README.md

---
base_model: omlab/Qwen2.5VL-3B-VLM-R1-REC-500steps
tags:
- mlx
---

# mlx-community/Qwen2.5VL-3B-VLM-R1

The Model [mlx-community/Qwen2.5VL-3B-VLM-R1](https://huggingface.co/mlx-community/Qwen2.5VL-3B-VLM-R1) was
converted to MLX format from [omlab/Qwen2.5VL-3B-VLM-R1-REC-500steps](https://huggingface.co/omlab/Qwen2.5VL-3B-VLM-R1-REC-500steps)
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/Qwen2.5VL-3B-VLM-R1")

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)
```