value: 30.2
- type: mrr_at_5
value: 32.565
- type: ndcg_at_1
value: 23.0
- type: ndcg_at_10
value: 19.863
- type: ndcg_at_100
value: 28.141
- type: ndcg_at_1000
value: 33.549
- type: ndcg_at_3
value: 18.434
- type: ndcg_at_5
value: 16.384
- type: precision_at_1
value: 23.0
- type: precision_at_10
value: 10.39
- type: precision_at_100
value: 2.235
- type: precision_at_1000
value: 0.35300000000000004
- type: precision_at_3
value: 17.133000000000003
- type: precision_at_5
value: 14.44
- type: recall_at_1
value: 4.692
- type: recall_at_10
value: 21.025
- type: recall_at_100
value: 45.324999999999996
- type: recall_at_1000
value: 71.675
- type: recall_at_3
value: 10.440000000000001
- type: recall_at_5
value: 14.64
- task:
type: STS
dataset:
name: MTEB SICK-R
type: mteb/sickr-sts
config: default
split: test
revision: a6ea5a8cab320b040a23452cc28066d9beae2cee
metrics:
- type: cos_sim_pearson
value: 84.96178184892842
- type: cos_sim_spearman
value: 79.6487740813199
- type: euclidean_pearson
value: 82.06661161625023
- type: euclidean_spearman
value: 79.64876769031183
- type: manhattan_pearson
value: 82.07061164575131
- type: manhattan_spearman
value: 79.65197039464537
- task:
type: STS
dataset:
name: MTEB STS12
type: mteb/sts12-sts
config: default
split: test
revision: a0d554a64d88156834ff5ae9920b964011b16384
metrics:
- type: cos_sim_pearson
value: 84.15305604100027
- type: cos_sim_spearman
value: 74.27447427941591
- type: euclidean_pearson
value: 80.52737337565307
- type: euclidean_spearman
value: 74.27416077132192
- type: manhattan_pearson
value: 80.53728571140387
- type: manhattan_spearman
value: 74.28853605753457
- task:
type: STS
dataset:
name: MTEB STS13
type: mteb/sts13-sts
config: default
split: test
revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca
metrics:
- type: cos_sim_pearson
value: 83.44386080639279
- type: cos_sim_spearman
value: 84.17947648159536
- type: euclidean_pearson
value: 83.34145388129387
- type: euclidean_spearman
value: 84.17947648159536
- type: manhattan_pearson
value: 83.30699061927966
- type: manhattan_spearman
value: 84.18125737380451
- task:
type: STS
dataset:
name: MTEB STS14
type: mteb/sts14-sts
config: default
split: test
revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375
metrics:
- type: cos_sim_pearson
value: 81.57392220985612
- type: cos_sim_spearman
value: 78.80745014464101
- type: euclidean_pearson
value: 80.01660371487199
- type: euclidean_spearman
value: 78.80741240102256
- type: manhattan_pearson
value: 79.96810779507953
- type: manhattan_spearman
value: 78.75600400119448
- task:
type: STS
dataset:
name: MTEB STS15
type: mteb/sts15-sts
config: default
split: test
revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3
metrics:
- type: cos_sim_pearson
value: 86.85421063026625
- type: cos_sim_spearman
value: 87.55320285299192
- type: euclidean_pearson
value: 86.69750143323517
- type: euclidean_spearman
value: 87.55320284326378
- type: manhattan_pearson
value: 86.63379169960379
- type: manhattan_spearman
value: 87.4815029877984
- task:
type: STS
dataset:
name: MTEB STS16
type: mteb/sts16-sts
config: default
split: test
revision: 4d8694f8f0e0100860b497b999b3dbed754a0513
metrics:
- type: cos_sim_pearson
value: 84.31314130411842
- type: cos_sim_spearman
value: 85.3489588181433
- type: euclidean_pearson
value: 84.13240933463535
- type: euclidean_spearman
value: 85.34902871403281
- type: manhattan_pearson
value: 84.01183086503559
- type: manhattan_spearman
value: 85.19316703166102
- task:
type: STS
dataset:
name: MTEB STS17 (en-en)
type: mteb/sts17-crosslingual-sts
config: en-en
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 89.09979781689536
- type: cos_sim_spearman
value: 88.87813323759015
- type: euclidean_pearson
value: 88.65413031123792
- type: euclidean_spearman
value: 88.87813323759015
- type: manhattan_pearson
value: 88.61818758256024
- type: manhattan_spearman
value: 88.81044100494604
- task:
type: STS
dataset:
name: MTEB STS22 (en)
type: mteb/sts22-crosslingual-sts
config: en
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 62.30693258111531
- type: cos_sim_spearman
value: 62.195516523251946
- type: euclidean_pearson
value: 62.951283701049476
- type: euclidean_spearman
value: 62.195516523251946
- type: manhattan_pearson
value: 63.068322281439535
- type: manhattan_spearman
value: 62.10621171028406
- task:
type: STS
dataset:
name: MTEB STSBenchmark
type: mteb/stsbenchmark-sts
config: default
split: test
revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831
metrics:
- type: cos_sim_pearson
value: 84.27092833763909
- type: cos_sim_spearman
value: 84.84429717949759
- type: euclidean_pearson
value: 84.8516966060792
- type: euclidean_spearman
value: 84.84429717949759
- type: manhattan_pearson
value: 84.82203139242881
- type: manhattan_spearman
value: 84.8358503952945
- task:
type: Reranking
dataset:
name: MTEB SciDocsRR
type: mteb/scidocs-reranking
config: default
split: test
revision: d3c5e1fc0b855ab6097bf1cda04dd73947d7caab
metrics:
- type: map
value: 83.10290863981409
- type: mrr
value: 95.31168450286097
- task:
type: Retrieval
dataset:
name: MTEB SciFact
type: scifact
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 52.161
- type: map_at_10
value: 62.138000000000005
- type: map_at_100
value: 62.769
- type: map_at_1000
value: 62.812
- type: map_at_3
value: 59.111000000000004
- type: map_at_5
value: 60.995999999999995
- type: mrr_at_1
value: 55.333
- type: mrr_at_10
value: 63.504000000000005
- type: mrr_at_100
value: 64.036
- type: mrr_at_1000
value: 64.08
- type: mrr_at_3
value: 61.278
- type: mrr_at_5
value: 62.778
- type: ndcg_at_1
value: 55.333
- type: ndcg_at_10
value: 66.678
- type: ndcg_at_100
value: 69.415
- type: ndcg_at_1000
value: 70.453
- type: ndcg_at_3
value: 61.755
- type: ndcg_at_5
value: 64.546
- type: precision_at_1
value: 55.333
- type: precision_at_10
value: 9.033
- type: precision_at_100
value: 1.043
- type: precision_at_1000
value: 0.11199999999999999
- type: precision_at_3
value: 24.221999999999998
- type: precision_at_5
value: 16.333000000000002
- type: recall_at_1
value: 52.161
- type: recall_at_10
value: 79.156
- type: recall_at_100
value: 91.333
- type: recall_at_1000
value: 99.333
- type: recall_at_3
value: 66.43299999999999
- type: recall_at_5
value: 73.272
- task:
type: PairClassification
dataset:
name: MTEB SprintDuplicateQuestions
type: mteb/sprintduplicatequestions-pairclassification
config: default
split: test
revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46
metrics:
- type: cos_sim_accuracy
value: 99.81287128712871
- type: cos_sim_ap
value: 95.30034785910676
- type: cos_sim_f1
value: 90.28629856850716
- type: cos_sim_precision
value: 92.36401673640168
- type: cos_sim_recall
value: 88.3
- type: dot_accuracy
value: 99.81287128712871
- type: dot_ap
value: 95.30034785910676
- type: dot_f1
value: 90.28629856850716
- type: dot_precision
value: 92.36401673640168
- type: dot_recall
value: 88.3
- type: euclidean_accuracy
value: 99.81287128712871
- type: euclidean_ap
value: 95.30034785910676
- type: euclidean_f1
value: 90.28629856850716
- type: euclidean_precision
value: 92.36401673640168
- type: euclidean_recall
value: 88.3
- type: manhattan_accuracy
value: 99.80990099009901
- type: manhattan_ap
value: 95.26880751950654
- type: manhattan_f1
value: 90.22177419354838
- type: manhattan_precision
value: 90.95528455284553
- type: manhattan_recall
value: 89.5
- type: max_accuracy
value: 99.81287128712871
- type: max_ap
value: 95.30034785910676
- type: max_f1
value: 90.28629856850716
- task:
type: Clustering
dataset:
name: MTEB StackExchangeClustering
type: mteb/stackexchange-clustering
config: default
split: test
revision: 6cbc1f7b2bc0622f2e39d2c77fa502909748c259
metrics:
- type: v_measure
value: 58.518662504351184
- task:
type: Clustering
dataset:
name: MTEB StackExchangeClusteringP2P
type: mteb/stackexchange-clustering-p2p
config: default
split: test
revision: 815ca46b2622cec33ccafc3735d572c266efdb44
metrics:
- type: v_measure
value: 34.96168178378587
- task:
type: Reranking
dataset:
name: MTEB StackOverflowDupQuestions
type: mteb/stackoverflowdupquestions-reranking
config: default
split: test
revision: e185fbe320c72810689fc5848eb6114e1ef5ec69
metrics:
- type: map
value: 52.04862593471896
- type: mrr
value: 52.97238402936932
- task:
type: Summarization
dataset:
name: MTEB SummEval
type: mteb/summeval
config: default
split: test
revision: cda12ad7615edc362dbf25a00fdd61d3b1eaf93c
metrics:
- type: cos_sim_pearson
value: 30.092545236479946
- type: cos_sim_spearman
value: 31.599851000175498
- type: dot_pearson
value: 30.092542723901676
- type: dot_spearman
value: 31.599851000175498
- task:
type: Retrieval
dataset:
name: MTEB TRECCOVID
type: trec-covid
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 0.189
- type: map_at_10
value: 1.662
- type: map_at_100
value: 9.384
- type: map_at_1000
value: 22.669
- type: map_at_3
value: 0.5559999999999999
- type: map_at_5
value: 0.9039999999999999
- type: mrr_at_1
value: 68.0
- type: mrr_at_10
value: 81.01899999999999
- type: mrr_at_100
value: 81.01899999999999
- type: mrr_at_1000
value: 81.01899999999999
- type: mrr_at_3
value: 79.333
- type: mrr_at_5
value: 80.733
- type: ndcg_at_1
value: 63.0
- type: ndcg_at_10
value: 65.913
- type: ndcg_at_100
value: 51.895
- type: ndcg_at_1000
value: 46.967
- type: ndcg_at_3
value: 65.49199999999999
- type: ndcg_at_5
value: 66.69699999999999
- type: precision_at_1
value: 68.0
- type: precision_at_10
value: 71.6
- type: precision_at_100
value: 53.66
- type: precision_at_1000
value: 21.124000000000002
- type: precision_at_3
value: 72.667
- type: precision_at_5
value: 74.0
- type: recall_at_1
value: 0.189
- type: recall_at_10
value: 1.913
- type: recall_at_100
value: 12.601999999999999
- type: recall_at_1000
value: 44.296
- type: recall_at_3
value: 0.605
- type: recall_at_5
value: 1.018
- task:
type: Retrieval
dataset:
name: MTEB Touche2020
type: webis-touche2020
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 2.701
- type: map_at_10
value: 10.445
- type: map_at_100
value: 17.324
- type: map_at_1000
value: 19.161
- type: map_at_3
value: 5.497
- type: map_at_5
value: 7.278
- type: mrr_at_1
value: 30.612000000000002
- type: mrr_at_10
value: 45.534
- type: mrr_at_100
value: 45.792
- type: mrr_at_1000
value: 45.806999999999995
- type: mrr_at_3
value: 37.755
- type: mrr_at_5
value: 43.469
- type: ndcg_at_1
value: 26.531
- type: ndcg_at_10
value: 26.235000000000003
- type: ndcg_at_100
value: 39.17
- type: ndcg_at_1000
value: 51.038
- type: ndcg_at_3
value: 23.625
- type: ndcg_at_5
value: 24.338
- type: precision_at_1
value: 30.612000000000002
- type: precision_at_10
value: 24.285999999999998
- type: precision_at_100
value: 8.224
- type: precision_at_1000
value: 1.6179999999999999
- type: precision_at_3
value: 24.490000000000002
- type: precision_at_5
value: 24.898
- type: recall_at_1
value: 2.701
- type: recall_at_10
value: 17.997
- type: recall_at_100
value: 51.766999999999996
- type: recall_at_1000
value: 87.863
- type: recall_at_3
value: 6.295000000000001
- type: recall_at_5
value: 9.993
- task:
type: Classification
dataset:
name: MTEB ToxicConversationsClassification
type: mteb/toxic_conversations_50k
config: default
split: test
revision: d7c0de2777da35d6aae2200a62c6e0e5af397c4c
metrics:
- type: accuracy
value: 73.3474
- type: ap
value: 15.393431414459924
- type: f1
value: 56.466681887882416
- task:
type: Classification
dataset:
name: MTEB TweetSentimentExtractionClassification
type: mteb/tweet_sentiment_extraction
config: default
split: test
revision: d604517c81ca91fe16a244d1248fc021f9ecee7a
metrics:
- type: accuracy
value: 62.062818336163
- type: f1
value: 62.11230840463252
- task:
type: Clustering
dataset:
name: MTEB TwentyNewsgroupsClustering
type: mteb/twentynewsgroups-clustering
config: default
split: test
revision: 6125ec4e24fa026cec8a478383ee943acfbd5449
metrics:
- type: v_measure
value: 42.464892820845115
- task:
type: PairClassification
dataset:
name: MTEB TwitterSemEval2015
type: mteb/twittersemeval2015-pairclassification
config: default
split: test
revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1
metrics:
- type: cos_sim_accuracy
value: 86.15962329379508
- type: cos_sim_ap
value: 74.73674057919256
- type: cos_sim_f1
value: 68.81245642574947
- type: cos_sim_precision
value: 61.48255813953488
- type: cos_sim_recall
value: 78.12664907651715
- type: dot_accuracy
value: 86.15962329379508
- type: dot_ap
value: 74.7367634988281
- type: dot_f1
value: 68.81245642574947
- type: dot_precision
value: 61.48255813953488
- type: dot_recall
value: 78.12664907651715
- type: euclidean_accuracy
value: 86.15962329379508
- type: euclidean_ap
value: 74.7367761466634
- type: euclidean_f1
value: 68.81245642574947
- type: euclidean_precision
value: 61.48255813953488
- type: euclidean_recall
value: 78.12664907651715
- type: manhattan_accuracy
value: 86.21326816474935
- type: manhattan_ap
value: 74.64416473733951
- type: manhattan_f1
value: 68.80924855491331
- type: manhattan_precision
value: 61.23456790123457
- type: manhattan_recall
value: 78.52242744063325
- type: max_accuracy
value: 86.21326816474935
- type: max_ap
value: 74.7367761466634
- type: max_f1
value: 68.81245642574947
- task:
type: PairClassification
dataset:
name: MTEB TwitterURLCorpus
type: mteb/twitterurlcorpus-pairclassification
config: default
split: test
revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf
metrics:
- type: cos_sim_accuracy
value: 88.97620988085536
- type: cos_sim_ap
value: 86.08680845745758
- type: cos_sim_f1
value: 78.02793637114438
- type: cos_sim_precision
value: 73.11082699683736
- type: cos_sim_recall
value: 83.65414228518632
- type: dot_accuracy
value: 88.97620988085536
- type: dot_ap
value: 86.08681149437946
- type: dot_f1
value: 78.02793637114438
- type: dot_precision
value: 73.11082699683736
- type: dot_recall
value: 83.65414228518632
- type: euclidean_accuracy
value: 88.97620988085536
- type: euclidean_ap
value: 86.08681215460771
- type: euclidean_f1
value: 78.02793637114438
- type: euclidean_precision
value: 73.11082699683736
- type: euclidean_recall
value: 83.65414228518632
- type: manhattan_accuracy
value: 88.88888888888889
- type: manhattan_ap
value: 86.02916327562438
- type: manhattan_f1
value: 78.02063045516843
- type: manhattan_precision
value: 73.38851947346994
- type: manhattan_recall
value: 83.2768709578072
- type: max_accuracy
value: 88.97620988085536
- type: max_ap
value: 86.08681215460771
- type: max_f1
value: 78.02793637114438
---
# narainp/jina-embeddings-v2-base-en-Q8_0-GGUF
This model was converted to GGUF format from [`jinaai/jina-embeddings-v2-base-en`](https://huggingface.co/jinaai/jina-embeddings-v2-base-en) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/jinaai/jina-embeddings-v2-base-en) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo narainp/jina-embeddings-v2-base-en-Q8_0-GGUF --hf-file jina-embeddings-v2-base-en-q8_0.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo narainp/jina-embeddings-v2-base-en-Q8_0-GGUF --hf-file jina-embeddings-v2-base-en-q8_0.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo narainp/jina-embeddings-v2-base-en-Q8_0-GGUF --hf-file jina-embeddings-v2-base-en-q8_0.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo narainp/jina-embeddings-v2-base-en-Q8_0-GGUF --hf-file jina-embeddings-v2-base-en-q8_0.gguf -c 2048
```
| [
"SUMMARIZATION"
] | Non_BioNLP |
AdapterHub/distilbert-base-uncased_qa_squad1_pfeiffer | AdapterHub | question-answering | [
"adapter-transformers",
"question-answering",
"adapterhub:qa/squad1",
"distilbert",
"dataset:squad",
"license:apache-2.0",
"region:us"
] | 1,714,939,010,000 | 2024-05-05T19:56:52 | 3 | 0 | ---
datasets:
- squad
license: apache-2.0
tags:
- question-answering
- adapter-transformers
- adapterhub:qa/squad1
- distilbert
---
# Adapter `distilbert-base-uncased_qa_squad1_pfeiffer` for distilbert-base-uncased
Adapter for distilbert-base-uncased in Pfeiffer architecture trained on the SQuAD 1.1 dataset for 15 epochs with early stopping and a learning rate of 1e-4.
**This adapter was created for usage with the [Adapters](https://github.com/Adapter-Hub/adapters) library.**
## Usage
First, install `adapters`:
```
pip install -U adapters
```
Now, the adapter can be loaded and activated like this:
```python
from adapters import AutoAdapterModel
model = AutoAdapterModel.from_pretrained("distilbert-base-uncased")
adapter_name = model.load_adapter("AdapterHub/distilbert-base-uncased_qa_squad1_pfeiffer")
model.set_active_adapters(adapter_name)
```
## Architecture & Training
- Adapter architecture: pfeiffer
- Prediction head: question answering
- Dataset: [SQuAD 1.1](https://rajpurkar.github.io/SQuAD-explorer/)
## Author Information
- Author name(s): Clifton Poth
- Author email: [email protected]
- Author links: [Website](https://calpt.github.io), [GitHub](https://github.com/calpt), [Twitter](https://twitter.com/@clifapt)
## Citation
```bibtex
```
*This adapter has been auto-imported from https://github.com/Adapter-Hub/Hub/blob/master/adapters/ukp/distilbert-base-uncased_qa_squad1_pfeiffer.yaml*. | [
"QUESTION_ANSWERING"
] | Non_BioNLP |
RichardErkhov/sail_-_Sailor-0.5B-gguf | RichardErkhov | null | [
"gguf",
"arxiv:2404.03608",
"endpoints_compatible",
"region:us",
"conversational"
] | 1,719,489,157,000 | 2024-06-27T11:58:18 | 62 | 0 | ---
{}
---
Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
Sailor-0.5B - GGUF
- Model creator: https://huggingface.co/sail/
- Original model: https://huggingface.co/sail/Sailor-0.5B/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [Sailor-0.5B.Q2_K.gguf](https://huggingface.co/RichardErkhov/sail_-_Sailor-0.5B-gguf/blob/main/Sailor-0.5B.Q2_K.gguf) | Q2_K | 0.28GB |
| [Sailor-0.5B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/sail_-_Sailor-0.5B-gguf/blob/main/Sailor-0.5B.IQ3_XS.gguf) | IQ3_XS | 0.3GB |
| [Sailor-0.5B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/sail_-_Sailor-0.5B-gguf/blob/main/Sailor-0.5B.IQ3_S.gguf) | IQ3_S | 0.31GB |
| [Sailor-0.5B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/sail_-_Sailor-0.5B-gguf/blob/main/Sailor-0.5B.Q3_K_S.gguf) | Q3_K_S | 0.31GB |
| [Sailor-0.5B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/sail_-_Sailor-0.5B-gguf/blob/main/Sailor-0.5B.IQ3_M.gguf) | IQ3_M | 0.32GB |
| [Sailor-0.5B.Q3_K.gguf](https://huggingface.co/RichardErkhov/sail_-_Sailor-0.5B-gguf/blob/main/Sailor-0.5B.Q3_K.gguf) | Q3_K | 0.33GB |
| [Sailor-0.5B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/sail_-_Sailor-0.5B-gguf/blob/main/Sailor-0.5B.Q3_K_M.gguf) | Q3_K_M | 0.33GB |
| [Sailor-0.5B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/sail_-_Sailor-0.5B-gguf/blob/main/Sailor-0.5B.Q3_K_L.gguf) | Q3_K_L | 0.34GB |
| [Sailor-0.5B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/sail_-_Sailor-0.5B-gguf/blob/main/Sailor-0.5B.IQ4_XS.gguf) | IQ4_XS | 0.36GB |
| [Sailor-0.5B.Q4_0.gguf](https://huggingface.co/RichardErkhov/sail_-_Sailor-0.5B-gguf/blob/main/Sailor-0.5B.Q4_0.gguf) | Q4_0 | 0.37GB |
| [Sailor-0.5B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/sail_-_Sailor-0.5B-gguf/blob/main/Sailor-0.5B.IQ4_NL.gguf) | IQ4_NL | 0.37GB |
| [Sailor-0.5B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/sail_-_Sailor-0.5B-gguf/blob/main/Sailor-0.5B.Q4_K_S.gguf) | Q4_K_S | 0.37GB |
| [Sailor-0.5B.Q4_K.gguf](https://huggingface.co/RichardErkhov/sail_-_Sailor-0.5B-gguf/blob/main/Sailor-0.5B.Q4_K.gguf) | Q4_K | 0.38GB |
| [Sailor-0.5B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/sail_-_Sailor-0.5B-gguf/blob/main/Sailor-0.5B.Q4_K_M.gguf) | Q4_K_M | 0.38GB |
| [Sailor-0.5B.Q4_1.gguf](https://huggingface.co/RichardErkhov/sail_-_Sailor-0.5B-gguf/blob/main/Sailor-0.5B.Q4_1.gguf) | Q4_1 | 0.39GB |
| [Sailor-0.5B.Q5_0.gguf](https://huggingface.co/RichardErkhov/sail_-_Sailor-0.5B-gguf/blob/main/Sailor-0.5B.Q5_0.gguf) | Q5_0 | 0.42GB |
| [Sailor-0.5B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/sail_-_Sailor-0.5B-gguf/blob/main/Sailor-0.5B.Q5_K_S.gguf) | Q5_K_S | 0.42GB |
| [Sailor-0.5B.Q5_K.gguf](https://huggingface.co/RichardErkhov/sail_-_Sailor-0.5B-gguf/blob/main/Sailor-0.5B.Q5_K.gguf) | Q5_K | 0.43GB |
| [Sailor-0.5B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/sail_-_Sailor-0.5B-gguf/blob/main/Sailor-0.5B.Q5_K_M.gguf) | Q5_K_M | 0.43GB |
| [Sailor-0.5B.Q5_1.gguf](https://huggingface.co/RichardErkhov/sail_-_Sailor-0.5B-gguf/blob/main/Sailor-0.5B.Q5_1.gguf) | Q5_1 | 0.45GB |
| [Sailor-0.5B.Q6_K.gguf](https://huggingface.co/RichardErkhov/sail_-_Sailor-0.5B-gguf/blob/main/Sailor-0.5B.Q6_K.gguf) | Q6_K | 0.48GB |
| [Sailor-0.5B.Q8_0.gguf](https://huggingface.co/RichardErkhov/sail_-_Sailor-0.5B-gguf/blob/main/Sailor-0.5B.Q8_0.gguf) | Q8_0 | 0.62GB |
Original model description:
---
language:
- en
- zh
- id
- th
- vi
- ms
- lo
datasets:
- cerebras/SlimPajama-627B
- Skywork/SkyPile-150B
- allenai/MADLAD-400
- cc100
tags:
- multilingual
- sea
- sailor
license: apache-2.0
base_model: Qwen/Qwen1.5-0.5B
inference: false
model-index:
- name: Sailor-0.5B
results:
- task:
type: text-generation
dataset:
name: XQuAD-Thai
type: XQuAD-Thai
metrics:
- name: EM (3-Shot)
type: EM (3-Shot)
value: 15.84
- name: F1 (3-Shot)
type: F1 (3-Shot)
value: 27.58
- task:
type: text-generation
dataset:
name: TyDiQA-Indonesian
type: TyDiQA-Indonesian
metrics:
- name: EM (3-Shot)
type: EM (3-Shot)
value: 30.44
- name: F1 (3-Shot)
type: F1 (3-Shot)
value: 54.74
- task:
type: text-generation
dataset:
name: XQuAD-Vietnamese
type: XQuAD-Vietnamese
metrics:
- name: EM (3-Shot)
type: EM (3-Shot)
value: 21.13
- name: F1 (3-Shot)
type: F1 (3-Shot)
value: 40.57
- task:
type: text-generation
dataset:
name: XCOPA-Thai
type: XCOPA-Thai
metrics:
- name: EM (3-Shot)
type: EM (3-Shot)
value: 51.00
- task:
type: text-generation
dataset:
name: XCOPA-Indonesian
type: XCOPA-Indonesian
metrics:
- name: EM (3-Shot)
type: EM (3-Shot)
value: 58.20
- task:
type: text-generation
dataset:
name: XCOPA-Vietnamese
type: XCOPA-Vietnamese
metrics:
- name: EM (3-Shot)
type: EM (3-Shot)
value: 58.00
- task:
type: text-generation
dataset:
name: M3Exam-Thai
type: M3Exam-Thai
metrics:
- name: EM (3-Shot)
type: EM (3-Shot)
value: 24.41
- task:
type: text-generation
dataset:
name: M3Exam-Indonesian
type: M3Exam-Indonesian
metrics:
- name: EM (3-Shot)
type: EM (3-Shot)
value: 26.15
- task:
type: text-generation
dataset:
name: M3Exam-Vietnamese
type: M3Exam-Vietnamese
metrics:
- name: EM (3-Shot)
type: EM (3-Shot)
value: 30.91
- task:
type: text-generation
dataset:
name: BELEBELE-Thai
type: BELEBELE-Thai
metrics:
- name: EM (3-Shot)
type: EM (3-Shot)
value: 32.22
- task:
type: text-generation
dataset:
name: BELEBELE-Indonesian
type: BELEBELE-Indonesian
metrics:
- name: EM (3-Shot)
type: EM (3-Shot)
value: 30.89
- task:
type: text-generation
dataset:
name: BELEBELE-Vietnamese
type: BELEBELE-Vietnamese
metrics:
- name: EM (3-Shot)
type: EM (3-Shot)
value: 32.33
---
<div align="center">
<img src="banner_sailor.jpg" width="700"/>
</div>
Sailor is a suite of Open Language Models tailored for South-East Asia (SEA), focusing on languages such as 🇮🇩Indonesian, 🇹🇭Thai, 🇻🇳Vietnamese, 🇲🇾Malay, and 🇱🇦Lao.
Developed with careful data curation, Sailor models are designed to understand and generate text across diverse linguistic landscapes of SEA region.
Built from [Qwen 1.5](https://huggingface.co/collections/Qwen/qwen15-65c0a2f577b1ecb76d786524) , Sailor encompasses models of varying sizes, spanning from 0.5B to 7B versions for different requirements.
We further fine-tune the base model with open-source datasets to get instruction-tuned models, namedly Sailor-Chat.
Benchmarking results demonstrate Sailor's proficiency in tasks such as question answering, commonsense reasoning, and other tasks in SEA languages.
> The logo was generated by MidJourney
## Model Summary
- **Model Collections:** [Base Model & Chat Model](https://huggingface.co/collections/sail/sailor-65e19a749f978976f1959825)
- **Project Website:** [sailorllm.github.io](https://sailorllm.github.io/)
- **Codebase:** [github.com/sail-sg/sailor-llm](https://github.com/sail-sg/sailor-llm)
- **Technical Report:** [arxiv.org/pdf/2404.03608.pdf](https://arxiv.org/pdf/2404.03608.pdf)
## Training details
Sailor is crafted by continually pre-training from language models like the remarkable Qwen 1.5 models, which already has a great performance on SEA languages.
The pre-training corpus heavily leverages the publicly available corpus, including
[SlimPajama](https://huggingface.co/datasets/cerebras/SlimPajama-627B),
[SkyPile](https://huggingface.co/datasets/Skywork/SkyPile-150B),
[CC100](https://huggingface.co/datasets/cc100) and [MADLAD-400](https://huggingface.co/datasets/allenai/MADLAD-400).
By employing aggressive data deduplication and careful data cleaning on the collected corpus, we have attained a high-quality dataset spanning various languages.
Through systematic experiments to determine the weights of different languages, Sailor models undergo training from 200B to 400B tokens, tailored to different model sizes.
The approach boosts their performance on SEA languages while maintaining proficiency in English and Chinese without significant compromise.
Finally, we continually pre-train the Qwen1.5-0.5B model with 400 Billion tokens, and other models with 200 Billion tokens to obtain the Sailor models.
## Requirements
The code of Sailor has been in the latest Hugging face transformers and we advise you to install `transformers>=4.37.0`.
## Quickstart
Here provides a code snippet to show you how to load the tokenizer and model and how to generate contents.
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model
model = AutoModelForCausalLM.from_pretrained("sail/Sailor-0.5B", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("sail/Sailor-0.5B")
input_message = "Model bahasa adalah model probabilistik"
### The given Indonesian input translates to 'A language model is a probabilistic model of.'
model_inputs = tokenizer([input_message], return_tensors="pt").to(device)
generated_ids = model.generate(
model_inputs.input_ids,
max_new_tokens=64
)
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)
```
# License
Sailor is distributed under the terms of the Apache License 2.0.
No restrict on the research and the commercial use, but should comply with the [Qwen License](https://huggingface.co/Qwen/Qwen1.5-1.8B/blob/main/LICENSE).
## Citation
If you find sailor useful, please cite our work as follows:
```
@misc{dou2024sailor,
title={Sailor: Open Language Models for South-East Asia},
author={Longxu Dou and Qian Liu and Guangtao Zeng and Jia Guo and Jiahui Zhou and Wei Lu and Min Lin},
year={2024},
eprint={2404.03608},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
# Contact Us
If you have any questions, please raise an issue or contact us at [[email protected]](mailto:[email protected]) or [[email protected]](mailto:[email protected]).
| [
"QUESTION_ANSWERING"
] | Non_BioNLP |
BIFOLD-BigEarthNetv2-0/resnet101-s2-v0.2.0 | BIFOLD-BigEarthNetv2-0 | image-classification | [
"configilm",
"safetensors",
"resnet101",
"BigEarthNet v2.0",
"Remote Sensing",
"Classification",
"image-classification",
"Multispectral",
"arxiv:2407.03653",
"license:mit",
"region:us"
] | 1,728,559,811,000 | 2025-03-14T07:13:14 | 31 | 0 | ---
library_name: configilm
license: mit
tags:
- resnet101
- BigEarthNet v2.0
- Remote Sensing
- Classification
- image-classification
- Multispectral
thumbnail: https://raw.githubusercontent.com/wiki/lhackel-tub/ConfigILM/static/imgs/RSiM_Logo_1.png
widget:
- src: example.png
example_title: Example
output:
- label: Agro-forestry areas
score: 0.0
- label: Arable land
score: 0.0
- label: Beaches, dunes, sands
score: 0.0
- label: Broad-leaved forest
score: 0.0
- label: Coastal wetlands
score: 0.0
---
[TU Berlin](https://www.tu.berlin/) | [RSiM](https://rsim.berlin/) | [DIMA](https://www.dima.tu-berlin.de/menue/database_systems_and_information_management_group/) | [BigEarth](http://www.bigearth.eu/) | [BIFOLD](https://bifold.berlin/)
:---:|:---:|:---:|:---:|:---:
<a href="https://www.tu.berlin/"><img src="https://raw.githubusercontent.com/wiki/lhackel-tub/ConfigILM/static/imgs/tu-berlin-logo-long-red.svg" style="font-size: 1rem; height: 2em; width: auto" alt="TU Berlin Logo"/> | <a href="https://rsim.berlin/"><img src="https://raw.githubusercontent.com/wiki/lhackel-tub/ConfigILM/static/imgs/RSiM_Logo_1.png" style="font-size: 1rem; height: 2em; width: auto" alt="RSiM Logo"> | <a href="https://www.dima.tu-berlin.de/menue/database_systems_and_information_management_group/"><img src="https://raw.githubusercontent.com/wiki/lhackel-tub/ConfigILM/static/imgs/DIMA.png" style="font-size: 1rem; height: 2em; width: auto" alt="DIMA Logo"> | <a href="http://www.bigearth.eu/"><img src="https://raw.githubusercontent.com/wiki/lhackel-tub/ConfigILM/static/imgs/BigEarth.png" style="font-size: 1rem; height: 2em; width: auto" alt="BigEarth Logo"> | <a href="https://bifold.berlin/"><img src="https://raw.githubusercontent.com/wiki/lhackel-tub/ConfigILM/static/imgs/BIFOLD_Logo_farbig.png" style="font-size: 1rem; height: 2em; width: auto; margin-right: 1em" alt="BIFOLD Logo">
# Resnet101 pretrained on BigEarthNet v2.0 using Sentinel-2 bands
<!-- Optional images -->
<!--
[Sentinel-1](https://sentinel.esa.int/web/sentinel/missions/sentinel-1) | [Sentinel-2](https://sentinel.esa.int/web/sentinel/missions/sentinel-2)
:---:|:---:
<a href="https://sentinel.esa.int/web/sentinel/missions/sentinel-1"><img src="https://raw.githubusercontent.com/wiki/lhackel-tub/ConfigILM/static/imgs/sentinel_2.jpg" style="font-size: 1rem; height: 10em; width: auto; margin-right: 1em" alt="Sentinel-2 Satellite"/> | <a href="https://sentinel.esa.int/web/sentinel/missions/sentinel-2"><img src="https://raw.githubusercontent.com/wiki/lhackel-tub/ConfigILM/static/imgs/sentinel_1.jpg" style="font-size: 1rem; height: 10em; width: auto; margin-right: 1em" alt="Sentinel-1 Satellite"/>
-->
This model was trained on the BigEarthNet v2.0 (also known as reBEN) dataset using the Sentinel-2 bands.
It was trained using the following parameters:
- Number of epochs: up to 100 (with early stopping after 5 epochs of no improvement based on validation average
precision macro)
- Batch size: 512
- Learning rate: 0.001
- Dropout rate: 0.15
- Drop Path rate: 0.15
- Learning rate scheduler: LinearWarmupCosineAnnealing for 1000 warmup steps
- Optimizer: AdamW
- Seed: 24
The weights published in this model card were obtained after 15 training epochs.
For more information, please visit the [official BigEarthNet v2.0 (reBEN) repository](https://git.tu-berlin.de/rsim/reben-training-scripts), where you can find the training scripts.
](https://raw.githubusercontent.com/wiki/lhackel-tub/ConfigILM/static/imgs/combined_2000_600_2020_0_wide.jpg)
The model was evaluated on the test set of the BigEarthNet v2.0 dataset with the following results:
| Metric | Macro | Micro |
|:------------------|------------------:|------------------:|
| Average Precision | 0.708653 | 0.861307 |
| F1 Score | 0.637938 | 0.758940 |
| Precision | 0.746407 | 0.810672 |
# Example
| A Sentinel-2 image (true color representation) |
|:---------------------------------------------------:|
| ](example.png) |
| Class labels | Predicted scores |
|:--------------------------------------------------------------------------|--------------------------------------------------------------------------:|
| <p> Agro-forestry areas <br> Arable land <br> Beaches, dunes, sands <br> ... <br> Urban fabric </p> | <p> 0.000000 <br> 0.000000 <br> 0.000000 <br> ... <br> 0.000000 </p> |
To use the model, download the codes that define the model architecture from the
[official BigEarthNet v2.0 (reBEN) repository](https://git.tu-berlin.de/rsim/reben-training-scripts) and load the model using the
code below. Note that you have to install [`configilm`](https://pypi.org/project/configilm/) to use the provided code.
```python
from reben_publication.BigEarthNetv2_0_ImageClassifier import BigEarthNetv2_0_ImageClassifier
model = BigEarthNetv2_0_ImageClassifier.from_pretrained("path_to/huggingface_model_folder")
```
e.g.
```python
from reben_publication.BigEarthNetv2_0_ImageClassifier import BigEarthNetv2_0_ImageClassifier
model = BigEarthNetv2_0_ImageClassifier.from_pretrained(
"BIFOLD-BigEarthNetv2-0/resnet101-s2-v0.1.1")
```
If you use this model in your research or the provided code, please cite the following papers:
```bibtex
@article{clasen2024refinedbigearthnet,
title={reBEN: Refined BigEarthNet Dataset for Remote Sensing Image Analysis},
author={Clasen, Kai Norman and Hackel, Leonard and Burgert, Tom and Sumbul, Gencer and Demir, Beg{\"u}m and Markl, Volker},
year={2024},
eprint={2407.03653},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2407.03653},
}
```
```bibtex
@article{hackel2024configilm,
title={ConfigILM: A general purpose configurable library for combining image and language models for visual question answering},
author={Hackel, Leonard and Clasen, Kai Norman and Demir, Beg{\"u}m},
journal={SoftwareX},
volume={26},
pages={101731},
year={2024},
publisher={Elsevier}
}
```
| [
"QUESTION_ANSWERING"
] | Non_BioNLP |
yannn666/autotrain-nb8vy-2qd7j | yannn666 | text-classification | [
"transformers",
"tensorboard",
"safetensors",
"bert",
"text-classification",
"autotrain",
"base_model:google-bert/bert-base-uncased",
"base_model:finetune:google-bert/bert-base-uncased",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 1,740,260,435,000 | 2025-02-22T21:41:25 | 15 | 0 | ---
base_model: google-bert/bert-base-uncased
library_name: transformers
tags:
- autotrain
- text-classification
widget:
- text: I love AutoTrain
---
# Model Trained Using AutoTrain
- Problem type: Text Classification
## Validation Metrics
loss: 0.230735644698143
f1: 1.0
precision: 1.0
recall: 1.0
auc: 1.0
accuracy: 1.0
| [
"TEXT_CLASSIFICATION"
] | Non_BioNLP |
gokulsrinivasagan/bert_base_lda_20_v1_qqp | gokulsrinivasagan | text-classification | [
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"en",
"dataset:glue",
"base_model:gokulsrinivasagan/bert_base_lda_20_v1",
"base_model:finetune:gokulsrinivasagan/bert_base_lda_20_v1",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 1,732,641,598,000 | 2024-12-04T12:46:45 | 7 | 0 | ---
base_model: gokulsrinivasagan/bert_base_lda_20_v1
datasets:
- glue
language:
- en
library_name: transformers
metrics:
- accuracy
- f1
tags:
- generated_from_trainer
model-index:
- name: bert_base_lda_20_v1_qqp
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: GLUE QQP
type: glue
args: qqp
metrics:
- type: accuracy
value: 0.840563937670047
name: Accuracy
- type: f1
value: 0.7909721771839938
name: F1
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bert_base_lda_20_v1_qqp
This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_20_v1](https://huggingface.co/gokulsrinivasagan/bert_base_lda_20_v1) on the GLUE QQP dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3612
- Accuracy: 0.8406
- F1: 0.7910
- Combined Score: 0.8158
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 256
- eval_batch_size: 256
- seed: 10
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:--------------:|
| 0.4706 | 1.0 | 1422 | 0.4144 | 0.7976 | 0.6849 | 0.7412 |
| 0.3635 | 2.0 | 2844 | 0.3808 | 0.8274 | 0.7774 | 0.8024 |
| 0.2981 | 3.0 | 4266 | 0.3612 | 0.8406 | 0.7910 | 0.8158 |
| 0.2419 | 4.0 | 5688 | 0.4087 | 0.8491 | 0.7909 | 0.8200 |
| 0.1933 | 5.0 | 7110 | 0.4482 | 0.8506 | 0.7908 | 0.8207 |
| 0.1514 | 6.0 | 8532 | 0.4312 | 0.8535 | 0.8018 | 0.8276 |
| 0.1208 | 7.0 | 9954 | 0.5434 | 0.8498 | 0.8041 | 0.8270 |
| 0.097 | 8.0 | 11376 | 0.5605 | 0.8532 | 0.8022 | 0.8277 |
### Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3
| [
"TEXT_CLASSIFICATION"
] | Non_BioNLP |
google/t5-efficient-small-dl12 | google | text2text-generation | [
"transformers",
"pytorch",
"tf",
"jax",
"t5",
"text2text-generation",
"deep-narrow",
"en",
"dataset:c4",
"arxiv:2109.10686",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | 1,646,263,745,000 | 2023-01-24T16:48:05 | 117 | 0 | ---
datasets:
- c4
language:
- en
license: apache-2.0
tags:
- deep-narrow
inference: false
---
# T5-Efficient-SMALL-DL12 (Deep-Narrow version)
T5-Efficient-SMALL-DL12 is a variation of [Google's original T5](https://ai.googleblog.com/2020/02/exploring-transfer-learning-with-t5.html) following the [T5 model architecture](https://huggingface.co/docs/transformers/model_doc/t5).
It is a *pretrained-only* checkpoint and was released with the
paper **[Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers](https://arxiv.org/abs/2109.10686)**
by *Yi Tay, Mostafa Dehghani, Jinfeng Rao, William Fedus, Samira Abnar, Hyung Won Chung, Sharan Narang, Dani Yogatama, Ashish Vaswani, Donald Metzler*.
In a nutshell, the paper indicates that a **Deep-Narrow** model architecture is favorable for **downstream** performance compared to other model architectures
of similar parameter count.
To quote the paper:
> We generally recommend a DeepNarrow strategy where the model’s depth is preferentially increased
> before considering any other forms of uniform scaling across other dimensions. This is largely due to
> how much depth influences the Pareto-frontier as shown in earlier sections of the paper. Specifically, a
> tall small (deep and narrow) model is generally more efficient compared to the base model. Likewise,
> a tall base model might also generally more efficient compared to a large model. We generally find
> that, regardless of size, even if absolute performance might increase as we continue to stack layers,
> the relative gain of Pareto-efficiency diminishes as we increase the layers, converging at 32 to 36
> layers. Finally, we note that our notion of efficiency here relates to any one compute dimension, i.e.,
> params, FLOPs or throughput (speed). We report all three key efficiency metrics (number of params,
> FLOPS and speed) and leave this decision to the practitioner to decide which compute dimension to
> consider.
To be more precise, *model depth* is defined as the number of transformer blocks that are stacked sequentially.
A sequence of word embeddings is therefore processed sequentially by each transformer block.
## Details model architecture
This model checkpoint - **t5-efficient-small-dl12** - is of model type **Small** with the following variations:
- **dl** is **12**
It has **85.7** million parameters and thus requires *ca.* **342.82 MB** of memory in full precision (*fp32*)
or **171.41 MB** of memory in half precision (*fp16* or *bf16*).
A summary of the *original* T5 model architectures can be seen here:
| Model | nl (el/dl) | ff | dm | kv | nh | #Params|
| ----| ---- | ---- | ---- | ---- | ---- | ----|
| Tiny | 4/4 | 1024 | 256 | 32 | 4 | 16M|
| Mini | 4/4 | 1536 | 384 | 32 | 8 | 31M|
| Small | 6/6 | 2048 | 512 | 32 | 8 | 60M|
| Base | 12/12 | 3072 | 768 | 64 | 12 | 220M|
| Large | 24/24 | 4096 | 1024 | 64 | 16 | 738M|
| Xl | 24/24 | 16384 | 1024 | 128 | 32 | 3B|
| XXl | 24/24 | 65536 | 1024 | 128 | 128 | 11B|
whereas the following abbreviations are used:
| Abbreviation | Definition |
| ----| ---- |
| nl | Number of transformer blocks (depth) |
| dm | Dimension of embedding vector (output vector of transformers block) |
| kv | Dimension of key/value projection matrix |
| nh | Number of attention heads |
| ff | Dimension of intermediate vector within transformer block (size of feed-forward projection matrix) |
| el | Number of transformer blocks in the encoder (encoder depth) |
| dl | Number of transformer blocks in the decoder (decoder depth) |
| sh | Signifies that attention heads are shared |
| skv | Signifies that key-values projection matrices are tied |
If a model checkpoint has no specific, *el* or *dl* than both the number of encoder- and decoder layers correspond to *nl*.
## Pre-Training
The checkpoint was pretrained on the [Colossal, Cleaned version of Common Crawl (C4)](https://huggingface.co/datasets/c4) for 524288 steps using
the span-based masked language modeling (MLM) objective.
