README.md

---
license: apache-2.0
language:
- en
- zh
base_model: MooreThreads/MusaCoder-27B
pipeline_tag: reinforcement-learning
tags:
- CUDA
- MUSA
- GPU-Kernel
- Reinforcement-Learning
- mlx
- mlx-my-repo
---

# cnfusion/MusaCoder-27B-mlx-4Bit

The Model [cnfusion/MusaCoder-27B-mlx-4Bit](https://huggingface.co/cnfusion/MusaCoder-27B-mlx-4Bit) was converted to MLX format from [MooreThreads/MusaCoder-27B](https://huggingface.co/MooreThreads/MusaCoder-27B) 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("cnfusion/MusaCoder-27B-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)
```