README.md

---
language:
- en
license: apache-2.0
library_name: transformers
tags:
- code
- qwen-coder
- finetune
- mlx
base_model: WhiteRabbitNeo/WhiteRabbitNeo-2.5-Qwen-2.5-Coder-7B
pipeline_tag: text-generation
---

# mitkox/WhiteRabbitNeo-2.5-Qwen-2.5-Coder-7B-mlx

The Model [mitkox/WhiteRabbitNeo-2.5-Qwen-2.5-Coder-7B-mlx](https://huggingface.co/mitkox/WhiteRabbitNeo-2.5-Qwen-2.5-Coder-7B-mlx) was converted to MLX format from [WhiteRabbitNeo/WhiteRabbitNeo-2.5-Qwen-2.5-Coder-7B](https://huggingface.co/WhiteRabbitNeo/WhiteRabbitNeo-2.5-Qwen-2.5-Coder-7B) using mlx-lm version **0.18.2**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mitkox/WhiteRabbitNeo-2.5-Qwen-2.5-Coder-7B-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)
```