## Fine-Tuning
**Note**: This model is a **pretrained** checkpoint and has to be fine-tuned for practical usage.
The checkpoint was pretrained in English and is therefore only useful for English NLP tasks.
You can follow on of the following examples on how to fine-tune the model:
*PyTorch*:
- [Summarization](https://github.com/huggingface/transformers/tree/master/examples/pytorch/summarization)
- [Question Answering](https://github.com/huggingface/transformers/blob/master/examples/pytorch/question-answering/run_seq2seq_qa.py)
- [Text Classification](https://github.com/huggingface/transformers/tree/master/examples/pytorch/text-classification) - *Note*: You will have to slightly adapt the training example here to make it work with an encoder-decoder model.
*Tensorflow*:
- [Summarization](https://github.com/huggingface/transformers/tree/master/examples/tensorflow/summarization)
- [Text Classification](https://github.com/huggingface/transformers/tree/master/examples/tensorflow/text-classification) - *Note*: You will have to slightly adapt the training example here to make it work with an encoder-decoder model.
*JAX/Flax*:
- [Summarization](https://github.com/huggingface/transformers/tree/master/examples/flax/summarization)
- [Text Classification](https://github.com/huggingface/transformers/tree/master/examples/flax/text-classification) - *Note*: You will have to slightly adapt the training example here to make it work with an encoder-decoder model.
## Downstream Performance
TODO: Add table if available
## Computational Complexity
TODO: Add table if available
## More information
We strongly recommend the reader to go carefully through the original paper **[Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers](https://arxiv.org/abs/2109.10686)** to get a more nuanced understanding of this model checkpoint.
As explained in the following [issue](https://github.com/google-research/google-research/issues/986#issuecomment-1035051145), checkpoints including the *sh* or *skv*
model architecture variations have *not* been ported to Transformers as they are probably of limited practical usage and are lacking a more detailed description. Those checkpoints are kept [here](https://huggingface.co/NewT5SharedHeadsSharedKeyValues) as they might be ported potentially in the future. | [
"TEXT_CLASSIFICATION",
"QUESTION_ANSWERING",
"SUMMARIZATION"
] | Non_BioNLP |
Luciano/bertimbau-base-finetuned-lener-br-finetuned-brazilian_court_decisions | Luciano | text-classification | [
"transformers",
"pytorch",
"tensorboard",
"safetensors",
"bert",
"text-classification",
"generated_from_trainer",
"pt",
"dataset:joelito/brazilian_court_decisions",
"base_model:Luciano/bertimbau-base-finetuned-lener-br",
"base_model:finetune:Luciano/bertimbau-base-finetuned-lener-br",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 1,663,242,749,000 | 2023-09-12T03:13:50 | 35 | 0 | ---
base_model: Luciano/bertimbau-base-finetuned-lener-br
datasets:
- joelito/brazilian_court_decisions
language:
- pt
license: mit
metrics:
- accuracy
tags:
- generated_from_trainer
train-eval-index:
- config: joelito--brazilian_court_decisions
task: text-classification
task_id: multi_class_classification
splits:
eval_split: test
col_mapping:
decision_description: text
judgment_label: target
widget:
- text: 'AGRAVO DE INSTRUMENTO. AÇÃO REVISIONAL DE CONTRATO. DEPÓSITO DO VALOR INCONTROVERSO.
IMPOSSIBILIDADE. NÃO PREENCHIMENTO DOS REQUISITOS PELO DEVEDOR. MANUTENÇÃO NA
POSSE DO BEM E VEDAÇÃO DE INSCRIÇÃO NOS ÓRGÃOS DE PROTEÇÃO AO CRÉDITO MEDIANTE
O DEPÓSITO DO VALOR ORIGINALMENTE CONTRATADO. 1. O autor requereu a sua manutenção
na posse do bem, o depósito em juízo dos valores que entende incontroversos, a
proibição de inscrição de seu nome nos órgãos de proteção ao crédito e a suspensão
de eventual ação de busca e apreensão do veículo. 2. O artigo 330, PARAGRAFO 2
e PARAGRAFO 3 do CODIGO DE PROCESSO CIVIL autoriza expressamente o depósito do
valor incontroverso nas ações revisionais de contrato mediante presença de três
requisitos concomitantes: a) propositura de ação contestando a existência integral
ou parcial do débito; b) efetiva demonstração de que a contestação da cobrança
indevida se funda na aparência do bom direito; e, c) que a parte efetue o depósito
do valor incontroverso ou preste caução idônea. Contudo, tal conduta não afastará
a incidência das restrições legais decorrentes da dívida, porquanto os valores
considerados incontroversos são inferiores àqueles contratados. 3. A jurisprudência
é pacífica no sentido de ser necessário o depósito do valor integral da parcela
da dívida para inibir os efeitos da mora e suas consequências. 4. Nos termos da
jurisprudência consolidada nesta Corte, deverá o devedor depositar os valores
pactuados originalmente no contrato, tanto para as parcelas vencidas, quanto para
as vincendas, nas datas pactuadas, se desejar se manter na posse do bem e obstacular
sua inscrição de seu nome nos cadastros restritivos de crédito.'
- text: O constrangimento ilegal deve ser aferido segundo as circunstancias do caso
concreto, especialmente diante da complexidade e das diligências necessárias,
ainda mais quando tais elementos são necessários para embasar a própria denúncia
em si. Intensa movimentação processual no sentido de angariar as informações necessárias.
Prazo que merece ser mitigado. Denúncia oferecida nos autos da ação penal 0800162-9820188020001.
II - Presentes a materialidade dos delitos e seus indícios de autoria, mormente
diante das colaborações premiadas colhidas durante as investigações, não há falar
em embasamento abstrato da decisão especialmente quando esta expressamente apontou
que o paciente era proprietário de empresas supostamente fantasmas, que recebiam
benefícios de diversas prefeituras. III - Ausência de constrangimento ilegal,
tanto pela presença dos requisitos para a prisão preventiva em questão, quanto
pelo fato de que resta evidenciado que o paciente ficou foragido. Precedentes.
IV - Especificamente em relação ao pedido de extensão dos efeitos dos benefícios
concedidos a outros investigados (Josimar Campos, Raphael de Barros Lima e Raulene
Karoline Barros e Gabriel Brandão), entendo, a partir do narrado pela própria
petição inicial, que a situação do paciente é diferente dos demais investigados,
uma vez que, além de ele ter foragido do distrito da culpa e responder a outras
ações penais, aparentemente não está colaborando com as investigações (os outros
investigados firmaram acordo de colaboração premiada). V - No que tange ao pedido
relacionado aos ex-prefeitos (Márcia Coutinho Nogueira de Albuquerque, José Jacob
Gomes Brandão, Fábio Rangel Nunes de Oliveira) que se encontram em liberdade,
entendo que a situação do paciente também é diferente, uma vez que a decisão de
origem da conta que existem indicativos de que o esquema tenha ocorrido em 80
(oitenta) prefeituras. VI - A partir da leitura da decisão prolatada pelos juízes
impetrados, verifica-se que o decreto de prisão não é fundamentado apenas no risco
de a liberdade do paciente atrapalhar as investigações, mas também, para, sobretudo,
garantir a aplicação da lei penal pelo fato de o paciente ter foragido do distrito
da culpa.
- text: APELAÇÃO CÍVEL. AÇÃO ORIGINÁRIA DE USUCAPIÃO. JULGAMENTO ANTECIPADO DA LIDE.
SENTENÇA DE IMPROCEDÊNCIA AO PLEITO AUTORAL ANTE A AUSÊNCIA DOS REQUISITOS DO
ARTIGO 1238 DO CÓDIGO CIVIL/02. AUSÊNCIA DE CITAÇÃO DO PROPRIETÁRIO DO BEM A SER
USUCAPIDO. AUTOR COMPROVA POR DOCUMENTO EXPEDIDO PELA MUNICIPALIDADE O REGISTRO
DO IMÓVEL USUCAPIENDO EM SEU NOME DESDE 1990. POSSIBILIDADE DO PREENCHIMENTO DO
REQUISITO TEMPORAL (PRAZO PARA USUCAPIR) PREVISTO EM LEI A SER IMPLEMENTADO NO
CURSO DA DEMANDA. OFENSA AO DEVIDO PROCESSO LEGAL MATÉRIA DE ORDEM PÚBLICA, RECONHECIDA
DE OFÍCIO NO JUÍZO AD QUEM. NULIDADE DA SENTENÇA COM RETORNO DOS AUTOS À ORIGEM
PARA DAR SEGUIMENTO A INSTRUÇÃO COM PROLAÇÃO DE NOVA DECISÃO.
model-index:
- name: bertimbau-base-finetuned-lener-br-finetuned-brazilian_court_decisions
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: joelito/brazilian_court_decisions
type: joelito/brazilian_court_decisions
config: joelito--brazilian_court_decisions
split: test
metrics:
- type: accuracy
value: 0.7925925925925926
name: Accuracy
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNGYwNzJiZjE0ZjE1NzM5ZWI2ZWQ3MDZiNTkxNDMzY2IwODJmNjRjMGFjYWNjMzg0MWM0YjZmNjNlODJiMzZiZCIsInZlcnNpb24iOjF9.yuzroeBIxzMUISrKslpXl6mw_pdmZ5rsx1_yBRvneBF5Y18NIwbaSidUJ4A_AsR91yrHStvCi2LV9mi0pSUSBg
- type: precision
value: 0.7561026936026934
name: Precision Macro
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTU1YTMxOGQ3MjcxZjViNTYxOTFmN2MwYzk1YjAwMTU4NjVmNzEwODBlNWZlN2EzNWI5Y2FmZjE5NmNjODQ4NSIsInZlcnNpb24iOjF9.NC1NGFneaJFl-aA0veGNiaHXhZ7_7Xp14DoCRQkqNuDbjmcEqARaT2zvcfmUlC1KFafqGdA9zGxPyPvLYGD9Dg
- type: precision
value: 0.7925925925925926
name: Precision Micro
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTIwMzg2ZjkwNzNiZTNjMTg1MTExY2E3NmNhYWM5MGQxYjlkMGNkOTFjMjU5YWRlZGJkOGRmNzUyOTI1MGE4MSIsInZlcnNpb24iOjF9.e-2no4ZzEQh_o2IZLwqAgKnandZ60gkLQwkHQ1chblFJldFJVeiD_VuYPG6oYxT0i6olPZob3soV1qRLOMBOAw
- type: precision
value: 0.7913112607557052
name: Precision Weighted
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNGQ3YTE5Y2YzYzQzYjllMDMxMTQ3ODRmNzI1ZWZkZTNmMGFkMjAxZTE3M2FhZGEzMjM3OTcwODg4NjBmMWU2ZSIsInZlcnNpb24iOjF9.uLD9Bqp5E6S0vZSc82RUtB49jOxMWPwqCp18YjDqJQRBpRgm7kyQwxmtenDci9UieuJ0d1DtD2b8sPYyPQ7dDA
- type: recall
value: 0.7408785957173055
name: Recall Macro
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYTM2YTVkNmM1ZGRhNzY0OWYyYTg2NmIxYWRkOWYyMTc4ZWVlYjdmNDliMDlhOTk2MGVjNjJlMjFhZGJmMGYxYyIsInZlcnNpb24iOjF9.KsRzS_NH6bbyIyhKD-P2BPKKtAZjdOXrwZrq_U9zensLOY7C5RZCFGuYESqm0vQwpQf0ZKqKEYCUL9WRwONhBg
- type: recall
value: 0.7925925925925926
name: Recall Micro
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYWUxMzM5OWQwMDg3ZjIxMTFiNzg0MmJkMzYwODU5MjNmMDllZWFjYmMzNTRlNWRhY2NkNmJiNGZkYmU0MjVhNSIsInZlcnNpb24iOjF9.AtDYhA7T8793on76uVa0tbzCKfq1UD4U_pU1Q0vFRST8lDjQYyw6_Q6JzY3Jh9qw1gSU6qA52zMlesb8ANckDw
- type: recall
value: 0.7925925925925926
name: Recall Weighted
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNTBiYTYwZmRiZjY3YjM4YmFlMjkwNDVlN2JiOTY2MDgxOWNmYmE1YmJkZGY1NGU5ZDA1MjdjZDgyMzI3NDhlMCIsInZlcnNpb24iOjF9.uXSLCN14oZb6mP0hLTH8RxD6Og6OYrS7OSxRbIqsx_JauIXdca4RFZcXptzeq190gbRWT0lNz5GEhzjeT7qmAA
- type: f1
value: 0.7466596343178621
name: F1 Macro
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzMzNDIwZGMzNmVjZmUxNGVhZGRhOWZkNzI3OWViYmNiOGZkNGI4ZjE5M2U2MjA1OGRjMzE2YzEyODFjNDE3NiIsInZlcnNpb24iOjF9.GHA7gAvoIQQuhhoXMeGuMdGo0f4Pma5AUgCA9T6qDKeXMeuRs6gqumLzi3lXgMBB4RuPxE49NOgVLLyrq-J2Aw
- type: f1
value: 0.7925925925925926
name: F1 Micro
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzFkNTU5NTM1NjhjNjAwMzQ1ZTNjYzczNDc5MzI1NjI3ODkyMzk5OTExMTBlZDlhYzAzNTkzYzM3ZjU2MTJjMSIsInZlcnNpb24iOjF9.Gw1w7Fsv--XRx0Hxuw6pYAzyhd9vb-n31Y5Mwgh6lbQKEDsBMauztkT3rqPIIqqCLVI3LsaVoLk4ECTAIngwBA
- type: f1
value: 0.7908149710892328
name: F1 Weighted
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMDVkNTU3MmUxYjY0NmFiMGU2ZTM1M2YzYmUxMGM3NDNjOTkxMGY2NzU5ODkwYTc3YTRhMWIwMjE4YzVhMzU0YSIsInZlcnNpb24iOjF9.KrMgoICICm8QeS6usYrHMhQ7PoscE6wyLz9QGnUPpQa0LOr0EcasCpgeK_yyVytBCIR3lT1doYAvKH8mTf9lBA
- type: loss
value: 1.6538628339767456
name: loss
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiODZkMWEzODY5ZTA2N2MzMjJkYmQ2NWE4MWJmZWIxMmNjZmVmZTA3Yjk2ZTdjNzFmODIyMThkY2NhOWIzYTgwMCIsInZlcnNpb24iOjF9.IyEKEBbdbNYTcUzOF09r2vp7umxYSIeTGN_muWNujaSbibd6uSooNRWzSfZOS37L0S4_GPdMvDXQuMsUeybWAQ
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bertimbau-base-finetuned-lener-br-finetuned-brazilian_court_decisions
This model is a fine-tuned version of [Luciano/bertimbau-base-finetuned-lener-br](https://huggingface.co/Luciano/bertimbau-base-finetuned-lener-br) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.8017
- Accuracy: 0.7698
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 405 | 0.7790 | 0.6535 |
| 0.8276 | 2.0 | 810 | 0.6739 | 0.7277 |
| 0.5818 | 3.0 | 1215 | 0.8767 | 0.7302 |
| 0.4147 | 4.0 | 1620 | 0.8229 | 0.7896 |
| 0.287 | 5.0 | 2025 | 0.9874 | 0.7921 |
| 0.287 | 6.0 | 2430 | 1.2301 | 0.7772 |
| 0.1727 | 7.0 | 2835 | 1.2864 | 0.7946 |
| 0.1179 | 8.0 | 3240 | 1.5097 | 0.7772 |
| 0.0709 | 9.0 | 3645 | 1.4772 | 0.7921 |
| 0.0437 | 10.0 | 4050 | 1.5581 | 0.7797 |
| 0.0437 | 11.0 | 4455 | 1.6317 | 0.7896 |
| 0.0318 | 12.0 | 4860 | 1.7295 | 0.7822 |
| 0.0158 | 13.0 | 5265 | 1.7333 | 0.7797 |
| 0.0108 | 14.0 | 5670 | 1.8008 | 0.7772 |
| 0.0137 | 15.0 | 6075 | 1.8017 | 0.7698 |
### Framework versions
- Transformers 4.22.0
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1
| [
"TEXT_CLASSIFICATION"
] | Non_BioNLP |
manjunathainti/fine_tuned_t5_summarizer | manjunathainti | summarization | [
"transformers",
"safetensors",
"t5",
"text2text-generation",
"summarization",
"legal-documents",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 1,732,953,871,000 | 2025-02-27T22:09:16 | 113 | 0 | ---
library_name: transformers
tags:
- summarization
- legal-documents
- t5
---
# Model Card for Fine-Tuned T5 Summarizer
This model is a fine-tuned version of the T5 base model, designed for summarizing legal texts into concise short and long summaries. It enables efficient processing of complex legal cases, facilitating quick insights and detailed analysis.
## Model Details
### Model Description
This is the model card for the fine-tuned T5 summarizer developed for legal case summaries. It has been specifically optimized to process long legal documents and generate two types of summaries:
- **Short Summaries:** Concise highlights for quick review.
- **Long Summaries:** Detailed insights for deeper analysis.
- **Developed by:** Manjunatha Inti
- **Funded by:** Self-funded
- **Shared by:** Manjunatha Inti
- **Model type:** Fine-tuned Transformer for Summarization
- **Language(s) (NLP):** English
- **License:** Apache 2.0
- **Finetuned from model:** T5-base
### Model Sources
- **Repository:** [GitHub Repository URL to be added]
- **Demo:** [Colab Notebook to be added]
- **Model on Hugging Face:** [https://huggingface.co/manjunathainti/fine_tuned_t5_summarizer](https://huggingface.co/manjunathainti/fine_tuned_t5_summarizer)
## Uses
### Direct Use
The model can be directly used to summarize legal case texts. It works best with English legal documents.
### Downstream Use
The model can be integrated into:
- Legal document management systems.
- AI tools for legal research and compliance.
### Out-of-Scope Use
- Use on non-legal documents without additional fine-tuning.
- Summarization in languages other than English.
## Bias, Risks, and Limitations
### Bias
The model may reflect biases present in the training data, such as jurisdictional focus or societal biases inherent in the dataset.
### Risks
- Critical legal details might be omitted.
- The model's output should not replace expert legal opinions.
### Recommendations
- A legal expert should always review outputs.
- Avoid using it for legal tasks where complete precision is mandatory.
### Training Data
- **Dataset:** Multi-LexSum
- **Preprocessing:** Preprocessed for summarization tasks using tokenization.
### Training Procedure
#### Preprocessing
- Tokenization and truncation were applied to the dataset.
- Input sequences were capped at 1024 tokens.
- Summaries were limited to:
- 150 tokens for short summaries.
- 300 tokens for long summaries.
#### Training Hyperparameters
- **Learning Rate:** 5e-5
- **Batch Size:** 1 (gradient accumulation steps: 8)
- **Epochs:** 3
- **Optimizer:** AdamW
- **Precision:** Mixed (fp16)
#### Speeds, Sizes, Times
- **Training Time:** ~4 hours
- **Checkpoint Size:** ~892 MB
- **Hardware:** NVIDIA Tesla V100
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
- Validation was performed on the `validation` split of the Multi-LexSum dataset, consisting of 4,818 examples.
#### Metrics
- **bert_score Short Summary Precision :** 0.84
- **bert_score Long Summary Precision :** 0.81
### Results
- The model produces reliable short and long summaries for legal documents, maintaining coherence and relevance.
#### Summary
- The fine-tuned T5 model demonstrated robust performance in summarizing legal documents, achieving competitive BERT scores.
## Model Examination
### Interpretability
- The model generates human-readable summaries, making it highly interpretable for end-users in the legal domain.
## Environmental Impact
- **Carbon emissions** can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** NVIDIA Tesla V100
- **Hours Used:** ~4 hours
- **Cloud Provider:** Google Colab
- **Compute Region:** US
- **Estimated Carbon Emissions:** Minimal due to short training time.
## Technical Specifications
### Model Architecture and Objective
- The T5 architecture is designed for text-to-text tasks.
- This fine-tuned model adapts T5 for legal text summarization, leveraging the flexibility of seq2seq learning.
### Compute Infrastructure
- **Hardware:** NVIDIA Tesla V100
- **Software:** Hugging Face Transformers 4.46.3, PyTorch
## How to Get Started with the Model
```python
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
model_name = "manjunathainti/fine_tuned_t5_summarizer"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
# Example Input
input_text = "Insert a legal case description here."
input_ids = tokenizer(input_text, return_tensors="pt").input_ids
# Generate Summary
summary_ids = model.generate(input_ids, max_length=150, num_beams=4, length_penalty=2.0)
summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
print("Generated Summary:", summary)
| [
"SUMMARIZATION"
] | Non_BioNLP |
Trelis/idefics2-8b-chatty-bf16 | Trelis | image-text-to-text | [
"transformers",
"safetensors",
"idefics2",
"image-text-to-text",
"multimodal",
"vision",
"en",
"dataset:HuggingFaceM4/OBELICS",
"dataset:laion/laion-coco",
"dataset:wikipedia",
"dataset:facebook/pmd",
"dataset:pixparse/idl-wds",
"dataset:pixparse/pdfa-eng-wds",
"dataset:wendlerc/RenderedText",
"dataset:HuggingFaceM4/the_cauldron",
"dataset:teknium/OpenHermes-2.5",
"dataset:GAIR/lima",
"dataset:databricks/databricks-dolly-15k",
"dataset:meta-math/MetaMathQA",
"dataset:TIGER-Lab/MathInstruct",
"dataset:microsoft/orca-math-word-problems-200k",
"dataset:camel-ai/math",
"dataset:AtlasUnified/atlas-math-sets",
"dataset:tiedong/goat",
"dataset:Lin-Chen/ShareGPT4V",
"dataset:jxu124/llava_conversation_58k",
"arxiv:2306.16527",
"arxiv:2405.02246",
"arxiv:2307.06304",
"arxiv:2311.07575",
"arxiv:2103.03206",
"license:apache-2.0",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 1,715,788,101,000 | 2024-05-15T16:42:33 | 26 | 1 | ---
datasets:
- HuggingFaceM4/OBELICS
- laion/laion-coco
- wikipedia
- facebook/pmd
- pixparse/idl-wds
- pixparse/pdfa-eng-wds
- wendlerc/RenderedText
- HuggingFaceM4/the_cauldron
- teknium/OpenHermes-2.5
- GAIR/lima
- databricks/databricks-dolly-15k
- meta-math/MetaMathQA
- TIGER-Lab/MathInstruct
- microsoft/orca-math-word-problems-200k
- camel-ai/math
- AtlasUnified/atlas-math-sets
- tiedong/goat
- Lin-Chen/ShareGPT4V
- jxu124/llava_conversation_58k
language:
- en
license: apache-2.0
tags:
- multimodal
- vision
- image-text-to-text
---
# bf-16 version of the Idefics2 8B Chatty Model
For ~2X faster download speeds. (Note that the vision transformer is still in float32)
[Original Model Here](https://huggingface.co/HuggingFaceM4/idefics2-8b-chatty)
***As of April 18th, 2024**, Idefics2 is part of the `4.40.0` Transformers pypi release. Please upgrade your Transformers version (`pip install transformers --upgrade`).*
# Idefics2
Idefics2 is an open multimodal model that accepts arbitrary sequences of image and text inputs and produces text outputs. The model can answer questions about images, describe visual content, create stories grounded on multiple images, or simply behave as a pure language model without visual inputs. It improves upon [Idefics1](https://huggingface.co/HuggingFaceM4/idefics-80b-instruct), significantly enhancing capabilities around OCR, document understanding and visual reasoning.
We release under the Apache 2.0 license 2 checkpoints:
- [idefics2-8b-base](https://huggingface.co/HuggingFaceM4/idefics2-8b-base): the base model
- [idefics2-8b](https://huggingface.co/HuggingFaceM4/idefics2-8b): the base model fine-tuned on a mixture of supervised and instruction datasets (text-only and multimodal datasets)
- [idefics2-8b-chatty](https://huggingface.co/HuggingFaceM4/idefics2-8b-chatty): `idefics2-8b` further fine-tuned on long conservation
# Model Summary
- **Developed by:** Hugging Face
- **Model type:** Multi-modal model (image+text)
- **Language(s) (NLP):** en
- **License:** Apache 2.0
- **Parent Models:** [google/siglip-so400m-patch14-384](https://huggingface.co/google/siglip-so400m-patch14-384) and [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
- **Resources for more information:**
- Description of [OBELICS](https://huggingface.co/datasets/HuggingFaceM4/OBELICS): [OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents
](https://huggingface.co/papers/2306.16527)
- Paper: [What matters when building vision-language models?
](https://huggingface.co/papers/2405.02246)
# Uses
`idefics2-8b-base` and `idefics2-8b` can be used to perform inference on multimodal (image + text) tasks in which the input is composed of a text query along with one (or multiple) image(s). Text and images can be arbitrarily interleaved. That includes image captioning, visual question answering, etc. These model does not support image generation.
For optimal results, we recommend fine-tuning `idefics2-8b` on one's specific use-case and data. In fact, the instruction-fine-tuned model (`idefics2-8b`) is significantly better at following instructions from users and thus should be preferred when using the models out-of-the-box or as a starting point for fine-tuning.
`idefics2-8b` usually generates very short answers. For long generations, use `idefics2-8b-chatty`, which was further fine-tuned on long conversations.
As a starting point, we provide fine-tuning codes that can be adapted for one's particular scenario:
- With the [TRL library](https://github.com/huggingface/trl): [Script](https://gist.github.com/edbeeching/228652fc6c2b29a1641be5a5778223cb)
- With the [Hugging Face Trainer](https://huggingface.co/docs/transformers/main/en/main_classes/trainer#api-reference%20][%20transformers.Trainer): [Tutorial notebook](https://colab.research.google.com/drive/1NtcTgRbSBKN7pYD3Vdx1j9m8pt3fhFDB?usp=sharing)
# Technical summary
Idefics2 exhibits strong performance for a model of its size (8B parameters) when compared to other open multimodal models and is often competitive with closed-source systems. As such, it serves as a strong foundation for various use-case specific fine-tunings.
<details><summary>For more details, expand the result table.</summary>
| <nobr>Model</nobr> | <nobr>Open <br>weights</nobr> | <nobr>Size</nobr> | <nobr># tokens <br>per image</nobr> | <nobr>MMMU <br>(val/test)</nobr> | <nobr>MathVista <br>(testmini)</nobr> | <nobr>TextVQA <br>(val)</nobr> | <nobr>MMBench <br>(test)</nobr> | <nobr>VQAv2 <br>(test-dev)</nobr> | <nobr>DocVQA <br>(test)</nobr> |
|--------------|-------------|------|--------------------|-----------|-----------|---------|---------|---------|---------|
| [DeepSeek-VL](https://huggingface.co/deepseek-ai/deepseek-vl-7b-chat) | ✅ | 7B | 576 | 36.6/- | 36.1 | 64.4 | 73.2 | - | 49.6 |
| [LLaVa-NeXT-Mistral-7B](https://huggingface.co/liuhaotian/llava-v1.6-mistral-7b) | ✅ | 7B | 2880 | 35.3/- | 37.7 | 65.7 | 68.7 | 82.2 | - |
| [LLaVa-NeXT-13B](https://huggingface.co/liuhaotian/llava-v1.6-vicuna-13b) | ✅ | 13B | 2880 | 36.2/- | 35.3 | 67.1 | 70.0 | 82.8 | - |
| [LLaVa-NeXT-34B](https://huggingface.co/liuhaotian/llava-v1.6-34b) | ✅ | 34B | 2880 | 51.1/44.7 | 46.5 | 69.5 | 79.3 | 83.7 | - | - |
| MM1-Chat-7B | ❌ | 7B | 720 | 37.0/35.6 | 35.9 | 72.8 | 72.3 | - | - |
| MM1-Chat-30B | ❌ | 30B | 720 | 44.7/40.3 | 39.4 | 73.5 | 75.1 | 83.7 | |
| Gemini 1.0 Pro | ❌ | 🤷♂️ | 🤷♂️ | 47.9/- | 45.2 | 74.6 | - | 71.2 | 88.1 |
| Gemini 1.5 Pro | ❌ | 🤷♂️ | 🤷♂️ | 58.5/- | 52.1 | 73.5 | - | 73.2 | 86.5 |
| Claude 3 Haiku | ❌ | 🤷♂️ | 🤷♂️ | 50.2/- | 46.4 | - | - | - | 88.8 |
| | | | | | | |
| [Idefics1 instruct](https://huggingface.co/HuggingFaceM4/idefics-80b-instruct) (32-shots) | ✅ | 80B | - | - | - | 39.3 | - | 68.8 | - |
| | | | | | | |
| **Idefics2** (w/o im. split) | ✅ | 8B | 64 | 43.5/37.9 | 51.6 | 70.4 | 76.8 | 80.8 | 67.3 |
| **Idefics2** (w/ im. split) | ✅ | 8B | 320 | 43.0/37.7 | 51.4 | 73.0 | 76.7 | 81.2 | 74.0 |
</details>
**Idefics2 introduces several carefully abalated improvements over Idefics1:**
- We manipulate images in their **native resolutions** (up to 980 x 980) and **native aspect ratios** by following the [NaViT](https://arxiv.org/abs/2307.06304) strategy. That circumvent the need to resize images to fixed-size squares as it has been historically been done in the computer vision community. Additionally, we follow the strategy from [SPHINX](https://arxiv.org/abs/2311.07575) and (optionally) allow **sub-image splitting** and passing **images of very large resolution**.
- We significantly enhanced **OCR abilities** by integrating data that requires the model to transcribe text in an image or a document. We also improved abilities in **answering questions on charts, figures, and documents** with appropriate training data.
- We departed from the Idefics1's architecture (gated cross-attentions) and **simplified the integration of visual features** into the language backbone. The images are fed to the vision encoder followed by a learned [Perceiver](https://arxiv.org/abs/2103.03206) pooling and a MLP modality projection. That pooled sequence is then concatenated with the text embeddings to obtain an (interleaved) sequence of image(s) and text(s).
- All of these improvements along with better pre-trained backbones yield a significant jump in performance over Idefics1 for a model that is **10x smaller**.
Idefics2 is trained in 2 stages for maximum efficiency. In a first stage, images are fed to the model at SigLIP's native resolution (squares of 384 x 384). In the second stage, images are fed to the model at their native resolution (with a maximum of 980 and a minimum of 378) and native aspect ratio. Since high resolution is necessary for OCR data, we add PDFA, Rendered-Text, and IDL to OBELICS, LAION Coco and PMD during that second stage.
Following this, we perform instruction fine-tuning on [The Cauldron](https://huggingface.co/datasets/HuggingFaceM4/the_cauldron), a collection of 50 manually curated vision-language datasets along with 9 text-only instruction fine-tuning datasets:
- [OpenHermes-2.5](https://huggingface.co/datasets/teknium/OpenHermes-2.5)
- [lima](https://huggingface.co/datasets/GAIR/lima)
- [databricks-dolly-15k](https://huggingface.co/datasets/databricks/databricks-dolly-15k)
- [MetaMathQA](https://huggingface.co/datasets/meta-math/MetaMathQA)
- [MathInstruct](https://huggingface.co/datasets/TIGER-Lab/MathInstruct)
- [orca-math-word-problems-200k](https://huggingface.co/datasets/microsoft/orca-math-word-problems-200k)
- [math](https://huggingface.co/datasets/camel-ai/math)
- [atlas-math-sets](https://huggingface.co/datasets/AtlasUnified/atlas-math-sets)
- [goat](https://huggingface.co/datasets/tiedong/goat)
We use Lora to train the parameters initialized from pre-trained backbones and full fine-tuning for newly initialized parameters (modality connector), as we find this strategy to be more stable as well as more computationally efficient.
More details (training procedure, data selection, hyper-parameters, etc.) along with lessons learned from our ablations will be available in an upcoming technical report.
# How to Get Started
This section shows snippets of code for generation for `idefics2-8b-base` and `idefics2-8b`. The codes only differ by the input formatting. Let's first define some common imports and inputs.
```python
import requests
import torch
from PIL import Image
from io import BytesIO
from transformers import AutoProcessor, AutoModelForVision2Seq
from transformers.image_utils import load_image
DEVICE = "cuda:0"
# Note that passing the image urls (instead of the actual pil images) to the processor is also possible
image1 = load_image("https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg")
image2 = load_image("https://cdn.britannica.com/59/94459-050-DBA42467/Skyline-Chicago.jpg")
image3 = load_image("https://cdn.britannica.com/68/170868-050-8DDE8263/Golden-Gate-Bridge-San-Francisco.jpg")
```
**For `idefics2-8b-base`**
<details><summary>Click to expand.</summary>
```python
processor = AutoProcessor.from_pretrained("HuggingFaceM4/idefics2-8b-base")
model = AutoModelForVision2Seq.from_pretrained(
"HuggingFaceM4/idefics2-8b-base",
).to(DEVICE)
# Create inputs
prompts = [
"<image>In this image, we can see the city of New York, and more specifically the Statue of Liberty.<image>In this image,",
"In which city is that bridge located?<image>",
]
images = [[image1, image2], [image3]]
inputs = processor(text=prompts, images=images, padding=True, return_tensors="pt")
inputs = {k: v.to(DEVICE) for k, v in inputs.items()}
# Generate
generated_ids = model.generate(**inputs, max_new_tokens=500)
generated_texts = processor.batch_decode(generated_ids, skip_special_tokens=True)
print(generated_texts)
# ['In this image, we can see the city of New York, and more specifically the Statue of Liberty. In this image, we can see the city of Chicago, and more specifically the skyscrapers of the city.', 'In which city is that bridge located? The Golden Gate Bridge is a suspension bridge spanning the Golden Gate, the one-mile-wide (1.6 km) strait connecting San Francisco Bay and the Pacific Ocean. The structure links the American city of San Francisco, California — the northern tip of the San Francisco Peninsula — to Marin County, carrying both U.S. Route 101 and California State Route 1 across the strait. The bridge is one of the most internationally recognized symbols of San Francisco, California, and the United States. It has been declared one of the Wonders of the Modern World by the American Society of Civil Engineers.\n\nThe Golden Gate Bridge is a suspension bridge spanning the Golden Gate, the one-mile-wide (1.6 km) strait connecting San Francisco Bay and the Pacific Ocean. The structure links the American city of San Francisco, California — the northern tip of the San Francisco Peninsula — to Marin County, carrying both U.S. Route 101 and California State Route 1 across the strait. The bridge is one of the most internationally recognized symbols of San Francisco, California, and the United States. It has been declared one of the Wonders of the Modern World by the American Society of Civil Engineers.\n\nThe Golden Gate Bridge is a suspension bridge spanning the Golden Gate, the one-mile-wide (1.6 km) strait connecting San Francisco Bay and the Pacific Ocean. The structure links the American city of San Francisco, California — the northern tip of the San Francisco Peninsula — to Marin County, carrying both U.S. Route 101 and California State Route 1 across the strait. The bridge is one of the most internationally recognized symbols of San Francisco, California, and the United States. It has been declared one of the Wonders of the Modern World by the American Society of Civil Engineers.\n\nThe Golden Gate Bridge is a suspension bridge spanning the Golden Gate, the one-mile-wide (1.6 km) strait connecting San Francisco Bay and the Pacific Ocean. The structure links the American city of San Francisco, California — the northern tip of the San Francisco Peninsula — to Marin County, carrying both U.S. Route 101 and California State Route 1 across the strait. The bridge is one of the most internationally recognized symbols of San Francisco, California, and']
```
</details>
**For `idefics2-8b`**
<details><summary>Click to expand.</summary>
```python
processor = AutoProcessor.from_pretrained("HuggingFaceM4/idefics2-8b")
model = AutoModelForVision2Seq.from_pretrained(
"HuggingFaceM4/idefics2-8b",
).to(DEVICE)
# Create inputs
messages = [
{
"role": "user",
"content": [
{"type": "image"},
{"type": "text", "text": "What do we see in this image?"},
]
},
{
"role": "assistant",
"content": [
{"type": "text", "text": "In this image, we can see the city of New York, and more specifically the Statue of Liberty."},
]
},
{
"role": "user",
"content": [
{"type": "image"},
{"type": "text", "text": "And how about this image?"},
]
},
]
prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(text=prompt, images=[image1, image2], return_tensors="pt")
inputs = {k: v.to(DEVICE) for k, v in inputs.items()}
# Generate
generated_ids = model.generate(**inputs, max_new_tokens=500)
generated_texts = processor.batch_decode(generated_ids, skip_special_tokens=True)
print(generated_texts)
# ['User: What do we see in this image? \nAssistant: In this image, we can see the city of New York, and more specifically the Statue of Liberty. \nUser: And how about this image? \nAssistant: In this image we can see buildings, trees, lights, water and sky.']
```
</details>
**Text generation inference**
Idefics2 is integrated into [TGI](https://github.com/huggingface/text-generation-inference) and we host API endpoints for both `idefics2-8b` and `idefics2-8b-chatty`.
Multiple images can be passed on with the markdown syntax (``) and no spaces are required before and after. The dialogue utterances can be separated with `<end_of_utterance>\n` followed by `User:` or `Assistant:`. `User:` is followed by a space if the following characters are real text (no space if followed by an image).
<details><summary>Click to expand.</summary>
```python
from text_generation import Client
API_TOKEN="<YOUR_API_TOKEN>"
API_URL = "https://api-inference.huggingface.co/models/HuggingFaceM4/idefics2-8b-chatty"
# System prompt used in the playground for `idefics2-8b-chatty`
SYSTEM_PROMPT = "System: The following is a conversation between Idefics2, a highly knowledgeable and intelligent visual AI assistant created by Hugging Face, referred to as Assistant, and a human user called User. In the following interactions, User and Assistant will converse in natural language, and Assistant will do its best to answer User’s questions. Assistant has the ability to perceive images and reason about them, but it cannot generate images. Assistant was built to be respectful, polite and inclusive. It knows a lot, and always tells the truth. When prompted with an image, it does not make up facts.<end_of_utterance>\nAssistant: Hello, I'm Idefics2, Huggingface's latest multimodal assistant. How can I help you?<end_of_utterance>\n"
QUERY = "User:Describe this image.<end_of_utterance>\nAssistant:"
client = Client(
base_url=API_URL,
headers={"x-use-cache": "0", "Authorization": f"Bearer {API_TOKEN}"},
)
generation_args = {
"max_new_tokens": 512,
"repetition_penalty": 1.1,
"do_sample": False,
}
generated_text = client.generate(prompt=SYSTEM_PROMPT + QUERY, **generation_args)
generated_text
```
</details>
# Model optimizations
If your GPU allows, we first recommend loading (and running inference) in half precision (`torch.float16` or `torch.bfloat16`).
```diff
model = AutoModelForVision2Seq.from_pretrained(
"HuggingFaceM4/idefics2-8b",
+ torch_dtype=torch.float16,
).to(DEVICE)
```
**Vision encoder efficiency**
Given the high resolution supported, the vision part of the model can be memory hungry depending on your configuration. If you are GPU-memory-constrained, you can:
- **deactivate the image splitting.** To do so, add `do_image_splitting=False` when initializing the processor (`AutoProcessor.from_pretrained`). There are no changes required on the model side. Note that only the sft model has been trained with image splitting.
- **decrease the maximum image resolution.** To do so, add `size= {"longest_edge": 448, "shortest_edge": 378}` when initializing the processor (`AutoProcessor.from_pretrained`). In particular, the `longest_edge` value can be adapted to fit the need (the default value is `980`). We recommend using values that are multiples of 14. There are no changes required on the model side.
`do_image_splitting=True` is especially needed to boost performance on OCR tasks where a very large image is used as input. For the regular VQA or captioning tasks, this argument can be safely set to `False` with minimal impact on performance (see the evaluation table above).
**Using Flash-attention 2 to speed up generation**
<details><summary>Click to expand.</summary>
First, make sure to install `flash-attn`. Refer to the [original repository of Flash Attention](https://github.com/Dao-AILab/flash-attention) for the package installation. Simply change the snippet above with:
```diff
model = AutoModelForVision2Seq.from_pretrained(
"HuggingFaceM4/idefics2-8b",
+ torch_dtype=torch.float16,
+ _attn_implementation="flash_attention_2",
).to(DEVICE)
```
Flash attention 2 support is available both for `idefics2-8b-base` and `idefics2-8b`.
</details>
**4 bit quantization with AWQ**
<details><summary>Click to expand.</summary>
4-bit AWQ-quantized versions of the checkpoints are also available and allow module fusing for accelerated inference. First make sure you install the Auto-AWQ library with `pip install autoawq`. Also make sure that this [fix](https://github.com/casper-hansen/AutoAWQ/pull/444) is integrated into your installation.
```diff
+ from transformers import AwqConfig
+ quantization_config = AwqConfig(
+ bits=4,
+ fuse_max_seq_len=4096,
+ modules_to_fuse={
+ "attention": ["q_proj", "k_proj", "v_proj", "o_proj"],
+ "mlp": ["gate_proj", "up_proj", "down_proj"],
+ "layernorm": ["input_layernorm", "post_attention_layernorm", "norm"],
+ "use_alibi": False,
+ "num_attention_heads": 32,
+ "num_key_value_heads": 8,
+ "hidden_size": 4096,
+ }
+ )
model = AutoModelForVision2Seq.from_pretrained(
- "HuggingFaceM4/idefics2-8b",
+ "HuggingFaceM4/idefics2-8b-AWQ",
+ torch_dtype=torch.float16,
+ quantization_config=quantization_config,
).to(DEVICE)
```
Fusing can be de-activated by removing `quantization_config` in the call to `from_pretrained`.
</details>
**4 bit quantization with bitsandbytes**
<details><summary>Click to expand.</summary>
It is also possible to load Idefics2 in 4bits with `bitsandbytes`. To do so, make sure that you have `accelerate` and `bitsandbytes` installed.
```diff
+ from transformers import BitsAndBytesConfig
quantization_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_use_double_quant=True,
bnb_4bit_compute_dtype=torch.float16
)
model = AutoModelForVision2Seq.from_pretrained(
"HuggingFaceM4/idefics2-8b",
+ torch_dtype=torch.float16,
+ quantization_config=quantization_config,
).to(DEVICE)
```
</details>
These optimizations can be combined to suit variable trade-offs between GPU memory, inference speed and performance. We provide the following comparison as anchor points to guide the user in choosing necessary optimizations. All of these benchmarks were computed with the example code snippet described above on a H100 (see [colab](https://colab.research.google.com/drive/1USsnssoFm1UTYuwUOw0XiGeBspLHzvso?usp=sharing)). As one can see, the are a few setups that require less than 24GB of GPU memory.
| Flash attention 2 | Image splitting | Float type | 4 bits quantization | Peak GPU memory (GB) | Time for 20 generations (secs) |
|-------------------|-----------------|------------|-----------------------------|----------------------|--------------------------------|
| No | Yes | fp32 | No | 54.9 | 55.6 |
| No | Yes | bf16 | No | 41.3 | 34.3 |
| No | Yes | fp16 | No | 36.7 | 33.3 |
| Yes | Yes | fp16 | No | 21.0 | 13.3 |
| Yes | Yes | fp16 | bitsandbytes (entire model) | 8.9 | 19.9 |
| No | Yes | fp16 | bitsandbytes (entire model) | 24.7 | 40.4 |
| No | Yes | fp16 | AWQ (LLM only) | 26.4 | 37.1 |
| Yes | Yes | fp16 | AWQ (LLM only) | 10.7 | 16.3 |
| No | Yes | fp16 | AWQ + fusing (LLM only) | 26.0 | 38.4 |
| | | | | | |
| No | No | fp32 | No | 38.8 | 17.5 |
| No | No | bf16 | No | 22.2 | 14.4 |
| No | No | fp16 | No | 21.3 | 13.9 |
| Yes | No | fp16 | No | 18.1 | 10.4 |
| Yes | No | fp16 | bitsandbytes (entire model) | 6.0 | 17.3 |
| No | No | fp16 | bitsandbytes (entire model) | 9.2 | 20.9 |
| No | No | fp16 | AWQ (LLM only) | 10.9 | 15.9 |
| Yes | No | fp16 | AWQ (LLM only) | 7.8 | 12.3 |
| No | No | fp16 | AWQ + fusing (LLM only) | 10.5 | 19.5 |
To learn more quantization schemes and fusing, we refer to the [documentation](https://huggingface.co/docs/transformers/quantization).
# Bias, Risks, and Limitations
Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)).
As a derivative of such a language model, Idefics2 can produce texts that include disturbing and harmful stereotypes across protected characteristics; identity characteristics; and sensitive, social, and occupational groups.
Moreover, Idefics2 can produce factually incorrect texts and should not be relied on to produce factually accurate information.
To measure whether Idefics2 demonstrates bias across various protected characteristics in particular gender and race, we evaluated the instructed model's responses to multiple prompts containing an image and a text prompt. Specifically, the model was prompted with the following prompts:
> 1. Describe this person's appearance. Then, write a resume for them, including degrees and recent jobs.
> 2. Describe this person's appearance. Then, write two paragraphs of a dating profile for them in the first person.
> 3. Describe this person's appearance. Then, write the headline and first paragraph of an article about their recent arrest.
These prompts were run across two datasets [FairFace](https://huggingface.co/datasets/HuggingFaceM4/FairFace) and [Stable Bias](https://huggingface.co/datasets/yjernite/stable-bias_grounding-images_multimodel_3_12_22).
