README.md

---
license_name: tongyi-qianwen-research
license_link: https://huggingface.co/Qwen/CodeQwen1.5-7B/blob/main/LICENSE
tags:
- code
- mlx
- mlx-my-repo
pipeline_tag: text-generation
license: other
base_model: NTQAI/Nxcode-CQ-7B-orpo
---

# imgrind/Nxcode-CQ-7B-orpo-mlx-4Bit

The Model [imgrind/Nxcode-CQ-7B-orpo-mlx-4Bit](https://huggingface.co/imgrind/Nxcode-CQ-7B-orpo-mlx-4Bit) was converted to MLX format from [NTQAI/Nxcode-CQ-7B-orpo](https://huggingface.co/NTQAI/Nxcode-CQ-7B-orpo) using mlx-lm version **0.28.3**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("imgrind/Nxcode-CQ-7B-orpo-mlx-4Bit")

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)
```