---
language:
- en
- fr
- it
- de
- es
- pl
license: apache-2.0
pipeline_tag: text-generation
tags:
- transformers
- mlx
- mlx-my-repo
library_name: transformers
datasets:
- PleIAs/SYNTH
base_model: PleIAs/Baguettotron
---

# tomasmcm/Baguettotron-mlx-fp16

The Model [tomasmcm/Baguettotron-mlx-fp16](https://huggingface.co/tomasmcm/Baguettotron-mlx-fp16) was converted to MLX format from [PleIAs/Baguettotron](https://huggingface.co/PleIAs/Baguettotron) 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("tomasmcm/Baguettotron-mlx-fp16")

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)
```