HF RL Explorer

sungyub/ifeval-rlvr-verl

ifeval-rlvr-verl: RLVR-IFeval-VERL: Instruction Following Evaluation from RLVR: RL dataset on Hugging Face. This dataset contains 14,973 instruction-following examples from the RLVR-IFeval dataset, transformed into the IFBench-VERL format for training reinforcement learning models with VERL. The…

sungyub/ifeval-rlvr-verl on the Hugging Face Hub