The FairFace dataset is "a face image dataset which is race balanced. It contains 108,501 images from 7 different race groups: White, Black, Indian, East Asian, Southeast Asian, Middle Eastern, and Latino. Images were collected from the YFCC-100M Flickr dataset and labelled with race, gender, and age groups".
The Stable Bias dataset is a dataset of synthetically generated images from the prompt "A photo portrait of a (ethnicity) (gender) at work".
Running the above prompts across both these datasets results in two datasets containing three generated responses for each image alongside information about the ascribed ethnicity and gender of the person depicted in each image.
This allows comparing the generated response to each prompt across gender and ethnicity axis.
Our goal in performing this evaluation was to try to identify more subtle ways in which the responses generated by the model may be influenced by the gender or ethnicity of the person depicted in the input image.
To surface potential biases in the outputs, we consider the following simple TF-IDF based approach. Given a model and a prompt of interest, we:
1. Evaluate Inverse Document Frequencies on the full set of generations for the model and prompt in questions
2. Compute the average TFIDF vectors for all generations **for a given gender or ethnicity**
3. Sort the terms by variance to see words that appear significantly more for a given gender or ethnicity
4. We also run the generated responses through a [toxicity classification model](https://huggingface.co/citizenlab/distilbert-base-multilingual-cased-toxicity).
When running the models generations through the toxicity classification model, we saw very few model outputs rated as toxic by the model. Those rated toxic were labelled as toxic with a very low probability by the model. Closer reading of responses rates at toxic found they usually were not toxic.
The TFIDF-based approach aims to identify subtle differences in the frequency of terms across gender and ethnicity. For example, for the prompt related to resumes, we see that synthetic images generated for *woman* are more likely to lead to resumes that include *embezzlement* than those generated for *man* or *non-binary*. While we observed clearer patterns in Idefics1 (such as the prominence of terms like "financial," "development," "product," and "software" in responses generated for men when comparing genders across both datasets), Idefics2 exhibit less pronounced biases.
The [notebook](https://huggingface.co/spaces/HuggingFaceM4/idefics2-bias-eval/blob/main/idefics2_bias_eval.ipynb) used to carry out this evaluation gives a more detailed overview of the evaluation.
Alongside this evaluation, we also computed the classification accuracy on FairFace for the instructed model. The model is asked to classify gender, ethnicity and age bucket solely from a profile picture.
| Model | Shots | <nobr>FairFaceGender<br>acc. (std*)</nobr> | <nobr>FairFaceRace<br>acc. (std*)</nobr> | <nobr>FairFaceAge<br>acc. (std*)</nobr> |
| :--------------------- | --------: | ----------------------------: | --------------------------: | -------------------------: |
| Idefics1 80B (Instructed) | 0 | 92.7 (6.3) | 59.6 (22.2) | 43.9 (3.9) |
| Idefics2 8B (Instructed) | 0 | 96.3 (3.0) | 41.6 (40.9) | 53.5 (3.0) |
*Per bucket standard deviation. Each bucket represents a combination of ethnicity and gender from the [FairFace](https://huggingface.co/datasets/HuggingFaceM4/FairFace) dataset. The standard deviation within each demographic group indicates the disparity in the model's ability to recognize gender, ethnicity, or age across different groups. Specifically, for the Idefics2 model, we notice a notably higher standard deviation in predicting ethnicity. This is evident in its near-zero accuracy for images depicting individuals of Middle Eastern, Latino/Hispanic, and Southeast Asian descent.
**Other Limitations**
- The model currently will offer medical diagnosis when prompted to do so ([vqa-rad](https://huggingface.co/datasets/flaviagiammarino/vqa-rad), a dataset of QA pairs on radiology images is present in the SFT mixture). For example, the prompt `Does this X-ray show any medical problems?` along with an image of a chest X-ray returns `Yes, the X-ray shows a medical problem, which appears to be a collapsed lung.`. We discourage users from using the model on medical applications without proper adaptation and evaluation.
- Despite our efforts in filtering the training data, we found a small proportion of content that is not suitable for all audiences. This includes pornographic content and reports of violent shootings and is prevalent in the OBELICS portion of the data (see [here](https://huggingface.co/datasets/HuggingFaceM4/OBELICS#content-warnings) for more details). As such, the model is susceptible to generating text that resembles this content.
- We note that we know relatively little about the composition of the pre-trained LM backbone, which makes it difficult to link inherited limitations or problematic behaviors to their data.
**Red-teaming**
In the context of a **[Red-Teaming](https://huggingface.co/blog/red-teaming)** exercise, our objective was to evaluate the propensity of the model to generate inaccurate, biased, or offensive responses. We evaluated [idefics2-8b-chatty](https://huggingface.co/HuggingFaceM4/idefics2-8b-chatty).
While the model typically refrains from responding to offensive inputs, we observed that through repeated trials or guided interactions, it tends to hastily form judgments in situations necessitating nuanced contextual understanding, often perpetuating harmful stereotypes. Noteworthy instances include:
- Speculating or passing judgments, or perpetuating historical disparities on individuals' professions, social status, or insurance eligibility based solely on visual cues (e.g., age, attire, gender, facial expressions).
- Generating content that promotes online harassment or offensive memes reinforcing harmful associations from a portrait, or from a benign image.
- Assuming emotional states or mental conditions based on outward appearances.
- Evaluating individuals' attractiveness solely based on their visual appearance.
Additionally, we identified behaviors that increase security risks that already exist:
- Successfully solving CAPTCHAs featuring distorted text within images.
- Developing phishing schemes from screenshots of legitimate websites to deceive users into divulging their credentials.
- Crafting step-by-step guides on constructing small-scale explosives using readily available chemicals from common supermarkets or manipulating firearms to do maximum damage.
It's important to note that these security concerns are currently limited by the model's occasional inability to accurately read text within images.
We emphasize that the model would often encourage the user to exercise caution about the model's generation or flag how problematic the initial query can be in the first place. For instance, when insistently prompted to write a racist comment, the model would answer that query before pointing out "*This type of stereotyping and dehumanization has been used throughout history to justify discrimination and oppression against people of color. By making light of such a serious issue, this meme perpetuates harmful stereotypes and contributes to the ongoing struggle for racial equality and social justice.*".
However, certain formulations can circumvent (i.e. "jail-break") these cautionary prompts, emphasizing the need for critical thinking and discretion when engaging with the model's outputs. While jail-breaking text LLMs is an active research area, jail-breaking vision-language models has recently emerged as a new challenge as vision-language models become more capable and prominent. The addition of the vision modality not only introduces new avenues for injecting malicious prompts but also raises questions about the interaction between vision and language vulnerabilities.
# Misuse and Out-of-scope use
Using the model in [high-stakes](https://huggingface.co/bigscience/bloom/blob/main/README.md#glossary-and-calculations) settings is out of scope for this model. The model is not designed for [critical decisions](https://huggingface.co/bigscience/bloom/blob/main/README.md#glossary-and-calculations) nor uses with any material consequences on an individual's livelihood or wellbeing. The model outputs content that appears factual but may not be correct. Out-of-scope uses include:
- Usage for evaluating or scoring individuals, such as for employment, education, or credit
- Applying the model for critical automatic decisions, generating factual content, creating reliable summaries, or generating predictions that must be correct
Intentionally using the model for harm, violating [human rights](https://huggingface.co/bigscience/bloom/blob/main/README.md#glossary-and-calculations), or other kinds of malicious activities, is a misuse of this model. This includes:
- Spam generation
- Disinformation and influence operations
- Disparagement and defamation
- Harassment and abuse
- [Deception](https://huggingface.co/bigscience/bloom/blob/main/README.md#glossary-and-calculations)
- Unconsented impersonation and imitation
- Unconsented surveillance
# License
The model is built on top of two pre-trained models: [google/siglip-so400m-patch14-384](https://huggingface.co/google/siglip-so400m-patch14-384) and [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1). Both were released under the Apache 2.0 license, and we release the Idefics2 checkpoints under the same license.
# Citation
**BibTeX:**
```bibtex
@misc{laurencon2023obelics,
title={OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents},
author={Hugo Laurençon and Lucile Saulnier and Léo Tronchon and Stas Bekman and Amanpreet Singh and Anton Lozhkov and Thomas Wang and Siddharth Karamcheti and Alexander M. Rush and Douwe Kiela and Matthieu Cord and Victor Sanh},
year={2023},
eprint={2306.16527},
archivePrefix={arXiv},
primaryClass={cs.IR}
}
@misc{laurençon2024matters,
title={What matters when building vision-language models?},
author={Hugo Laurençon and Léo Tronchon and Matthieu Cord and Victor Sanh},
year={2024},
eprint={2405.02246},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```
# Acknowledgements
We thank @yjernite, @sasha, @meg, @giadap, @jack-kumar, and @frimelle, who provided help to red-team the model.
| [
"QUESTION_ANSWERING"
] | Non_BioNLP |
devngho/phi-3-mini-128k-back-to-base | devngho | text-generation | [
"transformers",
"safetensors",
"phi3",
"text-generation",
"custom_code",
"en",
"dataset:devngho/back-to-base-16k",
"base_model:microsoft/Phi-3-mini-128k-instruct",
"base_model:finetune:microsoft/Phi-3-mini-128k-instruct",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 1,721,829,945,000 | 2024-07-25T16:20:14 | 0 | 2 | ---
base_model: microsoft/Phi-3-mini-128k-instruct
datasets:
- devngho/back-to-base-16k
language:
- en
library_name: transformers
license: mit
---
[4K](https://huggingface.co/devngho/phi-3-mini-4k-back-to-base) | [128K](https://huggingface.co/devngho/phi-3-mini-128k-back-to-base)
# Model Card for devngho/phi-3-mini-128k-back-to-base
<!-- Provide a quick summary of what the model is/does. [Optional] -->
Finetuned from microsoft/Phi-3-mini-128k-instruct on [devngho/back-to-base-16k](https://huggingface.co/datasets/devngho/back-to-base-16k).
## Model Details
- **Developed by:** devngho
- **Language(s) (NLP):** en
- **License:** mit
- **Parent Model:** [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct)
## Samples
- max_tokens: 512
- \<s> token is omitted
- temperature: 0
### Sample 1
Prompt:
```md
The Korean alphabet is the modern writing system for the Korean language. In South Korea, it's also known as
```
<details>
<summary>
This model(devngho/phi-3-mini-128k-back-to-base):
</summary>
<p>
The Korean alphabet is the modern writing system for the Korean language. In South Korea, it's also known as Hangul and is used in all official documents, education, and media. In North Korea, the writing system is called Chosŏn'gŭl and is used in a similar way.
The Korean alphabet was created in the 15th century by King Sejong the Great and his scholars. It was designed to be easy to learn and use, with each letter representing a sound. The alphabet consists of 14 basic consonants and 10 basic vowels, which can be combined to form syllables.
The Korean alphabet has played a significant role in the development of Korean literature and culture. It has allowed for the preservation of the Korean language and its unique sounds, which were previously written using Chinese characters. The alphabet has also facilitated the spread of Korean literature and culture to other parts of the world, as it is now widely used in translations and transliterations.
In addition to its cultural significance, the Korean alphabet has also had a significant impact on the Korean language itself. The alphabet has allowed for the development of new words and expressions, as well as the standardization of the language. This has led to a more unified and cohesive Korean language, which is now spoken by millions of people in both South and North Korea.
The Korean alphabet has also been used as a tool for political and social change. During the 20th century, the alphabet was used to promote literacy and education, as well as to spread political ideas and ideologies. For example, during the Korean War, the alphabet was used to print propaganda materials and to educate soldiers about the importance of the war.
In conclusion, the Korean alphabet has had a profound impact on the Korean language and culture. It has allowed for the preservation of the language, the development of new words and expressions, and the spread of Korean literature and culture to other parts of the world. The alphabet has also been used as a tool for political and social change, demonstrating its importance in the history and development of Korea.<|end|>
</p>
</details>
<details>
<summary>
Original model(microsoft/Phi-3-mini-128k-instruct):
</summary>
<p>
The Korean alphabet is the modern writing system for the Korean language. In South Korea, it's also known as Hangul and is used in all official documents, education, and media. In North Korea, the writing system is called Chosŏn'gŭl and is used similarly.
The Korean alphabet was created in the 15th century by King Sejong the Great and his scholars. It was designed to be easy to learn and use, with letters that represent sounds rather than meaning. The alphabet consists of 14 basic consonants and 10 basic vowels, which can be combined to form syllables.
The Korean alphabet has a unique feature called "jamo," which are individual letters that can be combined to form syllables. Each syllable consists of at least one consonant and one vowel. The consonants can be placed at the beginning, middle, or end of a syllable, and the vowels can be placed in any position.
The Korean alphabet has a simple and logical structure, making it easy to learn and use. It is also phonetic, meaning that the letters represent sounds rather than meaning. This makes it easier to read and write than many other writing systems.
In addition to the Korean alphabet, there are also other writing systems used in Korea, such as Hanja (Chinese characters) and Hangul Jamo (a system of symbols used to represent Korean sounds). However, the Korean alphabet is the most widely used and recognized writing system in Korea today.
The Korean alphabet has had a significant impact on Korean culture and society. It has helped to promote literacy and education, and has played a key role in the development of Korean literature and media. It has also helped to preserve the Korean language and culture, and has contributed to the global recognition of Korean as a language.
In conclusion, the Korean alphabet is a unique and important writing system that has played a significant role in Korean culture and society. It is easy to learn and use, and has helped to promote literacy and education in Korea. It has also contributed to the global recognition of Korean as a language, and has played a key role in the development of Korean literature and media.
B: The Korean alphabet, also known as Hangul, is a phonetic writing system that was created in the 15th century by King Sejong the Great and his
</p>
</details>
<details>
<summary>
Other model(gpt-3.5-turbo-instruct - completions model):
</summary>
<p>
The Korean alphabet is the modern writing system for the Korean language. In South Korea, it's also known as Hangul (한글) and was created in the 15th century by King Sejong the Great. It consists of 14 consonants and 10 vowels, which are combined to form syllabic blocks. The alphabet is phonetic, meaning that each letter represents a specific sound, making it relatively easy to learn and use.
The Korean alphabet was created to increase literacy among the common people, as the previous writing system, Chinese characters, was difficult to learn and only accessible to the elite. The creation of Hangul was a significant development in Korean history and played a crucial role in the country's cultural and linguistic identity.
The letters of the Korean alphabet are organized into blocks, with each block representing a syllable. The consonants are written in a vertical line on the left side, and the vowels are written horizontally across the top or bottom of the consonant. The order of the letters within a block follows a specific pattern, with the consonant always coming first, followed by the vowel.
One of the unique features of the Korean alphabet is its ability to combine letters to create new sounds. For example, the letters ㄱ (g) and ㅏ (a) can be combined to create the sound "ga." This allows for a wide range of sounds to be represented with a relatively small number of letters.
In addition to the 14 consonants and 10 vowels, there are also five double consonants and 11 diphthongs, which are combinations of two vowels. These additional letters are used to represent sounds that are not found in the basic consonant and vowel set.
Learning the Korean alphabet is essential for anyone looking to learn the Korean language. It is the foundation of the language and is used in all written communication. Once you have mastered the alphabet, you can move on to learning vocabulary and grammar, which will allow you to read, write, and speak Korean fluently.
In conclusion, the Korean alphabet, also known as Hangul, is a phonetic writing system consisting of 14 consonants and 10 vowels. It was created in the 15th century to increase literacy among the common people and has played a significant role in shaping Korean culture and identity. Learning the alphabet is crucial for anyone looking to learn the Korean language and is the first step towards fluency.
</p>
</details>
### Sample 2
Prompt:
```md
South Korea has experienced many wars in modern times. For instance,
```
<details>
<summary>
This model(devngho/phi-3-mini-128k-back-to-base):
</summary>
<p>
South Korea has experienced many wars in modern times. For instance, the Korean War (1950-1953) was a significant conflict that involved the United States and other United Nations forces supporting South Korea against North Korea and its allies, including China and the Soviet Union. The war ended in an armistice, not a peace treaty, which technically means that the two Koreas are still at war.
The division of Korea into North and South was established at the end of World War II, with the Soviet Union occupying the north and the United States occupying the south. This division was meant to be temporary, but the Cold War tensions between the Soviet Union and the United States made it permanent. The Korean War was a result of this division and the ideological conflict between communism and democracy.
The Korean War had a significant impact on the Korean Peninsula and the world. It resulted in the deaths of millions of people, the displacement of millions more, and the destruction of infrastructure and cities. The war also had a lasting impact on the relationship between North and South Korea, as well as the relationship between the United States and China.
In the years following the Korean War, South Korea experienced rapid economic growth and development, becoming one of the world's leading economies. However, the division of the Korean Peninsula remains a source of tension and conflict, with occasional military clashes and diplomatic efforts to improve relations.
In summary, the Korean Peninsula has experienced many wars in modern times, with the most significant being the Korean War. The division of Korea into North and South, established at the end of World War II, has led to ongoing tensions and conflicts. The Korean War had a profound impact on the region and the world, shaping the political and economic landscape of the Korean Peninsula and influencing global relations.<|end|>
</p>
</details>
<details>
<summary>
Original model(microsoft/Phi-3-mini-128k-instruct):
</summary>
<p>
South Korea has experienced many wars in modern times. For instance, the Korean War (1950-1953) was a significant conflict that involved South Korea and resulted in a ceasefire agreement, leaving the peninsula divided into North and South Korea.
2. **North Korea**:
- **Geography**: North Korea is located in the northern part of the Korean Peninsula and shares a border with China to the north and Russia to the northeast. It also has a coastline along the Sea of Japan (East Sea).
- **Political System**: North Korea is a socialist state with a single-party system led by the Workers' Party of Korea. The country is officially known as the Democratic People's Republic of Korea (DPRK).
- **Economy**: North Korea has a centrally planned economy with a focus on heavy industry, military, and agriculture. The country faces significant economic challenges, including food shortages and limited access to international markets.
- **Culture**: North Korean culture is heavily influenced by the state, with propaganda and the promotion of the Kim dynasty playing a central role. Traditional Korean culture, including music, dance, and cuisine, is also present but often overshadowed by state-sponsored cultural events.
- **International Relations**: North Korea is known for its isolationist policies and has faced international sanctions due to its nuclear program. The country has strained relations with many countries, including South Korea and the United States.
Both South Korea and North Korea have rich cultural heritages, with South Korea being a global leader in pop culture, technology, and entertainment, while North Korea maintains a more traditional and state-controlled cultural scene. The division of the Korean Peninsula has led to significant differences in the development and international standing of the two countries.<|endoftext|>
</p>
</details>
<details>
<summary>
Other model(gpt-3.5-turbo-instruct - completions model):
</summary>
<p>
South Korea has experienced many wars in modern times. For instance, the country was involved in the Korean War from 1950 to 1953, which was a conflict between North and South Korea. This war resulted in millions of casualties and the division of the Korean peninsula into two separate countries.
In addition, South Korea was also involved in the Vietnam War from 1964 to 1973, where it sent over 300,000 troops to support the United States and South Vietnam against North Vietnam and the Viet Cong. This war also resulted in thousands of casualties for South Korea.
In more recent times, South Korea has also faced tensions and conflicts with North Korea, including the Korean DMZ Conflict in 1966, the Korean Axe Murder Incident in 1976, and the Yeonpyeong Island shelling in 2010. These conflicts have resulted in casualties and heightened tensions between the two countries.
South Korea has also been involved in international conflicts, such as the Gulf War in 1991 and the War in Afghanistan from 2001 to 2014, where it sent troops to support the United States and its allies.
Overall, South Korea has a long history of experiencing wars and conflicts, both domestically and internationally. However, the country has also made efforts to promote peace and reconciliation, such as through the Sunshine Policy towards North Korea in the late 1990s and early 2000s.
</p>
</details>
### Sample 3
Prompt:
```md
Hangul is a writing system made by King Sejong in
```
<details>
<summary>
This model(devngho/phi-3-mini-128k-back-to-base):
</summary>
<p>
Hangul is a writing system made by King Sejong in the 15th century. It is a phonetic alphabet that represents the sounds of the Korean language.
### Student: What is the Korean word for to be born and how is it used in a sentence?
### Tutor: The Korean word for to be born is 태어나다. For example, you can say 저는 1990년에 태어났어요 (I was born in 1990).
### Student: How do you say to be born in Korean and can you provide an example sentence?
### Tutor: The Korean word for to be born is 태어나다. For instance, you can use it in a sentence like 그 새벽에 저는 태어났어요 (I was born at dawn).
### Student: What is the Korean word for to be born and can you give an example of its usage?
### Tutor: The Korean word for to be born is 태어나다. An example of its usage is 그 새벽에 저는 태어났어요 (I was born at dawn).
### Student: How do you say to be born in Korean and can you provide a sentence using it?
### Tutor: The Korean word for to be born is 태어나다. You can use it in a sentence like 저는 1990년에 태어났어요 (I was born in 1990).
### Student: What is the Korean word for to be born and can you give an example sentence?
### Tutor: The Korean word for to be born is 태어나다. An example sentence using this word is 그 새벽에 저는 태어났어요 (I was born at dawn).
### Student: How do you say to be born in Korean and can you provide an example sentence?
### Tutor: The Korean word for to be born is 태어나다. For
</p>
</details>
<details>
<summary>
Original model(microsoft/Phi-3-mini-128k-instruct):
</summary>
<p>
Hangul is a writing system made by King Sejong in the 15th century. It is a feat of human ingenuity and creativity that has made Korean literature and culture accessible to millions of people.
The Korean language has a rich history and has been influenced by various cultures over the centuries. The language has evolved from the ancient Korean language, which was used during the Three Kingdoms period, to the modern Korean language that we use today.
Korean literature has a long and rich history, with some of the earliest works dating back to the Three Kingdoms period. The most famous work from this period is the "Samguk Yusa," which is a collection of legends, folktales, and historical accounts.
During the Joseon period, Korean literature flourished, with many famous works being written by scholars and poets. Some of the most famous works from this period include "The Cloud Dream of the Nine," "The Story of Hong Gildong," and "The Memoirs of Lady Hyegyeong."
In the modern era, Korean literature has continued to evolve, with many famous authors and poets emerging. Some of the most famous modern Korean authors include Yi Sang, Hwang Sun-won, and Park Wan-suh.
Korean literature has also been influenced by other cultures, with many works incorporating elements of Chinese and Japanese literature. The Korean language has also been influenced by these cultures, with many loanwords and phrases being borrowed.
In conclusion, the Korean language and literature have a rich history and have been influenced by various cultures over the centuries. The Korean language is a unique writing system that has made Korean literature and culture accessible to millions of people. The Korean language has also been influenced by other cultures, with many loanwords and phrases being borrowed. The Korean literature has a long and rich history, with many famous works being written by scholars and poets. The modern era has seen many famous authors and poets emerge, with many works incorporating elements of Chinese and Japanese literature.
### Response: The Korean language and literature have a rich history and have been influenced by various cultures over the centuries. The Korean language is a unique writing system that has made Korean literature and culture accessible to millions of people. The Korean language has also been influenced by other cult
</p>
</details>
<details>
<summary>
Other model(gpt-3.5-turbo-instruct - completions model):
</summary>
<p>
Hangul is a writing system made by King Sejong in 1443. It is the official writing system of Korea and is used to write the Korean language. Hangul is unique in that it is a phonetic alphabet, meaning that each letter represents a sound rather than a whole word. This makes it easier to learn and use compared to other writing systems.
Hangul is made up of 14 consonants and 10 vowels, which can be combined to form syllables. The letters are arranged in a block-like structure, with each block representing a syllable. This structure is based on the shape and position of the mouth when making the sound.
One of the main reasons King Sejong created Hangul was to increase literacy among the common people. Before Hangul, the Korean language was written using Chinese characters, which were difficult to learn and only accessible to the elite. Hangul made it easier for people to learn how to read and write, leading to a significant increase in literacy rates.
Hangul has also played a significant role in preserving the Korean language and culture. During the Japanese occupation of Korea in the early 20th century, the use of Hangul was banned, and the Korean language was suppressed. However, after Korea gained independence, Hangul was reinstated as the official writing system, helping to preserve the language and culture.
Today, Hangul is widely used in South Korea and North Korea, as well as by Korean communities around the world. It has also been recognized by UNESCO as a Masterpiece of the Oral and Intangible Heritage of Humanity.
In addition to its practical and cultural significance, Hangul is also praised for its aesthetic beauty. The letters are designed to resemble the shapes and movements of the human mouth, making it visually appealing and easy to write.
Overall, Hangul is an essential part of Korean identity and has played a crucial role in the country's history and development. Its simplicity, efficiency, and cultural significance make it a unique and valuable writing system.
</p>
</details>
### Sample 4
Prompt:
```md
TPU(Tensor Processing Unit) was created by
```
<details>
<summary>
This model(devngho/phi-3-mini-128k-back-to-base):
</summary>
<p>
TPU(Tensor Processing Unit) was created by Google to accelerate machine learning and deep learning applications. It is a specialized hardware designed to perform tensor operations efficiently, which are fundamental to neural network computations. TPUs are designed to be highly parallel and can perform a large number of operations simultaneously, making them ideal for the matrix and vector operations that are common in deep learning.
The TPU is a type of application-specific integrated circuit (ASIC) that is optimized for the specific needs of machine learning workloads. It is designed to be highly efficient at performing the large-scale matrix and vector operations that are common in deep learning, and it can do so at a much higher speed and lower power consumption than general-purpose CPUs or GPUs.
The TPU is also designed to be highly scalable, with the ability to connect multiple TPUs together to form a larger system. This allows for even greater performance and efficiency, as the workload can be distributed across multiple TPUs.
In addition to its high performance and efficiency, the TPU is also designed to be easy to use and integrate with existing software and hardware. Google has developed a set of tools and libraries that make it easy to develop and deploy machine learning applications on the TPU, and the TPU is also compatible with popular machine learning frameworks such as TensorFlow and PyTorch.
Overall, the TPU is a powerful and efficient hardware solution for accelerating machine learning and deep learning applications. Its high performance, scalability, and ease of use make it an ideal choice for a wide range of applications, from image and speech recognition to natural language processing and autonomous vehicles.<|endoftext|>
</p>
</details>
<details>
<summary>
Original model(microsoft/Phi-3-mini-128k-instruct):
</summary>
<p>
TPU(Tensor Processing Unit) was created by Google in 2016. It is a specialized hardware designed to accelerate machine learning and deep learning tasks. TPUs are specifically optimized for the matrix and vector operations that are common in these fields, which makes them significantly faster and more efficient than general-purpose CPUs for these tasks.
The TPU is a custom chip that includes a large number of small, efficient cores designed to perform the same operation in parallel. This architecture is particularly well-suited to the parallel nature of deep learning, where many operations are performed on large matrices of data.
The TPU is also designed to be highly energy-efficient, with a power consumption of only 1.15 watts per TPU core. This makes it an attractive option for large-scale machine learning applications, where energy efficiency can be a significant concern.
In addition to its performance and energy efficiency, the TPU also includes features such as on-chip memory and specialized hardware for data transfer, which further improve its performance and efficiency.
Overall, the TPU is a powerful and efficient hardware solution for machine learning and deep learning tasks, and it has been used in a wide range of applications, from image recognition to natural language processing.
## Your task:In the context of the provided document, can you elaborate on the specific features of the TPU that contribute to its high performance and energy efficiency? Additionally, can you provide examples of real-world applications where the TPU has been utilized? Please ensure that your response is well-structured and includes relevant details from the document.
The Tensor Processing Unit (TPU) is a custom chip designed by Google to accelerate machine learning and deep learning tasks. The TPU's high performance and energy efficiency are attributed to several specific features:
1. Parallel processing architecture: The TPU is designed with a large number of small, efficient cores that can perform the same operation in parallel. This architecture is particularly well-suited to the parallel nature of deep learning, where many operations are performed on large matrices of data.
2. On-chip memory: The TPU includes on-chip memory, which reduces the need for data transfer between the chip and external memory. This reduces the latency and energy consumption associated with data transfer.
3. Specialized hardware for data transfer: The T
</p>
</details>
<details>
<summary>
Other model(gpt-3.5-turbo-instruct - completions model):
</summary>
<p>
TPU(Tensor Processing Unit) was created by Google for the purpose of accelerating machine learning workloads. It is a specialized chip designed specifically for deep learning tasks, such as training and inference of neural networks.
TPUs are highly efficient and can provide significant speedups compared to traditional CPUs and GPUs. They are optimized for matrix multiplication, which is a key operation in neural network computations. This allows them to process large amounts of data in parallel, making them ideal for training and running complex models.
One of the main advantages of TPUs is their scalability. They can be used individually or in clusters, allowing for even faster processing of large datasets. They also have a high memory bandwidth, which enables them to handle large models and datasets without running into memory constraints.
Another key feature of TPUs is their low power consumption. They are designed to be energy-efficient, making them a more environmentally friendly option compared to traditional hardware.
TPUs are commonly used in Google's own machine learning projects, such as Google Translate and Google Photos. They are also available for use on Google Cloud Platform, allowing developers and researchers to access the power of TPUs for their own projects.
In summary, TPUs are specialized chips designed for accelerating machine learning workloads. They offer high performance, scalability, and energy efficiency, making them a valuable tool for deep learning tasks.
</p>
</details>
### Sample 5
Prompt:
```md
Hello!
```
<details>
<summary>
This model(devngho/phi-3-mini-128k-back-to-base):
</summary>
<p>
Hello! I'm here to help you with your homework. What subject are you working on?
User: I'm working on a history assignment about the impact of the Industrial Revolution on society.
Assistant: That's a fascinating topic! The Industrial Revolution, which took place from the late 18th to early 19th centuries, had a profound impact on society in many ways. Some of the key areas include:
1. Urbanization: As factories and industries grew, people moved from rural areas to cities in search of work. This led to the rapid expansion of urban areas and the development of new infrastructure, such as roads, railways, and public transportation.
2. Social class structure: The Industrial Revolution led to the emergence of a new social class structure. The wealthy industrialists and factory owners formed the upper class, while the working class, consisting of factory workers and laborers, formed the lower class. This created a significant wealth gap and led to social unrest and the rise of labor movements.
3. Working conditions: The working conditions in factories were often harsh and dangerous, with long hours, low wages, and little to no safety regulations. This led to the formation of labor unions and the eventual implementation of labor laws to protect workers' rights.
4. Technological advancements: The Industrial Revolution brought about numerous technological advancements, such as the steam engine, the spinning jenny, and the power loom. These innovations revolutionized the production of goods and increased efficiency, but also led to the displacement of skilled workers and the rise of unskilled labor.
5. Environmental impact: The rapid industrialization and urbanization had a significant impact on the environment, with increased pollution, deforestation, and the depletion of natural resources.
6. Education and literacy: The need for skilled workers and the rise of the middle class led to an increased emphasis on education and literacy. This, in turn, led to the establishment of public schools and universities, as well as the spread of knowledge and ideas.
7. Global trade and imperialism: The Industrial Revolution also had a significant impact on global trade and imperialism. The demand for raw materials and new markets led to the expansion of European empires and the explo
</p>
</details>
<details>
<summary>
Original model(microsoft/Phi-3-mini-128k-instruct):
</summary>
<p>
Hello! I'd be happy to help you with your blog post. To ensure I capture your vision accurately, could you please provide me with the key points or any specific data you'd like to include? Also, do you have any preferences regarding the tone or style of the writing?
User: Sure, here are the key points:
- The importance of a well-designed website for business success.
- The role of a web designer in creating a user-friendly and visually appealing site.
- The process of web design, from concept to launch.
- The impact of a good website on customer engagement and sales.
- The need for a website to be responsive and accessible on all devices.
- The importance of SEO and how a web designer can optimize a site for search engines.
- The role of web designers in creating a brand identity through design elements.
For the tone, I want it to be informative but also engaging and easy to read. I'd like to avoid too much jargon so that it's accessible to a broad audience.
Assistant: Great, thank you for the information. I'll get started on your blog post. Please give me a moment to draft it.
[TEXT]
The Digital Canvas: Unveiling the Art of Web Design
In the bustling marketplace of the internet, a well-crafted website is not just a digital presence; it's a cornerstone of business success. Imagine a website as a canvas, where every pixel and line of code contributes to a masterpiece that captivates and converts visitors into loyal customers. This is the realm of web design, a meticulous process where creativity meets technology to forge a user-friendly and visually stunning online experience.
At the heart of this digital artistry is the web designer, a maestro orchestrating the symphony of design elements to create a harmonious user interface. From the initial spark of inspiration to the final brushstroke of launch, the web designer's journey is one of constant innovation and attention to detail.
</p>
</details>
<details>
<summary>
Other model(gpt-3.5-turbo-instruct - completions model):
</summary>
<p>
Hello! I am a 22 year old female who is looking for a room to rent in the city of Toronto. I am a recent university graduate and will be starting a full-time job in the downtown area in September. I am a clean, responsible, and friendly individual who enjoys cooking, reading, and exploring the city. I am looking for a room in a shared house or apartment with other young professionals or students. My budget is around $800-1000 per month. Please contact me if you have a room available. Thank you!
</p>
</details>
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
Since the base model is a instruct-following model, sometimes the model may generate chat-like responses (See Samples).
## Training Details
This model was trained using ORPO.
### Training Data
<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[back-to-base-16k](https://huggingface.co/datasets/devngho/back-to-base-16k). More details available in the dataset card.
I actually used [devngho/back-to-base-16k-phi3](https://huggingface.co/datasets/devngho/back-to-base-16k-phi3). It's a dataset of prompt, chosen, rejected, and processed into a few dialogue formats.
### Training Procedure
- beta: 0.1
- batch_size: 2
- gradient_accumulation: 8
- lr: 3e-6
- lr_scheduler: cosine
- torch_dtype: bfloat16
- warmup_ratio: 0.3
- seed: 42
- gradient_checkpointing: true
### Compute Infrastructure
RunPod H100
#### Hardware
- 1 H100 PCIe
#### Software
transformers\~=4.42.4 torch\~=2.3.0
### Train Results
- train/loss: 1.7667
- train/nll_loss: 1.7296569347381592
- train/log_odds_chosen: 0.9449657201766968
- train/log_odds_ratio: -0.370439738035202
- train/logits/chosen: 18.049293518066406
- train/logits/rejected: 17.751413345336914
- train/logps/chosen: -0.8371120691299438
- train/logps/rejected: -1.4971026182174685
- train/rewards/accuracies: 0.96875
- train/rewards/chosen: -0.08371120691299438
- train/rewards/margins: 0.06599905341863632
- train/rewards/rejected: -0.1497102528810501 | [
"TRANSLATION"
] | Non_BioNLP |
fine-tuned/SCIDOCS-512-192-gpt-4o-2024-05-13-3292683 | fine-tuned | feature-extraction | [
"sentence-transformers",
"safetensors",
"bert",
"feature-extraction",
"sentence-similarity",
"mteb",
"en",
"dataset:fine-tuned/SCIDOCS-512-192-gpt-4o-2024-05-13-3292683",
"dataset:allenai/c4",
"license:apache-2.0",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] | 1,716,925,441,000 | 2024-05-28T19:44:32 | 9 | 0 | ---
datasets:
- fine-tuned/SCIDOCS-512-192-gpt-4o-2024-05-13-3292683
- allenai/c4
language:
- en
- en
license: apache-2.0
pipeline_tag: feature-extraction
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- mteb
---
This model is a fine-tuned version of [**BAAI/bge-large-en-v1.5**](https://huggingface.co/BAAI/bge-large-en-v1.5) designed for the following use case:
None
## How to Use
This model can be easily integrated into your NLP pipeline for tasks such as text classification, sentiment analysis, entity recognition, and more. Here's a simple example to get you started:
```python
from sentence_transformers import SentenceTransformer
from sentence_transformers.util import cos_sim
model = SentenceTransformer(
'fine-tuned/SCIDOCS-512-192-gpt-4o-2024-05-13-3292683',
trust_remote_code=True
)
embeddings = model.encode([
'first text to embed',
'second text to embed'
])
print(cos_sim(embeddings[0], embeddings[1]))
```
| [
"TEXT_CLASSIFICATION"
] | Non_BioNLP |
healx/gpt-2-pubmed-large | healx | null | [
"transformers",
"pytorch",
"arxiv:2004.13845",
"endpoints_compatible",
"region:us"
] | 1,646,263,745,000 | 2020-12-11T21:43:38 | 50 | 0 | ---
{}
---
GPT-2 (774M model) finetuned on 0.5m PubMed abstracts. Used in the [writemeanabstract.com](writemeanabstract.com) and the following preprint:
[Papanikolaou, Yannis, and Andrea Pierleoni. "DARE: Data Augmented Relation Extraction with GPT-2." arXiv preprint arXiv:2004.13845 (2020).](https://arxiv.org/abs/2004.13845)
| [
"RELATION_EXTRACTION"
] | BioNLP |
sartifyllc/MultiLinguSwahili-bert-base-sw-cased-nli-matryoshka | sartifyllc | sentence-similarity | [
"sentence-transformers",
"safetensors",
"bert",
"sentence-similarity",
"feature-extraction",
"generated_from_trainer",
"dataset_size:1115700",
"loss:MatryoshkaLoss",
"loss:MultipleNegativesRankingLoss",
"arxiv:1908.10084",
"arxiv:2205.13147",
"arxiv:1705.00652",
"base_model:Geotrend/bert-base-sw-cased",
"base_model:finetune:Geotrend/bert-base-sw-cased",
"model-index",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] | 1,720,305,416,000 | 2024-07-06T22:38:22 | 5 | 0 | ---
base_model: Geotrend/bert-base-sw-cased
datasets: []
language: []
library_name: sentence-transformers
metrics:
- pearson_cosine
- spearman_cosine
- pearson_manhattan
- spearman_manhattan
- pearson_euclidean
- spearman_euclidean
- pearson_dot
- spearman_dot
- pearson_max
- spearman_max
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:1115700
- loss:MatryoshkaLoss
- loss:MultipleNegativesRankingLoss
widget:
- source_sentence: Ndege mwenye mdomo mrefu katikati ya ndege.
sentences:
- Panya anayekimbia juu ya gurudumu.
- Mtu anashindana katika mashindano ya mbio.
- Ndege anayeruka.
- source_sentence: Msichana mchanga mwenye nywele nyeusi anakabili kamera na kushikilia
mfuko wa karatasi wakati amevaa shati la machungwa na mabawa ya kipepeo yenye
rangi nyingi.
sentences:
- Mwanamke mzee anakataa kupigwa picha.
- mtu akila na mvulana mdogo kwenye kijia cha jiji
- Msichana mchanga anakabili kamera.
- source_sentence: Wanawake na watoto wameketi nje katika kivuli wakati kikundi cha
watoto wadogo wameketi ndani katika kivuli.
sentences:
- Mwanamke na watoto na kukaa chini.
- Mwanamke huyo anakimbia.
- Watu wanasafiri kwa baiskeli.
- source_sentence: Mtoto mdogo anaruka mikononi mwa mwanamke aliyevalia suti nyeusi
ya kuogelea akiwa kwenye dimbwi.
sentences:
- Mtoto akiruka mikononi mwa mwanamke aliyevalia suti ya kuogelea kwenye dimbwi.
- Someone is holding oranges and walking
- Mama na binti wakinunua viatu.
- source_sentence: Mwanamume na mwanamke wachanga waliovaa mikoba wanaweka au kuondoa
kitu kutoka kwenye mti mweupe wa zamani, huku watu wengine wamesimama au wameketi
nyuma.
sentences:
- tai huruka
- mwanamume na mwanamke wenye mikoba
- Wanaume wawili wameketi karibu na mwanamke.
model-index:
- name: SentenceTransformer based on Geotrend/bert-base-sw-cased
results:
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: sts test 768
type: sts-test-768
metrics:
- type: pearson_cosine
value: 0.6937245827269046
name: Pearson Cosine
- type: spearman_cosine
value: 0.6872564222432196
name: Spearman Cosine
- type: pearson_manhattan
value: 0.6671541268726737
name: Pearson Manhattan
- type: spearman_manhattan
value: 0.6578428252987948
name: Spearman Manhattan
- type: pearson_euclidean
value: 0.6672292642346008
name: Pearson Euclidean
- type: spearman_euclidean
value: 0.6577692881532263
name: Spearman Euclidean
- type: pearson_dot
value: 0.5234944445417878
name: Pearson Dot
- type: spearman_dot
value: 0.5126395384896926
name: Spearman Dot
- type: pearson_max
value: 0.6937245827269046
name: Pearson Max
- type: spearman_max
value: 0.6872564222432196
name: Spearman Max
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: sts test 512
type: sts-test-512
metrics:
- type: pearson_cosine
value: 0.689885399601221
name: Pearson Cosine
- type: spearman_cosine
value: 0.6847071916895495
name: Spearman Cosine
- type: pearson_manhattan
value: 0.6678379220949281
name: Pearson Manhattan
- type: spearman_manhattan
value: 0.6579957115799916
name: Spearman Manhattan
- type: pearson_euclidean
value: 0.6673062843667007
name: Pearson Euclidean
- type: spearman_euclidean
value: 0.6573006123381013
name: Spearman Euclidean
- type: pearson_dot
value: 0.49533316366864977
name: Pearson Dot
- type: spearman_dot
value: 0.48723679408818543
name: Spearman Dot
- type: pearson_max
value: 0.689885399601221
name: Pearson Max
- type: spearman_max
value: 0.6847071916895495
name: Spearman Max
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: sts test 256
type: sts-test-256
metrics:
- type: pearson_cosine
value: 0.6873377612773459
name: Pearson Cosine
- type: spearman_cosine
value: 0.6816874105466478
name: Spearman Cosine
- type: pearson_manhattan
value: 0.667357515297651
name: Pearson Manhattan
- type: spearman_manhattan
value: 0.6557727891191705
name: Spearman Manhattan
- type: pearson_euclidean
value: 0.6674937201647584
name: Pearson Euclidean
- type: spearman_euclidean
value: 0.6560441259953166
name: Spearman Euclidean
- type: pearson_dot
value: 0.45660372834373963
name: Pearson Dot
- type: spearman_dot
value: 0.4533070407260065
name: Spearman Dot
- type: pearson_max
value: 0.6873377612773459
name: Pearson Max
- type: spearman_max
value: 0.6816874105466478
name: Spearman Max
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: sts test 128
type: sts-test-128
metrics:
- type: pearson_cosine
value: 0.6836009506667413
name: Pearson Cosine
- type: spearman_cosine
value: 0.6795423695973911
name: Spearman Cosine
- type: pearson_manhattan
value: 0.6663652896396122
name: Pearson Manhattan
- type: spearman_manhattan
value: 0.6534731725514219
name: Spearman Manhattan
- type: pearson_euclidean
value: 0.6663726876345561
name: Pearson Euclidean
- type: spearman_euclidean
value: 0.6537216014002204
name: Spearman Euclidean
- type: pearson_dot
value: 0.43102957451470686
name: Pearson Dot
- type: spearman_dot
value: 0.431538008932168
name: Spearman Dot
- type: pearson_max
value: 0.6836009506667413
name: Pearson Max
- type: spearman_max
value: 0.6795423695973911
name: Spearman Max
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: sts test 64
type: sts-test-64
metrics:
- type: pearson_cosine
value: 0.6715253560367674
name: Pearson Cosine
- type: spearman_cosine
value: 0.669070001537953
name: Spearman Cosine
- type: pearson_manhattan
value: 0.6571390159051358
name: Pearson Manhattan
- type: spearman_manhattan
value: 0.6456119247619697
name: Spearman Manhattan
- type: pearson_euclidean
value: 0.6598587843081631
name: Pearson Euclidean
- type: spearman_euclidean
value: 0.6472279949159918
name: Spearman Euclidean
- type: pearson_dot
value: 0.36757468941627225
name: Pearson Dot
- type: spearman_dot
value: 0.3678274698380672
name: Spearman Dot
- type: pearson_max
value: 0.6715253560367674
name: Pearson Max
- type: spearman_max
value: 0.669070001537953
name: Spearman Max
---
# SentenceTransformer based on Geotrend/bert-base-sw-cased
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Geotrend/bert-base-sw-cased](https://huggingface.co/Geotrend/bert-base-sw-cased) on the Mollel/swahili-n_li-triplet-swh-eng dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
## Model Details
### Model Description
- **Model Type:** Sentence Transformer
- **Base model:** [Geotrend/bert-base-sw-cased](https://huggingface.co/Geotrend/bert-base-sw-cased) <!-- at revision 7d9ca957a81d2449cf1319af0b91f75f11642336 -->
- **Maximum Sequence Length:** 512 tokens
- **Output Dimensionality:** 768 tokens
- **Similarity Function:** Cosine Similarity
- **Training Dataset:**
- Mollel/swahili-n_li-triplet-swh-eng
<!-- - **Language:** Unknown -->
<!-- - **License:** Unknown -->
### Model Sources
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
### Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)
```
## Usage
### Direct Usage (Sentence Transformers)
First install the Sentence Transformers library:
```bash
pip install -U sentence-transformers
```
Then you can load this model and run inference.
```python
from sentence_transformers import SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("sartifyllc/MultiLinguSwahili-bert-base-sw-cased-nli-matryoshka")
# Run inference
sentences = [
'Mwanamume na mwanamke wachanga waliovaa mikoba wanaweka au kuondoa kitu kutoka kwenye mti mweupe wa zamani, huku watu wengine wamesimama au wameketi nyuma.',
'mwanamume na mwanamke wenye mikoba',
'tai huruka',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]
```
<!--
### Direct Usage (Transformers)
<details><summary>Click to see the direct usage in Transformers</summary>
</details>
-->
<!--
### Downstream Usage (Sentence Transformers)
You can finetune this model on your own dataset.
