Instructions to use jpacifico/Chocolatine-32B-Instruct-DPO-v1.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jpacifico/Chocolatine-32B-Instruct-DPO-v1.2 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="jpacifico/Chocolatine-32B-Instruct-DPO-v1.2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jpacifico/Chocolatine-32B-Instruct-DPO-v1.2")
model = AutoModelForCausalLM.from_pretrained("jpacifico/Chocolatine-32B-Instruct-DPO-v1.2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jpacifico/Chocolatine-32B-Instruct-DPO-v1.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jpacifico/Chocolatine-32B-Instruct-DPO-v1.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jpacifico/Chocolatine-32B-Instruct-DPO-v1.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jpacifico/Chocolatine-32B-Instruct-DPO-v1.2

SGLang

How to use jpacifico/Chocolatine-32B-Instruct-DPO-v1.2 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "jpacifico/Chocolatine-32B-Instruct-DPO-v1.2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jpacifico/Chocolatine-32B-Instruct-DPO-v1.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "jpacifico/Chocolatine-32B-Instruct-DPO-v1.2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jpacifico/Chocolatine-32B-Instruct-DPO-v1.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jpacifico/Chocolatine-32B-Instruct-DPO-v1.2 with Docker Model Runner:
```
docker model run hf.co/jpacifico/Chocolatine-32B-Instruct-DPO-v1.2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Chocolatine-32B-Instruct-DPO-v1.2

DPO fine-tuned of rombodawg/Rombos-LLM-V2.5-Qwen-32b based on Qwen/Qwen2.5-32B using the jpacifico/french-orca-dpo-pairs-revised rlhf dataset.
Training in French also improves the model, including in English, surpassing the performance of its base model.

Long-context Support up to 128K tokens and can generate up to 8K tokens.

OpenLLM Leaderboard

Coming soon.

OpenLLM French 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

Downloads last month: 8

Safetensors

Model size

33B params

Tensor type

F16

Model tree for jpacifico/Chocolatine-32B-Instruct-DPO-v1.2

Merges

2 models

Quantizations