README.md

---
language:
- fr
- en
pipeline_tag: text-generation
tags:
- chat
- llama
- llama3
- finetune
- french
- legal
- loi
library_name: transformers
inference: false
model_creator: MaziyarPanahi
quantized_by: MaziyarPanahi
base_model: meta-llama/Llama-3.2-3B
model_name: calme-3.3-llamaloi-3b
datasets:
- MaziyarPanahi/calme-legalkit-v0.2
license: llama3.2
---

<img src="./calme_3.png" alt="Calme-3 Models" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>

# MaziyarPanahi/calme-3.3-llamaloi-3b

This model is an advanced iteration of the powerful `meta-llama/Llama-3.2-3B`, specifically fine-tuned to enhance its capabilities in French Legal domain.


# ⚡ Quantized GGUF

All GGUF models are available here: [MaziyarPanahi/calme-3.3-llamaloi-3b-GGUF](https://huggingface.co/MaziyarPanahi/calme-3.3-llamaloi-3b-GGUF)


# 🏆 [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)

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


```python

# 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-llamaloi-3b")
pipe(messages)


# Load model directly

from transformers import AutoTokenizer, AutoModelForCausalLM

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