AlpaCare:Instruction-tuned Large Language Models for Medical Application
Paper • 2310.14558 • Published • 4
How to use xz97/AlpaCare-llama2-13b with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="xz97/AlpaCare-llama2-13b") # Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("xz97/AlpaCare-llama2-13b")
model = AutoModelForCausalLM.from_pretrained("xz97/AlpaCare-llama2-13b")How to use xz97/AlpaCare-llama2-13b with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xz97/AlpaCare-llama2-13b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "xz97/AlpaCare-llama2-13b",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/xz97/AlpaCare-llama2-13b
How to use xz97/AlpaCare-llama2-13b with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "xz97/AlpaCare-llama2-13b" \
--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": "xz97/AlpaCare-llama2-13b",
"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 "xz97/AlpaCare-llama2-13b" \
--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": "xz97/AlpaCare-llama2-13b",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use xz97/AlpaCare-llama2-13b with Docker Model Runner:
docker model run hf.co/xz97/AlpaCare-llama2-13b
This is the model weight of AlpaCare-LLaMA2-13B. AlpaCare are LLMs tuned on medical instructions.
Github page: https://github.com/XZhang97666/AlpaCare/
If you think it is a useful repo, please cite the paper:
@misc{zhang2023alpacareinstructiontuned,
title={AlpaCare:Instruction-tuned Large Language Models for Medical Application},
author={Xinlu Zhang and Chenxin Tian and Xianjun Yang and Lichang Chen and Zekun Li and Linda Ruth Petzold},
year={2023},
eprint={2310.14558},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
docker model run hf.co/xz97/AlpaCare-llama2-13b