Text Generation
Transformers
vector-quantization
vq2
Mixture of Experts
qwen
compression
triton
paged-streaming
Instructions to use ArthurLss/CompressAI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ArthurLss/CompressAI with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ArthurLss/CompressAI")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ArthurLss/CompressAI", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use ArthurLss/CompressAI with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ArthurLss/CompressAI" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ArthurLss/CompressAI", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ArthurLss/CompressAI
- SGLang
How to use ArthurLss/CompressAI 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 "ArthurLss/CompressAI" \ --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": "ArthurLss/CompressAI", "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 "ArthurLss/CompressAI" \ --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": "ArthurLss/CompressAI", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ArthurLss/CompressAI with Docker Model Runner:
docker model run hf.co/ArthurLss/CompressAI
Download codebooks.pt from ArthurLss/CompressAI: direct link, hf CLI and curl.
- Browser
- Download file 4.47 MB
-
https://huggingface.co/ArthurLss/CompressAI/resolve/b9426122b81247a94de445cbe4e7c725e91fe659/codebooks.pt
- Command line
-
hf download hf://ArthurLss/CompressAI@b9426122b81247a94de445cbe4e7c725e91fe659/codebooks.pt
-
curl -L -o codebooks.pt https://huggingface.co/ArthurLss/CompressAI/resolve/b9426122b81247a94de445cbe4e7c725e91fe659/codebooks.pt
4.47 MB
- Xet hash:
- 5b69b35e13085c7848937fe0a4fb1769e93f444cd30a0630ec52f22357e368b9
- Size of remote file:
- 4.47 MB
- SHA256:
- 9ac79a93b510a684def067528a8b266b5430aa50a41120be936474cd71c3c327
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.