README.md

metadata

base_model: HPAI-BSC/Llama3.1-Aloe-Beta-8B
datasets:
  - HPAI-BSC/Aloe-Beta-General-Collection
  - HPAI-BSC/chain-of-diagnosis
  - HPAI-BSC/MedS-Ins
  - HPAI-BSC/ultramedical
  - HPAI-BSC/pubmedqa-cot-llama31
  - HPAI-BSC/medqa-cot-llama31
  - HPAI-BSC/medmcqa-cot-llama31
  - HPAI-BSC/headqa-cot-llama31
  - HPAI-BSC/MMLU-medical-cot-llama31
  - HPAI-BSC/Polymed-QA
  - HPAI-BSC/Aloe-Beta-General-Collection
  - HPAI-BSC/Aloe-Beta-General-Collection
language:
  - en
library_name: transformers
license: llama3.1
pipeline_tag: question-answering
tags:
  - biology
  - medical
  - healthcare
  - mlx

mlx-community/Llama3.1-Aloe-Beta-8B

The Model mlx-community/Llama3.1-Aloe-Beta-8B was converted to MLX format from HPAI-BSC/Llama3.1-Aloe-Beta-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/Llama3.1-Aloe-Beta-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)