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
```

jpacifico commited on Nov 28, 2024

Commit

9ba59cd

verified ·

1 Parent(s): 7779496

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -1

README.md CHANGED Viewed

@@ -15,6 +15,7 @@ pipeline_tag: text-generation
 DPO fine-tuned of [rombodawg/Rombos-LLM-V2.5-Qwen-32b](https://huggingface.co/rombodawg/Rombos-LLM-V2.5-Qwen-32b) based on [Qwen/Qwen2.5-32B](https://huggingface.co/Qwen/Qwen2.5-32B)
 using the [jpacifico/french-orca-dpo-pairs-revised](https://huggingface.co/datasets/jpacifico/french-orca-dpo-pairs-revised) rlhf dataset.
 Long-context Support up to 128K tokens and can generate up to 8K tokens.
@@ -23,6 +24,10 @@ Long-context Support up to 128K tokens and can generate up to 8K tokens.
 Coming soon.
 ### Usage
 You can run Chocolatine using the following code:
@@ -60,7 +65,7 @@ print(sequences[0]['generated_text'])
 ### Limitations
-The Chocolatine model 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

 DPO fine-tuned of [rombodawg/Rombos-LLM-V2.5-Qwen-32b](https://huggingface.co/rombodawg/Rombos-LLM-V2.5-Qwen-32b) based on [Qwen/Qwen2.5-32B](https://huggingface.co/Qwen/Qwen2.5-32B)
 using the [jpacifico/french-orca-dpo-pairs-revised](https://huggingface.co/datasets/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.
 Coming soon.
+### OpenLLM French leaderboard
+Coming soon.
 ### Usage
 You can run Chocolatine using the following code:
 ### 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