Instructions to use FINGU-AI/Chocolatine-Fusion-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FINGU-AI/Chocolatine-Fusion-14B with Transformers:

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

pipe = pipeline("text-generation", model="FINGU-AI/Chocolatine-Fusion-14B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FINGU-AI/Chocolatine-Fusion-14B")
model = AutoModelForCausalLM.from_pretrained("FINGU-AI/Chocolatine-Fusion-14B")
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

vLLM

How to use FINGU-AI/Chocolatine-Fusion-14B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FINGU-AI/Chocolatine-Fusion-14B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FINGU-AI/Chocolatine-Fusion-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FINGU-AI/Chocolatine-Fusion-14B

SGLang

How to use FINGU-AI/Chocolatine-Fusion-14B 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 "FINGU-AI/Chocolatine-Fusion-14B" \
    --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": "FINGU-AI/Chocolatine-Fusion-14B",
		"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 "FINGU-AI/Chocolatine-Fusion-14B" \
        --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": "FINGU-AI/Chocolatine-Fusion-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FINGU-AI/Chocolatine-Fusion-14B with Docker Model Runner:
```
docker model run hf.co/FINGU-AI/Chocolatine-Fusion-14B
```

Chocolatine-Fusion-14B

FINGU-AI/Chocolatine-Fusion-14B is a merged model combining jpacifico/Chocolatine-2-14B-Instruct-v2.0b3 and jpacifico/Chocolatine-2-14B-Instruct-v2.0b2. This model maintains the strengths of Chocolatine while benefiting from an optimized fusion for improved reasoning and multi-turn conversation capabilities.

Training & Fine-Tuning

Chocolatine-Fusion-14B is based on DPO fine-tuning from the Chocolatine-2 series, which originated as a fine-tuned version of sometimesanotion/Lamarck-14B-v0.7.

The model has been trained using French and English RLHF datasets (including jpacifico/french-orca-dpo-pairs-revised) for enhanced bilingual capabilities.
Long-context support has been extended up to 128K tokens with the ability to generate up to 8K tokens.

OpenLLM Leaderboard

Coming soon.

MT-Bench

Coming soon.

Usage

You can run this model 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("FINGU-AI/Chocolatine-Fusion-14B")
prompt = tokenizer.apply_chat_template(message, add_generation_prompt=True, tokenize=False)

# Create pipeline
pipeline = transformers.pipeline(
    "text-generation",
    model="FINGU-AI/Chocolatine-Fusion-14B",
    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

Chocolatine-Fusion-14B is a demonstration of model merging techniques rather than a standalone fine-tuned model.

It does not have any built-in moderation mechanisms.
Responses may vary based on the interaction and prompt style.
Performance on highly technical or domain-specific queries may require further fine-tuning.

Developed by

Author: FINGU-AI, 2025
Base Models: jpacifico/Chocolatine-2-14B-Instruct-v2.0b3, jpacifico/Chocolatine-2-14B-Instruct-v2.0b2
Language(s): French, English
Model Type: Merged LLM
License: Apache-2.0

Downloads last month: 35

Safetensors

Model size

15B params

Tensor type

F32

F16

FINGU-AI
/

Chocolatine-Fusion-14B