Instructions to use winglian/phi-1_5-2x-fib with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use winglian/phi-1_5-2x-fib with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="winglian/phi-1_5-2x-fib", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("winglian/phi-1_5-2x-fib", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use winglian/phi-1_5-2x-fib with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "winglian/phi-1_5-2x-fib" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "winglian/phi-1_5-2x-fib", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/winglian/phi-1_5-2x-fib
- SGLang
How to use winglian/phi-1_5-2x-fib 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 "winglian/phi-1_5-2x-fib" \ --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": "winglian/phi-1_5-2x-fib", "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 "winglian/phi-1_5-2x-fib" \ --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": "winglian/phi-1_5-2x-fib", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use winglian/phi-1_5-2x-fib with Docker Model Runner:
docker model run hf.co/winglian/phi-1_5-2x-fib
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
2.6B Phi
This model was created by duplicating hidden layers from Microsoft's Phi 1.5.
Join us on the OpenAccess AI Collective Discord: https://discord.gg/jb763J4Q
- Downloads last month
- 12