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 "typeof/phi-2-qlora-ft" \
--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": "typeof/phi-2-qlora-ft",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'Quick Links
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
torch.set_default_device('cuda')
model = AutoModelForCausalLM.from_pretrained("typeof/phi-2-qlora-ft", trust_remote_code=True, torch_dtype="auto")
tokenizer = AutoTokenizer.from_pretrained("typeof/phi-2-qlora-ft", trust_remote_code=True, torch_dtype="auto")
prompt = "Are textbooks all you need?"
inputs = tokenizer(prompt,return_tensors="pt", return_attention_mask=False)
outputs = model.generate(
**inputs,
max_length=200,
do_sample=True, # for spontaneity 🤷
pad_token_id=tokenizer.eos_token_id,
eos_token_id=tokenizer.eos_token_id,
)
text = tokenizer.batch_decode(outputs)[0]
print(text)
- Downloads last month
- 11
Install from pip and serve model
# Install SGLang from pip: pip install sglang# Start the SGLang server: python3 -m sglang.launch_server \ --model-path "typeof/phi-2-qlora-ft" \ --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": "typeof/phi-2-qlora-ft", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'