README.md

metadata

base_model: m42-health/Llama3-Med42-8B
language:
  - en
license: llama3
license_name: llama3
pipeline_tag: text-generation
tags:
  - m42
  - health
  - healthcare
  - clinical-llm
  - mlx
inference: false

mlx-community/Llama3-Med42-8B

The Model mlx-community/Llama3-Med42-8B was converted to MLX format from m42-health/Llama3-Med42-8B using mlx-lm version 0.20.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Llama3-Med42-8B")

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)