---
license: apache-2.0
tags:
- chat
- mlx
- mlx-my-repo
library_name: transformers
language:
- en
- zh
base_model: baichuan-inc/Baichuan-M2-32B
---

# laukerry/Baichuan-M2-32B-mlx-8Bit

The Model [laukerry/Baichuan-M2-32B-mlx-8Bit](https://huggingface.co/laukerry/Baichuan-M2-32B-mlx-8Bit) was converted to MLX format from [baichuan-inc/Baichuan-M2-32B](https://huggingface.co/baichuan-inc/Baichuan-M2-32B) using mlx-lm version **0.26.0**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("laukerry/Baichuan-M2-32B-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)
```