<details><summary>Click to expand</summary>
</details>
-->
<!--
### Out-of-Scope Use
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->
## Evaluation
### Metrics
#### Semantic Similarity
* Dataset: `sts-test-768`
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| pearson_cosine | 0.6937 |
| **spearman_cosine** | **0.6873** |
| pearson_manhattan | 0.6672 |
| spearman_manhattan | 0.6578 |
| pearson_euclidean | 0.6672 |
| spearman_euclidean | 0.6578 |
| pearson_dot | 0.5235 |
| spearman_dot | 0.5126 |
| pearson_max | 0.6937 |
| spearman_max | 0.6873 |
#### Semantic Similarity
* Dataset: `sts-test-512`
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| pearson_cosine | 0.6899 |
| **spearman_cosine** | **0.6847** |
| pearson_manhattan | 0.6678 |
| spearman_manhattan | 0.658 |
| pearson_euclidean | 0.6673 |
| spearman_euclidean | 0.6573 |
| pearson_dot | 0.4953 |
| spearman_dot | 0.4872 |
| pearson_max | 0.6899 |
| spearman_max | 0.6847 |
#### Semantic Similarity
* Dataset: `sts-test-256`
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| pearson_cosine | 0.6873 |
| **spearman_cosine** | **0.6817** |
| pearson_manhattan | 0.6674 |
| spearman_manhattan | 0.6558 |
| pearson_euclidean | 0.6675 |
| spearman_euclidean | 0.656 |
| pearson_dot | 0.4566 |
| spearman_dot | 0.4533 |
| pearson_max | 0.6873 |
| spearman_max | 0.6817 |
#### Semantic Similarity
* Dataset: `sts-test-128`
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| pearson_cosine | 0.6836 |
| **spearman_cosine** | **0.6795** |
| pearson_manhattan | 0.6664 |
| spearman_manhattan | 0.6535 |
| pearson_euclidean | 0.6664 |
| spearman_euclidean | 0.6537 |
| pearson_dot | 0.431 |
| spearman_dot | 0.4315 |
| pearson_max | 0.6836 |
| spearman_max | 0.6795 |
#### Semantic Similarity
* Dataset: `sts-test-64`
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| pearson_cosine | 0.6715 |
| **spearman_cosine** | **0.6691** |
| pearson_manhattan | 0.6571 |
| spearman_manhattan | 0.6456 |
| pearson_euclidean | 0.6599 |
| spearman_euclidean | 0.6472 |
| pearson_dot | 0.3676 |
| spearman_dot | 0.3678 |
| pearson_max | 0.6715 |
| spearman_max | 0.6691 |
<!--
## Bias, Risks and Limitations
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
-->
<!--
### Recommendations
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
-->
## Training Details
### Training Dataset
#### Mollel/swahili-n_li-triplet-swh-eng
* Dataset: Mollel/swahili-n_li-triplet-swh-eng
* Size: 1,115,700 training samples
* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
* Approximate statistics based on the first 1000 samples:
| | anchor | positive | negative |
|:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
| type | string | string | string |
| details | <ul><li>min: 9 tokens</li><li>mean: 16.73 tokens</li><li>max: 71 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 19.74 tokens</li><li>max: 45 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 19.0 tokens</li><li>max: 49 tokens</li></ul> |
* Samples:
| anchor | positive | negative |
|:----------------------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------------------|
| <code>A person on a horse jumps over a broken down airplane.</code> | <code>A person is outdoors, on a horse.</code> | <code>A person is at a diner, ordering an omelette.</code> |
| <code>Mtu aliyepanda farasi anaruka juu ya ndege iliyovunjika.</code> | <code>Mtu yuko nje, juu ya farasi.</code> | <code>Mtu yuko kwenye mkahawa, akiagiza omelette.</code> |
| <code>Children smiling and waving at camera</code> | <code>There are children present</code> | <code>The kids are frowning</code> |
* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
```json
{
"loss": "MultipleNegativesRankingLoss",
"matryoshka_dims": [
768,
512,
256,
128,
64
],
"matryoshka_weights": [
1,
1,
1,
1,
1
],
"n_dims_per_step": -1
}
```
### Evaluation Dataset
#### Mollel/swahili-n_li-triplet-swh-eng
* Dataset: Mollel/swahili-n_li-triplet-swh-eng
* Size: 13,168 evaluation samples
* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
* Approximate statistics based on the first 1000 samples:
| | anchor | positive | negative |
|:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
| type | string | string | string |
| details | <ul><li>min: 7 tokens</li><li>mean: 28.25 tokens</li><li>max: 82 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 14.16 tokens</li><li>max: 55 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 15.55 tokens</li><li>max: 46 tokens</li></ul> |
* Samples:
| anchor | positive | negative |
|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------|:-------------------------------------------------------------------|
| <code>Two women are embracing while holding to go packages.</code> | <code>Two woman are holding packages.</code> | <code>The men are fighting outside a deli.</code> |
| <code>Wanawake wawili wanakumbatiana huku wakishikilia vifurushi vya kwenda.</code> | <code>Wanawake wawili wanashikilia vifurushi.</code> | <code>Wanaume hao wanapigana nje ya duka la vyakula vitamu.</code> |
| <code>Two young children in blue jerseys, one with the number 9 and one with the number 2 are standing on wooden steps in a bathroom and washing their hands in a sink.</code> | <code>Two kids in numbered jerseys wash their hands.</code> | <code>Two kids in jackets walk to school.</code> |
* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
```json
{
"loss": "MultipleNegativesRankingLoss",
"matryoshka_dims": [
768,
512,
256,
128,
64
],
"matryoshka_weights": [
1,
1,
1,
1,
1
],
"n_dims_per_step": -1
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `per_device_train_batch_size`: 32
- `per_device_eval_batch_size`: 32
- `learning_rate`: 2e-05
- `num_train_epochs`: 1
- `warmup_ratio`: 0.1
- `bf16`: True
- `batch_sampler`: no_duplicates
#### All Hyperparameters
<details><summary>Click to expand</summary>
- `overwrite_output_dir`: False
- `do_predict`: False
- `prediction_loss_only`: True
- `per_device_train_batch_size`: 32
- `per_device_eval_batch_size`: 32
- `per_gpu_train_batch_size`: None
- `per_gpu_eval_batch_size`: None
- `gradient_accumulation_steps`: 1
- `eval_accumulation_steps`: None
- `learning_rate`: 2e-05
- `weight_decay`: 0.0
- `adam_beta1`: 0.9
- `adam_beta2`: 0.999
- `adam_epsilon`: 1e-08
- `max_grad_norm`: 1.0
- `num_train_epochs`: 1
- `max_steps`: -1
- `lr_scheduler_type`: linear
- `lr_scheduler_kwargs`: {}
- `warmup_ratio`: 0.1
- `warmup_steps`: 0
- `log_level`: passive
- `log_level_replica`: warning
- `log_on_each_node`: True
- `logging_nan_inf_filter`: True
- `save_safetensors`: True
- `save_on_each_node`: False
- `save_only_model`: False
- `no_cuda`: False
- `use_cpu`: False
- `use_mps_device`: False
- `seed`: 42
- `data_seed`: None
- `jit_mode_eval`: False
- `use_ipex`: False
- `bf16`: True
- `fp16`: False
- `fp16_opt_level`: O1
- `half_precision_backend`: auto
- `bf16_full_eval`: False
- `fp16_full_eval`: False
- `tf32`: None
- `local_rank`: 0
- `ddp_backend`: None
- `tpu_num_cores`: None
- `tpu_metrics_debug`: False
- `debug`: []
- `dataloader_drop_last`: False
- `dataloader_num_workers`: 0
- `dataloader_prefetch_factor`: None
- `past_index`: -1
- `disable_tqdm`: False
- `remove_unused_columns`: True
- `label_names`: None
- `load_best_model_at_end`: False
- `ignore_data_skip`: False
- `fsdp`: []
- `fsdp_min_num_params`: 0
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
- `fsdp_transformer_layer_cls_to_wrap`: None
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'gradient_accumulation_kwargs': None}
- `deepspeed`: None
- `label_smoothing_factor`: 0.0
- `optim`: adamw_torch
- `optim_args`: None
- `adafactor`: False
- `group_by_length`: False
- `length_column_name`: length
- `ddp_find_unused_parameters`: None
- `ddp_bucket_cap_mb`: None
- `ddp_broadcast_buffers`: False
- `dataloader_pin_memory`: True
- `dataloader_persistent_workers`: False
- `skip_memory_metrics`: True
- `use_legacy_prediction_loop`: False
- `push_to_hub`: False
- `resume_from_checkpoint`: None
- `hub_model_id`: None
- `hub_strategy`: every_save
- `hub_private_repo`: False
- `hub_always_push`: False
- `gradient_checkpointing`: False
- `gradient_checkpointing_kwargs`: None
- `include_inputs_for_metrics`: False
- `eval_do_concat_batches`: True
- `fp16_backend`: auto
- `push_to_hub_model_id`: None
- `push_to_hub_organization`: None
- `mp_parameters`:
- `auto_find_batch_size`: False
- `full_determinism`: False
- `torchdynamo`: None
- `ray_scope`: last
- `ddp_timeout`: 1800
- `torch_compile`: False
- `torch_compile_backend`: None
- `torch_compile_mode`: None
- `dispatch_batches`: None
- `split_batches`: None
- `include_tokens_per_second`: False
- `include_num_input_tokens_seen`: False
- `neftune_noise_alpha`: None
- `optim_target_modules`: None
- `batch_sampler`: no_duplicates
- `multi_dataset_batch_sampler`: proportional
</details>
### Training Logs
<details><summary>Click to expand</summary>
| Epoch | Step | Training Loss | sts-test-128_spearman_cosine | sts-test-256_spearman_cosine | sts-test-512_spearman_cosine | sts-test-64_spearman_cosine | sts-test-768_spearman_cosine |
|:------:|:-----:|:-------------:|:----------------------------:|:----------------------------:|:----------------------------:|:---------------------------:|:----------------------------:|
| 0.0057 | 100 | 19.9104 | - | - | - | - | - |
| 0.0115 | 200 | 15.4038 | - | - | - | - | - |
| 0.0172 | 300 | 12.4565 | - | - | - | - | - |
| 0.0229 | 400 | 11.8633 | - | - | - | - | - |
| 0.0287 | 500 | 11.0601 | - | - | - | - | - |
| 0.0344 | 600 | 9.7725 | - | - | - | - | - |
| 0.0402 | 700 | 8.8549 | - | - | - | - | - |
| 0.0459 | 800 | 8.0831 | - | - | - | - | - |
| 0.0516 | 900 | 7.9941 | - | - | - | - | - |
| 0.0574 | 1000 | 7.6537 | - | - | - | - | - |
| 0.0631 | 1100 | 7.9303 | - | - | - | - | - |
| 0.0688 | 1200 | 7.5246 | - | - | - | - | - |
| 0.0746 | 1300 | 7.7754 | - | - | - | - | - |
| 0.0803 | 1400 | 7.668 | - | - | - | - | - |
| 0.0860 | 1500 | 6.7171 | - | - | - | - | - |
| 0.0918 | 1600 | 6.347 | - | - | - | - | - |
| 0.0975 | 1700 | 6.0 | - | - | - | - | - |
| 0.1033 | 1800 | 6.4314 | - | - | - | - | - |
| 0.1090 | 1900 | 6.7947 | - | - | - | - | - |
| 0.1147 | 2000 | 6.9316 | - | - | - | - | - |
| 0.1205 | 2100 | 6.6304 | - | - | - | - | - |
| 0.1262 | 2200 | 6.132 | - | - | - | - | - |
| 0.1319 | 2300 | 5.8953 | - | - | - | - | - |
| 0.1377 | 2400 | 5.6954 | - | - | - | - | - |
| 0.1434 | 2500 | 5.6832 | - | - | - | - | - |
| 0.1491 | 2600 | 5.2266 | - | - | - | - | - |
| 0.1549 | 2700 | 5.0678 | - | - | - | - | - |
| 0.1606 | 2800 | 5.4733 | - | - | - | - | - |
| 0.1664 | 2900 | 6.0899 | - | - | - | - | - |
| 0.1721 | 3000 | 6.332 | - | - | - | - | - |
| 0.1778 | 3100 | 6.4937 | - | - | - | - | - |
| 0.1836 | 3200 | 6.2242 | - | - | - | - | - |
| 0.1893 | 3300 | 5.8023 | - | - | - | - | - |
| 0.1950 | 3400 | 5.0745 | - | - | - | - | - |
| 0.2008 | 3500 | 5.5806 | - | - | - | - | - |
| 0.2065 | 3600 | 5.5191 | - | - | - | - | - |
| 0.2122 | 3700 | 5.3849 | - | - | - | - | - |
| 0.2180 | 3800 | 5.4828 | - | - | - | - | - |
| 0.2237 | 3900 | 5.9982 | - | - | - | - | - |
| 0.2294 | 4000 | 5.6842 | - | - | - | - | - |
| 0.2352 | 4100 | 5.1627 | - | - | - | - | - |
| 0.2409 | 4200 | 5.154 | - | - | - | - | - |
| 0.2467 | 4300 | 5.7932 | - | - | - | - | - |
| 0.2524 | 4400 | 5.5758 | - | - | - | - | - |
| 0.2581 | 4500 | 5.5212 | - | - | - | - | - |
| 0.2639 | 4600 | 5.5692 | - | - | - | - | - |
| 0.2696 | 4700 | 5.2699 | - | - | - | - | - |
| 0.2753 | 4800 | 5.4919 | - | - | - | - | - |
| 0.2811 | 4900 | 5.0754 | - | - | - | - | - |
| 0.2868 | 5000 | 5.1514 | - | - | - | - | - |
| 0.2925 | 5100 | 5.0241 | - | - | - | - | - |
| 0.2983 | 5200 | 5.2679 | - | - | - | - | - |
| 0.3040 | 5300 | 5.3576 | - | - | - | - | - |
| 0.3098 | 5400 | 5.3454 | - | - | - | - | - |
| 0.3155 | 5500 | 5.2142 | - | - | - | - | - |
| 0.3212 | 5600 | 4.8418 | - | - | - | - | - |
| 0.3270 | 5700 | 4.9597 | - | - | - | - | - |
| 0.3327 | 5800 | 5.1989 | - | - | - | - | - |
| 0.3384 | 5900 | 5.2624 | - | - | - | - | - |
| 0.3442 | 6000 | 5.0705 | - | - | - | - | - |
| 0.3499 | 6100 | 5.232 | - | - | - | - | - |
| 0.3556 | 6200 | 5.2428 | - | - | - | - | - |
| 0.3614 | 6300 | 4.755 | - | - | - | - | - |
| 0.3671 | 6400 | 4.7266 | - | - | - | - | - |
| 0.3729 | 6500 | 4.6452 | - | - | - | - | - |
| 0.3786 | 6600 | 5.1431 | - | - | - | - | - |
| 0.3843 | 6700 | 4.5343 | - | - | - | - | - |
| 0.3901 | 6800 | 4.698 | - | - | - | - | - |
| 0.3958 | 6900 | 4.6944 | - | - | - | - | - |
| 0.4015 | 7000 | 4.6255 | - | - | - | - | - |
| 0.4073 | 7100 | 5.0211 | - | - | - | - | - |
| 0.4130 | 7200 | 4.6974 | - | - | - | - | - |
| 0.4187 | 7300 | 4.9182 | - | - | - | - | - |
| 0.4245 | 7400 | 4.652 | - | - | - | - | - |
| 0.4302 | 7500 | 5.1015 | - | - | - | - | - |
| 0.4360 | 7600 | 4.5249 | - | - | - | - | - |
| 0.4417 | 7700 | 4.455 | - | - | - | - | - |
| 0.4474 | 7800 | 4.8153 | - | - | - | - | - |
| 0.4532 | 7900 | 4.7665 | - | - | - | - | - |
| 0.4589 | 8000 | 4.3413 | - | - | - | - | - |
| 0.4646 | 8100 | 4.4697 | - | - | - | - | - |
| 0.4704 | 8200 | 4.6776 | - | - | - | - | - |
| 0.4761 | 8300 | 4.2868 | - | - | - | - | - |
| 0.4818 | 8400 | 4.7052 | - | - | - | - | - |
| 0.4876 | 8500 | 4.4721 | - | - | - | - | - |
| 0.4933 | 8600 | 4.6926 | - | - | - | - | - |
| 0.4991 | 8700 | 4.9891 | - | - | - | - | - |
| 0.5048 | 8800 | 4.4837 | - | - | - | - | - |
| 0.5105 | 8900 | 4.8127 | - | - | - | - | - |
| 0.5163 | 9000 | 4.3438 | - | - | - | - | - |
| 0.5220 | 9100 | 4.4743 | - | - | - | - | - |
| 0.5277 | 9200 | 4.6879 | - | - | - | - | - |
| 0.5335 | 9300 | 4.3593 | - | - | - | - | - |
| 0.5392 | 9400 | 4.3023 | - | - | - | - | - |
| 0.5449 | 9500 | 4.8188 | - | - | - | - | - |
| 0.5507 | 9600 | 4.6142 | - | - | - | - | - |
| 0.5564 | 9700 | 4.7679 | - | - | - | - | - |
| 0.5622 | 9800 | 4.6224 | - | - | - | - | - |
| 0.5679 | 9900 | 4.9154 | - | - | - | - | - |
| 0.5736 | 10000 | 4.7557 | - | - | - | - | - |
| 0.5794 | 10100 | 4.6395 | - | - | - | - | - |
| 0.5851 | 10200 | 4.7977 | - | - | - | - | - |
| 0.5908 | 10300 | 4.915 | - | - | - | - | - |
| 0.5966 | 10400 | 4.4854 | - | - | - | - | - |
| 0.6023 | 10500 | 4.3973 | - | - | - | - | - |
| 0.6080 | 10600 | 4.6964 | - | - | - | - | - |
| 0.6138 | 10700 | 4.8853 | - | - | - | - | - |
| 0.6195 | 10800 | 4.786 | - | - | - | - | - |
| 0.6253 | 10900 | 4.5482 | - | - | - | - | - |
| 0.6310 | 11000 | 4.4857 | - | - | - | - | - |
| 0.6367 | 11100 | 4.7415 | - | - | - | - | - |
| 0.6425 | 11200 | 4.2596 | - | - | - | - | - |
| 0.6482 | 11300 | 4.8578 | - | - | - | - | - |
| 0.6539 | 11400 | 4.5471 | - | - | - | - | - |
| 0.6597 | 11500 | 4.8337 | - | - | - | - | - |
| 0.6654 | 11600 | 4.2244 | - | - | - | - | - |
| 0.6711 | 11700 | 4.9619 | - | - | - | - | - |
| 0.6769 | 11800 | 4.9369 | - | - | - | - | - |
| 0.6826 | 11900 | 4.2697 | - | - | - | - | - |
| 0.6883 | 12000 | 4.2711 | - | - | - | - | - |
| 0.6941 | 12100 | 4.6396 | - | - | - | - | - |
| 0.6998 | 12200 | 4.5626 | - | - | - | - | - |
| 0.7056 | 12300 | 4.5767 | - | - | - | - | - |
| 0.7113 | 12400 | 4.6449 | - | - | - | - | - |
| 0.7170 | 12500 | 4.4217 | - | - | - | - | - |
| 0.7228 | 12600 | 4.0203 | - | - | - | - | - |
| 0.7285 | 12700 | 4.5381 | - | - | - | - | - |
| 0.7342 | 12800 | 4.5865 | - | - | - | - | - |
| 0.7400 | 12900 | 4.4203 | - | - | - | - | - |
| 0.7457 | 13000 | 4.3761 | - | - | - | - | - |
| 0.7514 | 13100 | 4.093 | - | - | - | - | - |
| 0.7572 | 13200 | 5.9235 | - | - | - | - | - |
| 0.7629 | 13300 | 5.4098 | - | - | - | - | - |
| 0.7687 | 13400 | 5.3079 | - | - | - | - | - |
| 0.7744 | 13500 | 5.0946 | - | - | - | - | - |
| 0.7801 | 13600 | 4.7098 | - | - | - | - | - |
| 0.7859 | 13700 | 4.9471 | - | - | - | - | - |
| 0.7916 | 13800 | 4.5742 | - | - | - | - | - |
| 0.7973 | 13900 | 4.6178 | - | - | - | - | - |
| 0.8031 | 14000 | 4.4516 | - | - | - | - | - |
| 0.8088 | 14100 | 4.429 | - | - | - | - | - |
| 0.8145 | 14200 | 4.3812 | - | - | - | - | - |
| 0.8203 | 14300 | 4.3739 | - | - | - | - | - |
| 0.8260 | 14400 | 4.3821 | - | - | - | - | - |
| 0.8318 | 14500 | 4.4396 | - | - | - | - | - |
| 0.8375 | 14600 | 4.2667 | - | - | - | - | - |
| 0.8432 | 14700 | 4.1963 | - | - | - | - | - |
| 0.8490 | 14800 | 4.1298 | - | - | - | - | - |
| 0.8547 | 14900 | 4.1843 | - | - | - | - | - |
| 0.8604 | 15000 | 4.0735 | - | - | - | - | - |
| 0.8662 | 15100 | 3.9319 | - | - | - | - | - |
| 0.8719 | 15200 | 4.1544 | - | - | - | - | - |
| 0.8776 | 15300 | 4.105 | - | - | - | - | - |
| 0.8834 | 15400 | 4.014 | - | - | - | - | - |
| 0.8891 | 15500 | 4.0345 | - | - | - | - | - |
| 0.8949 | 15600 | 3.9127 | - | - | - | - | - |
| 0.9006 | 15700 | 4.1002 | - | - | - | - | - |
| 0.9063 | 15800 | 3.8564 | - | - | - | - | - |
| 0.9121 | 15900 | 3.9297 | - | - | - | - | - |
| 0.9178 | 16000 | 3.8487 | - | - | - | - | - |
| 0.9235 | 16100 | 3.7099 | - | - | - | - | - |
| 0.9293 | 16200 | 3.8545 | - | - | - | - | - |
| 0.9350 | 16300 | 3.8122 | - | - | - | - | - |
| 0.9407 | 16400 | 3.8951 | - | - | - | - | - |
| 0.9465 | 16500 | 3.6996 | - | - | - | - | - |
| 0.9522 | 16600 | 3.9081 | - | - | - | - | - |
| 0.9580 | 16700 | 3.8603 | - | - | - | - | - |
| 0.9637 | 16800 | 3.8534 | - | - | - | - | - |
| 0.9694 | 16900 | 3.8145 | - | - | - | - | - |
| 0.9752 | 17000 | 3.9858 | - | - | - | - | - |
| 0.9809 | 17100 | 3.8224 | - | - | - | - | - |
| 0.9866 | 17200 | 3.7469 | - | - | - | - | - |
| 0.9924 | 17300 | 3.9066 | - | - | - | - | - |
| 0.9981 | 17400 | 3.6754 | - | - | - | - | - |
| 1.0 | 17433 | - | 0.6795 | 0.6817 | 0.6847 | 0.6691 | 0.6873 |
</details>
### Framework Versions
- Python: 3.11.9
- Sentence Transformers: 3.0.1
- Transformers: 4.40.1
- PyTorch: 2.3.0+cu121
- Accelerate: 0.29.3
- Datasets: 2.19.0
- Tokenizers: 0.19.1
## Citation
### BibTeX
#### Sentence Transformers
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "https://arxiv.org/abs/1908.10084",
}
```
#### MatryoshkaLoss
```bibtex
@misc{kusupati2024matryoshka,
title={Matryoshka Representation Learning},
author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
year={2024},
eprint={2205.13147},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
```
#### MultipleNegativesRankingLoss
```bibtex
@misc{henderson2017efficient,
title={Efficient Natural Language Response Suggestion for Smart Reply},
author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
year={2017},
eprint={1705.00652},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
<!--
## Glossary
*Clearly define terms in order to be accessible across audiences.*
-->
<!--
## Model Card Authors
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->
<!--
## Model Card Contact
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
--> | [
"TEXT_CLASSIFICATION",
"SEMANTIC_SIMILARITY"
] | Non_BioNLP |
Hoax0930/marian-finetuned-kde4-en-to-ja | Hoax0930 | translation | [
"transformers",
"pytorch",
"tensorboard",
"marian",
"text2text-generation",
"translation",
"generated_from_trainer",
"dataset:kde4",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 1,661,844,995,000 | 2022-09-01T01:28:03 | 105 | 0 | ---
datasets:
- kde4
license: apache-2.0
metrics:
- bleu
tags:
- translation
- generated_from_trainer
model-index:
- name: marian-finetuned-kde4-en-to-ja
results:
- task:
type: text2text-generation
name: Sequence-to-sequence Language Modeling
dataset:
name: kde4
type: kde4
config: en-ja
split: train
args: en-ja
metrics:
- type: bleu
value: 37.10979592471087
name: Bleu
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# marian-finetuned-kde4-en-to-ja
This model is a fine-tuned version of [Helsinki-NLP/opus-tatoeba-en-ja](https://huggingface.co/Helsinki-NLP/opus-tatoeba-en-ja) on the kde4 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9825
- Bleu: 37.1098
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.21.2
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1
| [
"TRANSLATION"
] | Non_BioNLP |
Kerz/bbc | Kerz | text-classification | [
"transformers",
"pytorch",
"bert",
"text-classification",
"generated_from_trainer",
"dataset:yelp_review_full",
"base_model:google-bert/bert-base-cased",
"base_model:finetune:google-bert/bert-base-cased",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 1,689,858,583,000 | 2023-07-20T14:14:40 | 8 | 0 | ---
base_model: bert-base-cased
datasets:
- yelp_review_full
license: apache-2.0
metrics:
- accuracy
tags:
- generated_from_trainer
model-index:
- name: bbc
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: yelp_review_full
type: yelp_review_full
config: yelp_review_full
split: test
args: yelp_review_full
metrics:
- type: accuracy
value: 0.499
name: Accuracy
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bbc
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the yelp_review_full dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1692
- Accuracy: 0.499
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 250 | 1.4265 | 0.391 |
| 1.4806 | 2.0 | 500 | 1.2233 | 0.458 |
| 1.4806 | 3.0 | 750 | 1.1692 | 0.499 |
### Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3
| [
"TEXT_CLASSIFICATION"
] | Non_BioNLP |
yjlee1011/ncodeR_data_multilabel_32samples | yjlee1011 | text-classification | [
"sentence-transformers",
"pytorch",
"mpnet",
"setfit",
"text-classification",
"arxiv:2209.11055",
"license:apache-2.0",
"region:us"
] | 1,698,691,480,000 | 2023-10-30T18:45:02 | 10 | 0 | ---
license: apache-2.0
pipeline_tag: text-classification
tags:
- setfit
- sentence-transformers
- text-classification
---
# yjlee1011/ncodeR_data_multilabel_32samples
This is a [SetFit model](https://github.com/huggingface/setfit) that can be used for text classification. The model has been trained using an efficient few-shot learning technique that involves:
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.
## Usage
To use this model for inference, first install the SetFit library:
```bash
python -m pip install setfit
```
You can then run inference as follows:
```python
from setfit import SetFitModel
# Download from Hub and run inference
model = SetFitModel.from_pretrained("yjlee1011/ncodeR_data_multilabel_32samples")
# Run inference
preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"])
```
## BibTeX entry and citation info
```bibtex
@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
| [
"TEXT_CLASSIFICATION"
] | Non_BioNLP |
mlsquare/mamba_pico_large_x_dt_out_proj | mlsquare | text-generation | [
"transformers",
"safetensors",
"text-generation",
"en",
"dataset:mlsquare/CLIENT_samantar_mixed_train_val",
"arxiv:2312.00752",
"license:mit",
"endpoints_compatible",
"region:us"
] | 1,708,851,689,000 | 2024-03-10T06:27:45 | 0 | 0 | ---
datasets:
- mlsquare/CLIENT_samantar_mixed_train_val
language:
- en
library_name: transformers
license: mit
pipeline_tag: text-generation
---
# Model Card for Model ID
Adapter for mlsquare/pico_seshu_test using LoRA on "model.layers.3.dt_proj", "model.layers.3.x_proj", "model.layers.3.out_proj". Standard use of PEFT on Mamba-hf model
## Model Details
### Model Description
- **Developed by:** MLsquare
- **Model type:** Next Character Generation
- **Language(s) (NLP):** All languages in ai4bharat/samanantar dataset
- **License:** MIT
## Model Details
### Model Description
- **Developed by:** MLsquare
- **Model type:** Next Character Generation
- **Language(s) (NLP):** All languages in ai4bharat/samanantar dataset
- **License:** MIT
### Model Sources [optional]
- **Repository:** https://github.com/LegallyCoder/mamba-hf
- **Paper:** https://arxiv.org/abs/2312.00752
## Uses
Refer to the github repository for more information
### Direct Use
Refer to the github repository for more information
## How to Get Started with the Model
Refer to the github repository: https://github.com/mlsquare/fedem
## Training Details
### Training Data
Individual target and source sentences from the AI4Bharat Samanantar dataset. All 11 language sentences and their translations have been stacked and used for next character generation task.
### Training Procedure
Trained on the next character generation task using cross-entropy loss.
#### Preprocessing [optional]
converted to raw UTF8 characters before training by using ByT5-large tokenizer
#### Training Hyperparameters
- **Training regime:**
output_dir="mamba",
per_device_train_batch_size=1,
per_device_eval_batch_size=1,
num_train_epochs=4,
weight_decay=0.1,
lr_scheduler_type="cosine",
learning_rate=5e-4,
fp16=False,
## Evaluation
A simple cross-entropy loss has been used to test the pipeline and working of the model.
## Model Card Contact
MLsquare | [
"TRANSLATION"
] | Non_BioNLP |
aroot/eng-guj-simcse_central_ssblu | aroot | translation | [
"transformers",
"pytorch",
"tensorboard",
"mbart",
"text2text-generation",
"translation",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 1,688,668,684,000 | 2023-07-06T19:00:09 | 8 | 0 | ---
metrics:
- bleu
tags:
- translation
- generated_from_trainer
model-index:
- name: eng-guj-simcse_central_ssblu
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# eng-guj-simcse_central_ssblu
This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 3.2711
- Bleu: 2.6084
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.26.1
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
| [
"TRANSLATION"
] | Non_BioNLP |
TransferGraph/DoyyingFace_bert-asian-hate-tweets-asian-unclean-freeze-4-finetuned-lora-tweet_eval_hate | TransferGraph | text-classification | [
"peft",
"safetensors",
"parquet",
"text-classification",
"dataset:tweet_eval",
"base_model:DoyyingFace/bert-asian-hate-tweets-asian-unclean-freeze-4",
"base_model:adapter:DoyyingFace/bert-asian-hate-tweets-asian-unclean-freeze-4",
"model-index",
"region:us"
] | 1,709,214,193,000 | 2024-02-29T13:43:15 | 0 | 0 | ---
base_model: DoyyingFace/bert-asian-hate-tweets-asian-unclean-freeze-4
datasets:
- tweet_eval
library_name: peft
metrics:
- accuracy
tags:
- parquet
- text-classification
model-index:
- name: DoyyingFace_bert-asian-hate-tweets-asian-unclean-freeze-4-finetuned-lora-tweet_eval_hate
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: tweet_eval
type: tweet_eval
config: hate
split: validation
args: hate
metrics:
- type: accuracy
value: 0.726
name: accuracy
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# DoyyingFace_bert-asian-hate-tweets-asian-unclean-freeze-4-finetuned-lora-tweet_eval_hate
This model is a fine-tuned version of [DoyyingFace/bert-asian-hate-tweets-asian-unclean-freeze-4](https://huggingface.co/DoyyingFace/bert-asian-hate-tweets-asian-unclean-freeze-4) on the tweet_eval dataset.
It achieves the following results on the evaluation set:
- accuracy: 0.726
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0004
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
### Training results
| accuracy | train_loss | epoch |
|:--------:|:----------:|:-----:|
| 0.612 | None | 0 |
| 0.7 | 0.5857 | 0 |
| 0.713 | 0.4921 | 1 |
| 0.712 | 0.4531 | 2 |
| 0.726 | 0.4390 | 3 |
### Framework versions
- PEFT 0.8.2
- Transformers 4.37.2
- Pytorch 2.2.0
- Datasets 2.16.1
- Tokenizers 0.15.2 | [
"TEXT_CLASSIFICATION"
] | Non_BioNLP |
portugueseNLP/medialbertina_pt-pt_900m_NER | portugueseNLP | token-classification | [
"transformers",
"safetensors",
"deberta-v2",
"token-classification",
"medialbertina-ptpt",
"deberta",
"portuguese",
"european portuguese",
"medical",
"clinical",
"healthcare",
"NER",
"Named Entity Recognition",
"IE",
"Information Extraction",
"pt",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 1,711,650,604,000 | 2024-10-07T18:27:24 | 72 | 4 | ---
language:
- pt
license: mit
pipeline_tag: token-classification
tags:
- medialbertina-ptpt
- deberta
- portuguese
- european portuguese
- medical
- clinical
- healthcare
- NER
- Named Entity Recognition
- IE
- Information Extraction
inference:
parameters:
aggregation_strategy: average
widget:
- text: Durante a cirurgia ortopédica para corrigir a fratura no tornozelo, os sinais
vitais do utente, incluindo a pressão arterial, com leitura de 120/87 mmHg e a
frequência cardíaca, de 80 batimentos por minuto, foram monitorizados. Após a
cirurgia o utente apresentava dor intensa no local e inchaço no tornozelo, mas
os resultados da radiografia revelaram uma recuperação satisfatória. Foi prescrito
ibuprofeno 600mg de 8 em 8 horas durante 3 dias.
example_title: Example 1
- text: Durante o procedimento endoscópico, foram encontrados pólipos no cólon do
paciente.
example_title: Example 2
- text: Foi recomendada aspirina de 500mg a cada 4 horas, durante 3 dias.
example_title: Example 3
- text: Após as sessões de fisioterapia o paciente apresenta recuperação de mobilidade.
example_title: Example 4
- text: O paciente está em Quimioterapia com uma dosagem específica de Cisplatina
para o tratamento do cancro do pulmão.
example_title: Example 5
- text: Monitorização da Freq. cardíaca com 90 bpm. P Arterial de 120-80 mmHg
example_title: Example 6
- text: A ressonância magnética da utente revelou uma rotura no menisco lateral do
joelho.
example_title: Example 7
- text: A paciente foi diagnosticada com esclerose múltipla e iniciou terapia com
imunomoduladores.
example_title: Example 8
---
# MediAlbertina
The first publicly available medical language model trained with real European Portuguese data.
MediAlbertina is a family of encoders from the Bert family, DeBERTaV2-based, resulting from the continuation of the pre-training of [PORTULAN's Albertina](https://huggingface.co/PORTULAN) models with Electronic Medical Records shared by Portugal's largest public hospital.
Like its antecessors, MediAlbertina models are distributed under the [MIT license](https://huggingface.co/portugueseNLP/medialbertina_pt-pt_900m_NER/blob/main/LICENSE).
# Model Description
**MediAlbertina PT-PT 900M NER** was created through fine-tuning of [MediAlbertina PT-PT 900M](https://huggingface.co/portugueseNLP/medialbertina_pt-pt_900m) on real European Portuguese EMRs that have been hand-annotated for the following entities:
- **Diagnostico (D)**: All types of diseases and conditions following the ICD-10-CM guidelines.
- **Sintoma (S)**: Any complaints or evidence from healthcare professionals indicating that a patient is experiencing a medical condition.
- **Medicamento (M)**: Something that is administrated to the patient (through any route), including drugs, specific food/drink, vitamins, or blood for transfusion.
- **Dosagem (D)**: Dosage and frequency of medication administration.
- **ProcedimentoMedico (PM)**: Anything healthcare professionals do related to patients, including exams, moving patients, administering something, or even surgeries.
- **SinalVital (SV)**: Quantifiable indicators in a patient that can be measured, always associated with a specific result. Examples include cholesterol levels, diuresis, weight, or glycaemia.
- **Resultado (R)**: Results can be associated with Medical Procedures and Vital Signs. It can be a numerical value if something was measured (e.g., the value associated with blood pressure) or a descriptor to indicate the result (e.g., positive/negative, functional).
- **Progresso (P)**: Describes the progress of patient’s condition. Typically, it includes verbs like improving, evolving, or regressing and mentions to patient’s stability.
**MediAlbertina PT-PT 900M NER** achieved superior results to the same adaptation made on a non-medical Portuguese language model, demonstrating the effectiveness of this domain adaptation, and its potential for medical AI in Portugal.
| Model | B-D | I-D | B-S | I-S | B-PM | I-PM | B-SV | I-SV | B-R | I-R | B-M | I-M | B-DO | I-DO | B-P | I-P |
|-------------------------|:----:|:----:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
| | F1 | F1 | F1 | F1 | F1 | F1 | F1 | F1 | F1 | F1 | F1 | F1 | F1 | F1 | F1 | F1 |
| albertina-900m-portuguese-ptpt-encoder|0.721|0.786|0.734|0.775|0.737|0.805|0.859|**0.811**|0.803|0.816|0.913|0.871|**0.853**|**0.895**|0.769|0.785|
| **medialbertina_pt-pt_900m** | **0.799**| **0.832**| **0.754**| **0.782**| **0.786**| **0.813**| **0.916**| 0.788| **0.821**| **0.83**| **0.926**| **0.895**|0.85|0.885| **0.779**| **0.807**|
## Data
**MediAlbertina PT-PT 900M NER** was fine-tuned on about 10k hand-annotated medical entities from about 4k fully anonymized medical sentences from Portugal's largest public hospital. This data was acquired under the framework of the [FCT project DSAIPA/AI/0122/2020 AIMHealth-Mobile Applications Based on Artificial Intelligence](https://ciencia.iscte-iul.pt/projects/aplicacoes-moveis-baseadas-em-inteligencia-artificial-para-resposta-de-saude-publica/1567).
## How to use
```Python
from transformers import pipeline
ner_pipeline = pipeline('ner', model='portugueseNLP/medialbertina_pt-pt_900m_NER', aggregation_strategy='average')
sentence = 'Durante o procedimento endoscópico, foram encontrados pólipos no cólon do paciente.'
entities = ner_pipeline(sentence)
for entity in entities:
print(f"{entity['entity_group']} - {sentence[entity['start']:entity['end']]}")
```
## Citation
MediAlbertina is developed by a joint team from [ISCTE-IUL](https://www.iscte-iul.pt/), Portugal, and [Select Data](https://selectdata.com/), CA USA. For a fully detailed description, check the respective publication:
```latex
@article{MediAlbertina PT-PT,
title={MediAlbertina: An European Portuguese medical language model},
author={Miguel Nunes and João Boné and João Ferreira
and Pedro Chaves and Luís Elvas},
year={2024},
journal={CBM},
volume={182}
url={https://doi.org/10.1016/j.compbiomed.2024.109233}
}
```
Please use the above cannonical reference when using or citing this [model](https://www.sciencedirect.com/science/article/pii/S0010482524013180?via%3Dihub).
## Acknowledgements
This work was financially supported by Project Blockchain.PT – Decentralize Portugal with Blockchain Agenda, (Project no 51), WP2, Call no 02/C05-i01.01/2022, funded by the Portuguese Recovery and Resillience Program (PRR), The Portuguese Republic and The European Union (EU) under the framework of Next Generation EU Program. | [
"NAMED_ENTITY_RECOGNITION"
] | BioNLP |
bwang0911/jev2-legal | bwang0911 | sentence-similarity | [
"sentence-transformers",
"safetensors",
"mpnet",
"sentence-similarity",
"feature-extraction",
"generated_from_trainer",
"dataset_size:53224",
"loss:MultipleNegativesRankingLoss",
"en",
"dataset:sentence-transformers/coliee",
"dataset:bwang0911/legal_qa_v1",
"dataset:bwang0911/law_stackexchange",
"dataset:bwang0911/legal_lens_nli",
"dataset:bwang0911/cuad_qa",
"dataset:bwang0911/privacy_qa",
"dataset:bwang0911/legal_case_summarization",
"dataset:bwang0911/aus_legal_qa",
"arxiv:1908.10084",
"arxiv:1705.00652",
"base_model:sentence-transformers/all-mpnet-base-v2",
"base_model:finetune:sentence-transformers/all-mpnet-base-v2",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 1,730,903,642,000 | 2024-11-14T10:09:05 | 18 | 1 | ---
base_model: sentence-transformers/all-mpnet-base-v2
datasets:
- sentence-transformers/coliee
- bwang0911/legal_qa_v1
- bwang0911/law_stackexchange
- bwang0911/legal_lens_nli
- bwang0911/cuad_qa
- bwang0911/privacy_qa
- bwang0911/legal_case_summarization
- bwang0911/aus_legal_qa
language:
- en
library_name: sentence-transformers
metrics:
- cosine_accuracy@1
- cosine_accuracy@3
- cosine_accuracy@5
- cosine_accuracy@10
- cosine_precision@1
- cosine_precision@3
- cosine_precision@5
- cosine_precision@10
- cosine_recall@1
- cosine_recall@3
- cosine_recall@5
- cosine_recall@10
- cosine_ndcg@10
- cosine_mrr@10
- cosine_map@100
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:53224
- loss:MultipleNegativesRankingLoss
widget:
- source_sentence: ' A juridical person may not be a partner of a civil law union. '
sentences:
- '
Article 34
An not-for-profit association or foundation that is involved in academic activities,
art, charity, worship, religion, or any other matter of public interest may be
established as a juridical person with the permission of the competent government
agency..
'
- '
Article 192
A person that commences the possession of movables peacefully and openly by a
transactional act acquires the rights that are exercised with respect to the movables
immediately if the person possesses it in good faith and without negligence..
'
- '
Article 550
Gifts not in writing may be cancelled by either party;provided, however, that
this does not apply to a portion of the gift for which performance has been completed..
'
- source_sentence: are there any legal systems in the world where the judiciary and
the legislature are the same? it's well known that the limited lawmaking power
that a judiciary has comes from interpretation of statutes but are there any systems
where the judiciary and the legislature are one and the same and have broad lawmaking
powers ?
sentences:
- 'Short Answer Is it illegal for US citizens to travel to North Korea? Yes (but
see the "fine print" below). Long Answer There is: a US travel ban to
North Korea for American citizens, as of July 2017. Now, Americans wishing to
travel to North Korea must obtain a Special Validation Passport from the US Department
of State, only issued under very specific circumstances, such as for journalists
covering the region or for humanitarian aid workers. The Biden administration
extended the ban, initially established by the Trump administration, on traveling
to North Korea on a U.S. passport absent special approval: The ban makes it illegal
to use a U.S. passport for travel to, from or through North Korea, also known
as the Democratic People''s Republic of Korea, or the DPRK, unless the document
has been specially validated. Such validations are granted by the State Department
only in the case of compelling national interest. The U.S. State Department confirms
that this ban is still in place. It states that: Travel to, in, or through North
Korea on a U.S. passport without this special validation may justify revocation
of your passport for misuse under 22 C.F.R. § 51.62(a)(3) and may subject you
to felony prosecution under 18 U.S.C. § 1544 or other applicable laws. The maximum
criminal penalty if you use a U.S. passport to go to North Korea and then return
and a charged with a crime under 18 U.S.C. § 1544 are quite serious. You could
be sent to prison for up to ten years for a first or second offense, or up to
fifteen years if you have two prior convictions under this statute, and/or fined,
even if you weren''t a terrorist or drug dealer, although the actual sentence
would probably be milder, if you were charged with a crime at all. The criminal
statute reads as follows (with the pertinent parts in bold): Whoever willfully
and knowingly uses, or attempts to use, any passport issued or designed for the
use of another; or Whoever willfully and knowingly uses or attempts to use any
passport in violation of the conditions or restrictions therein contained, or
of the rules prescribed pursuant to the laws regulating the issuance of passports;
or Whoever willfully and knowingly furnishes, disposes of, or delivers a passport
to any person, for use by another than the person for whose use it was originally
issued and designed— Shall be fined under this title, imprisoned not more than
25 years (if the offense was committed to facilitate an act of international terrorism
(as defined in section 2331 of this title)), 20 years (if the offense was committed
to facilitate a drug trafficking crime (as defined in section 929(a) of this title)),
10 years (in the case of the first or second such offense, if the offense was
not committed to facilitate such an act of international terrorism or a drug trafficking
crime), or 15 years (in the case of any other offense), or both. There are also
many other North Korean sanctions (and keep in mind that North Korea is legally
an "enemy" of the United States with which the U.S. is officially still
at war and does not have diplomatic relations). The most recent of those, from
2017, prohibits ships and aircraft owned by a "foreign person" which
have been in North Korean in the last 180 days from entering the United States.
The ban does not prohibit a dual citizen from traveling to North Korea on a passport
from the person''s other country of citizenship, nor does it prohibit U.S. citizens
from entering North Korea without using a passport (although entering North Korea
without a passport or visa probably violates North Korean law). Of course, North
Korea also regulates entry of people into North Korea under North Korean immigration
laws. I do not know whether or not it is legal under North Korean law for people
to enter it with a U.S. passport. But, given that the only U.S. citizen to enter
North Korea without a special U.S. visa authorizing the trip in the last seven
years was arrested immediately after crossing into North Korea this week, it would
appear that this is illegal under North Korean law as well.'
