---
license: apache-2.0
library_name: transformers
pipeline_tag: text-generation
base_model: xwen-team/Xwen-72B-Chat
language:
- en
- zh
tags:
- mlx
---

# exdysa/Xwen-72B-Chat-Q4-mlx

The Model [exdysa/Xwen-72B-Chat-Q4-mlx](https://huggingface.co/exdysa/Xwen-72B-Chat-Q4-mlx) was converted to MLX format from [xwen-team/Xwen-72B-Chat](https://huggingface.co/xwen-team/Xwen-72B-Chat) using mlx-lm version **0.20.5**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("exdysa/Xwen-72B-Chat-Q4-mlx")

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)
```