README.md

---
license: mit
datasets:
- microsoft/mediflow
- ncbi/pubmed
- epfl-llm/guidelines
- starmpcc/Asclepius-Synthetic-Clinical-Notes
- akemiH/NoteChat
- zhengyun21/PMC-Patients
- jpcorb20/medical_wikipedia
language:
- en
base_model: microsoft/MediPhi-Instruct
library_name: mlx
tags:
- merge
- mergekit
- medical
- clinical
- mlx
pipeline_tag: text-generation
---

# mlx-community/MediPhi-Instruct-bf16

This model [mlx-community/MediPhi-Instruct-bf16](https://huggingface.co/mlx-community/MediPhi-Instruct-bf16) was
converted to MLX format from [microsoft/MediPhi-Instruct](https://huggingface.co/microsoft/MediPhi-Instruct)
using mlx-lm version **0.25.3**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/MediPhi-Instruct-bf16")

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)
```