metadata

base_model: epfl-llm/meditron-7b
datasets:
  - epfl-llm/guidelines
language:
  - en
license: llama2
metrics:
  - accuracy
  - perplexity
tags:
  - mlx

mlx-community/meditron-7b

The Model mlx-community/meditron-7b was converted to MLX format from epfl-llm/meditron-7b 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/meditron-7b")

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)