Text Generation
Transformers
Safetensors
English
phi-msft
nlp
code
custom_code
Eval Results (legacy)
Instructions to use lxuechen/phi-2-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lxuechen/phi-2-sft with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="lxuechen/phi-2-sft", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("lxuechen/phi-2-sft", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use lxuechen/phi-2-sft with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "lxuechen/phi-2-sft" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "lxuechen/phi-2-sft", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/lxuechen/phi-2-sft
- SGLang
How to use lxuechen/phi-2-sft with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "lxuechen/phi-2-sft" \ --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": "lxuechen/phi-2-sft", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use 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 "lxuechen/phi-2-sft" \ --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": "lxuechen/phi-2-sft", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use lxuechen/phi-2-sft with Docker Model Runner:
docker model run hf.co/lxuechen/phi-2-sft
Commit History
Update README.md cc447a5 verified
Update LICENSE 0c60d55 verified
Update README.md 340aca7
Update README.md 00396b7
Fix tokenizer. 6434eba
Xuechen Li commited on
Fix vocab. db8f431
Xuechen Li commited on
Fix config. 2d74010
Xuechen Li commited on
Update README.md 46edfec
Fix config. 7462fa4
Xuechen Li commited on
Merge branch 'main' of hf.co:lxuechen/phi-2-sft into main b47e1ad
Xuechen Li commited on
Fix config. e4330d7
Xuechen Li commited on
Create README.md d70a94f
Initial commit. 1a17e95
Xuechen Li commited on