Instructions to use microsoft/phi-1_5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/phi-1_5 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="microsoft/phi-1_5")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("microsoft/phi-1_5") model = AutoModelForCausalLM.from_pretrained("microsoft/phi-1_5") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use microsoft/phi-1_5 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "microsoft/phi-1_5" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "microsoft/phi-1_5", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/microsoft/phi-1_5
- SGLang
How to use microsoft/phi-1_5 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 "microsoft/phi-1_5" \ --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": "microsoft/phi-1_5", "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 "microsoft/phi-1_5" \ --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": "microsoft/phi-1_5", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use microsoft/phi-1_5 with Docker Model Runner:
docker model run hf.co/microsoft/phi-1_5
Prompt for GSM8K evaluations
Hello, thank you for the amazing work on Phi 1.5. I saw that there was a previous discussion about reproducing the GSM8K evaluation results (via code) that was closed (https://huggingface.co/microsoft/phi-1_5/discussions/36).
The evaluation snippet was helpful, but I'm still not able to reproduce the results from the technical report. In particular, I'm not sure what prompt I should use. All the prompts I've tried produce significantly lower results. Could you please provide the prompt that you actually used to get Phi1.5 to generate the code response for the GSM 8k evals?