---
library_name: transformers
license: other
license_name: qwen
license_link: https://huggingface.co/huihui-ai/Qwen2.5-72B-Instruct-abliterated/blob/main/LICENSE
language:
- en
pipeline_tag: text-generation
base_model: huihui-ai/Qwen2.5-72B-Instruct-abliterated
tags:
- chat
- abliterated
- uncensored
- mlx
- mlx-my-repo
---

# YuHaaa/Qwen2.5-72B-Instruct-abliterated-mlx-4Bit

The Model [YuHaaa/Qwen2.5-72B-Instruct-abliterated-mlx-4Bit](https://huggingface.co/YuHaaa/Qwen2.5-72B-Instruct-abliterated-mlx-4Bit) was converted to MLX format from [huihui-ai/Qwen2.5-72B-Instruct-abliterated](https://huggingface.co/huihui-ai/Qwen2.5-72B-Instruct-abliterated) 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("YuHaaa/Qwen2.5-72B-Instruct-abliterated-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)
```