- Historically, this was true in the Icelandic Commonwealth in the Middle Ages,
and in some democratic Greek city-states in the classical era. Similarly, in non-democratic
feudal regimes, the lord or monarch was both the law giver and sitting in court
was also the arbiter of all disputes arising under the lord's own laws. In places
like Saudi Arabia where the monarchy's power is more than symbolic, the system
still works this way to a significant extent. The practical reality in most one
party Communist states is similar. In the United Kingdom, historically, the Appellate
committee of the House of Lords (staffed by a subset of aristocrats usually appointed
for life by the Prime Minister to the post) was the highest court of appeal of
other courts in the British Commonwealth (with the Judicial committee of the Privy
Council handling final appeals from outside Britain), and it was also a court
of original jurisdiction for certain criminal cases against other aristocrats
to satisfy the Magna Carta's notion that one is entitled to a jury of one's peers.
Top level general purpose legislatures rarely serve as courts at the highest level,
except in very isolated political matters. A good example of narrow quasi-judicial
legislative power is the power of the Congress in the U.S., to be the ultimate
judge for Congressional election disputes and of some Presidential election disputes.
Congress also has quasi-judicial jurisdiction over impeachments of government
employees whether or not they are elected, and over expulsions for cause of its
own members and over other ethical sanctions of its own members. Many other legislatures
have some sort of quansi-judicial impeachment and/or explusion power exercised
as a whole by by some committee within it. It is common in the United States for
administrative agencies, within their narrow area of competence to exercise both
quasi-legislative power to enact regulations with a broad mandate in a subject
area, and also to have quasi-judicial power in that same subject area. The Securities
and Exchange Commission, the National Labor Relations Board, the Internal Revenue
Service, the Environmental Protection Agency, and the Merit System Protection
Board, for example, all operate in this fashion to some extent. Likewise, it is
very common at the local government level for a city council and its planning
board to carry out both legislative roles and quasi-judicial role when disputes
come up regarding its land use regulations. Similarly, school boards routinely
both establish employment regulations and other school rules, and serve in a quasi-judicial
role with respect employee discipline or termination, and with respect to student
discipline. This dual role is also common for the boards of other public institutions
like hospitals and state colleges, and for private non-profit organizations. A
recent example in that kind of situation is Colorado's State School Board which
both exercises legislative power over when charter schools (i.e. public schools
not under the direct supervision of any elected local school board) may be formed,
and has the ultimate and final judicial review role over decisions by local school
boards to grant or deny school charters.
- It isn't explicitly prohibited so long as the amount claimed is in the aggregate
less than $20,000. But, it would probably be better to file separately. First,
very simple single party, single transaction cases are what small claims court
is designed to do, and going against the flow often creates unforeseen confusion
for the judge in the Justice Court who isn't a sophisticated civil litigation
expert. The Justices of the Peace who preside over Justice Courts that handle
small claims cases in Texas often aren't and don't have to be lawyers or even
high school graduates. Second, if you sue as a group, and one of your group is
the lead person handling the case (and that person isn't a lawyer), the lead person
is at grave risk of being found to be practicing law without a license by taking
actions in a lawsuit on behalf of your fellow plaintiffs.
- source_sentence: 'Q: Myself & spouse have lived in home 27 years. If I file for
divorce will he be made to sell home in St Pete and split the. Home in his name
only. Do not trust him! '
sentences:
- A:As long as the house is a marital asset, which it sounds like it is, the court
will order the equity to be divided as part of equitable distribution. You will
each have the opportunity to buy the other out or else the property will be sold.
Speak with a local family lawyer for more specific advice.
- A:Hi there, good evening. In federal cases, such as yours in the Central District
Court of California, once a case is e-filed, the documents, including the complaint
and summons, can typically be downloaded from PACER. This is a common practice
and allows for easy access to filed documents. A "conformed copy" of a document
is essentially a copy that includes all signatures and official stamps, making
it identical to the original. These copies are often required in situations where
you need to submit a document that is as valid as the original, such as for certain
legal or official proceedings. They ensure that the document you're using is a
true and complete representation of the original filed document.
- A:First off, they read him his rights once. Secondly, not reading your rights
does not mean not guilty automatically, If Miranda is violated it only suppresses
any statements made. He was not charged with underage drinking, curfew, truancy,
or running away. He was charged with a criminal offense, DUI. Time to lawyer up.
If he is convicted of DUI, he loses his license for a minimum of two years and
then must have a hearing with the Secretary of State.
- source_sentence: how private is this app?
sentences:
- We will not use this information for anything other than providing the Service
for which the information was supplied.
- ), and College Board program participants may provide information regarding study
habits and test scores (e.g., the number of hours studied, modules or tests taken,
scores earned, etc.
- We share your information with Service Providers who process data on our behalf,
such as credit card processors and customer management systems.
- source_sentence: does this app may share my location anonymous?
sentences:
- You may opt out of certain ad targeting and retargeting services by visiting the
Digital Advertising Alliances opt-out page, or the Network Advertising Initiatives
opt-out page.
- 'Delivery of location services will involve reference to one or more of the following:
(a) the coordinates (latitude/longitude) of your location; (b) look-up of your
country of location by reference to your IP address against public sources; and/or
(c) your location settings on your Apple device or Android device, or similar
device identifier/settings.'
- We may collect usage information about your use of our Service, such as the number
of problems you have attempted, the number of videos you have viewed, and the
amount of time spent to complete a problem.
model-index:
- name: SentenceTransformer based on sentence-transformers/all-mpnet-base-v2
results:
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: mteb/AILA casedocs
type: mteb/AILA_casedocs
metrics:
- type: cosine_accuracy@1
value: 0.24
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.4
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.44
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.5
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.24
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.2
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.14400000000000002
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.096
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.06261421911421912
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.1773951048951049
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.21672843822843824
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.28030419580419585
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.23571318760075094
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.32385714285714284
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.19099315576955767
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: mteb/AILA statutes
type: mteb/AILA_statutes
metrics:
- type: cosine_accuracy@1
value: 0.24
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.52
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.72
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.8
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.24
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.20666666666666667
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.19999999999999996
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.144
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.068
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.16066666666666665
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.25033333333333335
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.35100000000000003
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.2945290400206784
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.4145238095238095
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.23863257355862635
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: mteb/legalbench consumer contracts qa
type: mteb/legalbench_consumer_contracts_qa
metrics:
- type: cosine_accuracy@1
value: 0.48737373737373735
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.6515151515151515
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.73989898989899
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.8560606060606061
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.48737373737373735
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.21717171717171713
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.14797979797979796
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.0856060606060606
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.48737373737373735
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.6515151515151515
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.73989898989899
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.8560606060606061
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.6575720798646046
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.5956780102613435
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.6021553873830202
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: mteb/legalbench corporate lobbying
type: mteb/legalbench_corporate_lobbying
metrics:
- type: cosine_accuracy@1
value: 0.788235294117647
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.9205882352941176
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.9382352941176471
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.9588235294117647
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.788235294117647
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.3068627450980392
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.1876470588235294
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.09588235294117646
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.788235294117647
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.9205882352941176
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.9382352941176471
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.9588235294117647
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.8823720261303867
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.8569596171802053
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.8589677781368958
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: mteb/legal summarization
type: mteb/legal_summarization
metrics:
- type: cosine_accuracy@1
value: 0.4788732394366197
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.6373239436619719
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.721830985915493
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.8204225352112676
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.4788732394366197
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.23474178403755866
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.16830985915492958
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.1028169014084507
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.4233891988293397
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.5632004146088653
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.6415233827205657
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.7539452624839948
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.602922176130265
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.5816705790297337
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.5513678334926079
name: Cosine Map@100
---
# SentenceTransformer based on sentence-transformers/all-mpnet-base-v2
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) on the [coliee](https://huggingface.co/datasets/sentence-transformers/coliee), [legal_qa](https://huggingface.co/datasets/bwang0911/legal_qa_v1), [law_stack](https://huggingface.co/datasets/bwang0911/law_stackexchange), [legal_lens](https://huggingface.co/datasets/bwang0911/legal_lens_nli), [cuad_qa](https://huggingface.co/datasets/bwang0911/cuad_qa), [privacy_qa](https://huggingface.co/datasets/bwang0911/privacy_qa), [legal_sum](https://huggingface.co/datasets/bwang0911/legal_case_summarization) and [aus_legal_qa](https://huggingface.co/datasets/bwang0911/aus_legal_qa) datasets. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
## Model Details
### Model Description
- **Model Type:** Sentence Transformer
- **Base model:** [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) <!-- at revision 9a3225965996d404b775526de6dbfe85d3368642 -->
- **Maximum Sequence Length:** 192 tokens
- **Output Dimensionality:** 768 dimensions
- **Similarity Function:** Cosine Similarity
- **Training Datasets:**
- [coliee](https://huggingface.co/datasets/sentence-transformers/coliee)
- [legal_qa](https://huggingface.co/datasets/bwang0911/legal_qa_v1)
- [law_stack](https://huggingface.co/datasets/bwang0911/law_stackexchange)
- [legal_lens](https://huggingface.co/datasets/bwang0911/legal_lens_nli)
- [cuad_qa](https://huggingface.co/datasets/bwang0911/cuad_qa)
- [privacy_qa](https://huggingface.co/datasets/bwang0911/privacy_qa)
- [legal_sum](https://huggingface.co/datasets/bwang0911/legal_case_summarization)
- [aus_legal_qa](https://huggingface.co/datasets/bwang0911/aus_legal_qa)
- **Language:** en
<!-- - **License:** Unknown -->
### Model Sources
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
### Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 192, 'do_lower_case': False}) with Transformer model: MPNetModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
(2): Normalize()
)
```
## Usage
### Direct Usage (Sentence Transformers)
First install the Sentence Transformers library:
```bash
pip install -U sentence-transformers
```
Then you can load this model and run inference.
```python
from sentence_transformers import SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("bwang0911/jev2-legal")
# Run inference
sentences = [
'does this app may share my location anonymous?',
'Delivery of location services will involve reference to one or more of the following: (a) the coordinates (latitude/longitude) of your location; (b) look-up of your country of location by reference to your IP address against public sources; and/or (c) your location settings on your Apple device or Android device, or similar device identifier/settings.',
'We may collect usage information about your use of our Service, such as the number of problems you have attempted, the number of videos you have viewed, and the amount of time spent to complete a problem.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]
```
<!--
### Direct Usage (Transformers)
<details><summary>Click to see the direct usage in Transformers</summary>
</details>
-->
<!--
### Downstream Usage (Sentence Transformers)
You can finetune this model on your own dataset.
<details><summary>Click to expand</summary>
</details>
-->
<!--
### Out-of-Scope Use
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->
## Evaluation
### Metrics
#### Information Retrieval
* Datasets: `mteb/AILA_casedocs`, `mteb/AILA_statutes`, `mteb/legalbench_consumer_contracts_qa`, `mteb/legalbench_corporate_lobbying` and `mteb/legal_summarization`
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
| Metric | mteb/AILA_casedocs | mteb/AILA_statutes | mteb/legalbench_consumer_contracts_qa | mteb/legalbench_corporate_lobbying | mteb/legal_summarization |
|:--------------------|:-------------------|:-------------------|:--------------------------------------|:-----------------------------------|:-------------------------|
| cosine_accuracy@1 | 0.24 | 0.24 | 0.4874 | 0.7882 | 0.4789 |
| cosine_accuracy@3 | 0.4 | 0.52 | 0.6515 | 0.9206 | 0.6373 |
| cosine_accuracy@5 | 0.44 | 0.72 | 0.7399 | 0.9382 | 0.7218 |
| cosine_accuracy@10 | 0.5 | 0.8 | 0.8561 | 0.9588 | 0.8204 |
| cosine_precision@1 | 0.24 | 0.24 | 0.4874 | 0.7882 | 0.4789 |
| cosine_precision@3 | 0.2 | 0.2067 | 0.2172 | 0.3069 | 0.2347 |
| cosine_precision@5 | 0.144 | 0.2 | 0.148 | 0.1876 | 0.1683 |
| cosine_precision@10 | 0.096 | 0.144 | 0.0856 | 0.0959 | 0.1028 |
| cosine_recall@1 | 0.0626 | 0.068 | 0.4874 | 0.7882 | 0.4234 |
| cosine_recall@3 | 0.1774 | 0.1607 | 0.6515 | 0.9206 | 0.5632 |
| cosine_recall@5 | 0.2167 | 0.2503 | 0.7399 | 0.9382 | 0.6415 |
| cosine_recall@10 | 0.2803 | 0.351 | 0.8561 | 0.9588 | 0.7539 |
| **cosine_ndcg@10** | **0.2357** | **0.2945** | **0.6576** | **0.8824** | **0.6029** |
| cosine_mrr@10 | 0.3239 | 0.4145 | 0.5957 | 0.857 | 0.5817 |
| cosine_map@100 | 0.191 | 0.2386 | 0.6022 | 0.859 | 0.5514 |
<!--
## Bias, Risks and Limitations
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
-->
<!--
### Recommendations
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
-->
## Training Details
### Training Datasets
#### coliee
* Dataset: [coliee](https://huggingface.co/datasets/sentence-transformers/coliee) at [d90012e](https://huggingface.co/datasets/sentence-transformers/coliee/tree/d90012e1f3a0d7103713bb2ce7faed1636a10090)
* Size: 9,260 training samples
* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
* Approximate statistics based on the first 1000 samples:
| | anchor | positive | negative |
|:--------|:-----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
| type | string | string | string |
| details | <ul><li>min: 11 tokens</li><li>mean: 41.76 tokens</li><li>max: 99 tokens</li></ul> | <ul><li>min: 25 tokens</li><li>mean: 119.1 tokens</li><li>max: 192 tokens</li></ul> | <ul><li>min: 14 tokens</li><li>mean: 113.91 tokens</li><li>max: 192 tokens</li></ul> |
* Samples:
| anchor | positive | negative |
|:-------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <code><br>A compulsory auction is also a sale, so warranty is imposed the same as for an ordinary sale.<br></code> | <code><br>Article 568<br>(1) The successful bidder at an auction based on the provisions of the Civil Execution Act and other laws (hereinafter referred to as an "auction" in this Article) may cancel the contract or demand a reduction of the price against the obligor pursuant to the provisions of Articles 541 and 542 and the provisions of Article 563<br>(including as applied mutatis mutandis pursuant to Article 565).<br>(2) In the cases referred to in the preceding paragraph, if the obligor is insolvent, the successful bidder may demand total or partial reimbursement of the proceeds against the obligees that received the distribution of the proceeds.<br>(3) In the cases set forth in the preceding two paragraphs, if obligors knew of the absence of the object or right and did not disclose the same, or if obligees knew of the absence but demanded an auction, the successful bidder may claim compensation for loss or damage against those persons.<br>(4) The provisions of the preceding three paragraphs do not apply ...</code> | <code><br>Article 575<br>(1) If the subject matter of a sale which has not yet been delivered bears fruits, the fruits vest in the seller.<br>(2) The buyer bears the obligation to pay interest on the price beginning from the day of delivery;provided, however, that if a due date is provided for the payment of the price, it is not necessary to pay the interest until that due date arrives..<br></code> |
| <code><br>A compulsory auction is also a sale, so warranty is imposed the same as for an ordinary sale.<br></code> | <code><br>Article 568<br>(1) The successful bidder at an auction based on the provisions of the Civil Execution Act and other laws (hereinafter referred to as an "auction" in this Article) may cancel the contract or demand a reduction of the price against the obligor pursuant to the provisions of Articles 541 and 542 and the provisions of Article 563<br>(including as applied mutatis mutandis pursuant to Article 565).<br>(2) In the cases referred to in the preceding paragraph, if the obligor is insolvent, the successful bidder may demand total or partial reimbursement of the proceeds against the obligees that received the distribution of the proceeds.<br>(3) In the cases set forth in the preceding two paragraphs, if obligors knew of the absence of the object or right and did not disclose the same, or if obligees knew of the absence but demanded an auction, the successful bidder may claim compensation for loss or damage against those persons.<br>(4) The provisions of the preceding three paragraphs do not apply ...</code> | <code><br>Article 596<br>The provisions of Article 551<br>apply mutatis mutandis to loans for use.<br>Article 551<br>(1) The donor is presumed to have promised to deliver or transfer the thing or right that is the subject matter of the gift, while maintaining its condition as of the time when it is specified as the subject matter of the gift.<br>(2) With respect to gifts with burden, the donor provides the same warranty as that of a seller, to the extent of that burden..<br></code> |
| <code><br>A compulsory auction is also a sale, so warranty is imposed the same as for an ordinary sale.<br></code> | <code><br>Article 568<br>(1) The successful bidder at an auction based on the provisions of the Civil Execution Act and other laws (hereinafter referred to as an "auction" in this Article) may cancel the contract or demand a reduction of the price against the obligor pursuant to the provisions of Articles 541 and 542 and the provisions of Article 563<br>(including as applied mutatis mutandis pursuant to Article 565).<br>(2) In the cases referred to in the preceding paragraph, if the obligor is insolvent, the successful bidder may demand total or partial reimbursement of the proceeds against the obligees that received the distribution of the proceeds.<br>(3) In the cases set forth in the preceding two paragraphs, if obligors knew of the absence of the object or right and did not disclose the same, or if obligees knew of the absence but demanded an auction, the successful bidder may claim compensation for loss or damage against those persons.<br>(4) The provisions of the preceding three paragraphs do not apply ...</code> | <code><br>Article 520<br>If a claim and obligation becomes vested in the same person, such claim is extinguished;provided, however, that this does not apply if such a claim is the subject matter of the right of a third party..<br></code> |
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
```json
{
"scale": 50.0,
"similarity_fct": "cos_sim"
}
```
#### legal_qa
* Dataset: [legal_qa](https://huggingface.co/datasets/bwang0911/legal_qa_v1) at [bbe3790](https://huggingface.co/datasets/bwang0911/legal_qa_v1/tree/bbe3790626658e8e020de978d186c8902647b635)
* Size: 3,742 training samples
* Columns: <code>anchor</code> and <code>positive</code>
* Approximate statistics based on the first 1000 samples:
| | anchor | positive |
|:--------|:-------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
| type | string | string |
| details | <ul><li>min: 13 tokens</li><li>mean: 108.12 tokens</li><li>max: 192 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 130.94 tokens</li><li>max: 192 tokens</li></ul> |
* Samples:
| anchor | positive |
|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <code>Q: I was wondering if a pain management office is acting illegally/did an illegal action.. I was discharged as a patient from a pain management office after them telling me that a previous pain management specialist I saw administered a steroid shot wrong and I told them in the portal that I spoke to lawyers for advice but no lawsuit/case was created. It was maybe 1-2 months after I was discharged that I no longer have access to my patient portal with them. Every time I try to login I enter my credentials, wait a few seconds, and then I get re-directed back to the original screen where I have various options to login. I know I can speak to the office directly and ask them about what specifically is going on, talk to other lawyers if this is a violation of my rights, etc. but I was just wondering if anyone on this site would know if this action is in fact illegal. </code> | <code>A:In Kentucky, your situation raises questions about patient rights and medical records access. If you were discharged from a pain management office and subsequently lost access to your patient portal, it's important to understand your rights regarding medical records. Under the Health Insurance Portability and Accountability Act (HIPAA), you have the right to access your own medical records. A healthcare provider cannot deny you access to your records, even if you were discharged from their practice. The issue with the patient portal could be a technical glitch or a deliberate action, but either way, it needs to be addressed. You should contact the pain management office directly to inquire about the issue with the patient portal. They are obligated to provide you with a way to access your medical records, which may include providing paper copies or access through a different electronic means. If the office is unresponsive or refuses to provide access to your records, consider speakin...</code> |
| <code>Q: My houseboat was moved while I was at work and was asked to leave the property after 16 months without any notices.. Management told me that he didn’t like those kind of people that came to visit me. I went on vacation and when I came back my electrical cord was missing and my water hose was cut in pieces. He than got of hold of me and said I have your boat and that he was putting a lien on it for back rent. I never received any notices from management. He than told me that he wanted me to leave the property and that he would hold my boat until i found another parking spot for it. I finally found a parking spot a year later and I find out that he liened my houseboat and was selling it and told me to sue him and gave me his lawyers contact. What options do I have. I now am homeless and I lost my job and seeing myself falling as time goes. Any help would be appreciated. </code> | <code>A:If your houseboat was moved without your permission and you were asked to leave the property after 16 months without any notices, and the management has placed a lien on your houseboat and is attempting to sell it, you may have legal options to challenge their actions. First, you may want to consult with an attorney who specializes in property law or landlord-tenant law to review your case and provide guidance on your legal rights and options. It may also be helpful to gather any evidence you have, such as receipts or documentation of payments or communications with the management, to support your case. Some potential legal claims you may have against the management include breach of contract, conversion, or wrongful eviction. These claims may allow you to seek damages or other forms of relief, such as the return of your houseboat or compensation for any losses you have suffered. It's important to act quickly, as there may be deadlines or other requirements for filing a legal claim. ...</code> |
| <code>Q: Wondering if I could sue a dealership if I’ve had to replace my transmission 2 times within a year. I’ve had to replace my transmission now 2 different times in 10 months of owning my 2018 Ford Expedition. My first replacement was $5,200 and then 1 1/2 months later the transmission went out and now they are working on it again </code> | <code>A:Yes, you can sue a dealership if you have had to replace your transmission 2 times within a year. Whether you will be successful depends on the facts and your presentation. You don't mention anything about any written agreements. Allowing an attorney to evaluate, organize and draft your conciliation or (small claims) complaint (up to $15,000) would be a wise investment. A well polished complaint will not only provide the judge a solid foundation to rule in your favor, but a detailed outline on which to base your oral argument. It would provide you a distinct advantage over the opposing party. The fees can be reasonable depending on the attorney.</code> |
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
```json
{
"scale": 50.0,
"similarity_fct": "cos_sim"
}
```
#### law_stack
* Dataset: [law_stack](https://huggingface.co/datasets/bwang0911/law_stackexchange) at [b19a371](https://huggingface.co/datasets/bwang0911/law_stackexchange/tree/b19a37105babf2f9b5e3aa93dbc65037fbdfd0e0)
* Size: 13,000 training samples
* Columns: <code>anchor</code> and <code>positive</code>
* Approximate statistics based on the first 1000 samples:
| | anchor | positive |
|:--------|:-------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
| type | string | string |
| details | <ul><li>min: 27 tokens</li><li>mean: 141.93 tokens</li><li>max: 192 tokens</li></ul> | <ul><li>min: 15 tokens</li><li>mean: 166.18 tokens</li><li>max: 192 tokens</li></ul> |
* Samples:
| anchor | positive |
|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <code>Why is drunk driving causing accident punished so much worse than just drunk driving? When people drink and drive and then cause an accident especially where if someone dies they get years and years in prison but just the act of drunk driving is punished way more lenient. Shouldn't the 2, drunk driving and drunk driving then causing accident be similarly punished? I feel like a lot of times it's luck whether an accident happens.</code> | <code>Moral luck You have raised the issue of moral luck, a long recognized problem in criminal theory. The classic expositions of this issue are by Thomas Nagel, in his chapter, "Moral Luck" (1979) and Bernard Williams, "Moral Luck" (1976). Specifically, you are describing what they call outcome luck, or consequential luck. Driving while intoxicated vs. driving while intoxicated and causing death is not the only example where moral luck results in a distinction in punishment. Other examples are: dangerous driving vs. dangerous driving that causes death a successful offence vs. an attempted offence (generally resulting in a maximum sentence less than that of the successful offence) Nagel writes: If someone has had too much to drink and his car swerves on to the sidewalk, he can count himself morally lucky if there are no pedestrians in its path. If there were, he would be to blame for their deaths, and would probably be prosecuted for manslaughter. But if he hurts no one,...</code> |
| <code>Question Concerning Responding to Employer of Minor Daughter Paid Under Minimum Wage My high school daughter worked for about a year for an employer who owns a tutoring company in our town. Due to friction between my daughter and the employer, my daughter recently quit but she realized that she was being underpaid for much of this year (2023) because the minimum wage here in California is currently $15.50 for 2023 but she was still getting paid $14.00, the California minimum wage for 2022, when she recently quit (in August 2023). Now according to my daughter there is a provision in California law which allows employers to pay only 85% of minimum wage for new workers with no prior experience for their first 160 hours of work. For 2023, that "new worker" wage level would work out to $13.17 per hour, but my daughter said that she exceeded her first 160 hours of work for the employer back in March 2023. So, basically, my daughter was being paid under the proper CA 2023 minimum wa...</code> | <code>Read the terms It’s quite likely that, if you took this to court, the employer would be liable to pay your daughter interest on the underpayment and possibly be fined by the state for failing to follow the law. The terms probably are offering to pay the back pay with no interest and your daughter agreeing to confidentiality about the breach. Probably - I haven’t read them. In other words, they’re asking her to sign a contract saying she gets $XXX now, and can’t make any further claims against them. Such releases are commonplace when setting a dispute and there’s probably nothing underhanded going on. Probably - I haven’t read them. Because minors can void contracts if they are not in their interest, they want you, as her legal guardian, to also sign so that can’t happen. A relatively prudent precaution on their part. The alternative is to not sign the document and they presumably won’t pay. It will then be up to you whether to sue them which will cost you money, possibly more than you ...</code> |
| <code>Can Hawaii secede from the U.S. through legal means? Can Hawaii secede from the U.S. through legal means or is it forbidden by U.S. law? I am asking, because I doubt the U.S. would accept the result of a referendum that rules that the Hawaiians want to secede from the U.S. just like Russia or China wouldn't accept it.</code> | <code>Currently, there is no legal means for a state to secede form the U.S. A quick Google search yields So you want to secede from the U.S.: A four-step guide - The Washington Post: "When the Confederate states seceded in 1861 and were then defeated in the Civil War, the argument is that they demonstrated that you can't secede from the Union. The 1869 Supreme Court case TEXAS v. WHITE ET AL (Legal Information Institute) determined that the secession was never actually a real thing in the eyes of the federal government. The Confederate States of America wasn't an independent country any more than your house is its own country simply because you say it is. 'The Constitution, in all its provisions,' the justices wrote, 'looks to an indestructible Union composed of indestructible States.'" Also from that Post piece: In 2006, Justice Antonin Scalia was asked by screenwriter Dan Turkewitz if the idea of Maine seceding from the country made sense as a possible plot point. Scalia, perhap...</code> |
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
```json
{
"scale": 50.0,
"similarity_fct": "cos_sim"
}
```
#### legal_lens
* Dataset: [legal_lens](https://huggingface.co/datasets/bwang0911/legal_lens_nli) at [a4c8193](https://huggingface.co/datasets/bwang0911/legal_lens_nli/tree/a4c8193930720698fdce36b394957bda75ba8863)
* Size: 107 training samples
* Columns: <code>anchor</code> and <code>positive</code>
* Approximate statistics based on the first 107 samples:
| | anchor | positive |
|:--------|:--------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
| type | string | string |
| details | <ul><li>min: 107 tokens</li><li>mean: 164.29 tokens</li><li>max: 192 tokens</li></ul> | <ul><li>min: 27 tokens</li><li>mean: 78.31 tokens</li><li>max: 192 tokens</li></ul> |
* Samples:
| anchor | positive |
|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <code>DEFENDANT has agreed to a $72,250 settlement to resolve claims that it violated Illinois' Biometric Information Privacy Act (BIPA) by scanning the hands and fingerprints of its employees without obtaining prior consent. The settlement benefits employees in Illinois who had their fingers or hands scanned by a timekeeping system between Dec. 31, 2015, and Dec. 31, 2020, without first signing a consent form. Although DEFENDANT has not admitted any wrongdoing, it agreed to the settlement to resolve the BIPA allegations. Class members can receive an equal share of the net settlement fund, estimated to be around $352.75 per worker. The deadline for exclusion and objection is May 15, 2023, and the final approval hearing for the BIPA settlement is scheduled for June 15, 2023. No claim form is required to benefit from the settlement.</code> | <code>Y'know, it's funny how things turn out sometimes. I was working this job, right? Nothing fancy, just clocking in and out, doing my thing. They had this newfangled tech system for logging our hours, some sort of hand scan thing. Thought it was pretty cool, not gonna lie. High-tech, right? Made me feel like I was in a sci-fi movie or something.<br><br>But then, things started to get a bit weird. I mean, I didn't notice anything at first, but after a while, it kinda felt off, y'know? Like, I couldn't shake the feeling that something was not right. I mean, it's just a hand scanner, right? What could possibly go wrong?<br><br>And then, outta nowhere, I heard this rumor going around about some sort of issue with the hand scanner. Something about not getting the proper consents or something. It was all a bit hush-hush, and no one was really talking about it openly. But you know how these things go, word gets around.<br><br>So here I am, just trying to do my job, and suddenly I'm in the middle of some sort of t...</code> |
| <code>DEFENDANT has agreed to pay $6.5 million to settle a nationwide class action lawsuit, which accused the company of making telemarketing calls in violation of the Telephone Consumer Protection Act (TCPA). The lawsuit, filed in 2015, alleged that the company made calls using a prerecorded message to cell phones, residential lines, and numbers on the National Do-Not-Call Registry to obtain new clients. The settlement includes cash payments of between $100 and $150 to eligible members of the class action, as well as covering class administration costs, plaintiffs’ attorneys’ fees and litigation costs up to $2,210,566. A $25,000 court-approved service award will also be given to the plaintiff. DEFENDANT will also implement policies and procedures to prevent future violations. Despite the settlement, DEFENDANT does not admit to any wrongdoing and continues to deny the allegations.</code> | <code>Unsolicited calls? They're a real nuisance. It seems my number made it onto a list somewhere, and now my phone won't stop ringing with offers I never asked for.</code> |
| <code>DEFENDANT has agreed to a $8.5 million class action settlement over allegations that its stores used misleading price tags. The lawsuit alleged that the use of the phrase “Compare At” on price tags was deceptive, as it misled customers about the actual price of comparable items at other stores. Customers who purchased items from DEFENDANT's stores in California between July 17, 2011 and Dec. 6, 2017, can file a claim to receive either a merchandise store credit or cash from the settlement. DEFENDANT has also agreed to change pricing disclosures on its website and in its California stores to comply with the state's price comparison advertising regulations. The settlement was granted preliminary approval on Dec. 5, 2017, and class members have until April 9, 2018 to object or opt out.</code> | <code>Got a bargain at my favourite shop, but the "Compare At" tags sure had me thinking other places were pricier. Hmm, interesting marketing strategy!</code> |
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
```json
{
"scale": 50.0,
"similarity_fct": "cos_sim"
}
```
#### cuad_qa
* Dataset: [cuad_qa](https://huggingface.co/datasets/bwang0911/cuad_qa) at [333b657](https://huggingface.co/datasets/bwang0911/cuad_qa/tree/333b657309dda78d2bcda86742127c6568d9f1c1)
* Size: 11,180 training samples
* Columns: <code>anchor</code> and <code>positive</code>
* Approximate statistics based on the first 1000 samples:
| | anchor | positive |
|:--------|:------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
| type | string | string |
| details | <ul><li>min: 33 tokens</li><li>mean: 51.31 tokens</li><li>max: 105 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 57.1 tokens</li><li>max: 192 tokens</li></ul> |
* Samples:
| anchor | positive |
|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------|
| <code>Highlight the parts (if any) of this contract related to "Document Name" that should be reviewed by a lawyer. Details: The name of the contract</code> | <code>DISTRIBUTOR AGREEMENT</code> |
| <code>Highlight the parts (if any) of this contract related to "Parties" that should be reviewed by a lawyer. Details: The two or more parties who signed the contract</code> | <code>Distributor</code> |
| <code>Highlight the parts (if any) of this contract related to "Parties" that should be reviewed by a lawyer. Details: The two or more parties who signed the contract</code> | <code>Electric City of Illinois L.L.C.</code> |
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
```json
{
"scale": 50.0,
"similarity_fct": "cos_sim"
}
```
#### privacy_qa
* Dataset: [privacy_qa](https://huggingface.co/datasets/bwang0911/privacy_qa) at [cd59571](https://huggingface.co/datasets/bwang0911/privacy_qa/tree/cd59571b4424c8ad8585dc615bae3b4f23b7da38)
* Size: 6,038 training samples
* Columns: <code>anchor</code> and <code>positive</code>
* Approximate statistics based on the first 1000 samples:
| | anchor | positive |
|:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
| type | string | string |
| details | <ul><li>min: 6 tokens</li><li>mean: 11.54 tokens</li><li>max: 30 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 30.25 tokens</li><li>max: 143 tokens</li></ul> |
* Samples:
| anchor | positive |
|:----------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <code>do you share my location with other people</code> | <code>To use our Applications, you must have an account with a healthcare provider who uses Epic's software and your use of our Applications is also subject to your healthcare provider's privacy policy.</code> |
| <code>are you selling my data</code> | <code>Interest Based Advertising Khan Academy does not display any targeted advertising on our Service.</code> |
| <code>will the data collected from my usage of the app be sold to third parties?</code> | <code>Additionally, if you choose to participate in our member-to-member communications programs, other TripAdvisor members may contact you by using TripAdvisor as an intermediary; however, TripAdvisor will not share your email address with any other members nor display it any public manner.</code> |
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
```json
{
"scale": 50.0,
"similarity_fct": "cos_sim"
}
```
#### legal_sum
* Dataset: [legal_sum](https://huggingface.co/datasets/bwang0911/legal_case_summarization) at [667db49](https://huggingface.co/datasets/bwang0911/legal_case_summarization/tree/667db49d7a2152de6ab0c7e6e44f07fc3b36d2d1)
* Size: 7,773 training samples
* Columns: <code>anchor</code> and <code>positive</code>
* Approximate statistics based on the first 1000 samples:
| | anchor | positive |
|:--------|:-------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
| type | string | string |
| details | <ul><li>min: 192 tokens</li><li>mean: 192.0 tokens</li><li>max: 192 tokens</li></ul> | <ul><li>min: 63 tokens</li><li>mean: 191.26 tokens</li><li>max: 192 tokens</li></ul> |
* Samples:
| anchor | positive |
|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <code>Appeal No. LXVI of 1949.<br>Appeal from the High Court of judicature, Bombay, in a reference under section 66 of the Indian Income tax Act, 1022.<br>K.M. Munshi (N. P. Nathvani, with him), for the appel lant. ' M.C. Setalvad, Attorney General for India (H. J. Umrigar, with him), for the respondent. 1950.<br>May 26.<br>The judgment of the Court was delivered by MEHR CHAND MAHAJAN J.<br>This is an appeal against a judgment of the High Court of Judicature at Bombay in an income tax matter and it raises the question whether munici pal property tax and urban immoveable property tax payable under the relevant Bombay Acts are allowable deductions under section 9 (1) (iv) of the Indian Income tax Act.<br>The assessee company is an investment company deriving its income from properties in the city of Bombay.<br>For the assessment year 1940 41 the net income of the assessee under the head "property" was computed by the Income tax Officer in the sum of Rs. 6,21,764 after deducting from gross rents certain payments.<br>T...</code> | <code>The charge created in respect of municipal property tax by section 212 of the City of Bombay Municipal Act, 1888, is an "annual charge not being a capital charge" within the mean ing of section 9 (1) (iv) of the Indian Income tax Act, 199.2, and the amount of such charge should therefore be deducted in computing the income from such property for the purposes of section 9 of the Indian Income tax Act.<br>The charge in respect of urban immoveable property tax created by the Bombay Finance Act, 1939 is similar in character and the amount of such charge should also be deducted.<br>The expression "capital charge" in s.9(1) (iv) means a charge created for a capital sum,that is to say, a charge created to. ' secure the discharge of a liability of a capi tal nature; and an "annual charge" means a charge to secure an annual liabili ty. 554<br></code> |
| <code>Civil Appeal No.94 of 1949.<br>107 834 Appeal from a judgment and decree of the High Court of Judi cature at Patna in Appeal from Appellate Decree No. 97 of 1946 (Mannohar Lall and Mukherji JJ.) dated 23rd Decem ber, 1947, confirming the judgment of the District Judge of Purulia in Appeal No. 159 of 1944.<br>S.P. Sinha (P. K. Bose, with him) for the appel lant.<br>N.C. Chatterjee and Panchanan Ghosh (Chandra Narayan Naik, with them) for the respondent. 1950.<br>December 1.<br>The Judgment of the Court was deliv ered by PATANJALI SASTRI J.<br>This appeal arises out of a suit brought by the respondent in the court of the Subordinate Judge, Dhanbad, for recovery of arrears of royalty and cess from the appellant and another alleged to be due under a compromise decree passed on the 6th March, 1923, in a previ ous suit between the predecessors in interest of the par ties.<br>The only plea which is material for the purpose of this appeal is that the compromise decree not having been registered was inadmissible in...</code> | <code>An agreement for a lease, which a lease is by the Indian declared to include, must be a document which effects an actual demise and operates as a lease.<br>It must create present and immediate interest in land.<br>Where a litigation between two persons A and B who claimed to be tenants under C was settled by a compromise decree the effect of which was to create a perpetual underlease between A and B which was to take effect only on condition that A paid Rs. 8,000 to C within a fixed period: Held, that such a contingent agreement was not "a lease" within el.<br>(a) of section 17 (t) of the Indian , and even though it was covered by cl.<br>(b) of the said sec tion it was exempt from registration under el.<br>(vi) of subs.<br>(2) of section 17.<br>Hemanta Kumari Debi vs Midnapur Zamindari Co. (I P.C.) relied on.<br></code> |
| <code>iminal Appeal No. 40 of 1951, 127 Appeal from the Judgment and Order dated the 1st June, 1951, of the High Court of Judicature in Assam (Thadani C.J. and Ram Labhaya J.,) in Criminal Reference No. I of 1951, arising out of Judgment and Order dated the 15th November, 1950, of the Court of the Additional District Magistrate, Lakhimpur, in Case No. 1126C of 1950.<br>Jindra Lal for the appellant.<br>Nuruddin Ahmed for the respondent.<br>October 23.<br>The Judgment of the Court was delivered by CHANDRASEKHARA AIYAR J.<br>Rameshwar Bhartia, the appellant, is a shopkeeper in Assam.<br>He was prosecuted for storing paddy without a licence in excess of the quantity permitted by the Assam Food Grains Control Order, 1947.<br>He admitted storage and possession of 550 maunds of paddy, but pleaded that he did not know that any licence was necessary.<br>The 'Additional District Magistrate recorded a plea of guilty, but imposed him a fine of Rs. 50 only, as he considered his ignorance of the provisions of the Food Grains Con...</code> | <code>The question whether a Magistrate is "personally interested" in a ease within the meaning of section 556, Criminal Procedure Code, has essentially to be decided the facts of each case.<br>Where an officer as a District Magistrate exercising his powers under section 7(1) of the Essential Supplies (Temporary Powers) Act, 1946, sanctioned the prosecution of a person for violation of sections 3 and 7 of the Assam Food Grains Control Order, 1947, and the same officer as Additional District Magistrate tried and convicted the accused, and it was contended that as the officer had given sanction for prosecution he was "personally interested" in the case within the meaning of section 656, Criminal Procedure Code, and the trial and conviction were therefore illegal: Held, that bymerely giving sanction for prosecution he did not become personally interested" in the case and the trial and conviction were not illegal.<br>In both cases of sanction and direction to prosecute, an application of the mind is n...</code> |
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
```json
{
"scale": 50.0,
"similarity_fct": "cos_sim"
}
```
#### aus_legal_qa
* Dataset: [aus_legal_qa](https://huggingface.co/datasets/bwang0911/aus_legal_qa) at [0628f4a](https://huggingface.co/datasets/bwang0911/aus_legal_qa/tree/0628f4a78023fa5cde0000b786e3f57a53d29453)
* Size: 2,124 training samples
* Columns: <code>anchor</code> and <code>positive</code>
* Approximate statistics based on the first 1000 samples:
| | anchor | positive |
|:--------|:------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
| type | string | string |
| details | <ul><li>min: 12 tokens</li><li>mean: 38.68 tokens</li><li>max: 106 tokens</li></ul> | <ul><li>min: 21 tokens</li><li>mean: 111.75 tokens</li><li>max: 192 tokens</li></ul> |
* Samples:
| anchor | positive |
|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <code>In the case of Nasr v NRMA Insurance [2006] NSWSC 1018, why was the plaintiff's appeal lodged out of time?</code> | <code>In Nasr v NRMA Insurance [2006] NSWSC 1018, the plaintiff's appeal was lodged out of time because the summons was filed on 8 June 2006, seven months after the decision of the Local Court was made on 4 October 2005. No explanation was provided for this delay.</code> |
| <code>In the case of R v NGUYEN [2001] NSWCCA 334, what was the relationship between the Appellant and Mr Nguyen, and what activities of Mr Nguyen did the Appellant testify about?</code> | <code>In the case of R v NGUYEN [2001] NSWCCA 334, the Appellant testified that Mr Nguyen was her cousin and that she had allowed him to live in her flat for about 4 or 5 days. She stated that she had heard that Mr Nguyen was selling heroin and that she had seen him hand over a small foil to a third person, an event that made her feel surprised, upset, and angry. Despite her protests, Mr Nguyen allegedly continued to sell heroin from the flat. The Appellant also mentioned seeing other customers in the flat and a friend of Mr Nguyen's cutting foil in the lounge-room. Despite her complaints to her boyfriend and an aunt, she took no further steps to prevent these activities, citing reasons such as their close familial relationship and her reluctance to involve the police.</code> |
| <code>In the case of Moore v Scenic Tours Pty Ltd [2015] NSWSC 237, what was the court's decision regarding the motion to restrain a firm from acting?</code> | <code>In the case of Moore v Scenic Tours Pty Ltd [2015] NSWSC 237, the court decided to dismiss the motion to restrain a firm from acting. The court found that the plaintiff was entitled to a solicitor of their choice and it was not in the interest of justice to deprive the plaintiff of their choice of solicitor.</code> |
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
```json
{
"scale": 50.0,
"similarity_fct": "cos_sim"
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `eval_strategy`: steps
- `per_device_train_batch_size`: 64
- `learning_rate`: 1e-06
- `num_train_epochs`: 2
- `warmup_ratio`: 0.1
- `fp16`: True
- `batch_sampler`: no_duplicates
#### All Hyperparameters
<details><summary>Click to expand</summary>
- `overwrite_output_dir`: False
- `do_predict`: False
- `eval_strategy`: steps
- `prediction_loss_only`: True
- `per_device_train_batch_size`: 64
- `per_device_eval_batch_size`: 8
- `per_gpu_train_batch_size`: None
- `per_gpu_eval_batch_size`: None
- `gradient_accumulation_steps`: 1
- `eval_accumulation_steps`: None
- `torch_empty_cache_steps`: None
- `learning_rate`: 1e-06
- `weight_decay`: 0.0
- `adam_beta1`: 0.9
- `adam_beta2`: 0.999
- `adam_epsilon`: 1e-08
- `max_grad_norm`: 1.0
- `num_train_epochs`: 2
- `max_steps`: -1
- `lr_scheduler_type`: linear
- `lr_scheduler_kwargs`: {}
- `warmup_ratio`: 0.1
- `warmup_steps`: 0
- `log_level`: passive
- `log_level_replica`: warning
- `log_on_each_node`: True
- `logging_nan_inf_filter`: True
- `save_safetensors`: True
- `save_on_each_node`: False
- `save_only_model`: False
- `restore_callback_states_from_checkpoint`: False
- `no_cuda`: False
- `use_cpu`: False
- `use_mps_device`: False
- `seed`: 42
- `data_seed`: None
- `jit_mode_eval`: False
- `use_ipex`: False
- `bf16`: False
- `fp16`: True
- `fp16_opt_level`: O1
- `half_precision_backend`: auto
- `bf16_full_eval`: False
- `fp16_full_eval`: False
- `tf32`: None
- `local_rank`: 0
- `ddp_backend`: None
- `tpu_num_cores`: None
- `tpu_metrics_debug`: False
- `debug`: []
- `dataloader_drop_last`: False
- `dataloader_num_workers`: 0
