Instructions to use medicalai/MedFound-176B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use medicalai/MedFound-176B with Transformers:

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

pipe = pipeline("text-generation", model="medicalai/MedFound-176B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("medicalai/MedFound-176B")
model = AutoModelForCausalLM.from_pretrained("medicalai/MedFound-176B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use medicalai/MedFound-176B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "medicalai/MedFound-176B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "medicalai/MedFound-176B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/medicalai/MedFound-176B

SGLang

How to use medicalai/MedFound-176B 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/MedFound-176B" \
    --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/MedFound-176B",
		"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/MedFound-176B" \
        --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/MedFound-176B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use medicalai/MedFound-176B with Docker Model Runner:
```
docker model run hf.co/medicalai/MedFound-176B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Introduction

For more information, visit our GitHub repository: https://github.com/medfound/medfound

This repository contains the model of the paper A Generalist Medical Language Model for Disease Diagnosis Assistance.

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 this article:
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

Downloads last month: 34

Safetensors

Model size

176B params

Tensor type

F16

Model tree for medicalai/MedFound-176B

Finetunes

1 model

Quantizations

1 model

Paper for medicalai/MedFound-176B

ClinicalGPT-R1: Pushing reasoning capability of generalist disease diagnosis with large language model

Paper • 2504.09421 • Published Apr 13, 2025 • 1