README.md

---
license: mit
language:
- ja
- en
pipeline_tag: translation
library_name: transformers
tags:
- translation
- machine-translation
- japanese
- english
- mlx
- mlx-my-repo
base_model: cyberagent/CAT-Translate-7b
---

# moutons/CAT-Translate-7b-mlx-4Bit

The Model [moutons/CAT-Translate-7b-mlx-4Bit](https://huggingface.co/moutons/CAT-Translate-7b-mlx-4Bit) was converted to MLX format from [cyberagent/CAT-Translate-7b](https://huggingface.co/cyberagent/CAT-Translate-7b) using mlx-lm version **0.31.2**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("moutons/CAT-Translate-7b-mlx-4Bit")

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)
```