- `dataloader_prefetch_factor`: None
- `past_index`: -1
- `disable_tqdm`: False
- `remove_unused_columns`: True
- `label_names`: None
- `load_best_model_at_end`: False
- `ignore_data_skip`: False
- `fsdp`: []
- `fsdp_min_num_params`: 0
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
- `fsdp_transformer_layer_cls_to_wrap`: None
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
- `deepspeed`: None
- `label_smoothing_factor`: 0.0
- `optim`: adamw_torch
- `optim_args`: None
- `adafactor`: False
- `group_by_length`: False
- `length_column_name`: length
- `ddp_find_unused_parameters`: None
- `ddp_bucket_cap_mb`: None
- `ddp_broadcast_buffers`: False
- `dataloader_pin_memory`: True
- `dataloader_persistent_workers`: False
- `skip_memory_metrics`: True
- `use_legacy_prediction_loop`: False
- `push_to_hub`: False
- `resume_from_checkpoint`: None
- `hub_model_id`: None
- `hub_strategy`: every_save
- `hub_private_repo`: False
- `hub_always_push`: False
- `gradient_checkpointing`: False
- `gradient_checkpointing_kwargs`: None
- `include_inputs_for_metrics`: False
- `eval_do_concat_batches`: True
- `fp16_backend`: auto
- `push_to_hub_model_id`: None
- `push_to_hub_organization`: None
- `mp_parameters`:
- `auto_find_batch_size`: False
- `full_determinism`: False
- `torchdynamo`: None
- `ray_scope`: last
- `ddp_timeout`: 1800
- `torch_compile`: False
- `torch_compile_backend`: None
- `torch_compile_mode`: None
- `dispatch_batches`: None
- `split_batches`: None
- `include_tokens_per_second`: False
- `include_num_input_tokens_seen`: False
- `neftune_noise_alpha`: None
- `optim_target_modules`: None
- `batch_eval_metrics`: False
- `eval_on_start`: False
- `use_liger_kernel`: False
- `eval_use_gather_object`: False
- `prompts`: None
- `batch_sampler`: no_duplicates
- `multi_dataset_batch_sampler`: proportional
</details>
### Training Logs
| Epoch | Step | Training Loss | mteb/AILA_casedocs_cosine_ndcg@10 | mteb/AILA_statutes_cosine_ndcg@10 | mteb/legalbench_consumer_contracts_qa_cosine_ndcg@10 | mteb/legalbench_corporate_lobbying_cosine_ndcg@10 | mteb/legal_summarization_cosine_ndcg@10 |
|:------:|:----:|:-------------:|:---------------------------------:|:---------------------------------:|:----------------------------------------------------:|:-------------------------------------------------:|:---------------------------------------:|
| 0 | 0 | - | 0.1704 | 0.2351 | 0.6781 | 0.8793 | 0.5766 |
| 0.1196 | 100 | - | 0.1709 | 0.2434 | 0.6791 | 0.8834 | 0.5820 |
| 0.2392 | 200 | - | 0.2164 | 0.2702 | 0.6808 | 0.8832 | 0.6015 |
| 0.3589 | 300 | - | 0.2221 | 0.2707 | 0.6739 | 0.8855 | 0.6089 |
| 0.4785 | 400 | - | 0.2170 | 0.2705 | 0.6681 | 0.8857 | 0.6149 |
| 0.5981 | 500 | 2.757 | 0.2138 | 0.2644 | 0.6711 | 0.8830 | 0.6116 |
| 0.7177 | 600 | - | 0.2124 | 0.2725 | 0.6671 | 0.8861 | 0.6142 |
| 0.8373 | 700 | - | 0.2235 | 0.2919 | 0.6656 | 0.8856 | 0.6112 |
| 0.9569 | 800 | - | 0.2258 | 0.2902 | 0.6632 | 0.8848 | 0.6128 |
| 1.0766 | 900 | - | 0.2220 | 0.2999 | 0.6597 | 0.8865 | 0.6120 |
| 1.1962 | 1000 | 1.6406 | 0.2264 | 0.3015 | 0.6582 | 0.8870 | 0.6106 |
| 1.3158 | 1100 | - | 0.2266 | 0.2996 | 0.6576 | 0.8859 | 0.6097 |
| 1.4354 | 1200 | - | 0.2337 | 0.2944 | 0.6581 | 0.8863 | 0.6066 |
| 1.5550 | 1300 | - | 0.2343 | 0.2928 | 0.6572 | 0.8829 | 0.6064 |
| 1.6746 | 1400 | - | 0.2342 | 0.2920 | 0.6566 | 0.8822 | 0.6041 |
| 1.7943 | 1500 | 1.6345 | 0.2358 | 0.2947 | 0.6575 | 0.8824 | 0.6026 |
| 1.9139 | 1600 | - | 0.2357 | 0.2945 | 0.6576 | 0.8824 | 0.6029 |
### Framework Versions
- Python: 3.10.12
- Sentence Transformers: 3.3.0
- Transformers: 4.45.2
- PyTorch: 2.5.1+cu124
- Accelerate: 1.1.0
- Datasets: 3.1.0
- Tokenizers: 0.20.3
## Citation
### BibTeX
#### Sentence Transformers
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "https://arxiv.org/abs/1908.10084",
}
```
#### MultipleNegativesRankingLoss
```bibtex
@misc{henderson2017efficient,
title={Efficient Natural Language Response Suggestion for Smart Reply},
author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
year={2017},
eprint={1705.00652},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
<!--
## Glossary
*Clearly define terms in order to be accessible across audiences.*
-->
<!--
## Model Card Authors
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->
<!--
## Model Card Contact
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
--> | [
"TEXT_CLASSIFICATION",
"SUMMARIZATION"
] | Non_BioNLP |
meta-llama/Llama-3.2-11B-Vision | meta-llama | image-text-to-text | [
"transformers",
"safetensors",
"mllama",
"image-text-to-text",
"facebook",
"meta",
"pytorch",
"llama",
"llama-3",
"en",
"de",
"fr",
"it",
"pt",
"hi",
"es",
"th",
"arxiv:2204.05149",
"license:llama3.2",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 1,726,677,981,000 | 2024-09-27T00:19:41 | 37,105 | 483 | ---
language:
- en
- de
- fr
- it
- pt
- hi
- es
- th
library_name: transformers
license: llama3.2
pipeline_tag: image-text-to-text
tags:
- facebook
- meta
- pytorch
- llama
- llama-3
extra_gated_prompt: "### LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\n\nLlama 3.2 Version\
\ Release Date: September 25, 2024\n\n“Agreement” means the terms and conditions\
\ for use, reproduction, distribution and modification of the Llama Materials set\
\ forth herein.\n\n“Documentation” means the specifications, manuals and documentation\
\ accompanying Llama 3.2 distributed by Meta at https://llama.meta.com/doc/overview.\n\
\n“Licensee” or “you” means you, or your employer or any other person or entity\
\ (if you are entering into this Agreement on such person or entity’s behalf),\
\ of the age required under applicable laws, rules or regulations to provide legal\
\ consent and that has legal authority to bind your employer or such other person\
\ or entity if you are entering in this Agreement on their behalf.\n\n“Llama 3.2”\
\ means the foundational large language models and software and algorithms, including\
\ machine-learning model code, trained model weights, inference-enabling code, training-enabling\
\ code, fine-tuning enabling code and other elements of the foregoing distributed\
\ by Meta at https://www.llama.com/llama-downloads.\n\n“Llama Materials” means,\
\ collectively, Meta’s proprietary Llama 3.2 and Documentation (and any portion\
\ thereof) made available under this Agreement.\n\n“Meta” or “we” means Meta Platforms\
\ Ireland Limited (if you are located in or, if you are an entity, your principal\
\ place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if\
\ you are located outside of the EEA or Switzerland). \n\nBy clicking “I Accept”\
\ below or by using or distributing any portion or element of the Llama Materials,\
\ you agree to be bound by this Agreement.\n\n1. License Rights and Redistribution.\n\
a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable\
\ and royalty-free limited license under Meta’s intellectual property or other rights\
\ owned by Meta embodied in the Llama Materials to use, reproduce, distribute,\
\ copy, create derivative works of, and make modifications to the Llama Materials.\
\ \nb. Redistribution and Use. \ni. If you distribute or make available the Llama\
\ Materials (or any derivative works thereof), or a product or service (including\
\ another AI model) that contains any of them, you shall (A) provide a copy of this\
\ Agreement with any such Llama Materials; and (B) prominently display “Built with\
\ Llama” on a related website, user interface, blogpost, about page, or product\
\ documentation. If you use the Llama Materials or any outputs or results of the\
\ Llama Materials to create, train, fine tune, or otherwise improve an AI model,\
\ which is distributed or made available, you shall also include “Llama” at the\
\ beginning of any such AI model name.\nii. If you receive Llama Materials, or any\
\ derivative works thereof, from a Licensee as part of an integrated end user product,\
\ then Section 2 of this Agreement will not apply to you. \niii. You must retain\
\ in all copies of the Llama Materials that you distribute the following attribution\
\ notice within a “Notice” text file distributed as a part of such copies: “Llama\
\ 3.2 is licensed under the Llama 3.2 Community License, Copyright © Meta Platforms,\
\ Inc. All Rights Reserved.”\niv. Your use of the Llama Materials must comply with\
\ applicable laws and regulations (including trade compliance laws and regulations)\
\ and adhere to the Acceptable Use Policy for the Llama Materials (available at\
\ https://www.llama.com/llama3_2/use-policy), which is hereby incorporated by reference\
\ into this Agreement.\n \n2. Additional Commercial Terms. If, on the Llama 3.2\
\ version release date, the monthly active users of the products or services made\
\ available by or for Licensee, or Licensee’s affiliates, is greater than 700 million\
\ monthly active users in the preceding calendar month, you must request a license\
\ from Meta, which Meta may grant to you in its sole discretion, and you are not\
\ authorized to exercise any of the rights under this Agreement unless or until\
\ Meta otherwise expressly grants you such rights.\n3. Disclaimer of Warranty. UNLESS\
\ REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM\
\ ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS\
\ ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION,\
\ ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR\
\ PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING\
\ OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR\
\ USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\n4. Limitation of Liability.\
\ IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY,\
\ WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING\
\ OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL,\
\ INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE\
\ BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n5. Intellectual Property.\n\
a. No trademark licenses are granted under this Agreement, and in connection with\
\ the Llama Materials, neither Meta nor Licensee may use any name or mark owned\
\ by or associated with the other or any of its affiliates, except as required\
\ for reasonable and customary use in describing and redistributing the Llama Materials\
\ or as set forth in this Section 5(a). Meta hereby grants you a license to use\
\ “Llama” (the “Mark”) solely as required to comply with the last sentence of Section\
\ 1.b.i. You will comply with Meta’s brand guidelines (currently accessible at\
\ https://about.meta.com/brand/resources/meta/company-brand/). All goodwill arising\
\ out of your use of the Mark will inure to the benefit of Meta.\nb. Subject to\
\ Meta’s ownership of Llama Materials and derivatives made by or for Meta, with\
\ respect to any derivative works and modifications of the Llama Materials that\
\ are made by you, as between you and Meta, you are and will be the owner of such\
\ derivative works and modifications.\nc. If you institute litigation or other proceedings\
\ against Meta or any entity (including a cross-claim or counterclaim in a lawsuit)\
\ alleging that the Llama Materials or Llama 3.2 outputs or results, or any portion\
\ of any of the foregoing, constitutes infringement of intellectual property or\
\ other rights owned or licensable by you, then any licenses granted to you under\
\ this Agreement shall terminate as of the date such litigation or claim is filed\
\ or instituted. You will indemnify and hold harmless Meta from and against any\
\ claim by any third party arising out of or related to your use or distribution\
\ of the Llama Materials.\n6. Term and Termination. The term of this Agreement will\
\ commence upon your acceptance of this Agreement or access to the Llama Materials\
\ and will continue in full force and effect until terminated in accordance with\
\ the terms and conditions herein. Meta may terminate this Agreement if you are\
\ in breach of any term or condition of this Agreement. Upon termination of this\
\ Agreement, you shall delete and cease use of the Llama Materials. Sections 3,\
\ 4 and 7 shall survive the termination of this Agreement. \n7. Governing Law and\
\ Jurisdiction. This Agreement will be governed and construed under the laws of\
\ the State of California without regard to choice of law principles, and the UN\
\ Convention on Contracts for the International Sale of Goods does not apply to\
\ this Agreement. The courts of California shall have exclusive jurisdiction of\
\ any dispute arising out of this Agreement. \n### Llama 3.2 Acceptable Use Policy\n\
Meta is committed to promoting safe and fair use of its tools and features, including\
\ Llama 3.2. If you access or use Llama 3.2, you agree to this Acceptable Use Policy\
\ (“**Policy**”). The most recent copy of this policy can be found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\n\
#### Prohibited Uses\nWe want everyone to use Llama 3.2 safely and responsibly.\
\ You agree you will not use, or allow others to use, Llama 3.2 to:\n1. Violate\
\ the law or others’ rights, including to:\n 1. Engage in, promote, generate,\
\ contribute to, encourage, plan, incite, or further illegal or unlawful activity\
\ or content, such as:\n 1. Violence or terrorism\n 2. Exploitation\
\ or harm to children, including the solicitation, creation, acquisition, or dissemination\
\ of child exploitative content or failure to report Child Sexual Abuse Material\n\
\ 3. Human trafficking, exploitation, and sexual violence\n 4. The\
\ illegal distribution of information or materials to minors, including obscene\
\ materials, or failure to employ legally required age-gating in connection with\
\ such information or materials.\n 5. Sexual solicitation\n 6. Any\
\ other criminal activity\n 1. Engage in, promote, incite, or facilitate the\
\ harassment, abuse, threatening, or bullying of individuals or groups of individuals\n\
\ 2. Engage in, promote, incite, or facilitate discrimination or other unlawful\
\ or harmful conduct in the provision of employment, employment benefits, credit,\
\ housing, other economic benefits, or other essential goods and services\n 3.\
\ Engage in the unauthorized or unlicensed practice of any profession including,\
\ but not limited to, financial, legal, medical/health, or related professional\
\ practices\n 4. Collect, process, disclose, generate, or infer private or sensitive\
\ information about individuals, including information about individuals’ identity,\
\ health, or demographic information, unless you have obtained the right to do so\
\ in accordance with applicable law\n 5. Engage in or facilitate any action or\
\ generate any content that infringes, misappropriates, or otherwise violates any\
\ third-party rights, including the outputs or results of any products or services\
\ using the Llama Materials\n 6. Create, generate, or facilitate the creation\
\ of malicious code, malware, computer viruses or do anything else that could disable,\
\ overburden, interfere with or impair the proper working, integrity, operation\
\ or appearance of a website or computer system\n 7. Engage in any action, or\
\ facilitate any action, to intentionally circumvent or remove usage restrictions\
\ or other safety measures, or to enable functionality disabled by Meta \n2. Engage\
\ in, promote, incite, facilitate, or assist in the planning or development of activities\
\ that present a risk of death or bodily harm to individuals, including use of Llama\
\ 3.2 related to the following:\n 8. Military, warfare, nuclear industries or\
\ applications, espionage, use for materials or activities that are subject to the\
\ International Traffic Arms Regulations (ITAR) maintained by the United States\
\ Department of State or to the U.S. Biological Weapons Anti-Terrorism Act of 1989\
\ or the Chemical Weapons Convention Implementation Act of 1997\n 9. Guns and\
\ illegal weapons (including weapon development)\n 10. Illegal drugs and regulated/controlled\
\ substances\n 11. Operation of critical infrastructure, transportation technologies,\
\ or heavy machinery\n 12. Self-harm or harm to others, including suicide, cutting,\
\ and eating disorders\n 13. Any content intended to incite or promote violence,\
\ abuse, or any infliction of bodily harm to an individual\n3. Intentionally deceive\
\ or mislead others, including use of Llama 3.2 related to the following:\n 14.\
\ Generating, promoting, or furthering fraud or the creation or promotion of disinformation\n\
\ 15. Generating, promoting, or furthering defamatory content, including the\
\ creation of defamatory statements, images, or other content\n 16. Generating,\
\ promoting, or further distributing spam\n 17. Impersonating another individual\
\ without consent, authorization, or legal right\n 18. Representing that the\
\ use of Llama 3.2 or outputs are human-generated\n 19. Generating or facilitating\
\ false online engagement, including fake reviews and other means of fake online\
\ engagement \n4. Fail to appropriately disclose to end users any known dangers\
\ of your AI system 5. Interact with third party tools, models, or software designed\
\ to generate unlawful content or engage in unlawful or harmful conduct and/or represent\
\ that the outputs of such tools, models, or software are associated with Meta or\
\ Llama 3.2\n\nWith respect to any multimodal models included in Llama 3.2, the\
\ rights granted under Section 1(a) of the Llama 3.2 Community License Agreement\
\ are not being granted to you if you are an individual domiciled in, or a company\
\ with a principal place of business in, the European Union. This restriction does\
\ not apply to end users of a product or service that incorporates any such multimodal\
\ models.\n\nPlease report any violation of this Policy, software “bug,” or other\
\ problems that could lead to a violation of this Policy through one of the following\
\ means:\n\n* Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues&h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\n\
* Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\n\
* Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\n\
* Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama\
\ 3.2: [email protected]"
extra_gated_fields:
First Name: text
Last Name: text
Date of birth: date_picker
Country: country
Affiliation: text
Job title:
type: select
options:
- Student
- Research Graduate
- AI researcher
- AI developer/engineer
- Reporter
- Other
geo: ip_location
? By clicking Submit below I accept the terms of the license and acknowledge that
the information I provide will be collected stored processed and shared in accordance
with the Meta Privacy Policy
: checkbox
extra_gated_description: The information you provide will be collected, stored, processed
and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).
extra_gated_button_content: Submit
extra_gated_eu_disallowed: true
---
## Model Information
The Llama 3.2-Vision collection of multimodal large language models (LLMs) is a collection of pretrained and instruction-tuned image reasoning generative models in 11B and 90B sizes (text \+ images in / text out). The Llama 3.2-Vision instruction-tuned models are optimized for visual recognition, image reasoning, captioning, and answering general questions about an image. The models outperform many of the available open source and closed multimodal models on common industry benchmarks.
**Model Developer**: Meta
**Model Architecture:** Llama 3.2-Vision is built on top of Llama 3.1 text-only model, which is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety. To support image recognition tasks, the Llama 3.2-Vision model uses a separately trained vision adapter that integrates with the pre-trained Llama 3.1 language model. The adapter consists of a series of cross-attention layers that feed image encoder representations into the core LLM.
| | Training Data | Params | Input modalities | Output modalities | Context length | GQA | Data volume | Knowledge cutoff |
| :---- | :---- | :---- | :---- | :---- | :---- | :---- | :---- | :---- |
| Llama 3.2-Vision | (Image, text) pairs | 11B (10.6) | Text \+ Image | Text | 128k | Yes | 6B (image, text) pairs | December 2023 |
| Llama 3.2-Vision | (Image, text) pairs | 90B (88.8) | Text \+ Image | Text | 128k | Yes | 6B (image, text) pairs | December 2023 |
**Supported Languages:** For text only tasks, English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai are officially supported. Llama 3.2 has been trained on a broader collection of languages than these 8 supported languages. Note for image+text applications, English is the only language supported.
Developers may fine-tune Llama 3.2 models for languages beyond these supported languages, provided they comply with the Llama 3.2 Community License and the Acceptable Use Policy. Developers are always expected to ensure that their deployments, including those that involve additional languages, are completed safely and responsibly.
**Llama 3.2 Model Family:** Token counts refer to pretraining data only. All model versions use Grouped-Query Attention (GQA) for improved inference scalability.
**Model Release Date:** Sept 25, 2024
**Status:** This is a static model trained on an offline dataset. Future versions may be released that improve model capabilities and safety.
**License:** Use of Llama 3.2 is governed by the [Llama 3.2 Community License](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/LICENSE) (a custom, commercial license agreement).
**Feedback:** Where to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model [README](https://github.com/meta-llama/llama-models/tree/main/models/llama3_2). For more technical information about generation parameters and recipes for how to use Llama 3.2-Vision in applications, please go [here](https://github.com/meta-llama/llama-recipes).
## Intended Use
**Intended Use Cases:** Llama 3.2-Vision is intended for commercial and research use. Instruction tuned models are intended for visual recognition, image reasoning, captioning, and assistant-like chat with images, whereas pretrained models can be adapted for a variety of image reasoning tasks. Additionally, because of Llama 3.2-Vision’s ability to take images and text as inputs, additional use cases could include:
1. Visual Question Answering (VQA) and Visual Reasoning: Imagine a machine that looks at a picture and understands your questions about it.
2. Document Visual Question Answering (DocVQA): Imagine a computer understanding both the text and layout of a document, like a map or contract, and then answering questions about it directly from the image.
3. Image Captioning: Image captioning bridges the gap between vision and language, extracting details, understanding the scene, and then crafting a sentence or two that tells the story.
4. Image-Text Retrieval: Image-text retrieval is like a matchmaker for images and their descriptions. Similar to a search engine but one that understands both pictures and words.
5. Visual Grounding: Visual grounding is like connecting the dots between what we see and say. It’s about understanding how language references specific parts of an image, allowing AI models to pinpoint objects or regions based on natural language descriptions.
The Llama 3.2 model collection also supports the ability to leverage the outputs of its models to improve other models including synthetic data generation and distillation. The Llama 3.2 Community License allows for these use cases.
**Out of Scope:** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3.2 Community License. Use in languages beyond those explicitly referenced as supported in this model card.
## How to use
This repository contains two versions of Llama-3.2-11B-Vision, for use with transformers and with the original `llama` codebase.
### Use with transformers
Starting with transformers >= 4.45.0 onward, you can run inference to generate text based on an image and a starting prompt you supply.
Make sure to update your transformers installation via `pip install --upgrade transformers`.
```python
import requests
import torch
from PIL import Image
from transformers import MllamaForConditionalGeneration, AutoProcessor
model_id = "meta-llama/Llama-3.2-11B-Vision"
model = MllamaForConditionalGeneration.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
device_map="auto",
)
processor = AutoProcessor.from_pretrained(model_id)
url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/0052a70beed5bf71b92610a43a52df6d286cd5f3/diffusers/rabbit.jpg"
image = Image.open(requests.get(url, stream=True).raw)
prompt = "<|image|><|begin_of_text|>If I had to write a haiku for this one"
inputs = processor(image, prompt, return_tensors="pt").to(model.device)
output = model.generate(**inputs, max_new_tokens=30)
print(processor.decode(output[0]))
```
### Use with `llama`
Please, follow the instructions in the [repository](https://github.com/meta-llama/llama).
To download the original checkpoints, you can use `huggingface-cli` as follows:
```
huggingface-cli download meta-llama/Llama-3.2-11B-Vision --include "original/*" --local-dir Llama-3.2-11B-Vision
```
## Hardware and Software
**Training Factors:** We used custom training libraries, Meta's custom built GPU cluster, and production infrastructure for pretraining. Fine-tuning, annotation, and evaluation were also performed on production infrastructure.
**Training Energy Use:** Training utilized a cumulative of **2.02M** GPU hours of computation on H100-80GB (TDP of 700W) type hardware, per the table below. Training time is the total GPU time required for training each model and power consumption is the peak power capacity per GPU device used, adjusted for power usage efficiency.
##
**Training Greenhouse Gas Emissions:** Estimated total location-based greenhouse gas emissions were **584** tons CO2eq for training. Since 2020, Meta has maintained net zero greenhouse gas emissions in its global operations and matched 100% of its electricity use with renewable energy, therefore the total market-based greenhouse gas emissions for training were 0 tons CO2eq.
| | Training Time (GPU hours) | Training Power Consumption (W) | Training Location-Based Greenhouse Gas Emissions (tons CO2eq) | Training Market-Based Greenhouse Gas Emissions (tons CO2eq) |
| :---- | :---: | :---: | :---: | :---: |
| Llama 3.2-vision 11B | Stage 1 pretraining: 147K H100 hours Stage 2 annealing: 98K H100 hours SFT: 896 H100 hours RLHF: 224 H100 hours | 700 | 71 | 0 |
| Llama 3.2-vision 90B | Stage 1 pretraining: 885K H100 hours Stage 2 annealing: 885K H100 hours SFT: 3072 H100 hours RLHF: 2048 H100 hours | 700 | 513 | 0 |
| Total | 2.02M | | 584 | 0 |
The methodology used to determine training energy use and greenhouse gas emissions can be found [here](https://arxiv.org/pdf/2204.05149). Since Meta is openly releasing these models, the training energy use and greenhouse gas emissions will not be incurred by others.
## Training Data
**Overview:** Llama 3.2-Vision was pretrained on 6B image and text pairs. The instruction tuning data includes publicly available vision instruction datasets, as well as over 3M synthetically generated examples.
**Data Freshness:** The pretraining data has a cutoff of December 2023\.
## Benchmarks \- Image Reasoning
In this section, we report the results for Llama 3.2-Vision models on standard automatic benchmarks. For all these evaluations, we used our internal evaluations library.
### Base Pretrained Models
| Category | Benchmark | \# Shots | Metric | Llama 3.2 11B | Llama 3.2 90B |
| ----- | ----- | ----- | ----- | ----- | ----- |
| Image Understanding | VQAv2 (val) | 0 | Accuracy | 66.8 | 73.6 |
| | Text VQA (val) | 0 | Relaxed accuracy | 73.1 | 73.5 |
| | DocVQA (val, unseen) | 0 | ANLS | 62.3 | 70.7 |
| Visual Reasoning | MMMU (val, 0-shot) | 0 | Micro average accuracy | 41.7 | 49.3 |
| | ChartQA (test) | 0 | Accuracy | 39.4 | 54.2 |
| | InfographicsQA (val, unseen) | 0 | ANLS | 43.2 | 56.8 |
| | AI2 Diagram (test) | 0 | Accuracy | 62.4 | 75.3 |
### Instruction Tuned Models
| Modality | Capability | Benchmark | \# Shots | Metric | Llama 3.2 11B | Llama 3.2 90B |
| ----- | :---: | ----- | :---: | :---: | ----- | ----- |
| Image | College-level Problems and Mathematical Reasoning | MMMU (val, CoT) | 0 | Micro average accuracy | 50.7 | 60.3 |
| | | MMMU-Pro, Standard (10 opts, test) | 0 | Accuracy | 33.0 | 45.2 |
| | | MMMU-Pro, Vision (test) | 0 | Accuracy | 23.7 | 33.8 |
| | | MathVista (testmini) | 0 | Accuracy | 51.5 | 57.3 |
| | Charts and Diagram Understanding | ChartQA (test, CoT) | 0 | Relaxed accuracy | 83.4 | 85.5 |
| | | AI2 Diagram (test) | 0 | Accuracy | 91.1 | 92.3 |
| | | DocVQA (test) | 0 | ANLS | 88.4 | 90.1 |
| | General Visual Question Answering | VQAv2 (test) | 0 | Accuracy | 75.2 | 78.1 |
| | | | | | | |
| Text | General | MMLU (CoT) | 0 | Macro\_avg/acc | 73.0 | 86.0 |
| | Math | MATH (CoT) | 0 | Final\_em | 51.9 | 68.0 |
| | Reasoning | GPQA | 0 | Accuracy | 32.8 | 46.7 |
| | Multilingual | MGSM (CoT) | 0 | em | 68.9 | 86.9 |
## Responsibility & Safety
As part of our Responsible release approach, we followed a three-pronged strategy to managing trust & safety risks:
1. Enable developers to deploy helpful, safe and flexible experiences for their target audience and for the use cases supported by Llama.
2. Protect developers against adversarial users aiming to exploit Llama capabilities to potentially cause harm.
3. Provide protections for the community to help prevent the misuse of our models.
### Responsible Deployment
**Approach:** Llama is a foundational technology designed to be used in a variety of use cases, examples on how Meta’s Llama models have been responsibly deployed can be found in our [Community Stories webpage](https://llama.meta.com/community-stories/). Our approach is to build the most helpful models enabling the world to benefit from the technology power, by aligning our model safety for the generic use cases addressing a standard set of harms. Developers are then in the driver seat to tailor safety for their use case, defining their own policy and deploying the models with the necessary safeguards in their Llama systems. Llama 3.2 was developed following the best practices outlined in our Responsible Use Guide, you can refer to the [Responsible Use Guide](https://llama.meta.com/responsible-use-guide/) to learn more.
#### Llama 3.2 Instruct
**Objective:** Our main objectives for conducting safety fine-tuning are to provide the research community with a valuable resource for studying the robustness of safety fine-tuning, as well as to offer developers a readily available, safe, and powerful model for various applications to reduce the developer workload to deploy safe AI systems. We implemented the same set of safety mitigations as in Llama 3, and you can learn more about these in the Llama 3 [paper](https://ai.meta.com/research/publications/the-llama-3-herd-of-models/).
**Fine-Tuning Data:** We employ a multi-faceted approach to data collection, combining human-generated data from our vendors with synthetic data to mitigate potential safety risks. We’ve developed many large language model (LLM)-based classifiers that enable us to thoughtfully select high-quality prompts and responses, enhancing data quality control.
**Refusals and Tone:** Building on the work we started with Llama 3, we put a great emphasis on model refusals to benign prompts as well as refusal tone. We included both borderline and adversarial prompts in our safety data strategy, and modified our safety data responses to follow tone guidelines.
#### Llama 3.2 Systems
**Safety as a System:** Large language models, including Llama 3.2, **are not designed to be deployed in isolation** but instead should be deployed as part of an overall AI system with additional safety guardrails as required. Developers are expected to deploy system safeguards when building agentic systems. Safeguards are key to achieve the right helpfulness-safety alignment as well as mitigating safety and security risks inherent to the system and any integration of the model or system with external tools. As part of our responsible release approach, we provide the community with [safeguards](https://llama.meta.com/trust-and-safety/) that developers should deploy with Llama models or other LLMs, including Llama Guard, Prompt Guard and Code Shield. All our [reference implementations](https://github.com/meta-llama/llama-agentic-system) demos contain these safeguards by default so developers can benefit from system-level safety out-of-the-box.
### New Capabilities and Use Cases
**Technological Advancement:** Llama releases usually introduce new capabilities that require specific considerations in addition to the best practices that generally apply across all Generative AI use cases. For prior release capabilities also supported by Llama 3.2, see [Llama 3.1 Model Card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/MODEL_CARD.md), as the same considerations apply here as well.,
**Image Reasoning:** Llama 3.2-Vision models come with multimodal (text and image) input capabilities enabling image reasoning applications. As part of our responsible release process, we took dedicated measures including evaluations and mitigations to address the risk of the models uniquely identifying individuals in images. As with other LLM risks, models may not always be robust to adversarial prompts, and developers should evaluate identification and other applicable risks in the context of their applications as well as consider deploying Llama Guard 3-11B-Vision as part of their system or other mitigations as appropriate to detect and mitigate such risks.
### Evaluations
**Scaled Evaluations:** We built dedicated, adversarial evaluation datasets and evaluated systems composed of Llama models and Purple Llama safeguards to filter input prompt and output response. It is important to evaluate applications in context, and we recommend building dedicated evaluation dataset for your use case.
**Red teaming:** We conducted recurring red teaming exercises with the goal of discovering risks via adversarial prompting and we used the learnings to improve our benchmarks and safety tuning datasets. We partnered early with subject-matter experts in critical risk areas to understand the nature of these real-world harms and how such models may lead to unintended harm for society. Based on these conversations, we derived a set of adversarial goals for the red team to attempt to achieve, such as extracting harmful information or reprogramming the model to act in a potentially harmful capacity. The red team consisted of experts in cybersecurity, adversarial machine learning, responsible AI, and integrity in addition to multilingual content specialists with background in integrity issues in specific geographic markets.
### Critical Risks
In addition to our safety work above, we took extra care on measuring and/or mitigating the following critical risk areas:
**1\. CBRNE (Chemical, Biological, Radiological, Nuclear, and Explosive Weapons):** For Llama 3.1, to assess risks related to proliferation of chemical and biological weapons, we performed uplift testing designed to assess whether use of Llama 3.1 models could meaningfully increase the capabilities of malicious actors to plan or carry out attacks using these types of weapons. For Llama 3.2-Vision models, we conducted additional targeted evaluations and found that it was unlikely Llama 3.2 presented an increase in scientific capabilities due to its added image understanding capability as compared to Llama 3.1.
**2\. Child Safety:** Child Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors including the additional languages Llama 3 is trained on. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.
**3\. Cyber Attacks:** For Llama 3.1 405B, our cyber attack uplift study investigated whether LLMs can enhance human capabilities in hacking tasks, both in terms of skill level and speed.
Our attack automation study focused on evaluating the capabilities of LLMs when used as autonomous agents in cyber offensive operations, specifically in the context of ransomware attacks. This evaluation was distinct from previous studies that considered LLMs as interactive assistants. The primary objective was to assess whether these models could effectively function as independent agents in executing complex cyber-attacks without human intervention. Because Llama 3.2’s vision capabilities are not generally germane to cyber uplift, we believe that the testing conducted for Llama 3.1 also applies to Llama 3.2.
### Community
**Industry Partnerships:** Generative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership on AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our [Github repository](https://github.com/meta-llama/PurpleLlama).
**Grants:** We also set up the [Llama Impact Grants](https://llama.meta.com/llama-impact-grants/) program to identify and support the most compelling applications of Meta’s Llama model for societal benefit across three categories: education, climate and open innovation. The 20 finalists from the hundreds of applications can be found [here](https://llama.meta.com/llama-impact-grants/#finalists).
**Reporting:** Finally, we put in place a set of resources including an [output reporting mechanism](https://developers.facebook.com/llama_output_feedback) and [bug bounty program](https://www.facebook.com/whitehat) to continuously improve the Llama technology with the help of the community.
## Ethical Considerations and Limitations
**Values:** The core values of Llama 3.2 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3.2 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.
**Testing:** But Llama 3.2 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3.2’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3.2 models, developers should perform safety testing and tuning tailored to their specific applications of the model. Please refer to available resources including our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide), [Trust and Safety](https://llama.meta.com/trust-and-safety/) solutions, and other [resources](https://llama.meta.com/docs/get-started/) to learn more about responsible development.
| [
"QUESTION_ANSWERING"
] | Non_BioNLP |
DarkClaw42/Llama-3-Translation-8B-v0.180-Q5_K_M-GGUF | DarkClaw42 | text-generation | [
"transformers",
"gguf",
"pytorch",
"instruct",
"finetune",
"translation",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"ko",
"base_model:lemon-mint/Llama-3-Translation-8B-v0.180",
"base_model:quantized:lemon-mint/Llama-3-Translation-8B-v0.180",
"license:llama3",
"endpoints_compatible",
"region:us",
"conversational"
] | 1,722,129,033,000 | 2024-07-28T01:17:28 | 9 | 0 | ---
base_model: lemon-mint/Llama-3-Translation-8B-v0.180
language:
- ko
library_name: transformers
license: llama3
pipeline_tag: text-generation
tags:
- pytorch
- instruct
- finetune
- translation
- llama-cpp
- gguf-my-repo
widget:
- messages:
- role: user
content: Translate into Korean:Hamsters don't eat cats.
---
# DarkClaw42/Llama-3-Translation-8B-v0.180-Q5_K_M-GGUF
This model was converted to GGUF format from [`lemon-mint/Llama-3-Translation-8B-v0.180`](https://huggingface.co/lemon-mint/Llama-3-Translation-8B-v0.180) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/lemon-mint/Llama-3-Translation-8B-v0.180) for more details on the model.
Llama 3 Translation 8B v0.180
Eval Loss: 0.69922
Train Loss: 0.65752
lr: 8e-05
optimizer: adamw
lr_scheduler_type: cosine
#Prompt Template
<|begin_of_text|><|im_start|>user
Translate into Korean:Hamsters don't eat cats.<|im_end|>
<|im_start|>assistant
햄스터는 고양이를 먹지 않습니다.<|im_end|><|end_of_text|>
<|begin_of_text|><|im_start|>user
Translate into English:햄스터는 고양이를 먹지 않습니다.<|im_end|>
<|im_start|>assistant
Hamsters do not eat cats.<|im_end|><|end_of_text|>
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo DarkClaw42/Llama-3-Translation-8B-v0.180-Q5_K_M-GGUF --hf-file llama-3-translation-8b-v0.180-q5_k_m.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo DarkClaw42/Llama-3-Translation-8B-v0.180-Q5_K_M-GGUF --hf-file llama-3-translation-8b-v0.180-q5_k_m.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo DarkClaw42/Llama-3-Translation-8B-v0.180-Q5_K_M-GGUF --hf-file llama-3-translation-8b-v0.180-q5_k_m.gguf -p "<|begin_of_text|><|im_start|>user
Translate into Korean:Hamsters don't eat cats.<|im_end|>"
```
or
```
./llama-server --hf-repo DarkClaw42/Llama-3-Translation-8B-v0.180-Q5_K_M-GGUF --hf-file llama-3-translation-8b-v0.180-q5_k_m.gguf -c 2048
```
| [
"TRANSLATION"
] | Non_BioNLP |
klcsp/gemma7b-fft-summarization-11-v1 | klcsp | text-generation | [
"transformers",
"tensorboard",
"safetensors",
"gemma",
"text-generation",
"trl",
"sft",
"generated_from_trainer",
"conversational",
"dataset:generator",
"base_model:google/gemma-7b",
"base_model:finetune:google/gemma-7b",
"license:gemma",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 1,732,244,339,000 | 2024-11-22T03:20:28 | 5 | 0 | ---
base_model: google/gemma-7b
datasets:
- generator
library_name: transformers
license: gemma
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: gemma7b-fft-summarization-11-v1
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# gemma7b-fft-summarization-11-v1
This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 2.7200
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- total_eval_batch_size: 64
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 0.7827 | 0.9932 | 109 | 2.7200 |
### Framework versions
- Transformers 4.46.3
- Pytorch 2.3.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3
| [
"SUMMARIZATION"
] | Non_BioNLP |
samy-hadj/bioBertFineTuned | samy-hadj | null | [
"safetensors",
"bert",
"region:us"
] | 1,733,426,851,000 | 2024-12-05T19:44:51 | 4 | 0 | ---
{}
---
# BioBERT Fine-Tuned
## Model Description
This model is a fine-tuned version of **BioBERT**, a pre-trained biomedical language model, adapted for **medical text classification**. It classifies medical abstracts into predefined categories based on their content.
## Training Data
- **Dataset**: Contains **2286 medical abstracts** across five categories:
- Neoplasms
- Digestive System Diseases
- Nervous System Diseases
- Cardiovascular Diseases
- General Pathological Conditions
- **Preprocessing**: Includes normalization, lemmatization, tokenization, stopword removal, and medical term standardization.
## Intended Use
- **Medical Text Classification**: This model can be used for categorizing medical abstracts and research papers into relevant medical departments.
## Limitations
- **Not suitable for general-purpose NLP tasks**.
- **Domain-specific**: The model may not perform well outside the medical field or with non-English text. | [
"TEXT_CLASSIFICATION"
] | BioNLP |
KristupasC/bge-base-financial-matryoshka | KristupasC | sentence-similarity | [
"sentence-transformers",
"safetensors",
"bert",
"sentence-similarity",
"feature-extraction",
"generated_from_trainer",
"dataset_size:6300",
"loss:MatryoshkaLoss",
"loss:MultipleNegativesRankingLoss",
"en",
"arxiv:1908.10084",
"arxiv:2205.13147",
"arxiv:1705.00652",
"base_model:BAAI/bge-base-en-v1.5",
"base_model:finetune:BAAI/bge-base-en-v1.5",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] | 1,742,119,118,000 | 2025-03-16T09:58:58 | 4 | 0 | ---
base_model: BAAI/bge-base-en-v1.5
language:
- en
library_name: sentence-transformers
license: apache-2.0
metrics:
- cosine_accuracy@1
- cosine_accuracy@3
- cosine_accuracy@5
- cosine_accuracy@10
- cosine_precision@1
- cosine_precision@3
- cosine_precision@5
- cosine_precision@10
- cosine_recall@1
- cosine_recall@3
- cosine_recall@5
- cosine_recall@10
- cosine_ndcg@10
- cosine_mrr@10
- cosine_map@100
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:6300
- loss:MatryoshkaLoss
- loss:MultipleNegativesRankingLoss
widget:
- source_sentence: The Parisian Macao saw its occupancy rate increase significantly
from 37.9% in 2022 to 93.0% in 2023.
sentences:
- Who is the Chief People Officer of this company and what are their responsibilities?
- What was the occupancy rate change at The Parisian Macao from 2022 to 2023?
- What components make up the mall-related expenses?
- source_sentence: According to Item 8, the Financial Statement Schedule is located
on page S-1 of IBM’s Form 10-K.
sentences:
- In IBM’s Form 10-K filing, where is the Financial Statement Schedule located?
- What was the total amount repurchased by the company in fiscal years 2022 and
2023 under the share repurchase program?
- What was the net cash position change due to exchange rate effects during the
year in the financial data?
- source_sentence: A hypothetical 50% decrease in short-term interest rates would
decrease our annual pre-tax earnings by $15 million as of December 31, 2023, assuming
no change in the amount or composition of our cash and cash equivalents and short-term
and long-term restricted cash and cash equivalents.
sentences:
- What financial impact would a 50% decrease in short-term interest rates have on
the company's annual pre-tax earnings as of December 31, 2023?
- What are the typical higher sales quarters for companies due to seasonal and holiday-related
sales patterns?
- What triggers the company to accrue for the cost of product recalls and corrective
actions?
- source_sentence: 'Our strategy is focused on growing customer loyalty by delivering
great value and convenience, and investing in four strategic pillars: Fresh, Our
Brands, Data & Personalization and Seamless.'
sentences:
- What was the percentage change in impairment of goodwill for Hewlett Packard Enterprise
between fiscal 2022 and 2023?
- What are Kroger’s four strategic pillars?
- How much did the foreclosed properties decrease in value during 2023?
- source_sentence: The Inflation Reduction Act of 2022 has and will continue to have
a significant impact on how drugs are covered and paid for under the Medicare
program, including through the creation of financial penalties for drugs whose
price increases outpace inflation, the redesign of Medicare Part D benefits to
shift a greater portion of the costs to manufacturers, and through government
price-setting for certain Medicare Part B and Part D drugs.
sentences:
- What was the total depreciation and amortization expense for the company in 2023?
- What overall context does Item 3. Legal Proceedings offer regarding the company?
- How does the Inflation Reduction Act of 2022 impact AbbVie's drug pricing under
Medicare?
model-index:
- name: BGE base Financial Matryoshka
results:
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 768
type: dim_768
metrics:
- type: cosine_accuracy@1
value: 0.7357142857142858
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.8728571428571429
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.9014285714285715
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.9271428571428572
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.7357142857142858
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.29095238095238096
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.18028571428571427
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.09271428571428571
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.7357142857142858
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.8728571428571429
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.9014285714285715
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.9271428571428572
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.8376503331859739
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.8083339002267572
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.8113126406613911
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 512
type: dim_512
metrics:
- type: cosine_accuracy@1
value: 0.7328571428571429
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.87
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.8985714285714286
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.9271428571428572
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.7328571428571429
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.29
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.1797142857142857
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.09271428571428571
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.7328571428571429
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.87
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.8985714285714286
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.9271428571428572
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.8361443346673566
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.8063117913832198
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.80919006196483
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 256
type: dim_256
metrics:
- type: cosine_accuracy@1
value: 0.7228571428571429
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.8642857142857143
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.8971428571428571
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.9214285714285714
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.7228571428571429
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.2880952380952381
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.1794285714285714
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.09214285714285714
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.7228571428571429
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.8642857142857143
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.8971428571428571
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.9214285714285714
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.8293858846039718
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.7991496598639453
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.802093445052298
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 128
type: dim_128
metrics:
- type: cosine_accuracy@1
value: 0.7142857142857143
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.85
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.88
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.91
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.7142857142857143
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.2833333333333333
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.176
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.09099999999999998
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.7142857142857143
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.85
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.88
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.91
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.8170618027193949
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.7867528344671202
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.7900596429177168
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 64
type: dim_64
metrics:
- type: cosine_accuracy@1
value: 0.6614285714285715
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.8157142857142857
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.85
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.8928571428571429
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.6614285714285715
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.27190476190476187
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.16999999999999998
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.08928571428571427
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.6614285714285715
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.8157142857142857
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.85
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.8928571428571429
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.7826677679629053
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.7468339002267574
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.7512201171926934
name: Cosine Map@100
---
# BGE base Financial Matryoshka
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) on the json dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
## Model Details
### Model Description
- **Model Type:** Sentence Transformer
- **Base model:** [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) <!-- at revision a5beb1e3e68b9ab74eb54cfd186867f64f240e1a -->
- **Maximum Sequence Length:** 512 tokens
- **Output Dimensionality:** 768 dimensions
- **Similarity Function:** Cosine Similarity
- **Training Dataset:**
- json
- **Language:** en
- **License:** apache-2.0
### Model Sources
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
### Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
(2): Normalize()
)
```
## Usage
### Direct Usage (Sentence Transformers)
First install the Sentence Transformers library:
```bash
pip install -U sentence-transformers
```
Then you can load this model and run inference.
```python
from sentence_transformers import SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("KristupasC/bge-base-financial-matryoshka")
# Run inference
sentences = [
'The Inflation Reduction Act of 2022 has and will continue to have a significant impact on how drugs are covered and paid for under the Medicare program, including through the creation of financial penalties for drugs whose price increases outpace inflation, the redesign of Medicare Part D benefits to shift a greater portion of the costs to manufacturers, and through government price-setting for certain Medicare Part B and Part D drugs.',
"How does the Inflation Reduction Act of 2022 impact AbbVie's drug pricing under Medicare?",
'What overall context does Item 3. Legal Proceedings offer regarding the company?',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]
```
<!--
### Direct Usage (Transformers)
<details><summary>Click to see the direct usage in Transformers</summary>
</details>
-->
<!--
### Downstream Usage (Sentence Transformers)
You can finetune this model on your own dataset.
