MathMindsAGI/sokoban_qwen3_4b_instruct_tis_8k_3box_k3_kl1e-3_colocate_async_step1800 4B • Updated 5 days ago • 108
MathMindsAGI/sokoban_qwen3_4b_instruct_sc_tis_8k_3box_colocate_async_step1300 4B • Updated 5 days ago • 109
MathMindsAGI/sokoban_qwen3_4b_instruct_replay_layers_final_8k_3box_colocate_async_step1000 4B • Updated 5 days ago • 110
MathMindsAGI/sokoban_qwen3_4b_instruct_dppo_tv_8k_3box_colocate_async_step1200 4B • Updated 5 days ago • 107
MathMindsAGI/delethinkIter_R1DistillQwen1.5B_DEEPSCALER_BASELINE_20250812Baseline_seed_274631821 Updated Aug 26, 2025 • 4
MathMindsAGI/delethinkIter_R1DistillQwen1.5B_DEEPSCALER_LONG_20250812Long_seed_2746318213 Updated Aug 26, 2025 • 3