|
--- |
|
license: cc-by-nc-4.0 |
|
base_model: mlabonne/OmniBeagle14-7B |
|
datasets: |
|
- yleo/emerton_dpo_pairs |
|
tags: |
|
- dpo |
|
--- |
|
--- |
|
|
|
# 🦜 ParrotOgno-7B |
|
|
|
ParrotOgno-7B is a DPO fine-tune of [paulml/OGNO-7B](https://huggingface.co/paulml/OGNO-7B) using the [yleo/emerton_dpo_pairs_judge](https://huggingface.co/datasets/yleo/emerton_dpo_pairs_judge) preference dataset created from [Intel/orca_dpo_pairs](https://huggingface.co/datasets/Intel/orca_dpo_pairs) by replacing gpt 3.5 answer by a gpt4 Turbo answer. Then, gpt4 Turbo is put as chosen whereas gpt4 is put as rejected. |
|
|
|
## 🔍 Applications |
|
|
|
This model uses a context window of 8k. It is compatible with different templates, like chatml and Llama's chat template. |
|
|
|
## 🏆 Evaluation |
|
|
|
### Open LLM Leaderboard |
|
|
|
To come... |
|
|
|
## 💻 Usage |
|
|
|
```python |
|
!pip install -qU transformers accelerate |
|
from transformers import AutoTokenizer |
|
import transformers |
|
import torch |
|
model = "yleo/ParrotOgno-7B" |
|
messages = [{"role": "user", "content": "How to improve LLM fine-tuning?"}] |
|
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"]) |
|
``` |