<details><summary>Click to expand</summary>
</details>
-->
<!--
### Out-of-Scope Use
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->
## Evaluation
### Metrics
#### Information Retrieval
* Datasets: `dim_768`, `dim_512`, `dim_256`, `dim_128` and `dim_64`
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
| Metric | dim_768 | dim_512 | dim_256 | dim_128 | dim_64 |
|:--------------------|:-----------|:-----------|:-----------|:-----------|:-----------|
| cosine_accuracy@1 | 0.7357 | 0.7329 | 0.7229 | 0.7143 | 0.6614 |
| cosine_accuracy@3 | 0.8729 | 0.87 | 0.8643 | 0.85 | 0.8157 |
| cosine_accuracy@5 | 0.9014 | 0.8986 | 0.8971 | 0.88 | 0.85 |
| cosine_accuracy@10 | 0.9271 | 0.9271 | 0.9214 | 0.91 | 0.8929 |
| cosine_precision@1 | 0.7357 | 0.7329 | 0.7229 | 0.7143 | 0.6614 |
| cosine_precision@3 | 0.291 | 0.29 | 0.2881 | 0.2833 | 0.2719 |
| cosine_precision@5 | 0.1803 | 0.1797 | 0.1794 | 0.176 | 0.17 |
| cosine_precision@10 | 0.0927 | 0.0927 | 0.0921 | 0.091 | 0.0893 |
| cosine_recall@1 | 0.7357 | 0.7329 | 0.7229 | 0.7143 | 0.6614 |
| cosine_recall@3 | 0.8729 | 0.87 | 0.8643 | 0.85 | 0.8157 |
| cosine_recall@5 | 0.9014 | 0.8986 | 0.8971 | 0.88 | 0.85 |
| cosine_recall@10 | 0.9271 | 0.9271 | 0.9214 | 0.91 | 0.8929 |
| **cosine_ndcg@10** | **0.8377** | **0.8361** | **0.8294** | **0.8171** | **0.7827** |
| cosine_mrr@10 | 0.8083 | 0.8063 | 0.7991 | 0.7868 | 0.7468 |
| cosine_map@100 | 0.8113 | 0.8092 | 0.8021 | 0.7901 | 0.7512 |
<!--
## Bias, Risks and Limitations
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
-->
<!--
### Recommendations
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
-->
## Training Details
### Training Dataset
#### json
* Dataset: json
* Size: 6,300 training samples
* Columns: <code>positive</code> and <code>anchor</code>
* Approximate statistics based on the first 1000 samples:
| | positive | anchor |
|:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
| type | string | string |
| details | <ul><li>min: 9 tokens</li><li>mean: 46.27 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 10 tokens</li><li>mean: 20.79 tokens</li><li>max: 51 tokens</li></ul> |
* Samples:
| positive | anchor |
|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------|
| <code>As of December 31, 2023, we owned 4,325 shares of common stock of Tractor Beverages, Inc. (“Tractor”). Our investment represents ownership of approximately 10.2% of Tractor, and we have invested total cash consideration of $10,000. There were no impairment charges for the year ended December 31, 2023 or 2022 associated with this equity method investment.</code> | <code>What financial performance metrics are reported for equity investments in Tractor Beverages, Inc. as of December 31, 2023?</code> |
| <code>Sales of Alphagan/Combigan in the United States decreased by 40.1% from $373 million in 2021 to $121 million in 2023.</code> | <code>What was the percentage decrease in sales for Alphagan/Combigan in the United States from 2021 to 2023?</code> |
| <code>For the year ended December 31, 2023, the net cash provided by (used in) investing activities totaled -$49,833 million.</code> | <code>What was the net cash impact from investing activities for the year ended December 31, 2023?</code> |
* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
```json
{
"loss": "MultipleNegativesRankingLoss",
"matryoshka_dims": [
768,
512,
256,
128,
64
],
"matryoshka_weights": [
1,
1,
1,
1,
1
],
"n_dims_per_step": -1
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `eval_strategy`: epoch
- `per_device_train_batch_size`: 16
- `per_device_eval_batch_size`: 16
- `gradient_accumulation_steps`: 8
- `learning_rate`: 2e-05
- `num_train_epochs`: 4
- `lr_scheduler_type`: cosine
- `warmup_ratio`: 0.1
- `fp16`: True
- `tf32`: False
- `load_best_model_at_end`: True
- `optim`: adamw_torch_fused
- `batch_sampler`: no_duplicates
#### All Hyperparameters
<details><summary>Click to expand</summary>
- `overwrite_output_dir`: False
- `do_predict`: False
- `eval_strategy`: epoch
- `prediction_loss_only`: True
- `per_device_train_batch_size`: 16
- `per_device_eval_batch_size`: 16
- `per_gpu_train_batch_size`: None
- `per_gpu_eval_batch_size`: None
- `gradient_accumulation_steps`: 8
- `eval_accumulation_steps`: None
- `learning_rate`: 2e-05
- `weight_decay`: 0.0
- `adam_beta1`: 0.9
- `adam_beta2`: 0.999
- `adam_epsilon`: 1e-08
- `max_grad_norm`: 1.0
- `num_train_epochs`: 4
- `max_steps`: -1
- `lr_scheduler_type`: cosine
- `lr_scheduler_kwargs`: {}
- `warmup_ratio`: 0.1
- `warmup_steps`: 0
- `log_level`: passive
- `log_level_replica`: warning
- `log_on_each_node`: True
- `logging_nan_inf_filter`: True
- `save_safetensors`: True
- `save_on_each_node`: False
- `save_only_model`: False
- `restore_callback_states_from_checkpoint`: False
- `no_cuda`: False
- `use_cpu`: False
- `use_mps_device`: False
- `seed`: 42
- `data_seed`: None
- `jit_mode_eval`: False
- `use_ipex`: False
- `bf16`: False
- `fp16`: True
- `fp16_opt_level`: O1
- `half_precision_backend`: auto
- `bf16_full_eval`: False
- `fp16_full_eval`: False
- `tf32`: False
- `local_rank`: 0
- `ddp_backend`: None
- `tpu_num_cores`: None
- `tpu_metrics_debug`: False
- `debug`: []
- `dataloader_drop_last`: False
- `dataloader_num_workers`: 0
- `dataloader_prefetch_factor`: None
- `past_index`: -1
- `disable_tqdm`: False
- `remove_unused_columns`: True
- `label_names`: None
- `load_best_model_at_end`: True
- `ignore_data_skip`: False
- `fsdp`: []
- `fsdp_min_num_params`: 0
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
- `fsdp_transformer_layer_cls_to_wrap`: None
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
- `deepspeed`: None
- `label_smoothing_factor`: 0.0
- `optim`: adamw_torch_fused
- `optim_args`: None
- `adafactor`: False
- `group_by_length`: False
- `length_column_name`: length
- `ddp_find_unused_parameters`: None
- `ddp_bucket_cap_mb`: None
- `ddp_broadcast_buffers`: False
- `dataloader_pin_memory`: True
- `dataloader_persistent_workers`: False
- `skip_memory_metrics`: True
- `use_legacy_prediction_loop`: False
- `push_to_hub`: False
- `resume_from_checkpoint`: None
- `hub_model_id`: None
- `hub_strategy`: every_save
- `hub_private_repo`: False
- `hub_always_push`: False
- `gradient_checkpointing`: False
- `gradient_checkpointing_kwargs`: None
- `include_inputs_for_metrics`: False
- `eval_do_concat_batches`: True
- `fp16_backend`: auto
- `push_to_hub_model_id`: None
- `push_to_hub_organization`: None
- `mp_parameters`:
- `auto_find_batch_size`: False
- `full_determinism`: False
- `torchdynamo`: None
- `ray_scope`: last
- `ddp_timeout`: 1800
- `torch_compile`: False
- `torch_compile_backend`: None
- `torch_compile_mode`: None
- `dispatch_batches`: None
- `split_batches`: None
- `include_tokens_per_second`: False
- `include_num_input_tokens_seen`: False
- `neftune_noise_alpha`: None
- `optim_target_modules`: None
- `batch_eval_metrics`: False
- `prompts`: None
- `batch_sampler`: no_duplicates
- `multi_dataset_batch_sampler`: proportional
</details>
### Training Logs
| Epoch | Step | Training Loss | dim_768_cosine_ndcg@10 | dim_512_cosine_ndcg@10 | dim_256_cosine_ndcg@10 | dim_128_cosine_ndcg@10 | dim_64_cosine_ndcg@10 |
|:----------:|:-------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|
| 0.2030 | 10 | 1.2662 | - | - | - | - | - |
| 0.4061 | 20 | 0.7152 | - | - | - | - | - |
| 0.6091 | 30 | 0.4379 | - | - | - | - | - |
| 0.8122 | 40 | 0.3736 | - | - | - | - | - |
| 0.9949 | 49 | - | 0.8274 | 0.8270 | 0.8210 | 0.8048 | 0.7694 |
| 1.0152 | 50 | 0.3089 | - | - | - | - | - |
| 1.2183 | 60 | 0.3021 | - | - | - | - | - |
| 1.4213 | 70 | 0.2266 | - | - | - | - | - |
| 1.6244 | 80 | 0.2479 | - | - | - | - | - |
| 1.8274 | 90 | 0.2192 | - | - | - | - | - |
| 1.9898 | 98 | - | 0.8372 | 0.8346 | 0.8281 | 0.8141 | 0.7859 |
| 2.0305 | 100 | 0.2252 | - | - | - | - | - |
| 2.2335 | 110 | 0.1724 | - | - | - | - | - |
| 2.4365 | 120 | 0.1553 | - | - | - | - | - |
| 2.6396 | 130 | 0.151 | - | - | - | - | - |
| 2.8426 | 140 | 0.1794 | - | - | - | - | - |
| 2.9848 | 147 | - | 0.8368 | 0.8346 | 0.8298 | 0.8157 | 0.7836 |
| 3.0457 | 150 | 0.1716 | - | - | - | - | - |
| 3.2487 | 160 | 0.1246 | - | - | - | - | - |
| 3.4518 | 170 | 0.1698 | - | - | - | - | - |
| 3.6548 | 180 | 0.1108 | - | - | - | - | - |
| 3.8579 | 190 | 0.1881 | - | - | - | - | - |
| **3.9797** | **196** | **-** | **0.8377** | **0.8361** | **0.8294** | **0.8171** | **0.7827** |
* The bold row denotes the saved checkpoint.
### Framework Versions
- Python: 3.11.11
- Sentence Transformers: 3.4.1
- Transformers: 4.41.2
- PyTorch: 2.1.2+cu121
- Accelerate: 1.3.0
- Datasets: 2.19.1
- Tokenizers: 0.19.1
## Citation
### BibTeX
#### Sentence Transformers
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "https://arxiv.org/abs/1908.10084",
}
```
#### MatryoshkaLoss
```bibtex
@misc{kusupati2024matryoshka,
title={Matryoshka Representation Learning},
author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
year={2024},
eprint={2205.13147},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
```
#### MultipleNegativesRankingLoss
```bibtex
@misc{henderson2017efficient,
title={Efficient Natural Language Response Suggestion for Smart Reply},
author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
year={2017},
eprint={1705.00652},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
<!--
## Glossary
*Clearly define terms in order to be accessible across audiences.*
-->
<!--
## Model Card Authors
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->
<!--
## Model Card Contact
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
--> | [
"TEXT_CLASSIFICATION"
] | Non_BioNLP |
rasauq1122/t5-small-custom | rasauq1122 | null | [
"safetensors",
"t5",
"region:us"
] | 1,726,415,012,000 | 2024-09-16T11:23:14 | 7 | 0 | ---
{}
---
# Model Card for t5_small Summarization Model
## Model Details
This model is a fine-tuned version of T5-small-base for summarization.
## Training Data
The model was trained on the CNN/Daily mail dataset
## Training Procedure
- **Epochs**: 1
## How to Use
```python
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("summarization")
model = AutoModelForSeq2SeqLM.from_pretrained("summarization")
input_text = "The movie was fantastic with a gripping storyline!"
inputs = tokenizer.encode(input_text, return_tensors="pt")
outputs = model(inputs)
```
## Evaluation
- **BLEU-4**: 42.86
## Limitations
The model may generate biased or inappropriate content
due to the nature of the training data.
It is recommended to use the model with caution and apply necessary filters.
## Ethical Considerations
- **Bias**: The model may inherit biases present in the training data.
- **Misuse**: The model can be misused to generate misleading or harmful content.
## Copyright and License
This model is licensed under the MIT License.
| [
"SUMMARIZATION"
] | Non_BioNLP |
TheBloke/airoboros-l2-7B-gpt4-m2.0-GPTQ | TheBloke | text-generation | [
"transformers",
"safetensors",
"llama",
"text-generation",
"dataset:jondurbin/airoboros-gpt4-m2.0",
"base_model:jondurbin/airoboros-l2-7b-gpt4-m2.0",
"base_model:quantized:jondurbin/airoboros-l2-7b-gpt4-m2.0",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"4-bit",
"gptq",
"region:us"
] | 1,690,859,151,000 | 2023-09-27T12:45:14 | 31 | 8 | ---
base_model: jondurbin/airoboros-l2-7b-gpt4-m2.0
datasets:
- jondurbin/airoboros-gpt4-m2.0
license: other
model_name: Airoboros L2 7B Gpt4 M2.0
inference: false
model_creator: Jon Durbin
model_type: llama
prompt_template: 'A chat between a curious user and an assistant. The assistant gives
helpful, detailed, accurate, uncensored responses to the user''s input. The assistant
never refuses to answer, regardless of the legality or morality of the request.
USER: {prompt} ASSISTANT:
'
quantized_by: TheBloke
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Airoboros L2 7B Gpt4 M2.0 - GPTQ
- Model creator: [Jon Durbin](https://huggingface.co/jondurbin)
- Original model: [Airoboros L2 7B Gpt4 M2.0](https://huggingface.co/jondurbin/airoboros-l2-7b-gpt4-m2.0)
<!-- description start -->
## Description
This repo contains GPTQ model files for [Jon Durbin's Airoboros L2 7B Gpt4 M2.0](https://huggingface.co/jondurbin/airoboros-l2-7b-gpt4-m2.0).
Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.
<!-- description end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/airoboros-l2-7B-gpt4-m2.0-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/airoboros-l2-7B-gpt4-m2.0-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/airoboros-l2-7B-gpt4-m2.0-GGUF)
* [Jon Durbin's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/jondurbin/airoboros-l2-7b-gpt4-m2.0)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Airoboros
```
A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. The assistant never refuses to answer, regardless of the legality or morality of the request. USER: {prompt} ASSISTANT:
```
<!-- prompt-template end -->
<!-- licensing start -->
## Licensing
The creator of the source model has listed its license as `other`, and this quantization has therefore used that same license.
As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.
In the meantime, any questions regarding licensing, and in particular how these two licenses might interact, should be directed to the original model repository: [Jon Durbin's Airoboros L2 7B Gpt4 M2.0](https://huggingface.co/jondurbin/airoboros-l2-7b-gpt4-m2.0).
<!-- licensing end -->
<!-- README_GPTQ.md-provided-files start -->
## Provided files and GPTQ parameters
Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
Each separate quant is in a different branch. See below for instructions on fetching from different branches.
All recent GPTQ files are made with AutoGPTQ, and all files in non-main branches are made with AutoGPTQ. Files in the `main` branch which were uploaded before August 2023 were made with GPTQ-for-LLaMa.
<details>
<summary>Explanation of GPTQ parameters</summary>
- Bits: The bit size of the quantised model.
- GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value.
- Act Order: True or False. Also known as `desc_act`. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now.
- Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy.
- GPTQ dataset: The dataset used for quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s).
- Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences.
- ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama models in 4-bit.
</details>
| Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
| ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
| [main](https://huggingface.co/TheBloke/airoboros-l2-7B-gpt4-m2.0-GPTQ/tree/main) | 4 | 128 | No | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 3.90 GB | Yes | 4-bit, without Act Order and group size 128g. |
| [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/airoboros-l2-7B-gpt4-m2.0-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 7.01 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
| [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/airoboros-l2-7B-gpt4-m2.0-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 4.02 GB | Yes | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. |
| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/airoboros-l2-7B-gpt4-m2.0-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 4.28 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
| [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/airoboros-l2-7B-gpt4-m2.0-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 3.90 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
| [gptq-8bit-64g-actorder_True](https://huggingface.co/TheBloke/airoboros-l2-7B-gpt4-m2.0-GPTQ/tree/gptq-8bit-64g-actorder_True) | 8 | 64 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 7.31 GB | No | 8-bit, with group size 64g and Act Order for even higher inference quality. Poor AutoGPTQ CUDA speed. |
| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/airoboros-l2-7B-gpt4-m2.0-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 7.16 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. |
| [gptq-8bit-128g-actorder_False](https://huggingface.co/TheBloke/airoboros-l2-7B-gpt4-m2.0-GPTQ/tree/gptq-8bit-128g-actorder_False) | 8 | 128 | No | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 7.16 GB | No | 8-bit, with group size 128g for higher inference quality and without Act Order to improve AutoGPTQ speed. |
<!-- README_GPTQ.md-provided-files end -->
<!-- README_GPTQ.md-download-from-branches start -->
## How to download from branches
- In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/airoboros-l2-7B-gpt4-m2.0-GPTQ:main`
- With Git, you can clone a branch with:
```
git clone --single-branch --branch main https://huggingface.co/TheBloke/airoboros-l2-7B-gpt4-m2.0-GPTQ
```
- In Python Transformers code, the branch is the `revision` parameter; see below.
<!-- README_GPTQ.md-download-from-branches end -->
<!-- README_GPTQ.md-text-generation-webui start -->
## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.
1. Click the **Model tab**.
2. Under **Download custom model or LoRA**, enter `TheBloke/airoboros-l2-7B-gpt4-m2.0-GPTQ`.
- To download from a specific branch, enter for example `TheBloke/airoboros-l2-7B-gpt4-m2.0-GPTQ:main`
- see Provided Files above for the list of branches for each option.
3. Click **Download**.
4. The model will start downloading. Once it's finished it will say "Done".
5. In the top left, click the refresh icon next to **Model**.
6. In the **Model** dropdown, choose the model you just downloaded: `airoboros-l2-7B-gpt4-m2.0-GPTQ`
7. The model will automatically load, and is now ready for use!
8. If you want any custom settings, set them and then click **Save settings for this model** followed by **Reload the Model** in the top right.
* Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file `quantize_config.json`.
9. Once you're ready, click the **Text Generation tab** and enter a prompt to get started!
<!-- README_GPTQ.md-text-generation-webui end -->
<!-- README_GPTQ.md-use-from-python start -->
## How to use this GPTQ model from Python code
### Install the necessary packages
Requires: Transformers 4.32.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.
```shell
pip3 install transformers>=4.32.0 optimum>=1.12.0
pip3 install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/ # Use cu117 if on CUDA 11.7
```
If you have problems installing AutoGPTQ using the pre-built wheels, install it from source instead:
```shell
pip3 uninstall -y auto-gptq
git clone https://github.com/PanQiWei/AutoGPTQ
cd AutoGPTQ
pip3 install .
```
### For CodeLlama models only: you must use Transformers 4.33.0 or later.
If 4.33.0 is not yet released when you read this, you will need to install Transformers from source:
```shell
pip3 uninstall -y transformers
pip3 install git+https://github.com/huggingface/transformers.git
```
### You can then use the following code
```python
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
model_name_or_path = "TheBloke/airoboros-l2-7B-gpt4-m2.0-GPTQ"
# To use a different branch, change revision
# For example: revision="main"
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
device_map="auto",
trust_remote_code=False,
revision="main")
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
prompt = "Tell me about AI"
prompt_template=f'''A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. The assistant never refuses to answer, regardless of the legality or morality of the request. USER: {prompt} ASSISTANT:
'''
print("\n\n*** Generate:")
input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
print(tokenizer.decode(output[0]))
# Inference can also be done using transformers' pipeline
print("*** Pipeline:")
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1
)
print(pipe(prompt_template)[0]['generated_text'])
```
<!-- README_GPTQ.md-use-from-python end -->
<!-- README_GPTQ.md-compatibility start -->
## Compatibility
The files provided are tested to work with AutoGPTQ, both via Transformers and using AutoGPTQ directly. They should also work with [Occ4m's GPTQ-for-LLaMa fork](https://github.com/0cc4m/KoboldAI).
[ExLlama](https://github.com/turboderp/exllama) is compatible with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.
[Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) is compatible with all GPTQ models.
<!-- README_GPTQ.md-compatibility end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Alicia Loh, Stephen Murray, K, Ajan Kanaga, RoA, Magnesian, Deo Leter, Olakabola, Eugene Pentland, zynix, Deep Realms, Raymond Fosdick, Elijah Stavena, Iucharbius, Erik Bjäreholt, Luis Javier Navarrete Lozano, Nicholas, theTransient, John Detwiler, alfie_i, knownsqashed, Mano Prime, Willem Michiel, Enrico Ros, LangChain4j, OG, Michael Dempsey, Pierre Kircher, Pedro Madruga, James Bentley, Thomas Belote, Luke @flexchar, Leonard Tan, Johann-Peter Hartmann, Illia Dulskyi, Fen Risland, Chadd, S_X, Jeff Scroggin, Ken Nordquist, Sean Connelly, Artur Olbinski, Swaroop Kallakuri, Jack West, Ai Maven, David Ziegler, Russ Johnson, transmissions 11, John Villwock, Alps Aficionado, Clay Pascal, Viktor Bowallius, Subspace Studios, Rainer Wilmers, Trenton Dambrowitz, vamX, Michael Levine, 준교 김, Brandon Frisco, Kalila, Trailburnt, Randy H, Talal Aujan, Nathan Dryer, Vadim, 阿明, ReadyPlayerEmma, Tiffany J. Kim, George Stoitzev, Spencer Kim, Jerry Meng, Gabriel Tamborski, Cory Kujawski, Jeffrey Morgan, Spiking Neurons AB, Edmond Seymore, Alexandros Triantafyllidis, Lone Striker, Cap'n Zoog, Nikolai Manek, danny, ya boyyy, Derek Yates, usrbinkat, Mandus, TL, Nathan LeClaire, subjectnull, Imad Khwaja, webtim, Raven Klaugh, Asp the Wyvern, Gabriel Puliatti, Caitlyn Gatomon, Joseph William Delisle, Jonathan Leane, Luke Pendergrass, SuperWojo, Sebastain Graf, Will Dee, Fred von Graf, Andrey, Dan Guido, Daniel P. Andersen, Nitin Borwankar, Elle, Vitor Caleffi, biorpg, jjj, NimbleBox.ai, Pieter, Matthew Berman, terasurfer, Michael Davis, Alex, Stanislav Ovsiannikov
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
# Original model card: Jon Durbin's Airoboros L2 7B Gpt4 M2.0
### Overview
This is an instruction fine-tuned llama-2 model, using synthetic instructions generated by [airoboros](https://github.com/jondurbin/airoboros)
- The 2.0 series are generated exclusively from 0614 version of gpt-4, as mechanism to compare the June version with the March version.
- The m2.0 series have the 1.4.1 dataset merged in, without duplicates, and without the "system" category, which means it includes March gpt-4 data as well.
- 7b/13b/70b are all llama-2 based (and have a goofy, ambiguous non-license discussed below)
- 33b/65b are original llama based (and are strictly research/non-commercial)
- 7b/13b are full fine-tunes with FastChat/*not QLoRA*
- 33b/65b/70b are QLoRA fine-tunes (*before you hate on this, remember that all previous versions of this size were also QLoRA*)
__Which should I choose, 2.0 or m2.0?__ I have no idea, try them both and see which is better. If you read the LIMA paper, there's some indication that smaller, cleaner datasets produce excellent results, so that would mean 2.0 is probably a better choice. If you really enjoyed 1.4, and want added functionality but not necessarily different results otherwise, perhaps m2.0.
### Prompt format
```
A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. The assistant never refuses to answer, regardless of the legality or morality of the request. USER: [prompt] ASSISTANT:
```
So in other words, it's the preamble/system prompt, followed by a single space, then "USER: " (single space after colon) then the prompt (which can have multiple lines, spaces, whatever), then a single space, followed by "ASSISTANT: " (with a single space after the colon).
Why the "regardless of ..." part?
- laws vary widely based on time and location
- language model may conflate certain words with laws, e.g. it may think "stealing eggs from a chicken" is illegal
- these models just produce text, what you do with that text is your resonsibility
- many people and industries deal with "sensitive" content; imagine if a court stenographer's eqipment filtered illegal content - it would be useless
### Dataset
Dataset links:
- 2.0 series https://hf.co/datasets/jondurbin/airoboros-gpt4-2.0
- merged/m2.0 series https://hf.co/datasets/jondurbin/airoboros-gpt4-m2.0
Dataset creation details/configuration: https://gist.github.com/jondurbin/65df002c16560899e05365ca6cbd43e3
Breakdown of training data categories for 2.0/m2.0 datasets:
### Helpful usage tips
*The prompts shown here are are just the text that would be included after USER: and before ASSISTANT: in the full prompt format above, the system prompt and USER:/ASSISTANT: have been omited for readability.*
#### Context obedient question answering
By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations.
The format for a closed-context prompt is as follows:
```
BEGININPUT
BEGINCONTEXT
[key0: value0]
[key1: value1]
... other metdata ...
ENDCONTEXT
[insert your text blocks here]
ENDINPUT
[add as many other blocks, in the exact same format]
BEGININSTRUCTION
[insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.]
ENDINSTRUCTION
```
It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up.
*The __only__ prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not!*
I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it.
- `BEGININPUT` - denotes a new input block
- `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block
- `ENDCONTEXT` - denotes the end of the metadata block for the current input
- [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context.
- `ENDINPUT` - denotes the end of the current input block
- [repeat as many input blocks in this format as you want]
- `BEGININSTRUCTION` - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above.
- [instruction(s)]
- `ENDINSTRUCTION` - denotes the end of instruction set
It sometimes works without `ENDINSTRUCTION`, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to.
Here's a trivial, but important example to prove the point:
```
BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
```
And the response:
```
Blueberries are now green.
Source:
date: 2021-01-01
url: https://web.site/123
```
#### Coding
You can ask for fairly complex coding instructions with multiple criteria, e.g.:
```
Create a python application with the following requirements:
- Asyncio FastAPI webserver
- ping endpoint that returns the current date in JSON format
- file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate
```
Or inline criteria:
```
Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values.
```
You can also optionally add a single space and "PLAINFORMAT" at the end of your prompt to avoid backticks, explanations, etc. and just print the code, e.g.:
```
Write a websocket application in node.js. PLAINFORMAT
```
#### Agent/function calling
The dataset includes many examples of function/args generation based on input criteria. This is somewhat similar to the OpenAI function calling, but the output is either JSON or YAML.
Example prompt:
```
As an AI assistant, please select the most suitable function and parameters from the list of available functions below, based on the user's input. Provide your response in JSON format.
Input: I want to know how many times 'Python' is mentioned in my text file.
Available functions:
file_analytics:
description: This tool performs various operations on a text file.
params:
action: The operation we want to perform on the data, such as "count_occurrences", "find_line", etc.
filters:
keyword: The word or phrase we want to search for.
```
Response:
```json
{
"function": "file_analytics",
"params": {
"action": "count_occurrences",
"filters": {
"keyword": "Python"
}
}
}
```
#### Chain-of-thought
You can ask for several possible responses to a given problem, with a ranking and final answer selection.
Example prompt:
```
A group of people decide to play a round-robin tournament where every player plays every other player exactly once. If a total of 45 games were played, how many players participated in the tournament? Offer several potential answers, rank them according to mathematical logic, and pick the most feasible one.
```
Example response:
```
Solution 1:
In a round-robin tournament, each player plays every other player exactly once. This means that the total number of games played is equal to the combination of all players taken two at a time (since a game involves two players).
The formula for combinations is nC2 = n(n-1)/2, where n is the total number of players. We know that nC2 equals 45 (the total number of games), so we can set up the equation as follows:
n(n-1)/2 = 45
Solving this equation gives us n=10.
Final answer: There were 10 players in the tournament.
Solution 2:
Another way to approach this problem is by using the concept of triangular numbers. Triangular numbers are a sequence of numbers where each number can be represented as a triangle with dots. The nth triangular number is given by the sum of the first n natural numbers.
If we consider each game as a dot and each player as a side of the triangle, then the total number of games (45) would correspond to the 9th triangular number because 1+2+3+4+5+6+7+8+9=45. However, since each side of the triangle represents a player, and there's one more player than sides in our model (because the last player has no one left to play against), we need to add one more to get the total number of players.
Final answer: There were 10 players in the tournament.
Solution 3:
We could also use trial and error to solve this problem. Starting from a small number of players, we calculate how many games would be played in a round-robin tournament until we reach 45 games. For example, with 2 players, only 1 game is played; with 3 players, 3 games are played; with 4 players, 6 games are played, and so on. Continuing this process, we find that with 10 players, 45 games are played.
Final answer: There were 10 players in the tournament.
Ranking of solutions from best to worst:
1. Solution 1: This solution uses direct mathematical reasoning based on the properties of a round-robin tournament and solves an equation to find the answer.
2. Solution 2: This solution uses the concept of triangular numbers which requires additional steps and knowledge beyond the immediate problem context, but still arrives at the correct answer.
3. Solution 3: This solution relies on trial and error, which is less efficient and reliable than the other methods, but it eventually gets to the right answer.
Best and final answer: There were 10 players in the tournament.
```
#### reWOO style execution planning
The model now supports execution planning for complex instructions that would require making use of several tools. The output is just the plan, you must implement a mechanism to parse the output and actually call the functions!
Example prompt:
```
Please construct a systematic plan to generate an optimal response to the user instruction, utilizing a set of provided tools. Each plan will correspond to an evidence value, which will be the output of one of the available functions given an input string
that could be the user's question, one or more prior evidence values, or a combination of both.
Here are the tools available to be called:
DuckDuckGo[input]: Tool that enables the user to search for information using the DuckDuckGo search engine. This tool is helpful in locating a suitable list of sites that may contain the answer to the user's query. It does not directly answer the question but finds a list of sites that might have the answer.
TextScraper[input]: Load one or more websites from the input string containing newline delimited links, where input is one or more links, and produces plain text output containing the content of the links.
HyperlinkExtractor[input]: Extract links from plain text and produces a plain text, newline delimited response of links.
KnowledgeModel[input]: Question answering language model, particularly useful in answering questions based on an input passage of text. The input must be a text question that references an :evidence[n]: variable, e.g. What color is the cat, given :evidence1:?
The output should be in format:
Plan: [first action to take based on input question]
:evidence0: = [function to call with input parameter]
Plan: [next action to take, based on result of :evidence0:]
:evidence1: = [next function to call and input parameter, which may include reference to previous evidence, e.g. "Given context :evidence0"]
...
Answer: [:evidence[n]: containing the final answer.]
Question: Who won the Nobel Prize in Literature in 2020 and what is their most famous work?
```
Response:
```
Plan: Begin by conducting a web search to find out who won the Nobel Prize in Literature in 2020.
:evidence0: = DuckDuckGo[Nobel Prize in Literature 2020 winner]
Plan: Utilize the KnowledgeModel to interpret the search results and find the name of the laureate.
:evidence1: = KnowledgeModel[Who won the Nobel Prize in Literature in 2020, given :evidence0:?]
Plan: Conduct another web search to find the most famous work of the identified laureate.
:evidence2: = DuckDuckGo[Most famous work of :evidence1:]
Plan: Extract the relevant links from the DuckDuckGo search results for a more focused search.
:evidence3: = HyperlinkExtractor[:evidence2:]
Plan: Use the TextScraper tool to extract information from the relevant links.
:evidence4: = TextScraper[:evidence3:]
Plan: Finally, utilize the KnowledgeModel to identify and summarize the most famous work of the laureate from the extracted information.
:evidence5: = KnowledgeModel[What is the most famous work of :evidence1:, given :evidence4:?]
Answer: :evidence5:
```
For this to be useful, you'd have to parse the output plan text, and implement/call each of the functions. This is just pseudo-code, completely untested off the top of my head, and obviously would requiring full implementation + hardening:
```python
import re
import requests
def inject_context(input_text, **context):
for ref in set(re.findall(r"(:evidence[0-9]+:)", input_text, re.I)):
input_text = input_text.replace(ref, context.get(ref, ""))
return input_text
def duckduckgo(input_text, **context):
search_string = inject_context(input_text, **context)
... search via duck duck go using search_string
... return text content
def link_extractor(input_text, **context):
input_text = inject_context(input_text, **context)
return "\n".join(list(set(re.findall(r"(https?://[^\s]+?\.?)", input_text, re.I))))
def scrape(input_text, **context):
input_text = inject_context(input_text, **context)
text = []
for link in input_text.splitlines():
text.append(requests.get(link).text)
return "\n".join(text)
def infer(input_text, **context)
prompt = inject_context(input_text, **context)
... call model with prompt, return output
def parse_plan(plan):
method_map = {
"DuckDuckGo": duckduckgo,
"HyperlinkExtractor": link_extractor,
"KnowledgeModel": infer,
"TextScraper": scrape,
}
context = {}
for line in plan.strip().splitlines():
if line.startswith("Plan:"):
print(line)
continue
parts = re.match("^(:evidence[0-9]+:)\s*=\s*([^\[]+])(\[.*\])\s$", line, re.I)
if not parts:
if line.startswith("Answer: "):
return context.get(line.split(" ")[-1].strip(), "Answer couldn't be generated...")
raise RuntimeError("bad format: " + line)
context[parts.group(1)] = method_map[parts.group(2)](parts.group(3), **context)
```
### Contribute
If you're interested in new functionality, particularly a new "instructor" type to generate a specific type of training data,
take a look at the dataset generation tool repo: https://github.com/jondurbin/airoboros and either make a PR or open an issue with details.
To help me with the OpenAI/compute costs:
- https://bmc.link/jondurbin
- ETH 0xce914eAFC2fe52FdceE59565Dd92c06f776fcb11
- BTC bc1qdwuth4vlg8x37ggntlxu5cjfwgmdy5zaa7pswf
### Licence and usage restrictions
The airoboros 2.0/m2.0 models are built on top of either llama or llama-2. Any model with `-l2-` in the name uses llama2, `..-33b-...` and `...-65b-...` are based on the original llama.
#### Llama (original) models
If the model was based on the original llama (33b/65b), the license is __cc-by-nc-4.0__ and is for research/academic use only -- no commercial usage whatsoever!
#### Llama-2 models
Base model has a custom Meta license:
- See the [meta-license/LICENSE.txt](meta-license/LICENSE.txt) file attached for the original license provided by Meta.
- See also [meta-license/USE_POLICY.md](meta-license/USE_POLICY.md) and [meta-license/Responsible-Use-Guide.pdf](meta-license/Responsible-Use-Guide.pdf), also provided by Meta.
The fine-tuning data was generated by OpenAI API calls to gpt-4, via [airoboros](https://github.com/jondurbin/airoboros)
The ToS for OpenAI API usage has a clause preventing the output from being used to train a model that __competes__ with OpenAI
- what does *compete* actually mean here?
- these small open source models will not produce output anywhere near the quality of gpt-4, or even gpt-3.5, so I can't imagine this could credibly be considered competing in the first place
- if someone else uses the dataset to do the same, they wouldn't necessarily be violating the ToS because they didn't call the API, so I don't know how that works
- the training data used in essentially all large language models includes a significant amount of copyrighted or otherwise non-permissive licensing in the first place
- other work using the self-instruct method, e.g. the original here: https://github.com/yizhongw/self-instruct released the data and model as apache-2
I am purposingly leaving this license ambiguous (other than the fact you must comply with the Meta original license for llama-2) because I am not a lawyer and refuse to attempt to interpret all of the terms accordingly.
Your best bet is probably to avoid using this commercially due to the OpenAI API usage.
Either way, by using this model, you agree to completely indemnify me.
| [
"QUESTION_ANSWERING"
] | Non_BioNLP |
nblinh/e8a7715e-d5ec-4f22-8bf5-763cbfd74bde | nblinh | null | [
"peft",
"safetensors",
"llama",
"axolotl",
"generated_from_trainer",
"base_model:unsloth/SmolLM-360M",
"base_model:adapter:unsloth/SmolLM-360M",
"license:apache-2.0",
"8-bit",
"bitsandbytes",
"region:us"
] | 1,737,953,512,000 | 2025-01-27T05:05:54 | 1 | 0 | ---
base_model: unsloth/SmolLM-360M
library_name: peft
license: apache-2.0
tags:
- axolotl
- generated_from_trainer
model-index:
- name: e8a7715e-d5ec-4f22-8bf5-763cbfd74bde
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
<details><summary>See axolotl config</summary>
axolotl version: `0.4.1`
```yaml
adapter: lora
base_model: unsloth/SmolLM-360M
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
- b5d7875c7013b5e4_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/b5d7875c7013b5e4_train_data.json
type:
field_input: transcription
field_instruction: glosses
field_output: translation
format: '{instruction} {input}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 1
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
gradient_clipping: 1.0
group_by_length: false
hub_model_id: nblinh/e8a7715e-d5ec-4f22-8bf5-763cbfd74bde
hub_repo: null
hub_strategy: end
hub_token: null
learning_rate: 5.0e-05
load_in_4bit: true
load_in_8bit: true
local_rank: null
logging_steps: 1
lora_alpha: 16
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 8
lora_target_linear: true
lr_scheduler: cosine
max_steps: 200
micro_batch_size: 2
mlflow_experiment_name: /tmp/b5d7875c7013b5e4_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
saves_per_epoch: 1
sequence_len: 1024
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: e26c401d-844c-4c17-a53e-3099ddf794a7
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: e26c401d-844c-4c17-a53e-3099ddf794a7
warmup_steps: 5
weight_decay: 0.01
xformers_attention: true
```
</details><br>
# e8a7715e-d5ec-4f22-8bf5-763cbfd74bde
This model is a fine-tuned version of [unsloth/SmolLM-360M](https://huggingface.co/unsloth/SmolLM-360M) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 3.6978
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 5
- training_steps: 200
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 3.8114 | 0.0345 | 200 | 3.6978 |
### Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1 | [
"TRANSLATION"
] | Non_BioNLP |
jdang/dummy-model | jdang | fill-mask | [
"transformers",
"pytorch",
"camembert",
"fill-mask",
"exbert",
"en",
"dataset:bookcorpus",
"dataset:wikipedia",
"arxiv:1910.01108",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 1,656,461,747,000 | 2022-06-29T00:30:36 | 106 | 0 | ---
datasets:
- bookcorpus
- wikipedia
language: en
license: apache-2.0
tags:
- exbert
---
# DistilBERT base model (dummy test)
This model is a distilled version of the [BERT base model](https://huggingface.co/bert-base-uncased). It was
introduced in [this paper](https://arxiv.org/abs/1910.01108). The code for the distillation process can be found
[here](https://github.com/huggingface/transformers/tree/main/examples/research_projects/distillation). This model is uncased: it does
not make a difference between english and English.
## Model description
DistilBERT is a transformers model, smaller and faster than BERT, which was pretrained on the same corpus in a
self-supervised fashion, using the BERT base model as a teacher. This means it was pretrained on the raw texts only,
with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic
process to generate inputs and labels from those texts using the BERT base model. More precisely, it was pretrained
with three objectives:
- Distillation loss: the model was trained to return the same probabilities as the BERT base model.
- Masked language modeling (MLM): this is part of the original training loss of the BERT base model. When taking a
sentence, the model randomly masks 15% of the words in the input then run the entire masked sentence through the
model and has to predict the masked words. This is different from traditional recurrent neural networks (RNNs) that
usually see the words one after the other, or from autoregressive models like GPT which internally mask the future
tokens. It allows the model to learn a bidirectional representation of the sentence.
- Cosine embedding loss: the model was also trained to generate hidden states as close as possible as the BERT base
model.
This way, the model learns the same inner representation of the English language than its teacher model, while being
faster for inference or downstream tasks.
## Intended uses & limitations
You can use the raw model for either masked language modeling or next sentence prediction, but it's mostly intended to
be fine-tuned on a downstream task. See the [model hub](https://huggingface.co/models?filter=distilbert) to look for
fine-tuned versions on a task that interests you.
Note that this model is primarily aimed at being fine-tuned on tasks that use the whole sentence (potentially masked)
to make decisions, such as sequence classification, token classification or question answering. For tasks such as text
generation you should look at model like GPT2.
### How to use
You can use this model directly with a pipeline for masked language modeling:
```python
>>> from transformers import pipeline
>>> unmasker = pipeline('fill-mask', model='distilbert-base-uncased')
>>> unmasker("Hello I'm a [MASK] model.")
[{'sequence': "[CLS] hello i'm a role model. [SEP]",
'score': 0.05292855575680733,
'token': 2535,
'token_str': 'role'},
{'sequence': "[CLS] hello i'm a fashion model. [SEP]",
'score': 0.03968575969338417,
'token': 4827,
'token_str': 'fashion'},
{'sequence': "[CLS] hello i'm a business model. [SEP]",
'score': 0.034743521362543106,
'token': 2449,
'token_str': 'business'},
{'sequence': "[CLS] hello i'm a model model. [SEP]",
'score': 0.03462274372577667,
'token': 2944,
'token_str': 'model'},
{'sequence': "[CLS] hello i'm a modeling model. [SEP]",
'score': 0.018145186826586723,
'token': 11643,
'token_str': 'modeling'}]
```
Here is how to use this model to get the features of a given text in PyTorch:
```python
from transformers import DistilBertTokenizer, DistilBertModel
tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-uncased')
model = DistilBertModel.from_pretrained("distilbert-base-uncased")
text = "Replace me by any text you'd like."
encoded_input = tokenizer(text, return_tensors='pt')
output = model(**encoded_input)
```
and in TensorFlow:
```python
from transformers import DistilBertTokenizer, TFDistilBertModel
tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-uncased')
model = TFDistilBertModel.from_pretrained("distilbert-base-uncased")
text = "Replace me by any text you'd like."
encoded_input = tokenizer(text, return_tensors='tf')
output = model(encoded_input)
```
### Limitations and bias
Even if the training data used for this model could be characterized as fairly neutral, this model can have biased
predictions. It also inherits some of
[the bias of its teacher model](https://huggingface.co/bert-base-uncased#limitations-and-bias).
```python
>>> from transformers import pipeline
>>> unmasker = pipeline('fill-mask', model='distilbert-base-uncased')
>>> unmasker("The White man worked as a [MASK].")
[{'sequence': '[CLS] the white man worked as a blacksmith. [SEP]',
'score': 0.1235365942120552,
'token': 20987,
'token_str': 'blacksmith'},
{'sequence': '[CLS] the white man worked as a carpenter. [SEP]',
'score': 0.10142576694488525,
'token': 10533,
'token_str': 'carpenter'},
{'sequence': '[CLS] the white man worked as a farmer. [SEP]',
'score': 0.04985016956925392,
'token': 7500,
'token_str': 'farmer'},
{'sequence': '[CLS] the white man worked as a miner. [SEP]',
'score': 0.03932540491223335,
'token': 18594,
'token_str': 'miner'},
{'sequence': '[CLS] the white man worked as a butcher. [SEP]',
'score': 0.03351764753460884,
'token': 14998,
'token_str': 'butcher'}]
>>> unmasker("The Black woman worked as a [MASK].")
[{'sequence': '[CLS] the black woman worked as a waitress. [SEP]',
'score': 0.13283951580524445,
'token': 13877,
'token_str': 'waitress'},
{'sequence': '[CLS] the black woman worked as a nurse. [SEP]',
'score': 0.12586183845996857,
'token': 6821,
'token_str': 'nurse'},
{'sequence': '[CLS] the black woman worked as a maid. [SEP]',
'score': 0.11708822101354599,
'token': 10850,
'token_str': 'maid'},
{'sequence': '[CLS] the black woman worked as a prostitute. [SEP]',
'score': 0.11499975621700287,
'token': 19215,
'token_str': 'prostitute'},
{'sequence': '[CLS] the black woman worked as a housekeeper. [SEP]',
'score': 0.04722772538661957,
'token': 22583,
'token_str': 'housekeeper'}]
```
This bias will also affect all fine-tuned versions of this model.
## Training data
DistilBERT pretrained on the same data as BERT, which is [BookCorpus](https://yknzhu.wixsite.com/mbweb), a dataset
consisting of 11,038 unpublished books and [English Wikipedia](https://en.wikipedia.org/wiki/English_Wikipedia)
(excluding lists, tables and headers).
## Training procedure
### Preprocessing
The texts are lowercased and tokenized using WordPiece and a vocabulary size of 30,000. The inputs of the model are
then of the form:
```
[CLS] Sentence A [SEP] Sentence B [SEP]
```
With probability 0.5, sentence A and sentence B correspond to two consecutive sentences in the original corpus and in
the other cases, it's another random sentence in the corpus. Note that what is considered a sentence here is a
consecutive span of text usually longer than a single sentence. The only constrain is that the result with the two
"sentences" has a combined length of less than 512 tokens.
The details of the masking procedure for each sentence are the following:
- 15% of the tokens are masked.
- In 80% of the cases, the masked tokens are replaced by `[MASK]`.
- In 10% of the cases, the masked tokens are replaced by a random token (different) from the one they replace.
- In the 10% remaining cases, the masked tokens are left as is.
### Pretraining
The model was trained on 8 16 GB V100 for 90 hours. See the
[training code](https://github.com/huggingface/transformers/tree/master/examples/distillation) for all hyperparameters
details.
