README.md

---
license: apache-2.0
datasets:
- FreedomIntelligence/medical-o1-reasoning-SFT
- FreedomIntelligence/medical-o1-verifiable-problem
language:
- en
- zh
base_model: FreedomIntelligence/HuatuoGPT-o1-72B
pipeline_tag: text-generation
tags:
- medical
- mlx
---

# mlx-community/HuatuoGPT-o1-72B-4bit

The Model [mlx-community/HuatuoGPT-o1-72B-4bit](https://huggingface.co/mlx-community/HuatuoGPT-o1-72B-4bit) was
converted to MLX format from [FreedomIntelligence/HuatuoGPT-o1-72B](https://huggingface.co/FreedomIntelligence/HuatuoGPT-o1-72B)
using mlx-lm version **0.20.6**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/HuatuoGPT-o1-72B-4bit")

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)
```