---
base_model: KaraKaraWitch/Golddiamondgold-Paperbliteration-L33-70b
library_name: transformers
tags:
- heretic
- uncensored
- abliterated
- llama-3
- mlx
- mlx-my-repo
license: other
---

# labrystechresearch/Golddiamondgold-Paperbliteration-L33-70b-mlx-4Bit

The Model [labrystechresearch/Golddiamondgold-Paperbliteration-L33-70b-mlx-4Bit](https://huggingface.co/labrystechresearch/Golddiamondgold-Paperbliteration-L33-70b-mlx-4Bit) was converted to MLX format from [KaraKaraWitch/Golddiamondgold-Paperbliteration-L33-70b](https://huggingface.co/KaraKaraWitch/Golddiamondgold-Paperbliteration-L33-70b) using mlx-lm version **0.29.1**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("labrystechresearch/Golddiamondgold-Paperbliteration-L33-70b-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)
```