README.md

---
datasets: open-r1/openr1-220k-math
library_name: transformers
model_name: OpenR1-Qwen-7B
tags:
- generated_from_trainer
- trl
- sft
- mlx
licence: license
license: apache-2.0
base_model: open-r1/OpenR1-Qwen-7B
---

# mlx-community/OpenR1-Qwen-7B-4bit

The Model [mlx-community/OpenR1-Qwen-7B-4bit](https://huggingface.co/mlx-community/OpenR1-Qwen-7B-4bit) was
converted to MLX format from [open-r1/OpenR1-Qwen-7B](https://huggingface.co/open-r1/OpenR1-Qwen-7B)
using mlx-lm version **0.21.4**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/OpenR1-Qwen-7B-4bit")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```