Instructions to use SkunkworksAI/phi-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SkunkworksAI/phi-2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="SkunkworksAI/phi-2", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("SkunkworksAI/phi-2", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use SkunkworksAI/phi-2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "SkunkworksAI/phi-2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SkunkworksAI/phi-2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/SkunkworksAI/phi-2
- SGLang
How to use SkunkworksAI/phi-2 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 "SkunkworksAI/phi-2" \ --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": "SkunkworksAI/phi-2", "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 "SkunkworksAI/phi-2" \ --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": "SkunkworksAI/phi-2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use SkunkworksAI/phi-2 with Docker Model Runner:
docker model run hf.co/SkunkworksAI/phi-2
Commit History
Update README.md 2fbb425
Update README.md 858d90f
Update README.md 6c49320
Update README.md b5d96a7
Update config.json 120f978
Rename model_mixformer_sequential.py to modeling_mixformer_sequential.py ba5e497
moved all to root for hf transformers 37c6959
moved all files and configs to root for hf transformers e91643d
moved model.bin files to correct folder 8c4e9fd
Update README.md f315165
Upload 15 files 503dc31
Update README.md c100b91
Upload 6 files fb05ee1
initial commit 69298e1
Farouk commited on