FreedomIntelligence/ShizhenGPT-7B-LLM

<div align="center"> <h1> ShizhenGPT-7B-LLM </h1> </div>

<div align="center"> <a href="https://github.com/FreedomIntelligence/ShizhenGPT" target="blank">GitHub</a> | <a href="https://arxiv.org/abs/2508.14706" target="blank">Paper</a> </div>

ShizhenGPT is the first multimodal LLM for Traditional Chinese Medicine (TCM). It not only possesses strong expertise in TCM, but also supports TCM multimodal diagnostic capabilities, which involve looking (望), listening/smelling (闻), questioning (问), and pulse-taking (切).

👉 More details on GitHub: ShizhenGPT

<span>Model Info</span>

ShizhenGPT-7B-LLM is an LLM-only variant derived from ShizhenGPT-7B-Omni. If your use case requires only text-based capabilities, this version is recommended. Otherwise, please choose the appropriate multimodal version below:

Note: The LLM and VL models are parameter-split variants of ShizhenGPT-7B-Omni. Since their architectures align with Qwen2.5 and Qwen2.5-VL, they are easier to adapt to different environments. In contrast, ShizhenGPT-7B-Omni requires `transformers==4.51.0`.

<span>Usage</span>

You can use ShizhenGPT-7B-LLM in the same way as Qwen2.5-7B-Instruct. You can deploy it with tools like vllm or Sglang, or perform direct inference:

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("FreedomIntelligence/ShizhenGPT-7B-LLM",torch_dtype="auto",device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("FreedomIntelligence/ShizhenGPT-7B-LLM")

input_text = "为什么我总是手脚冰凉，是阳虚吗？"
messages = [{"role": "user", "content": input_text}]

inputs = tokenizer(tokenizer.apply_chat_template(messages, tokenize=False,add_generation_prompt=True
), return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=2048)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

<span>📖 Citation</span>

@misc{chen2025shizhengptmultimodalllmstraditional,
      title={ShizhenGPT: Towards Multimodal LLMs for Traditional Chinese Medicine}, 
      author={Junying Chen and Zhenyang Cai and Zhiheng Liu and Yunjin Yang and Rongsheng Wang and Qingying Xiao and Xiangyi Feng and Zhan Su and Jing Guo and Xiang Wan and Guangjun Yu and Haizhou Li and Benyou Wang},
      year={2025},
      eprint={2508.14706},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2508.14706},
}