metadata

license: cc-by-nc-4.0
base_model: mlabonne/Monarch-7B
datasets:
  - yleo/emerton_dpo_pairs_judge
tags:
  - dpo

🦜 EmertonMonarch-7B

EmertonOmniBeagle-7B-dpo is a DPO fine-tune of mlabonne/Monarch-7B using the yleo/emerton_dpo_pairs_judge preference dataset created from Intel/orca_dpo_pairs by replacing gpt 3.5 answer by a gpt4 Turbo answer. Then, LLM-Blender is used to judge between GPT4 and GPT4 Turbo.

🔍 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

!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "yleo/EmertonMonarch-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"])