MedExQA: Medical Question Answering Benchmark with Multiple Explanations
Paper • 2406.06331 • Published
How to use bluesky333/medphi2 with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="bluesky333/medphi2", trust_remote_code=True) # Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("bluesky333/medphi2", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("bluesky333/medphi2", trust_remote_code=True)How to use bluesky333/medphi2 with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bluesky333/medphi2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "bluesky333/medphi2",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/bluesky333/medphi2
How to use bluesky333/medphi2 with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "bluesky333/medphi2" \
--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": "bluesky333/medphi2",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'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 "bluesky333/medphi2" \
--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": "bluesky333/medphi2",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use bluesky333/medphi2 with Docker Model Runner:
docker model run hf.co/bluesky333/medphi2
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("bluesky333/medphi2", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("bluesky333/medphi2", trust_remote_code=True)MedPhi-2 is a Phi-2, 2.7 billion parameters, further trained for the biomedical domain. It was proposed in MedExQA paper.
📄 Paper • ⏬ Dataset • ⚕️ MedPhi2
BibTeX:
@article{kim2024medexqa,
title={MedExQA: Medical Question Answering Benchmark with Multiple Explanations},
author={Kim, Yunsoo and Wu, Jinge and Abdulle, Yusuf and Wu, Honghan},
journal={arXiv e-prints},
pages={arXiv--2406},
year={2024}
}
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="bluesky333/medphi2", trust_remote_code=True)