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 "TitleOS/CodePhi2" \
--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": "TitleOS/CodePhi2",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'Quick Links
Model Summary
CodePhi2 is finetuning of the Microsoft Phi-2 LLM with 2.7 billion parameters. It was finetuned on TokenBender's code_instructions_122k_alpaca_style. The end goal was to increase Phi-2's coding ability while imbuing the Alpaca format.
Instruction Format (Alpaca)
CodePhi2 has been finetuned on the Alpaca instruction format, and as such should be prompted like below:
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{instruction}
### Response:
Notes
If you are using transformers>=4.36.0, always load the model with trust_remote_code=True to prevent side-effects.
- Downloads last month
- 8
Model tree for TitleOS/CodePhi2
Base model
microsoft/phi-2
Install from pip and serve model
# Install SGLang from pip: pip install sglang# Start the SGLang server: python3 -m sglang.launch_server \ --model-path "TitleOS/CodePhi2" \ --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": "TitleOS/CodePhi2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'