hyunseoki/rltr-qwen3-8b-polaris-baseline
Updated
RLTR: Learning Robust Reasoning via Transfer
Checkpoints (bf16, 50-step) + train/eval data for RLTR (transfer-reward RL) incl. cross-family (gemma) receiver.
Checkpoints (bf16, 50-step) + train/eval data for RLTR (transfer-reward RL) incl. cross-family (gemma) receiver.