85 lines
2.6 KiB
Markdown
85 lines
2.6 KiB
Markdown
|
---
|
||
|
|
library_name: transformers
|
||
|
|
license: apache-2.0
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
language:
|
||
|
|
- en
|
||
|
|
- zh
|
||
|
|
base_model:
|
||
|
|
- Qwen/Qwen3-8B-Base
|
||
|
|
tags:
|
||
|
|
- medical
|
||
|
|
- reasoning
|
||
|
|
---
|
||
|
|
|
||
|
|
<div align="center">
|
||
|
|
<h1>🩺 HuatuoGPT-3-8B</h1>
|
||
|
|
</div>
|
||
|
|
|
||
|
|
<div align="center">
|
||
|
|
<a href="https://github.com/FreedomIntelligence/HuatuoGPT-3" target="_blank">🏠 GitHub</a>
|
||
|
|
|
|
||
|
|
<a href="" target="_blank">📄 Paper</a>
|
||
|
|
</div>
|
||
|
|
|
||
|
|
# <span>Introduction</span>
|
||
|
|
|
||
|
|
**HuatuoGPT-3** is an open-source medical LLM trained with **SeedRL**, an RL-only domain adaptation paradigm that transforms a base model into a medical expert in a single RL stage.
|
||
|
|
|
||
|
|
For more information, visit our GitHub repository:
|
||
|
|
[https://github.com/FreedomIntelligence/HuatuoGPT-3](https://github.com/FreedomIntelligence/HuatuoGPT-3)
|
||
|
|
|
||
|
|
> [!IMPORTANT]
|
||
|
|
> **HuatuoGPT-3-8B is set to thinking mode by default.** The output contains a `<think>...</think>` reasoning block followed by the final response after `</think>`.
|
||
|
|
|
||
|
|
# <span>Model Info</span>
|
||
|
|
|
||
|
|
| Model | Description | Backbone | Link |
|
||
|
|
| --- | --- | --- | --- |
|
||
|
|
| **HuatuoGPT-3-32B** | 32B medical LLM trained with SeedRL | Qwen3-32B | [HF Link](https://huggingface.co/FreedomIntelligence/HuatuoGPT-3-32B) |
|
||
|
|
| **HuatuoGPT-3-8B** | 8B medical LLM trained with SeedRL | Qwen3-8B-Base | [HF Link](https://huggingface.co/FreedomIntelligence/HuatuoGPT-3-8B) |
|
||
|
|
| **HuatuoGPT-3-7B-Pangu** | 7B medical LLM trained with SeedRL | openPangu-Embedded-7B | [HF Link](https://huggingface.co/FreedomIntelligence/HuatuoGPT-3-7B-Pangu) |
|
||
|
|
|
||
|
|
# <span>Usage</span>
|
||
|
|
|
||
|
|
You can use HuatuoGPT-3-8B in the same way as `Qwen3-8B`. You can deploy it with tools like [vLLM](https://github.com/vllm-project/vllm) or [SGLang](https://github.com/sgl-project/sglang), or perform direct inference:
|
||
|
|
|
||
|
|
```python
|
||
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||
|
|
|
||
|
|
model_name = "FreedomIntelligence/HuatuoGPT-3-8B"
|
||
|
|
|
||
|
|
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||
|
|
model = AutoModelForCausalLM.from_pretrained(
|
||
|
|
model_name,
|
||
|
|
torch_dtype="auto",
|
||
|
|
device_map="auto"
|
||
|
|
)
|
||
|
|
|
||
|
|
messages = [
|
||
|
|
{"role": "user", "content": "What are the common causes of chest pain?"}
|
||
|
|
]
|
||
|
|
|
||
|
|
text = tokenizer.apply_chat_template(
|
||
|
|
messages,
|
||
|
|
tokenize=False,
|
||
|
|
add_generation_prompt=True
|
||
|
|
)
|
||
|
|
|
||
|
|
inputs = tokenizer([text], return_tensors="pt").to(model.device)
|
||
|
|
outputs = model.generate(**inputs, max_new_tokens=4096)
|
||
|
|
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
||
|
|
```
|
||
|
|
|
||
|
|
|
||
|
|
# <span>📖 Citation</span>
|
||
|
|
|
||
|
|
```bibtex
|
||
|
|
@article{huatuogpt3,
|
||
|
|
title={HuatuoGPT-3: RL-Only Domain Adaptation from Base Models via Off-Policy Seeding},
|
||
|
|
author={Coming soon},
|
||
|
|
journal={arXiv preprint},
|
||
|
|
year={2026}
|
||
|
|
}
|
||
|
|
```
|