---
language:
- en
license: llama3
tags:
- m42
- health
- healthcare
- clinical-llm
- mlx
- mlx-my-repo
pipeline_tag: text-generation
inference: false
license_name: llama3
base_model: m42-health/Llama3-Med42-70B
---

# sjgdr/Llama3-Med42-70B-mlx-6Bit

The Model [sjgdr/Llama3-Med42-70B-mlx-6Bit](https://huggingface.co/sjgdr/Llama3-Med42-70B-mlx-6Bit) was converted to MLX format from [m42-health/Llama3-Med42-70B](https://huggingface.co/m42-health/Llama3-Med42-70B) using mlx-lm version **0.26.4**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("sjgdr/Llama3-Med42-70B-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)
```