jucamohedano/oxford-pets-grpo

oxford-pets-grpo: Oxford-IIIT Pet — GRPO training data: RL dataset on Hugging Face. GRPO (verl) training data for Oxford-IIIT Pet breed classification. The model classifies the pet directly; the reward scores a whole-token match of the predicted label plus answer format. Splits: train 2,944 rows…