File size: 294 Bytes
3efd08c | 1 2 3 4 5 6 7 8 | # RLVR baseline checkpoint
dsr128, grpo, semantic step 600.
Original DSR128 pure GRPO; weight hashes from historical single-answer evaluation protocol.
Pure GRPO/RLVR baseline (Teacher rejection disabled). This repository contains inference weights and tokenizer files, not optimizer state.
|