Instructions to use YangyiH/PEFT-Arena-RL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use YangyiH/PEFT-Arena-RL with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="YangyiH/PEFT-Arena-RL")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("YangyiH/PEFT-Arena-RL", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use YangyiH/PEFT-Arena-RL with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "YangyiH/PEFT-Arena-RL" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "YangyiH/PEFT-Arena-RL", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/YangyiH/PEFT-Arena-RL
- SGLang
How to use YangyiH/PEFT-Arena-RL 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 "YangyiH/PEFT-Arena-RL" \ --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": "YangyiH/PEFT-Arena-RL", "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 "YangyiH/PEFT-Arena-RL" \ --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": "YangyiH/PEFT-Arena-RL", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use YangyiH/PEFT-Arena-RL with Docker Model Runner:
docker model run hf.co/YangyiH/PEFT-Arena-RL
PEFT-Arena RL Checkpoints
This repository contains RLVR checkpoints for PEFT-Arena. Full finetuning checkpoints are stored as dense Hugging Face model checkpoints. PEFT checkpoints are stored as adapter checkpoints. Training-state directories such as actor/, optimizer shards, and extra-state shards are intentionally excluded.