---
license: other
license_name: health-ai-developer-foundations
license_link: https://developers.google.com/health-ai-developer-foundations/terms
library_name: transformers
pipeline_tag: text-generation
base_model: pszemraj/medgemma-27b-text-heretic_med
tags:
- medical
- clinical-reasoning
- thinking
- heretic
- uncensored
- decensored
- abliterated
- mlx
- mlx-my-repo
language:
- en
---

# Wwayu/medgemma-27b-text-heretic_med-mlx-6Bit

The Model [Wwayu/medgemma-27b-text-heretic_med-mlx-6Bit](https://huggingface.co/Wwayu/medgemma-27b-text-heretic_med-mlx-6Bit) was converted to MLX format from [pszemraj/medgemma-27b-text-heretic_med](https://huggingface.co/pszemraj/medgemma-27b-text-heretic_med) 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("Wwayu/medgemma-27b-text-heretic_med-mlx-6Bit")

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)
```