Instructions to use ulkaa/phi-2-asym_int5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ulkaa/phi-2-asym_int5 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ulkaa/phi-2-asym_int5")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("ulkaa/phi-2-asym_int5") model = AutoModelForCausalLM.from_pretrained("ulkaa/phi-2-asym_int5", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use ulkaa/phi-2-asym_int5 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ulkaa/phi-2-asym_int5" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ulkaa/phi-2-asym_int5", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ulkaa/phi-2-asym_int5
- SGLang
How to use ulkaa/phi-2-asym_int5 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 "ulkaa/phi-2-asym_int5" \ --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": "ulkaa/phi-2-asym_int5", "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 "ulkaa/phi-2-asym_int5" \ --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": "ulkaa/phi-2-asym_int5", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ulkaa/phi-2-asym_int5 with Docker Model Runner:
docker model run hf.co/ulkaa/phi-2-asym_int5
Commit History
-
Upload pytorch_model.bin with huggingface_hub
Verified signaturea9fc1e9 -
Upload vocab.json with huggingface_hub
Verified signature0254df1 -
Upload merges.txt with huggingface_hub
Verified signature74c4220 -
Upload added_tokens.json with huggingface_hub
Verified signature7b8de63 -
Upload load_keys.json with huggingface_hub
Verified signature7edf3bd -
Upload tokenizer_config.json with huggingface_hub
Verified signature29b44e5 -
Upload generation_config.json with huggingface_hub
Verified signature110b59c -
Upload tokenizer.json with huggingface_hub
Verified signature545dbd2 -
Upload config.json with huggingface_hub
Verified signature47ec5be -
Upload special_tokens_map.json with huggingface_hub
Verified signature3a077d0 -
initial commit
Verified signature77e34bd