license, license_name, license_link, language, pipeline_tag, tags, library_name, inference, model_creator, quantized_by, base_model, model_name, datasets

license	license_name	license_link	language	pipeline_tag	tags	library_name	inference	model_creator	quantized_by	base_model	model_name	datasets
other	qwen-research	https://huggingface.co/Qwen/Qwen2.5-3B/blob/main/LICENSE	fr en	text-generation	chat qwen qwen2.5 finetune french legal loi	transformers	false	MaziyarPanahi	MaziyarPanahi	Qwen/Qwen2.5-3B	calme-3.3-baguette-3b	MaziyarPanahi/calme-legalkit-v0.2

Tip

This is avery small model, so it might not perform well for some prompts and may be sensitive to hyper parameters. I would appreciate any feedback to see if I can fix any issues in the next iteration. ❤️

MaziyarPanahi/calme-3.3-baguette-3b

This model is an advanced iteration of the powerful Qwen/Qwen2.5-3B, specifically fine-tuned to enhance its capabilities in French Legal domain.

⚡ Quantized GGUF

All GGUF models are available here: MaziyarPanahi/calme-3.3-baguette-3b-GGUF

🏆 Open LLM Leaderboard Evaluation Results

Leaderboard 2 coming soon!

Prompt Template

This model uses ChatML prompt template:

<|im_start|>system
{System}
<|im_end|>
<|im_start|>user
{User}
<|im_end|>
<|im_start|>assistant
{Assistant}

How to use

# Use a pipeline as a high-level helper

from transformers import pipeline

messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe = pipeline("text-generation", model="MaziyarPanahi/calme-3.3-baguette-3b")
pipe(messages)


# Load model directly

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MaziyarPanahi/calme-3.3-baguette-3b")
model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/calme-3.3-baguette-3b")

Ethical Considerations

As with any large language model, users should be aware of potential biases and limitations. We recommend implementing appropriate safeguards and human oversight when deploying this model in production environments.