README.md

---
license: apache-2.0
base_model: Kwaipilot/KAT-Dev-72B-Exp
tags:
- mlx
---

# m-i/KAT-Dev-72B-Exp-mlx-8Bit

The Model [m-i/KAT-Dev-72B-Exp-mlx-8Bit](https://huggingface.co/m-i/KAT-Dev-72B-Exp-mlx-8Bit) was converted to MLX format from [Kwaipilot/KAT-Dev-72B-Exp](https://huggingface.co/Kwaipilot/KAT-Dev-72B-Exp) using mlx-lm version **0.26.4**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("m-i/KAT-Dev-72B-Exp-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)
```