---
license: apache-2.0
license_link: https://huggingface.co/huihui-ai/Qwen2.5-14B-Instruct-1M-abliterated/blob/main/LICENSE
language:
- en
pipeline_tag: text-generation
base_model: huihui-ai/Qwen2.5-14B-Instruct-1M-abliterated
tags:
- chat
- abliterated
- uncensored
- mlx
library_name: mlx
---

# CallMcMargin/Qwen2.5-14B-Instruct-1M-abliterated-mlx-bf16-affine-qgroup32-q5

This model [CallMcMargin/Qwen2.5-14B-Instruct-1M-abliterated-mlx-bf16-affine-qgroup32-q5](https://huggingface.co/CallMcMargin/Qwen2.5-14B-Instruct-1M-abliterated-mlx-bf16-affine-qgroup32-q5) was
converted to MLX format from [huihui-ai/Qwen2.5-14B-Instruct-1M-abliterated](https://huggingface.co/huihui-ai/Qwen2.5-14B-Instruct-1M-abliterated)
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("CallMcMargin/Qwen2.5-14B-Instruct-1M-abliterated-mlx-bf16-affine-qgroup32-q5")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```