PEFT-Arena-RL / README.md
YangyiH's picture
Initialize RL checkpoint repo
a8aeed9 verified
|
Raw
History Blame Contribute Delete
399 Bytes
metadata
library_name: transformers
pipeline_tag: text-generation

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.