warshanks's picture
Upload README.md with huggingface_hub
3ead37d verified
|
raw
history blame
1.56 kB
---
license: other
license_name: health-ai-developer-foundations
license_link: https://developers.google.com/health-ai-developer-foundations/terms
library_name: transformers
pipeline_tag: image-text-to-text
extra_gated_heading: Access MedGemma on Hugging Face
extra_gated_prompt: To access MedGemma on Hugging Face, you're required to review
and agree to [Health AI Developer Foundation's terms of use](https://developers.google.com/health-ai-developer-foundations/terms).
To do this, please ensure you're logged in to Hugging Face and click below. Requests
are processed immediately.
extra_gated_button_content: Acknowledge license
base_model: google/medgemma-27b-text-it
tags:
- medical
- clinical-reasoning
- thinking
- mlx
- mlx-my-repo
---
# mlx-community/medgemma-27b-text-it-8bit
The Model [mlx-community/medgemma-27b-text-it-8bit](https://huggingface.co/mlx-community/medgemma-27b-text-it-8bit) was converted to MLX format from [google/medgemma-27b-text-it](https://huggingface.co/google/medgemma-27b-text-it) using mlx-lm version **0.24.1**.
## Use with mlx
```bash
pip install mlx-lm
```
```python
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/medgemma-27b-text-it-8bit")
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)
```