README.md

---
base_model: mergekit-community/QWQ-Rombos-ties-TEST2
library_name: transformers
tags:
- mergekit
- merge
- mlx
---

# qkC8KADS/QWQ-Rombos-ties-TEST2-mlx_4

The Model [qkC8KADS/QWQ-Rombos-ties-TEST2-mlx_4](https://huggingface.co/qkC8KADS/QWQ-Rombos-ties-TEST2-mlx_4) was
converted to MLX format from [mergekit-community/QWQ-Rombos-ties-TEST2](https://huggingface.co/mergekit-community/QWQ-Rombos-ties-TEST2)
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("qkC8KADS/QWQ-Rombos-ties-TEST2-mlx_4")

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)
```