ChatDoctor: A Medical Chat Model Fine-tuned on LLaMA Model using Medical Domain Knowledge
Paper • 2303.14070 • Published • 10
How to use Dong237/ChatDoctor with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="Dong237/ChatDoctor") # Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("Dong237/ChatDoctor")
model = AutoModelForCausalLM.from_pretrained("Dong237/ChatDoctor")How to use Dong237/ChatDoctor with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Dong237/ChatDoctor"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "Dong237/ChatDoctor",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/Dong237/ChatDoctor
How to use Dong237/ChatDoctor with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "Dong237/ChatDoctor" \
--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": "Dong237/ChatDoctor",
"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 "Dong237/ChatDoctor" \
--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": "Dong237/ChatDoctor",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use Dong237/ChatDoctor with Docker Model Runner:
docker model run hf.co/Dong237/ChatDoctor
This is a simple copy of ChatDoctor from Li et al, with this issue fixed to enable a direct loading.