Instructions to use bluesky333/medphi2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

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)

# pip install -U transformers accelerate
# 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, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bluesky333/medphi2 with vLLM:

Install from pip and serve model

# 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
	}'

Use Docker

docker model run hf.co/bluesky333/medphi2

SGLang

How to use bluesky333/medphi2 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 "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
	}'

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 "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 Model Runner
How to use bluesky333/medphi2 with Docker Model Runner:
```
docker model run hf.co/bluesky333/medphi2
```

Model Summary

MedPhi-2 is a Phi-2, 2.7 billion parameters, further trained for the biomedical domain. It was proposed in MedExQA paper.

🧑‍⚕️ MedExQA

Medical Question Answering Benchmark with Multiple Explanations

📄 Paper • ⏬ Dataset • ⚕️ MedPhi2

Model Details

Model Description

Model type: Clinical LLM (Large Language Model)
Language(s) (NLP): English
License: MIT license
Finetuned from model [optional]: Phi-2

Citation

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}
}

Downloads last month: 19

Safetensors

Model size

3B params

Tensor type

BF16

Paper for bluesky333/medphi2

MedExQA: Medical Question Answering Benchmark with Multiple Explanations

Paper • 2406.06331 • Published Jun 10, 2024