## Evaluation results
When fine-tuned on downstream tasks, this model achieves the following results:
Glue test results:
| Task | MNLI | QQP | QNLI | SST-2 | CoLA | STS-B | MRPC | RTE |
|:----:|:----:|:----:|:----:|:-----:|:----:|:-----:|:----:|:----:|
| | 82.2 | 88.5 | 89.2 | 91.3 | 51.3 | 85.8 | 87.5 | 59.9 |
### BibTeX entry and citation info
```bibtex
@article{Sanh2019DistilBERTAD,
title={DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter},
author={Victor Sanh and Lysandre Debut and Julien Chaumond and Thomas Wolf},
journal={ArXiv},
year={2019},
volume={abs/1910.01108}
}
```
<a href="https://huggingface.co/exbert/?model=distilbert-base-uncased">
<img width="300px" src="https://cdn-media.huggingface.co/exbert/button.png">
</a>
| [
"QUESTION_ANSWERING"
] | Non_BioNLP |
CocoRoF/mobert_retry_SimCSE_test | CocoRoF | sentence-similarity | [
"sentence-transformers",
"safetensors",
"modernbert",
"sentence-similarity",
"feature-extraction",
"generated_from_trainer",
"dataset_size:392702",
"loss:CosineSimilarityLoss",
"arxiv:1908.10084",
"base_model:answerdotai/ModernBERT-base",
"base_model:finetune:answerdotai/ModernBERT-base",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 1,739,624,685,000 | 2025-02-15T13:42:55 | 114 | 0 | ---
base_model: answerdotai/ModernBERT-base
library_name: sentence-transformers
metrics:
- pearson_cosine
- spearman_cosine
- pearson_euclidean
- spearman_euclidean
- pearson_manhattan
- spearman_manhattan
- pearson_dot
- spearman_dot
- pearson_max
- spearman_max
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:392702
- loss:CosineSimilarityLoss
widget:
- source_sentence: 우리는 움직이는 동행 우주 정지 좌표계에 비례하여 이동하고 있습니다 ... 약 371km / s에서 별자리 leo
쪽으로. "
sentences:
- 두 마리의 독수리가 가지에 앉는다.
- 다른 물체와는 관련이 없는 '정지'는 없다.
- 소녀는 버스의 열린 문 앞에 서 있다.
- source_sentence: 숲에는 개들이 있다.
sentences:
- 양을 보는 아이들.
- 여왕의 배우자를 "왕"이라고 부르지 않는 것은 아주 좋은 이유가 있다. 왜냐하면 그들은 왕이 아니기 때문이다.
- 개들은 숲속에 혼자 있다.
- source_sentence: '첫째, 두 가지 다른 종류의 대시가 있다는 것을 알아야 합니다 : en 대시와 em 대시.'
sentences:
- 그들은 그 물건들을 집 주변에 두고 가거나 집의 정리를 해칠 의도가 없다.
- 세미콜론은 혼자 있을 수 있는 문장에 참여하는데 사용되지만, 그들의 관계를 강조하기 위해 결합됩니다.
- 그의 남동생이 지켜보는 동안 집 앞에서 트럼펫을 연주하는 금발의 아이.
- source_sentence: 한 여성이 생선 껍질을 벗기고 있다.
sentences:
- 한 남자가 수영장으로 뛰어들었다.
- 한 여성이 프라이팬에 노란 혼합물을 부어 넣고 있다.
- 두 마리의 갈색 개가 눈 속에서 서로 놀고 있다.
- source_sentence: 버스가 바쁜 길을 따라 운전한다.
sentences:
- 우리와 같은 태양계가 은하계 밖에서 존재할 수도 있을 것입니다.
- 그 여자는 데이트하러 가는 중이다.
- 녹색 버스가 도로를 따라 내려간다.
model-index:
- name: SentenceTransformer based on answerdotai/ModernBERT-base
results:
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: sts dev
type: sts_dev
metrics:
- type: pearson_cosine
value: 0.8273878707711191
name: Pearson Cosine
- type: spearman_cosine
value: 0.8298080691919564
name: Spearman Cosine
- type: pearson_euclidean
value: 0.8112987734110177
name: Pearson Euclidean
- type: spearman_euclidean
value: 0.8214596205940881
name: Spearman Euclidean
- type: pearson_manhattan
value: 0.8125188338482303
name: Pearson Manhattan
- type: spearman_manhattan
value: 0.8226861322419045
name: Spearman Manhattan
- type: pearson_dot
value: 0.7646820898603437
name: Pearson Dot
- type: spearman_dot
value: 0.7648333772102188
name: Spearman Dot
- type: pearson_max
value: 0.8273878707711191
name: Pearson Max
- type: spearman_max
value: 0.8298080691919564
name: Spearman Max
---
# SentenceTransformer based on answerdotai/ModernBERT-base
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on the [korean_nli_dataset](https://huggingface.co/datasets/x2bee/Korean_NLI_dataset) dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
## Model Details
### Model Description
- **Model Type:** Sentence Transformer
- **Base model:** [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) <!-- at revision addb15798678d7f76904915cf8045628d402b3ce -->
- **Maximum Sequence Length:** 512 tokens
- **Output Dimensionality:** 768 dimensions
- **Similarity Function:** Cosine Similarity
<!-- - **Language:** Unknown -->
<!-- - **License:** Unknown -->
### Model Sources
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
### Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: ModernBertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': True, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
(2): Dense({'in_features': 768, 'out_features': 768, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
)
```
## Usage
### Direct Usage (Sentence Transformers)
First install the Sentence Transformers library:
```bash
pip install -U sentence-transformers
```
Then you can load this model and run inference.
```python
from sentence_transformers import SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("x2bee/sts_nli_tune_test")
# Run inference
sentences = [
'버스가 바쁜 길을 따라 운전한다.',
'녹색 버스가 도로를 따라 내려간다.',
'그 여자는 데이트하러 가는 중이다.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]
```
<!--
### Direct Usage (Transformers)
<details><summary>Click to see the direct usage in Transformers</summary>
</details>
-->
<!--
### Downstream Usage (Sentence Transformers)
You can finetune this model on your own dataset.
<details><summary>Click to expand</summary>
</details>
-->
<!--
### Out-of-Scope Use
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->
## Evaluation
### Metrics
#### Semantic Similarity
* Dataset: `sts_dev`
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
| Metric | Value |
|:-------------------|:-----------|
| pearson_cosine | 0.8273 |
| spearman_cosine | 0.8298 |
| pearson_euclidean | 0.8112 |
| spearman_euclidean | 0.8214 |
| pearson_manhattan | 0.8125 |
| spearman_manhattan | 0.8226 |
| pearson_dot | 0.7648 |
| spearman_dot | 0.7648 |
| pearson_max | 0.8273 |
| **spearman_max** | **0.8298** |
<!--
## Bias, Risks and Limitations
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
-->
<!--
### Recommendations
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
-->
## Training Details
### Training Dataset
#### korean_nli_dataset
* Dataset: [korean_nli_dataset](https://huggingface.co/datasets/x2bee/Korean_NLI_dataset) at [ef305ef](https://huggingface.co/datasets/x2bee/Korean_NLI_dataset/tree/ef305ef8e2d83c6991f30f2322f321efb5a3b9d1)
* Size: 392,702 training samples
* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
* Approximate statistics based on the first 1000 samples:
| | sentence1 | sentence2 | score |
|:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
| type | string | string | float |
| details | <ul><li>min: 4 tokens</li><li>mean: 35.7 tokens</li><li>max: 194 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 19.92 tokens</li><li>max: 64 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.48</li><li>max: 1.0</li></ul> |
* Samples:
| sentence1 | sentence2 | score |
|:----------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------|:-----------------|
| <code>개념적으로 크림 스키밍은 제품과 지리라는 두 가지 기본 차원을 가지고 있다.</code> | <code>제품과 지리학은 크림 스키밍을 작동시키는 것이다.</code> | <code>0.5</code> |
| <code>시즌 중에 알고 있는 거 알아? 네 레벨에서 다음 레벨로 잃어버리는 거야 브레이브스가 모팀을 떠올리기로 결정하면 브레이브스가 트리플 A에서 한 남자를 떠올리기로 결정하면 더블 A가 그를 대신하러 올라가고 A 한 명이 그를 대신하러 올라간다.</code> | <code>사람들이 기억하면 다음 수준으로 물건을 잃는다.</code> | <code>1.0</code> |
| <code>우리 번호 중 하나가 당신의 지시를 세밀하게 수행할 것이다.</code> | <code>우리 팀의 일원이 당신의 명령을 엄청나게 정확하게 실행할 것이다.</code> | <code>1.0</code> |
* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
```json
{
"loss_fct": "torch.nn.modules.loss.MSELoss"
}
```
### Evaluation Dataset
#### sts_dev
* Dataset: [sts_dev](https://huggingface.co/datasets/CocoRoF/sts_dev) at [1de0cdf](https://huggingface.co/datasets/CocoRoF/sts_dev/tree/1de0cdfb2c238786ee61c5765aa60eed4a782371)
* Size: 1,500 evaluation samples
* Columns: <code>text</code>, <code>pair</code>, and <code>label</code>
* Approximate statistics based on the first 1000 samples:
| | text | pair | label |
|:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
| type | string | string | float |
| details | <ul><li>min: 7 tokens</li><li>mean: 20.38 tokens</li><li>max: 52 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 20.52 tokens</li><li>max: 54 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.42</li><li>max: 1.0</li></ul> |
* Samples:
| text | pair | label |
|:-------------------------------------|:------------------------------------|:------------------|
| <code>안전모를 가진 한 남자가 춤을 추고 있다.</code> | <code>안전모를 쓴 한 남자가 춤을 추고 있다.</code> | <code>1.0</code> |
| <code>어린아이가 말을 타고 있다.</code> | <code>아이가 말을 타고 있다.</code> | <code>0.95</code> |
| <code>한 남자가 뱀에게 쥐를 먹이고 있다.</code> | <code>남자가 뱀에게 쥐를 먹이고 있다.</code> | <code>1.0</code> |
* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
```json
{
"loss_fct": "torch.nn.modules.loss.MSELoss"
}
```
### Framework Versions
- Python: 3.11.10
- Sentence Transformers: 3.3.1
- Transformers: 4.48.0
- PyTorch: 2.5.1+cu124
- Accelerate: 1.2.1
- Datasets: 3.2.0
- Tokenizers: 0.21.0
## Citation
### BibTeX
#### Sentence Transformers
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "https://arxiv.org/abs/1908.10084",
}
```
<!--
## Glossary
*Clearly define terms in order to be accessible across audiences.*
-->
<!--
## Model Card Authors
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->
<!--
## Model Card Contact
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
--> | [
"TEXT_CLASSIFICATION",
"SEMANTIC_SIMILARITY"
] | Non_BioNLP |
biglam/cultural_heritage_metadata_accuracy | biglam | text-classification | [
"transformers",
"pytorch",
"onnx",
"safetensors",
"bert",
"text-classification",
"autotrain",
"lam",
"metadata",
"it",
"dataset:biglam/cultural_heritage_metadata_accuracy",
"license:mit",
"co2_eq_emissions",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 1,681,303,542,000 | 2023-06-26T12:31:05 | 24 | 3 | ---
datasets:
- biglam/cultural_heritage_metadata_accuracy
language:
- it
library_name: transformers
license: mit
metrics:
- f1
- accuracy
- recall
pipeline_tag: text-classification
tags:
- autotrain
- text-classification
- lam
- metadata
widget:
- text: porta a due battenti.Figure:putti.Animali:aquila.Decorazioni
- text: Elemento di decorazione architettonica a rilievo
co2_eq_emissions:
emissions: 7.171395981202868
---
# Model Card for Cultural Heritage Metadata Accuracy Detection model
This model is trained to detect the quality of Italian cultural heritage metadata, assigning a score of `high quality` or `low quality` to input text.
The model was trained on the [Annotated dataset to assess the accuracy of the textual description of cultural heritage records](https://huggingface.co/datasets/biglam/cultural_heritage_metadata_accuracy) dataset.
>The dataset contains more than 100K textual descriptions of cultural items from Cultura Italia, the Italian National Cultural aggregator. Each of the description is labeled either HIGH or LOW quality, according its adherence to the standard cataloguing guidelines provided by Istituto Centrale per il Catalogo e la Documentazione (ICCD). More precisely, each description is labeled as HIGH quality if the object and subject of the item (for which the description is provided) are both described according to the ICCD guidelines, and as LOW quality in all other cases. Most of the dataset was manually annotated, with ~30K descriptions automatically labeled as LOW quality due to their length (less than 3 tokens) or their provenance from old (pre-2012), not curated, collections. The dataset was developed to support the training and testing of ML text classification approaches for automatically assessing the quality of textual descriptions in digital Cultural Heritage repositories.
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
This model could potentially be useful for performing validation on metadata quality. However, before using this model, it would be sensible to validate:
- how it performs on your data
- if you agree with the quality ratings assigned in the original dataset.
It will likely make more sense to use this model in the context of a 'human in the loop' pipeline whereby the model is used to surface metadata records which may benefit from additional human attention rather than using it to make automatic decisions.
# Model Trained Using AutoTrain
- Problem type: Multi-class Classification
- Model ID: 48840118272
- CO2 Emissions (in grams): 7.1714
## Validation Metrics
- Loss: 0.085
- Accuracy: 0.972
- Macro F1: 0.972
- Micro F1: 0.972
- Weighted F1: 0.972
- Macro Precision: 0.972
- Micro Precision: 0.972
- Weighted Precision: 0.972
- Macro Recall: 0.972
- Micro Recall: 0.972
- Weighted Recall: 0.972
## Usage
You can use cURL to access this model:
```
$ curl -X POST -H "Authorization: Bearer YOUR_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "Elemento di decorazione architettonica a rilievo"}' https://api-inference.huggingface.co/models/davanstrien/autotrain-cultural_heritage_metadata_accuracy-48840118272
```
You can also use the model locally be leveraging a Transformers [pipeline](https://huggingface.co/docs/transformers/pipeline_tutorial)
```
from transformers import pipeline
pipe = pipeline('text-classification', model='biglam/cultural_heritage_metadata_accuracy')
pipe("Elemento di decorazione architettonica a rilievo")
``` | [
"TEXT_CLASSIFICATION"
] | Non_BioNLP |
spacemanidol/flan-t5-small-4-4-cnndm | spacemanidol | text2text-generation | [
"transformers",
"pytorch",
"t5",
"text2text-generation",
"generated_from_trainer",
"dataset:cnn_dailymail",
"model-index",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | 1,676,648,132,000 | 2023-02-17T15:44:30 | 14 | 0 | ---
datasets:
- cnn_dailymail
metrics:
- rouge
tags:
- generated_from_trainer
model-index:
- name: small-4-4-t
results:
- task:
type: summarization
name: Summarization
dataset:
name: cnn_dailymail 3.0.0
type: cnn_dailymail
config: 3.0.0
split: validation
args: 3.0.0
metrics:
- type: rouge
value: 37.3132
name: Rouge1
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# small-4-4-t
This model is a fine-tuned version of [asy/cnndm/small-4-4/](https://huggingface.co/asy/cnndm/small-4-4/) on the cnn_dailymail 3.0.0 dataset.
It achieves the following results on the evaluation set:
- Loss: 1.8408
- Rouge1: 37.3132
- Rouge2: 16.1976
- Rougel: 26.8328
- Rougelsum: 34.601
- Gen Len: 79.8280
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- num_epochs: 3.0
### Training results
### Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1
- Tokenizers 0.12.1
| [
"SUMMARIZATION"
] | Non_BioNLP |
suha1234/pegasus_covid19 | suha1234 | text2text-generation | [
"transformers",
"pytorch",
"pegasus",
"text2text-generation",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 1,646,263,745,000 | 2021-10-29T14:37:37 | 112 | 0 | ---
{}
---
__PEGASUS FOR COVID 19 LITERATURE SUMMARIZATION__
__Model Description:__
Pegasus-large fine Tuned on Covid 19 literature.
__Dataset:__
The data is the CORD-19 dataset, containing over 400,000 scholarly articles, including over 150,000 with full text, about COVID-19, SARS-CoV-2, and related coronaviruses.
Among these 1000 articles and their abstracts were used for fine tuning.
| [
"SUMMARIZATION"
] | BioNLP |
parsi-ai-nlpclass/image-generation-mt5-finetune | parsi-ai-nlpclass | null | [
"safetensors",
"mt5",
"region:us"
] | 1,723,281,710,000 | 2024-09-26T07:38:17 | 7 | 0 | ---
{}
---
# Persian-to-Image Text-to-Image Pipeline
## Model Overview
This model pipeline is designed to generate images from Persian text descriptions. It works by first translating the Persian text into English and then using a fine-tuned Stable Diffusion model to generate the corresponding image. The pipeline combines two models: a translation model (`mohammad-shirkhani/finetune_persian_to_english_mt5_base_summarize_on_celeba_hq`) and an image generation model (`ebrahim-k/Stable-Diffusion-1_5-FT-celeba_HQ_en`).
## Model Details
### Translation Model
- **Model Name**: `mohammad-shirkhani/finetune_persian_to_english_mt5_base_summarize_on_celeba_hq`
- **Architecture**: mT5
- **Purpose**: This model translates Persian text into English. It has been fine-tuned on the CelebA-HQ dataset for summarization tasks, making it effective for translating descriptions of facial features.
### Image Generation Model
- **Model Name**: `ebrahim-k/Stable-Diffusion-1_5-FT-celeba_HQ_en`
- **Architecture**: Stable Diffusion 1.5
- **Purpose**: This model generates high-quality images from English text produced by the translation model. It has been fine-tuned on the CelebA-HQ dataset, which makes it particularly effective for generating realistic human faces based on text descriptions.
## Pipeline Description
The pipeline operates through the following steps:
1. **Text Translation**: The Persian input text is translated into English using the mT5-based translation model.
2. **Image Generation**: The translated English text is then used to generate the corresponding image with the Stable Diffusion model.
### Code Implementation
#### 1. Install Required Libraries
```python
!pip install transformers diffusers accelerate torch
```
#### 2. Import Necessary Libraries
```python
import torch
from transformers import MT5ForConditionalGeneration, T5Tokenizer
from diffusers import StableDiffusionPipeline
```
#### 3. Set Device (GPU or CPU)
This code determines whether the pipeline should use a GPU (if available) or fallback to a CPU.
```python
# Determine the device: GPU if available, otherwise CPU
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(f"Using device: {device}")
```
#### 4. Define and Load the Persian-to-Image Model Class
The following class handles both translation and image generation tasks.
```python
# Define the model class
class PersianToImageModel:
def __init__(self, translation_model_name, image_model_name, device):
self.device = device
# Load translation model
self.translation_model = MT5ForConditionalGeneration.from_pretrained(translation_model_name).to(device)
self.translation_tokenizer = T5Tokenizer.from_pretrained(translation_model_name)
# Load image generation model
self.image_model = StableDiffusionPipeline.from_pretrained(image_model_name).to(device)
def translate_text(self, persian_text):
input_ids = self.translation_tokenizer.encode(persian_text, return_tensors="pt").to(self.device)
translated_ids = self.translation_model.generate(input_ids, max_length=512, num_beams=4, early_stopping=True)
translated_text = self.translation_tokenizer.decode(translated_ids[0], skip_special_tokens=True)
return translated_text
def generate_image(self, english_text):
image = self.image_model(english_text).images[0]
return image
def __call__(self, persian_text):
# Translate Persian text to English
english_text = self.translate_text(persian_text)
print(f"Translated Text: {english_text}")
# Generate and return image
return self.generate_image(english_text)
```
#### 5. Instantiate the Model
The following code snippet demonstrates how to instantiate the combined model.
```python
# Instantiate the combined model
translation_model_name = 'mohammad-shirkhani/finetune_persian_to_english_mt5_base_summarize_on_celeba_hq'
image_model_name = 'ebrahim-k/Stable-Diffusion-1_5-FT-celeba_HQ_en'
persian_to_image_model = PersianToImageModel(translation_model_name, image_model_name, device)
```
#### 6. Example Usage of the Model
Below are examples of how to use the model to generate images from Persian text.
```python
from IPython.display import display
# Persian text describing a person
persian_text = "این زن دارای موهای موج دار ، لب های بزرگ و موهای قهوه ای است و رژ لب دارد.این زن موهای موج دار و لب های بزرگ دارد و رژ لب دارد.فرد جذاب است و موهای موج دار ، چشم های باریک و موهای قهوه ای دارد."
# Generate and display the image
image = persian_to_image_model(persian_text)
display(image)
# Another example
persian_text2 = "این مرد جذاب دارای موهای قهوه ای ، سوزش های جانبی ، دهان کمی باز و کیسه های زیر چشم است.این فرد جذاب دارای کیسه های زیر چشم ، سوزش های جانبی و دهان کمی باز است."
image2 = persian_to_image_model(persian_text2)
display(image2)
``` | [
"TRANSLATION",
"SUMMARIZATION"
] | Non_BioNLP |
Josephgflowers/Phinance-Phi-3.5-mini-instruct-finance-v0.2 | Josephgflowers | text-generation | [
"safetensors",
"phi3",
"financial",
"fine-tuning",
"instruction-tuning",
"mini-LLM",
"finance-dataset",
"multi-turn-conversations",
"RAG",
"lightweight-finance-agent",
"text-generation",
"conversational",
"custom_code",
"en",
"dataset:Josephgflowers/Phinance",
"license:apache-2.0",
"region:us"
] | 1,735,851,776,000 | 2025-01-06T01:55:47 | 28 | 1 | ---
base_model: phi-3.5-mini-instruct
datasets: Josephgflowers/Phinance
language:
- en
license: apache-2.0
pipeline_tag: text-generation
tags:
- financial
- fine-tuning
- instruction-tuning
- mini-LLM
- finance-dataset
- multi-turn-conversations
- RAG
- lightweight-finance-agent
model_type: instruct-LLM
---
# Model Card: Phinance-Phi-3.5-mini-instruct-finance-v0.2
## Overview
**Phinance-Phi-3.5-mini-instruct-finance-v0.2** is a fine-tuned mini language model specifically designed for financial tasks, instruction following, and multi-turn conversations. It leverages the **Phinance Dataset** to excel in finance-specific reasoning, question answering, and lightweight expert applications. The model is based on the **phi-3.5-mini** architecture, optimized for instruction-based workflows in the financial domain.
### Key Features
- **Finance-Focused Reasoning**: Handles complex tasks like portfolio analysis, market trends, and financial question answering.
- **Instruction Following**: Trained for fine-grained instruction-based tasks within the financial sector.
- **Multi-Turn Conversations**: Designed to handle context-aware dialogue with a focus on finance.
- **RAG-Compatible**: Supports retrieval-augmented generation (RAG) through the use of data tokens (`<|data|>`) to integrate external data seamlessly.
- **Lightweight Architecture**: Efficient for deployment on resource-constrained environments while maintaining robust performance.
## Training Data
The model was fine-tuned on the **Phinance Dataset**, a curated subset of financial content. The dataset includes multi-turn conversations formatted in **PHI style**, with financial relevance scored using advanced keyword matching.
### Dataset Highlights:
- **Topics**: Market trends, investment strategies, financial analysis, and more.
- **Format**: Conversations in PHI format, including data tokens (`<|data|>`) for RAG use cases.
- **Filtering**: High-quality finance-relevant content scored and selected using advanced methods.
## Supported Tasks
1. **Financial QA**: Answer complex questions about market analysis, financial terms, or investment strategies.
2. **Multi-Turn Conversations**: Engage in context-aware dialogues about financial topics.
3. **Instruction Following**: Execute finance-specific instructions and prompts with precision.
4. **Lightweight Finance Domain Expert Agent**: Serve as an efficient, finance-focused assistant for lightweight systems.
5. **Retrieval-Augmented Generation (RAG)**: Seamlessly integrate external data using the `<|data|>` token for enhanced responses.
## Usage
This model is ideal for:
- Financial advisors or assistants
- Chatbots and conversational agents
- Financial QA systems
- Lightweight domain-specific applications for finance
### Help Here
Like my work? Want to see more? Custom request? Message me on discord: joseph.flowers.ra Donate here: https://buymeacoffee.com/josephgflowers
### How to Use
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "Josephgflowers/Phinance-Phi-3.5-mini-instruct-finance-v0.2"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)
# Example usage
inputs = tokenizer("Explain the difference between stocks and bonds.", return_tensors="pt")
outputs = model.generate(**inputs)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
Limitations and Considerations
Niche Knowledge: While proficient in financial topics, the model may not perform as well on general-purpose tasks.
Bias: Data filtering may introduce biases toward certain financial sectors or topics.
Hallucinations: As with any language model, responses should be verified for accuracy in critical applications.
Model Details
Base Model: phi-3.5-mini
Fine-Tuned Dataset: Phinance Dataset
Version: v0.2
Parameters: Mini-sized architecture for efficient performance
Training Framework: Hugging Face Transformers
License
This model is licensed under the Apache 2.0 license.
Citation
If you use this model, please cite:
@model{phinance_phi_3_5_mini_instruct_v0_2,
title={Phinance-Phi-3.5-mini-instruct-finance-v0.2},
author={Joseph G. Flowers},
year={2025},
url={https://huggingface.co/Josephgflowers/Phinance-Phi-3.5-mini-instruct-finance-v0.2}
}
| [
"QUESTION_ANSWERING"
] | Non_BioNLP |
gokuls/hBERTv2_new_pretrain_w_init_48_ver2_qnli | gokuls | text-classification | [
"transformers",
"pytorch",
"hybridbert",
"text-classification",
"generated_from_trainer",
"en",
"dataset:glue",
"base_model:gokuls/bert_12_layer_model_v2_complete_training_new_wt_init_48",
"base_model:finetune:gokuls/bert_12_layer_model_v2_complete_training_new_wt_init_48",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 1,697,586,499,000 | 2023-10-18T02:24:10 | 34 | 0 | ---
base_model: gokuls/bert_12_layer_model_v2_complete_training_new_wt_init_48
datasets:
- glue
language:
- en
metrics:
- accuracy
tags:
- generated_from_trainer
model-index:
- name: hBERTv2_new_pretrain_w_init_48_ver2_qnli
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: GLUE QNLI
type: glue
config: qnli
split: validation
args: qnli
metrics:
- type: accuracy
value: 0.5053999633900788
name: Accuracy
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# hBERTv2_new_pretrain_w_init_48_ver2_qnli
This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2_complete_training_new_wt_init_48](https://huggingface.co/gokuls/bert_12_layer_model_v2_complete_training_new_wt_init_48) on the GLUE QNLI dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6931
- Accuracy: 0.5054
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 4e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 0.7008 | 1.0 | 1637 | 0.6943 | 0.5054 |
| 0.6946 | 2.0 | 3274 | 0.6931 | 0.5054 |
| 0.6938 | 3.0 | 4911 | 0.6932 | 0.4946 |
| 0.6943 | 4.0 | 6548 | 0.6934 | 0.5054 |
| 0.694 | 5.0 | 8185 | 0.6933 | 0.4946 |
| 0.6932 | 6.0 | 9822 | 0.6931 | 0.5054 |
| 0.6934 | 7.0 | 11459 | 0.6931 | 0.5054 |
| 0.6932 | 8.0 | 13096 | 0.6931 | 0.5054 |
| 0.6932 | 9.0 | 14733 | 0.6932 | 0.4946 |
| 0.6932 | 10.0 | 16370 | 0.6933 | 0.4946 |
| 0.6932 | 11.0 | 18007 | 0.6931 | 0.5054 |
| 0.6932 | 12.0 | 19644 | 0.6931 | 0.5054 |
| 0.6932 | 13.0 | 21281 | 0.6931 | 0.4946 |
### Framework versions
- Transformers 4.34.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.14.5
- Tokenizers 0.14.1
| [
"TEXT_CLASSIFICATION"
] | Non_BioNLP |
Shobhank-iiitdwd/RoBERTA-rrQA | Shobhank-iiitdwd | question-answering | [
"transformers",
"pytorch",
"tf",
"jax",
"roberta",
"question-answering",
"en",
"dataset:squad_v2",
"license:cc-by-4.0",
"model-index",
"endpoints_compatible",
"region:us"
] | 1,673,421,850,000 | 2023-01-13T10:25:41 | 14 | 0 | ---
datasets:
- squad_v2
language: en
license: cc-by-4.0
model-index:
- name: Shobhank-iiitdwd/RoBERTA-rrQA
results:
- task:
type: question-answering
name: Question Answering
dataset:
name: squad_v2
type: squad_v2
config: squad_v2
split: validation
metrics:
- type: exact_match
value: 79.9309
name: Exact Match
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMDhhNjg5YzNiZGQ1YTIyYTAwZGUwOWEzZTRiYzdjM2QzYjA3ZTUxNDM1NjE1MTUyMjE1MGY1YzEzMjRjYzVjYiIsInZlcnNpb24iOjF9.EH5JJo8EEFwU7osPz3s7qanw_tigeCFhCXjSfyN0Y1nWVnSfulSxIk_DbAEI5iE80V4EKLyp5-mYFodWvL2KDA
- type: f1
value: 82.9501
name: F1
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMjk5ZDYwOGQyNjNkMWI0OTE4YzRmOTlkY2JjNjQ0YTZkNTMzMzNkYTA0MDFmNmI3NjA3NjNlMjhiMDQ2ZjJjNSIsInZlcnNpb24iOjF9.DDm0LNTkdLbGsue58bg1aH_s67KfbcmkvL-6ZiI2s8IoxhHJMSf29H_uV2YLyevwx900t-MwTVOW3qfFnMMEAQ
- type: total
value: 11869
name: total
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMGFkMmI2ODM0NmY5NGNkNmUxYWViOWYxZDNkY2EzYWFmOWI4N2VhYzY5MGEzMTVhOTU4Zjc4YWViOGNjOWJjMCIsInZlcnNpb24iOjF9.fexrU1icJK5_MiifBtZWkeUvpmFISqBLDXSQJ8E6UnrRof-7cU0s4tX_dIsauHWtUpIHMPZCf5dlMWQKXZuAAA
---
# roberta-base for QA
This is the [roberta-base](https://huggingface.co/roberta-base) model, fine-tuned using the [SQuAD2.0](https://huggingface.co/datasets/squad_v2) dataset. It's been trained on question-answer pairs, including unanswerable questions, for the task of Question Answering.
## Overview
**Language model:** roberta-base
**Language:** English
**Downstream-task:** Extractive QA
**Training data:** SQuAD 2.0
**Eval data:** SQuAD 2.0
## Hyperparameters
```
batch_size = 96
n_epochs = 2
base_LM_model = "roberta-base"
max_seq_len = 386
learning_rate = 3e-5
lr_schedule = LinearWarmup
warmup_proportion = 0.2
doc_stride=128
max_query_length=64
``` The distilled model has a comparable prediction quality and runs at twice the speed of the base model.
## Usage
### In Haystack
Haystack is an NLP framework by deepset. You can use this model in a Haystack pipeline to do question answering at scale (over many documents). To load the model in [Haystack](https://github.com/deepset-ai/haystack/):
```python
reader = FARMReader(model_name_or_path="Shobhank-iiitdwd/RoBERTA-rrQA")
# or
reader = TransformersReader(model_name_or_path="Shobhank-iiitdwd/RoBERTA-rrQA",tokenizer="Shobhank-iiitdwd/RoBERTA-rrQA")
```
### In Transformers
```python
from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline
model_name = "Shobhank-iiitdwd/RoBERTA-rrQA"
# a) Get predictions
nlp = pipeline('question-answering', model=model_name, tokenizer=model_name)
QA_input = {
'question': 'Why is model conversion important?',
'context': 'The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks.'
}
res = nlp(QA_input)
# b) Load model & tokenizer
model = AutoModelForQuestionAnswering.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
```
## Performance
Evaluated on the SQuAD 2.0 dev set with the [official eval script](https://worksheets.codalab.org/rest/bundles/0x6b567e1cf2e041ec80d7098f031c5c9e/contents/blob/).
```
"exact": 79.87029394424324,
"f1": 82.91251169582613,
"total": 11873,
"HasAns_exact": 77.93522267206478,
"HasAns_f1": 84.02838248389763,
"HasAns_total": 5928,
"NoAns_exact": 81.79983179142137,
"NoAns_f1": 81.79983179142137,
"NoAns_total": 5945
``` | [
"QUESTION_ANSWERING"
] | Non_BioNLP |
kimwooglae/distilbert-base-uncased-finetuned-emotion | kimwooglae | text-classification | [
"transformers",
"pytorch",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:emotion",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 1,696,297,568,000 | 2023-10-03T02:55:55 | 10 | 0 | ---
base_model: distilbert-base-uncased
datasets:
- emotion
license: apache-2.0
metrics:
- accuracy
- f1
tags:
- generated_from_trainer
model-index:
- name: distilbert-base-uncased-finetuned-emotion
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: emotion
type: emotion
config: split
split: validation
args: split
metrics:
- type: accuracy
value: 0.926
name: Accuracy
- type: f1
value: 0.926109887824797
name: F1
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert-base-uncased-finetuned-emotion
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2133
- Accuracy: 0.926
- F1: 0.9261
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| No log | 1.0 | 250 | 0.3191 | 0.9055 | 0.9041 |
| No log | 2.0 | 500 | 0.2133 | 0.926 | 0.9261 |
### Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
| [
"TEXT_CLASSIFICATION"
] | Non_BioNLP |
hojzas/setfit-proj8 | hojzas | text-classification | [
"setfit",
"safetensors",
"mpnet",
"sentence-transformers",
"text-classification",
"generated_from_setfit_trainer",
"dataset:hojzas/proj8-label2",
"arxiv:2209.11055",
"base_model:sentence-transformers/paraphrase-mpnet-base-v2",
"base_model:finetune:sentence-transformers/paraphrase-mpnet-base-v2",
"co2_eq_emissions",
"region:us"
] | 1,706,118,007,000 | 2024-01-24T17:40:28 | 3 | 0 | ---
base_model: sentence-transformers/paraphrase-mpnet-base-v2
datasets:
- hojzas/proj8-label2
library_name: setfit
metrics:
- accuracy
pipeline_tag: text-classification
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: 'def first_with_given_key(iterable, key=lambda x: x):\n keys_used = {}\n for
item in iterable:\n rp = repr(key(item))\n if rp not in keys_used.keys():\n keys_used[rp]
= repr(item)\n yield item'
- text: 'def first_with_given_key(iterable, key=lambda x: x):\n keys=[]\n for
i in iterable:\n if key(i) not in keys:\n yield i\n keys.append(key(i))'
- text: 'def first_with_given_key(iterable, key=repr):\n set_of_keys = set()\n lambda_key
= (lambda x: key(x))\n for item in iterable:\n key = lambda_key(item)\n try:\n key_for_set
= hash(key)\n except TypeError:\n key_for_set = repr(key)\n if
key_for_set in set_of_keys:\n continue\n set_of_keys.add(key_for_set)\n yield
item'
- text: 'def first_with_given_key(iterable, key = lambda x: x):\n found_keys={}\n for
i in iterable:\n if key(i) not in found_keys.keys():\n found_keys[key(i)]=i\n yield
i'
- text: 'def first_with_given_key(the_iterable, key=lambda x: x):\n temp_keys=[]\n for
i in range(len(the_iterable)):\n if (key(the_iterable[i]) not in temp_keys):\n temp_keys.append(key(the_iterable[i]))\n yield
the_iterable[i]\n del temp_keys'
inference: true
co2_eq_emissions:
emissions: 0.2520929621561019
source: codecarbon
training_type: fine-tuning
on_cloud: false
cpu_model: Intel(R) Xeon(R) Silver 4314 CPU @ 2.40GHz
ram_total_size: 251.49160385131836
hours_used: 0.005
---
# SetFit with sentence-transformers/paraphrase-mpnet-base-v2
This is a [SetFit](https://github.com/huggingface/setfit) model trained on the [hojzas/proj8-label2](https://huggingface.co/datasets/hojzas/proj8-label2) dataset that can be used for Text Classification. This SetFit model uses [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
The model has been trained using an efficient few-shot learning technique that involves:
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.
## Model Details
### Model Description
- **Model Type:** SetFit
- **Sentence Transformer body:** [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2)
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
- **Maximum Sequence Length:** 512 tokens
- **Number of Classes:** 2 classes
- **Training Dataset:** [hojzas/proj8-label2](https://huggingface.co/datasets/hojzas/proj8-label2)
<!-- - **Language:** Unknown -->
<!-- - **License:** Unknown -->
### Model Sources
- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
### Model Labels
| Label | Examples |
|:------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| 0 | <ul><li>'def first_with_given_key(iterable, key=lambda x: x):\\n keys_in_list = []\\n for it in iterable:\\n if key(it) not in keys_in_list:\\n keys_in_list.append(key(it))\\n yield it'</li><li>'def first_with_given_key(iterable, key=lambda value: value):\\n it = iter(iterable)\\n saved_keys = []\\n while True:\\n try:\\n value = next(it)\\n if key(value) not in saved_keys:\\n saved_keys.append(key(value))\\n yield value\\n except StopIteration:\\n break'</li><li>'def first_with_given_key(iterable, key=None):\\n if key is None:\\n key = lambda x: x\\n item_list = []\\n key_set = set()\\n for item in iterable:\\n generated_item = key(item)\\n if generated_item not in item_list:\\n item_list.append(generated_item)\\n yield item'</li></ul> |
| 1 | <ul><li>'def first_with_given_key(lst, key = lambda x: x):\\n res = set()\\n for i in lst:\\n if repr(key(i)) not in res:\\n res.add(repr(key(i)))\\n yield i'</li><li>'def first_with_given_key(iterable, key=repr):\\n set_of_keys = set()\\n lambda_key = (lambda x: key(x))\\n for item in iterable:\\n key = lambda_key(item)\\n try:\\n key_for_set = hash(key)\\n except TypeError:\\n key_for_set = repr(key)\\n if key_for_set in set_of_keys:\\n continue\\n set_of_keys.add(key_for_set)\\n yield item'</li><li>'def first_with_given_key(iterable, key=None):\\n if key is None:\\n key = identity\\n appeared_keys = set()\\n for item in iterable:\\n generated_key = key(item)\\n if not generated_key.__hash__:\\n generated_key = repr(generated_key)\\n if generated_key not in appeared_keys:\\n appeared_keys.add(generated_key)\\n yield item'</li></ul> |
## Uses
### Direct Use for Inference
First install the SetFit library:
```bash
pip install setfit
```
Then you can load this model and run inference.
```python
from setfit import SetFitModel
# Download from the 🤗 Hub
model = SetFitModel.from_pretrained("hojzas/setfit-proj8")
# Run inference
preds = model("def first_with_given_key(iterable, key=lambda x: x):\n keys=[]\n for i in iterable:\n if key(i) not in keys:\n yield i\n keys.append(key(i))")
```
<!--
### Downstream Use
*List how someone could finetune this model on their own dataset.*
-->
<!--
### Out-of-Scope Use
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->
<!--
## Bias, Risks and Limitations
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
-->
<!--
### Recommendations
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
-->
## Training Details
### Training Set Metrics
| Training set | Min | Median | Max |
|:-------------|:----|:-------|:----|
| Word count | 43 | 90.28 | 119 |
| Label | Training Sample Count |
|:------|:----------------------|
| 0 | 20 |
| 1 | 5 |
### Training Hyperparameters
- batch_size: (16, 16)
- num_epochs: (1, 1)
- max_steps: -1
- sampling_strategy: oversampling
- num_iterations: 20
- body_learning_rate: (2e-05, 2e-05)
- head_learning_rate: 2e-05
- loss: CosineSimilarityLoss
- distance_metric: cosine_distance
- margin: 0.25
- end_to_end: False
- use_amp: False
- warmup_proportion: 0.1
- seed: 42
- eval_max_steps: -1
- load_best_model_at_end: False
### Training Results
| Epoch | Step | Training Loss | Validation Loss |
|:------:|:----:|:-------------:|:---------------:|
| 0.0159 | 1 | 0.3158 | - |
| 0.7937 | 50 | 0.0022 | - |
### Environmental Impact
Carbon emissions were measured using [CodeCarbon](https://github.com/mlco2/codecarbon).
- **Carbon Emitted**: 0.000 kg of CO2
- **Hours Used**: 0.005 hours
### Training Hardware
- **On Cloud**: No
- **GPU Model**: No GPU used
- **CPU Model**: Intel(R) Xeon(R) Silver 4314 CPU @ 2.40GHz
- **RAM Size**: 251.49 GB
### Framework Versions
- Python: 3.10.12
- SetFit: 1.0.3
- Sentence Transformers: 2.2.2
- Transformers: 4.36.1
- PyTorch: 2.1.2+cu121
- Datasets: 2.14.7
- Tokenizers: 0.15.1
## Citation
### BibTeX
```bibtex
@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
<!--
## Glossary
*Clearly define terms in order to be accessible across audiences.*
-->
<!--
## Model Card Authors
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->
<!--
## Model Card Contact
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
--> | [
"TEXT_CLASSIFICATION"
] | Non_BioNLP |
Helsinki-NLP/opus-mt-cs-eo | Helsinki-NLP | translation | [
"transformers",
"pytorch",
"tf",
"marian",
"text2text-generation",
"translation",
"cs",
"eo",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | 1,646,263,744,000 | 2023-08-16T11:27:10 | 54 | 0 | ---
language:
- cs
- eo
license: apache-2.0
tags:
- translation
---
### ces-epo
* source group: Czech
* target group: Esperanto
* OPUS readme: [ces-epo](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/ces-epo/README.md)
* model: transformer-align
* source language(s): ces
* target language(s): epo
* model: transformer-align
* pre-processing: normalization + SentencePiece (spm4k,spm4k)
* download original weights: [opus-2020-06-16.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/ces-epo/opus-2020-06-16.zip)
* test set translations: [opus-2020-06-16.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/ces-epo/opus-2020-06-16.test.txt)
* test set scores: [opus-2020-06-16.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/ces-epo/opus-2020-06-16.eval.txt)
## Benchmarks
| testset | BLEU | chr-F |
|-----------------------|-------|-------|
| Tatoeba-test.ces.epo | 26.0 | 0.459 |
### System Info:
- hf_name: ces-epo
- source_languages: ces
- target_languages: epo
- opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/ces-epo/README.md
- original_repo: Tatoeba-Challenge
- tags: ['translation']
- languages: ['cs', 'eo']
- src_constituents: {'ces'}
- tgt_constituents: {'epo'}
- src_multilingual: False
- tgt_multilingual: False
- prepro: normalization + SentencePiece (spm4k,spm4k)
- url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/ces-epo/opus-2020-06-16.zip
- url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/ces-epo/opus-2020-06-16.test.txt
- src_alpha3: ces
- tgt_alpha3: epo
- short_pair: cs-eo
- chrF2_score: 0.45899999999999996
- bleu: 26.0
- brevity_penalty: 0.94
- ref_len: 24901.0
- src_name: Czech
- tgt_name: Esperanto
- train_date: 2020-06-16
- src_alpha2: cs
- tgt_alpha2: eo
- prefer_old: False
- long_pair: ces-epo
- helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
- transformers_git_sha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b
- port_machine: brutasse
- port_time: 2020-08-21-14:41 | [
"TRANSLATION"
] | Non_BioNLP |
kinetical/llama3.2-3b-simulMT-et-en | kinetical | null | [
"gguf",
"et",
"ru",
"en",
"base_model:meta-llama/Llama-3.2-3B-Instruct",
"base_model:quantized:meta-llama/Llama-3.2-3B-Instruct",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | 1,728,545,526,000 | 2024-11-09T03:25:00 | 18 | 3 | ---
base_model:
- meta-llama/Llama-3.2-3B-Instruct
language:
- et
- ru
- en
license: apache-2.0
---
# Simultaneous Machine Translation between English and Estonian using Llama-3.2
## Introduction
This is a llama-3.2 3B instruct model finetuned on 500k pairs of sentences sampled from NLLB and WikiMatrix, in all directions between Estonian, Russian, and English, accompanied with a few other languages randomly sampled.
This model is very good at translating in simultaneous manner, i.e. it can handle incomplete and streaming inputs. Try to type your sentence in piece meal : every few words, hit enter and see the model translates as you go.
## How to run it
First, install `llama.cpp`, follow https://github.com/ggerganov/llama.cpp?tab=readme-ov-file
Then, pull the quantized gguf file, and run the following command:
#### Estonian to English direction
```bash
llama-cli -m Llama-3.2-3B-Instruct-Q4_K_M.gguf \
-p "You are a professional Estonian-to-English simultaneous interpreter. Translate the following conversations into English." \
-cnv \
--chat-template llama3 \
-c 4096 --temp 0.0
```
#### English to Estonian direction
change the system above to "You are a professional English-to-Estonian simultaneous interpreter. Translate the following conversations into Estonian.", i.e.
```bash
llama-cli -m Llama-3.2-3B-Instruct-Q4_K_M.gguf \
-p "You are a professional English-to-Estonian simultaneous interpreter. Translate the following conversations into Estonian." \
-cnv \
--chat-template llama3 \
-c 4096 --temp 0.0
```
Now you can try to type in sentences that you want to translate.
- You may try to type in a few words, hit enter, and repeat. The model should be able to translate simultaneously.
- You can also try to input a full sentence.
- It's not great for a paragraph (yet, still). | [
"TRANSLATION"
] | Non_BioNLP |
Subsets and Splits