Instructions to use skytree/smoothquant-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use skytree/smoothquant-models with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="skytree/smoothquant-models")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("skytree/smoothquant-models") model = AutoModelForCausalLM.from_pretrained("skytree/smoothquant-models", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use skytree/smoothquant-models with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "skytree/smoothquant-models" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "skytree/smoothquant-models", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/skytree/smoothquant-models
- SGLang
How to use skytree/smoothquant-models 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 "skytree/smoothquant-models" \ --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": "skytree/smoothquant-models", "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 "skytree/smoothquant-models" \ --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": "skytree/smoothquant-models", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use skytree/smoothquant-models with Docker Model Runner:
docker model run hf.co/skytree/smoothquant-models
Download pytorch_model.bin from skytree/smoothquant-models: direct link, hf CLI and curl.
- Browser
- Download file 251 MB
-
https://huggingface.co/skytree/smoothquant-models/resolve/main/pytorch_model.bin
- Command line
-
hf download hf://skytree/smoothquant-models/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/skytree/smoothquant-models/resolve/main/pytorch_model.bin
251 MB
- Xet hash:
- ec527019f9c8f684d04a5bde5aa54deee12f04b5c21c77c6b2f4ceb98a7631c2
- Size of remote file:
- 251 MB
- SHA256:
- a6cfadb3ad5f4f8df3368e438765ad4dc46fdc4c97179807573d01b84d6b3524
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.