---
tags:
- text-generation-inference
- transformers
- sft
- chocolatine
license: mit
language:
- fr
---

# Description model

Chocolatine-3B version specialized in French culinary language, supervised fine-tuning of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct).    
This model is based on 283 specific terms and definitions of French cuisine. 

# Fine Tuning

Fine tuning done efficiently with Unsloth,
with which I saved processing time on a single T4 GPU (AzureML compute instance).

For this version of the model I experimented a training method with a double fine-tuning, SFT then DPO.  
I generated two datasets exclusively for this model, with GPT-4o deployed on Azure OpenAI.  
The challenge was to achieve a consistent alignment between the two fine-tuning methods.   
SFT to teach the terms and DPO to reinforce the understanding achieved during the first learning.  

# Usage

The recommended usage is by loading the low-rank adapter using unsloth:

```python
from unsloth import FastLanguageModel

model_name = "jpacifico/chocolatine-admin-3B-sft-v0.2"
model, tokenizer = FastLanguageModel.from_pretrained(
  model_name = model_name,
  max_seq_length = 2048,
  dtype = None,
  load_in_4bit = True,
)

FastLanguageModel.for_inference(model)
```

### 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
- **License:** MIT
- **Finetuned from model :** microsoft/Phi-3.5-mini-instruct