---
language:
- fr
- en
library_name: transformers
tags:
- dpo
- post-training
- french
- alignment
- model-merging
- qwen3
- chocolatine
- comparia
- mlx
- mlx-my-repo
license: apache-2.0
base_model: jpacifico/Chocolatine-2-4B-Instruct-DPO-v2.1
datasets:
- jpacifico/comparia-dpo-pairs-bt-6k
- jpacifico/french-orca-dpo-pairs-revised
---

# jpacifico/Chocolatine-2-4B-Instruct-DPO-v2.1-mlx-8Bit

The Model [jpacifico/Chocolatine-2-4B-Instruct-DPO-v2.1-mlx-8Bit](https://huggingface.co/jpacifico/Chocolatine-2-4B-Instruct-DPO-v2.1-mlx-8Bit) was converted to MLX format from [jpacifico/Chocolatine-2-4B-Instruct-DPO-v2.1](https://huggingface.co/jpacifico/Chocolatine-2-4B-Instruct-DPO-v2.1) using mlx-lm version **0.29.1**.

## Use with mlx

```bash
pip install mlx-lm
```

```python
from mlx_lm import load, generate

model, tokenizer = load("jpacifico/Chocolatine-2-4B-Instruct-DPO-v2.1-mlx-8Bit")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```