README.md

metadata

license: apache-2.0
datasets:
  - FreedomIntelligence/medical-o1-reasoning-SFT
  - FreedomIntelligence/medical-o1-verifiable-problem
language:
  - en
base_model: FreedomIntelligence/HuatuoGPT-o1-8B
pipeline_tag: text-generation
tags:
  - medical
  - mlx
  - mlx-my-repo

cnfusion/HuatuoGPT-o1-8B-Q4-mlx

The Model cnfusion/HuatuoGPT-o1-8B-Q4-mlx was converted to MLX format from FreedomIntelligence/HuatuoGPT-o1-8B using mlx-lm version 0.20.5.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("cnfusion/HuatuoGPT-o1-8B-Q4-mlx")

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)