File size: 271 Bytes
435d00c | 1 2 3 4 5 6 7 8 | # RLVR baseline checkpoint
pi1, grpo, semantic step 500.
Historical pi1 pure GRPO; matches per-checkpoint evaluation provenance.
Pure GRPO/RLVR baseline (Teacher rejection disabled). This repository contains inference weights and tokenizer files, not optimizer state.
|