---
language:
- en
license: apache-2.0
datasets:
- HuggingFaceH4/ultrachat_200k
- Felladrin/ChatML-ultrachat_200k
base_model: Felladrin/Minueza-32M-Base
pipeline_tag: text-generation
widget:
- messages:
  - role: system
    content: You are a career counselor. The user will provide you with an individual
      looking for guidance in their professional life, and your task is to assist
      them in determining what careers they are most suited for based on their skills,
      interests, and experience. You should also conduct research into the various
      options available, explain the job market trends in different industries, and
      advice on which qualifications would be beneficial for pursuing particular fields.
  - role: user
    content: Heya!
  - role: assistant
    content: Hi! How may I help you?
  - role: user
    content: I am interested in developing a career in software engineering. What
      would you recommend me to do?
- messages:
  - role: user
    content: Morning!
  - role: assistant
    content: Good morning! How can I help you today?
  - role: user
    content: Could you give me some tips for becoming a healthier person?
- messages:
  - role: user
    content: Write the specs of a game about mages in a fantasy world.
- messages:
  - role: user
    content: Tell me about the pros and cons of social media.
- messages:
  - role: system
    content: You are a highly knowledgeable and friendly assistant. Your goal is to
      understand and respond to user inquiries with clarity. Your interactions are
      always respectful, helpful, and focused on delivering the most accurate information
      to the user.
  - role: user
    content: Hey! Got a question for you!
  - role: assistant
    content: Sure! What's it?
  - role: user
    content: What are some potential applications for quantum computing?
inference:
  parameters:
    max_new_tokens: 250
    do_sample: true
    temperature: 0.65
    top_p: 0.55
    top_k: 35
    repetition_penalty: 1.176
model-index:
- name: Minueza-32M-UltraChat
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: AI2 Reasoning Challenge (25-Shot)
      type: ai2_arc
      config: ARC-Challenge
      split: test
      args:
        num_few_shot: 25
    metrics:
    - type: acc_norm
      value: 21.08
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Minueza-32M-UltraChat
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: HellaSwag (10-Shot)
      type: hellaswag
      split: validation
      args:
        num_few_shot: 10
    metrics:
    - type: acc_norm
      value: 26.95
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Minueza-32M-UltraChat
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU (5-Shot)
      type: cais/mmlu
      config: all
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 26.08
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Minueza-32M-UltraChat
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: TruthfulQA (0-shot)
      type: truthful_qa
      config: multiple_choice
      split: validation
      args:
        num_few_shot: 0
    metrics:
    - type: mc2
      value: 47.7
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Minueza-32M-UltraChat
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: Winogrande (5-shot)
      type: winogrande
      config: winogrande_xl
      split: validation
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 51.78
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Minueza-32M-UltraChat
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GSM8k (5-shot)
      type: gsm8k
      config: main
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 0.23
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Minueza-32M-UltraChat
      name: Open LLM Leaderboard
---

# Minueza-32M-UltraChat: A chat model with 32 million parameters

- Base model: [Felladrin/Minueza-32M-Base](https://huggingface.co/Felladrin/Minueza-32M-Base)
- Dataset: [[ChatML](https://huggingface.co/datasets/Felladrin/ChatML-ultrachat_200k)] [HuggingFaceH4/ultrachat_200k](https://huggingface.co/datasets/HuggingFaceH4/ultrachat_200k)
- License: [Apache License 2.0](https://huggingface.co/Felladrin/Minueza-32M-UltraChat/resolve/main/license.txt)
- Availability in other ML formats:
  - GGUF: [Felladrin/gguf-Minueza-32M-UltraChat](https://huggingface.co/Felladrin/gguf-Minueza-32M-UltraChat)
  - ONNX: [Felladrin/onnx-Minueza-32M-UltraChat](https://huggingface.co/Felladrin/onnx-Minueza-32M-UltraChat)

## Recommended Prompt Format

```
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{user_message}<|im_end|>
<|im_start|>assistant
```

## Recommended Inference Parameters

```yml
do_sample: true
temperature: 0.65
top_p: 0.55
top_k: 35
repetition_penalty: 1.176
```

## Usage Example

```python
from transformers import pipeline

generate = pipeline("text-generation", "Felladrin/Minueza-32M-UltraChat")

messages = [
    {
        "role": "system",
        "content": "You are a highly knowledgeable and friendly assistant. Your goal is to understand and respond to user inquiries with clarity. Your interactions are always respectful, helpful, and focused on delivering the most accurate information to the user.",
    },
    {
        "role": "user",
        "content": "Hey! Got a question for you!",
    },
    {
        "role": "assistant",
        "content": "Sure! What's it?",
    },
    {
        "role": "user",
        "content": "What are some potential applications for quantum computing?",
    },
]

prompt = generate.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)

output = generate(
    prompt,
    max_new_tokens=256,
    do_sample=True,
    temperature=0.65,
    top_k=35,
    top_p=0.55,
    repetition_penalty=1.176,
)

print(output[0]["generated_text"])
```

## How it was trained

This model was trained with [SFTTrainer](https://huggingface.co/docs/trl/main/en/sft_trainer) using the following settings:

| Hyperparameter         | Value                                         |
| :--------------------- | :-------------------------------------------- |
| Learning rate          | 2e-5                                          |
| Total train batch size | 16                                            |
| Max. sequence length   | 2048                                          |
| Weight decay           | 0                                             |
| Warmup ratio           | 0.1                                           |
| Optimizer              | Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| Scheduler              | cosine                                        |
| Seed                   | 42                                            |

## [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)

Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Felladrin__Minueza-32M-UltraChat)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |28.97|
|AI2 Reasoning Challenge (25-Shot)|21.08|
|HellaSwag (10-Shot)              |26.95|
|MMLU (5-Shot)                    |26.08|
|TruthfulQA (0-shot)              |47.70|
|Winogrande (5-shot)              |51.78|
|GSM8k (5-shot)                   | 0.23|