Instructions to use FlyLee/bayesian-peft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use FlyLee/bayesian-peft with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="FlyLee/bayesian-peft")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("FlyLee/bayesian-peft", dtype="auto") - PEFT
How to use FlyLee/bayesian-peft with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use FlyLee/bayesian-peft with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "FlyLee/bayesian-peft" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "FlyLee/bayesian-peft", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/FlyLee/bayesian-peft
- SGLang
How to use FlyLee/bayesian-peft 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 "FlyLee/bayesian-peft" \ --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": "FlyLee/bayesian-peft", "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 "FlyLee/bayesian-peft" \ --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": "FlyLee/bayesian-peft", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use FlyLee/bayesian-peft with Docker Model Runner:
docker model run hf.co/FlyLee/bayesian-peft
Improve model card: Add pipeline tag, library name, paper, and code links
#2
by nielsr HF Staff - opened
This PR enhances the model card by:
- Adding the
pipeline_tag: text-generationto ensure better discoverability for causal language modeling tasks on the Hub. - Specifying
library_name: transformers, as the model, being a PEFT adapter for a Causal Language Model, is compatible with the Hugging Face Transformers library. - Including a link to the associated paper: Training-Free Bayesianization for Low-Rank Adapters of Large Language Models.
- Adding a link to the official GitHub repository for code: https://github.com/Wang-ML-Lab/bayesian-peft.
- Providing a description of the model based on its abstract for better context.
Please review and merge this PR.