How to use from
SGLangUse 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 "sangdal/ChatBot" \
--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": "sangdal/ChatBot",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'Quick Links
https://huggingface.co/taeminlee/kogpt2์ ๊ธฐ๋ฐ์ผ๋ก https://github.com/codertimo/KorQuAD-Question-Generation ์ ๊ฐ์ง๊ณ ๋ฌธ๋งฅ์ ์ ๋ ฅ ํ์๋ ์ง๋ฌธ์ ๋ฝ์์ฃผ๋ ๋ชจ๋ธ๋ก ์์ ํ์์ต๋๋ค. ํ์์์ ํ๋ก์ ํธ๋ก ์ฐ๊ธฐ ์ํด ์ ์ ํ์์ต๋๋ค.
์ฝ๋ฉ์์ ์ฌ์ฉ ๊ฐ๋ฅํ๊ฒ ์ฝ๋ฉ ์์ค๋ ํจ๊ป ๋ฐฐํฌํ๊ฒ ์ต๋๋ค. tokenizer์ vocab.json, merges.txt ์์น ์ ์ก์์ฃผ์ ์ผํฉ๋๋ค.
2023-08-06
- ํ์ต์ฉ ๋ฐ์ดํฐ๋ ์ด : 4087
- Train : 3269 [train.jsonํ์ผ]
- Test : 818 [dev.jsonํ์ผ] ** ์ต์ ์ ๋ก๋ ๋ชจ๋ธ
- Downloads last month
- 4
Install from pip and serve model
# Install SGLang from pip: pip install sglang# Start the SGLang server: python3 -m sglang.launch_server \ --model-path "sangdal/ChatBot" \ --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": "sangdal/ChatBot", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'