Instructions to use oongaboongahacker/phi-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use oongaboongahacker/phi-2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="oongaboongahacker/phi-2", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("oongaboongahacker/phi-2", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use oongaboongahacker/phi-2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "oongaboongahacker/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": "oongaboongahacker/phi-2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/oongaboongahacker/phi-2
- SGLang
How to use oongaboongahacker/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 "oongaboongahacker/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": "oongaboongahacker/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 "oongaboongahacker/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": "oongaboongahacker/phi-2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use oongaboongahacker/phi-2 with Docker Model Runner:
docker model run hf.co/oongaboongahacker/phi-2
Can't find file while downloading model
While downloading model I get an error:
OSError: oongaboongahacker/fi-2 does not appear to have a file named modeling_mixformer_sequential.py. Checkout 'https://huggingface.co/oongaboongahacker/fi-2/main' for available files.
And I see a file named configuration_mixformer_sequential.py is in the main brach, so is this some kind of misspelling
My version of transformers is 4.32.1. Throughout stack traceback all errors are in transformers library
Hmm probably due to it not being hf compatible. Were you able to download the .bin files though?
If not, I shall delete the file(modeling_mixformer_sequential.py) and put it separately in gist or something
with transformers downloader no, it only downloaded these files
- config.json
- configuration_mixformer_sequential.py
This should work: https://huggingface.co/mixedbreadai/phi-2
This repo is gone, but other 'mirrors' are still up. Maybe this was a manual self-delete for some reason? According to the license text distribution is prohibited, so these 'mirrors' may not stay up for long...
There is a modeling_mixformer_sequential.py file missing I think https://huggingface.co/oongaboongahacker/phi-2/blob/main/config.json#L16