Instructions to use medicalai/ClinicalGPT-base-zh with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use medicalai/ClinicalGPT-base-zh with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="medicalai/ClinicalGPT-base-zh")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("medicalai/ClinicalGPT-base-zh")
model = AutoModelForCausalLM.from_pretrained("medicalai/ClinicalGPT-base-zh", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use medicalai/ClinicalGPT-base-zh with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "medicalai/ClinicalGPT-base-zh"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "medicalai/ClinicalGPT-base-zh",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/medicalai/ClinicalGPT-base-zh

SGLang

How to use medicalai/ClinicalGPT-base-zh with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "medicalai/ClinicalGPT-base-zh" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "medicalai/ClinicalGPT-base-zh",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "medicalai/ClinicalGPT-base-zh" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "medicalai/ClinicalGPT-base-zh",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use medicalai/ClinicalGPT-base-zh with Docker Model Runner:
```
docker model run hf.co/medicalai/ClinicalGPT-base-zh
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

ClinicalGPT

This model card introduces ClinicalGPT model, a large language model designed and optimized for clinical scenarios. ClinicalGPT is fine-tuned on extensive and diverse medical datasets, including medical records, domain-specific knowledge, and multi-round dialogue consultations. The model is undergoing ongoing and continuous updates.

Model Fine-tuning

We set the learning rate to 5e-5, with a batch size of 128 and a maximum length of 1,024, training across 3 epochs.

How to use the model

Load the model via the transformers library:

from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("medicalai/ClinicalGPT-base-zh")
model = AutoModelForCausalLM.from_pretrained("medicalai/ClinicalGPT-base-zh")

Limitations

The project is intended for research purposes only and restricted from commercial or clinical use. The generated content by the model is subject to factors such as model computations, randomness, misinterpretation, and biases, and this project cannot guarantee its accuracy. This project assumes no legal liability for any content produced by the model. Users are advised to exercise caution and independently verify the generated results.

Citation

Please cite these articles:
1.Wang, G., Liu, X., Liu, H., Yang, G. et al. A Generalist Medical Language Model for Disease Diagnosis Assistance. Nat Med (2025). https://doi.org/10.1038/s41591-024-03416-6
2.Wang, G., Yang, G., Du, Z., Fan, L., & Li, X. (2023). ClinicalGPT: large language models finetuned with diverse medical data and comprehensive evaluation. arXiv preprint arXiv:2306.09968.

Downloads last month: 92

Model tree for medicalai/ClinicalGPT-base-zh

Quantizations

2 models

Spaces using medicalai/ClinicalGPT-base-zh 6

Paper for medicalai/ClinicalGPT-base-zh

ClinicalGPT: Large Language Models Finetuned with Diverse Medical Data and Comprehensive Evaluation

Paper • 2306.09968 • Published Jun 16, 2023