README.md

---
license: mit
thumbnail: https://cdn-uploads.huggingface.co/production/uploads/6625f4a8a8d1362ebcc3851a/iyzgR89q50pp1T8HeeP15.png
base_model: ArliAI/GLM-4.5-Air-Derestricted
pipeline_tag: text-generation
tags:
- abliterated
- derestricted
- glm-4.5-air
- unlimited
- uncensored
- mlx
- mlx-my-repo
---

# garrison/GLM-4.5-Air-Derestricted-mlx-2Bit

The Model [garrison/GLM-4.5-Air-Derestricted-mlx-2Bit](https://huggingface.co/garrison/GLM-4.5-Air-Derestricted-mlx-2Bit) was converted to MLX format from [ArliAI/GLM-4.5-Air-Derestricted](https://huggingface.co/ArliAI/GLM-4.5-Air-Derestricted) 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("garrison/GLM-4.5-Air-Derestricted-mlx-2Bit")

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)
```