|
|
--- |
|
|
license: other |
|
|
base_model: cognitivecomputations/dolphin-2.9-llama3-8b-1m |
|
|
library_name: transformers |
|
|
tags: |
|
|
- 4-bit |
|
|
- AWQ |
|
|
- text-generation |
|
|
- autotrain_compatible |
|
|
- endpoints_compatible |
|
|
- generated_from_trainer |
|
|
- axolotl |
|
|
model-index: |
|
|
- name: out |
|
|
results: [] |
|
|
datasets: |
|
|
- cognitivecomputations/Dolphin-2.9 |
|
|
- teknium/OpenHermes-2.5 |
|
|
- m-a-p/CodeFeedback-Filtered-Instruction |
|
|
- cognitivecomputations/dolphin-coder |
|
|
- cognitivecomputations/samantha-data |
|
|
- HuggingFaceH4/ultrachat_200k |
|
|
- microsoft/orca-math-word-problems-200k |
|
|
- abacusai/SystemChat-1.1 |
|
|
- Locutusque/function-calling-chatml |
|
|
- internlm/Agent-FLAN |
|
|
pipeline_tag: text-generation |
|
|
inference: false |
|
|
quantized_by: Suparious |
|
|
--- |
|
|
# cognitivecomputations/dolphin-2.9-llama3-8b-1m AWQ |
|
|
|
|
|
- Model creator: [cognitivecomputations](https://huggingface.co/cognitivecomputations) |
|
|
- Original model: [dolphin-2.9-llama3-8b-1m](https://huggingface.co/cognitivecomputations/dolphin-2.9-llama3-8b-1m) |
|
|
|
|
|
<img src="https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/ldkN1J0WIDQwU4vutGYiD.png" width="600" /> |
|
|
|
|
|
## Model Summary |
|
|
|
|
|
Curated and trained by Eric Hartford, Lucas Atkins, and Fernando Fernandes, and Cognitive Computations |
|
|
|
|
|
This version of Dolphin has a 1 million token context. I have applied `winglian/llama-3-1m-context-gradient-lora` - created by @gradientai and @winglian and sponsored by @CrusoeCloud |
|
|
|
|
|
A bug has been found in the Dolphin 2.9 dataset in SystemConversations that causes the model to overly talk about the "SYSTEM MESSAGE". To counter this, we recommend you add a statement in the system message directing the model not to mention the system message. An example system message is "The assistant is named Dolphin. A helpful and friendly AI assistant, Dolphin avoids discussing the system message unless directly asked about it." |
|
|
|
|
|
My appreciation for the sponsors of Dolphin 2.9: |
|
|
- [Crusoe Cloud](https://crusoe.ai/) - provided excellent on-demand 10xL40S node |
|
|
|
|
|
This model is based on Llama-3-8b, and is governed by [META LLAMA 3 COMMUNITY LICENSE AGREEMENT](LICENSE) |
|
|
|
|
|
The base model has 8k context, and the full-weight fine-tuning was with 4k sequence length. |
|
|
|
|
|
It took 2.5 days on 8x L40S provided by Crusoe Cloud |
|
|
|
|
|
This model was trained FFT on all parameters, using ChatML prompt template format. |
|
|
|
|
|
## How to use |
|
|
|
|
|
### Install the necessary packages |
|
|
|
|
|
```bash |
|
|
pip install --upgrade autoawq autoawq-kernels |
|
|
``` |
|
|
|
|
|
### Example Python code |
|
|
|
|
|
```python |
|
|
from awq import AutoAWQForCausalLM |
|
|
from transformers import AutoTokenizer, TextStreamer |
|
|
|
|
|
model_path = "solidrust/dolphin-2.9-llama3-8b-1m-AWQ" |
|
|
system_message = "You are dolphin-2.9-llama3-8b-1m, incarnated as a powerful AI. You were created by cognitivecomputations." |
|
|
|
|
|
# Load model |
|
|
model = AutoAWQForCausalLM.from_quantized(model_path, |
|
|
fuse_layers=True) |
|
|
tokenizer = AutoTokenizer.from_pretrained(model_path, |
|
|
trust_remote_code=True) |
|
|
streamer = TextStreamer(tokenizer, |
|
|
skip_prompt=True, |
|
|
skip_special_tokens=True) |
|
|
|
|
|
# Convert prompt to tokens |
|
|
prompt_template = """\ |
|
|
<|im_start|>system |
|
|
{system_message}<|im_end|> |
|
|
<|im_start|>user |
|
|
{prompt}<|im_end|> |
|
|
<|im_start|>assistant""" |
|
|
|
|
|
prompt = "You're standing on the surface of the Earth. "\ |
|
|
"You walk one mile south, one mile west and one mile north. "\ |
|
|
"You end up exactly where you started. Where are you?" |
|
|
|
|
|
tokens = tokenizer(prompt_template.format(system_message=system_message,prompt=prompt), |
|
|
return_tensors='pt').input_ids.cuda() |
|
|
|
|
|
# Generate output |
|
|
generation_output = model.generate(tokens, |
|
|
streamer=streamer, |
|
|
max_new_tokens=512) |
|
|
``` |
|
|
|
|
|
### About AWQ |
|
|
|
|
|
AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings. |
|
|
|
|
|
AWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead. |
|
|
|
|
|
It is supported by: |
|
|
|
|
|
- [Text Generation Webui](https://github.com/oobabooga/text-generation-webui) - using Loader: AutoAWQ |
|
|
- [vLLM](https://github.com/vllm-project/vllm) - version 0.2.2 or later for support for all model types. |
|
|
- [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) |
|
|
- [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 and later, from any code or client that supports Transformers |
|
|
- [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) - for use from Python code |
|
|
|
