README.md

---
license: apache-2.0
language:
- en
base_model: alamios/QwQwen-0.5B
pipeline_tag: text-generation
library_name: transformers
tags:
- qwen
- qwen2.5
- qwq
- mlx
- mlx-my-repo
---

# janboe91/QwQwen-0.5B-mlx-8Bit

The Model [janboe91/QwQwen-0.5B-mlx-8Bit](https://huggingface.co/janboe91/QwQwen-0.5B-mlx-8Bit) was converted to MLX format from [alamios/QwQwen-0.5B](https://huggingface.co/alamios/QwQwen-0.5B) using mlx-lm version **0.22.1**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("janboe91/QwQwen-0.5B-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)
```