README.md

---
base_model: Ba2han/QwQenSeek-coder
library_name: transformers
tags:
- mergekit
- merge
- mlx
- mlx-my-repo
---

# m-i/QwQenSeek-coder-Q8-mlx

The Model [m-i/QwQenSeek-coder-Q8-mlx](https://huggingface.co/m-i/QwQenSeek-coder-Q8-mlx) was converted to MLX format from [Ba2han/QwQenSeek-coder](https://huggingface.co/Ba2han/QwQenSeek-coder) 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("m-i/QwQenSeek-coder-Q8-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)
```