jpacifico/Chocolatine-78B-Instruct-DPO-v1.3

Chocolatine-78B-Instruct-DPO-v1.3

DPO fine-tuned of dfurman/CalmeRys-78B-Orpo-v0.1 itself based on multiple fine tunings; initialy based on the foundation model Qwen/Qwen2-72B-Instruct
using the jpacifico/french-orca-dpo-pairs-revised rlhf dataset.

My goal here is to verify whether the French DPO fine-tuning I developed for my Chocolatine model series can be applied with equal performance to model sizes > 70B params,
especially if it can be combined with several previous fine-tunings.

OpenLLM Leaderboard

Coming soon.

Usage

You can run Chocolatine using the following code:

import transformers
from transformers import AutoTokenizer

# Format prompt
message = [
    {"role": "system", "content": "You are a helpful assistant chatbot."},
    {"role": "user", "content": "What is a Large Language Model?"}
]
tokenizer = AutoTokenizer.from_pretrained(new_model)
prompt = tokenizer.apply_chat_template(message, add_generation_prompt=True, tokenize=False)

# Create pipeline
pipeline = transformers.pipeline(
    "text-generation",
    model=new_model,
    tokenizer=tokenizer
)

# Generate text
sequences = pipeline(
    prompt,
    do_sample=True,
    temperature=0.7,
    top_p=0.9,
    num_return_sequences=1,
    max_length=200,
)
print(sequences[0]['generated_text'])

Limitations

The Chocolatine model series is a quick demonstration that a base model can be easily fine-tuned to achieve compelling performance.
It does not have any moderation mechanism.

• Developed by: Jonathan Pacifico, 2024
• Model type: LLM
• Language(s) (NLP): French, English
• License: Apache 2.0

Made with ❤️ in France