talzoomanzoo/limr_grpo_sat_mia_epoch_0
8B • Updated • 5
Minju Gwak
talzoomanzoo
AI & ML interests
None yet
Recent Activity
authored a paper 6 days ago
Self-Improvement with Auxiliary Rewards: Learning from Verified Traces and Evaluating Transfer submitted a paper 7 days ago
Self-Improvement with Auxiliary Rewards: Learning from Verified Traces and Evaluating TransferOrganizations
talzoomanzoo/eurus_grpo_sat_mia_epoch_2
8B • Updated • 7
talzoomanzoo/eurus_grpo_sat_mia_epoch_1
8B • Updated • 6
talzoomanzoo/eurus_grpo_sat_mia_epoch_0
8B • Updated • 5
talzoomanzoo/limr_grpo_kk_mia_epoch_2
8B • Updated • 6
talzoomanzoo/limr_grpo_kk_mia_epoch_1
8B • Updated • 6
talzoomanzoo/limr_grpo_kk_mia_epoch_0
8B • Updated • 6
talzoomanzoo/eurus_grpo_kk_mia_epoch_2
8B • Updated • 6
talzoomanzoo/eurus_grpo_kk_mia_epoch_1
8B • Updated • 13 • 1
talzoomanzoo/eurus_grpo_kk_mia_epoch_0
8B • Updated • 11
talzoomanzoo/qwen2.5-1.5b-sft-rewrite-filtered
2B • Updated • 3
talzoomanzoo/qwen2.5-1.5b-sft-rewrite
2B • Updated • 3
talzoomanzoo/qwen2.5-1.5b-sft
2B • Updated • 7
talzoomanzoo/qwen2.5-3b-sft-rewrite-filtered
3B • Updated • 3
talzoomanzoo/qwen2.5-3b-sft-rewrite
3B • Updated • 2
talzoomanzoo/qwen2.5-3b-sft
3B • Updated • 3
talzoomanzoo/qwen2.5-7b-sft-rewrite
8B • Updated • 8
talzoomanzoo/qwen2.5-7b-sft-rewrite-filtered
8B • Updated • 3
talzoomanzoo/qwen2.5-7b-naive-distill
8B • Updated • 2
talzoomanzoo/qwen3-30b-base-um-math
Updated
talzoomanzoo/qwen3-8b-base-superior
Updated
talzoomanzoo/qwen3-8b-base-um-math
Updated
talzoomanzoo/qwen3-4b-base-math-32k
Text Generation • Updated • 4
talzoomanzoo/eurus_grpo_rlmia_epoch_2
8B • Updated • 1
talzoomanzoo/eurus_grpo_rlmia_epoch_1
8B • Updated • 2
talzoomanzoo/eurus_grpo_rlmia_epoch_0
8B • Updated • 9
talzoomanzoo/eurus_member3_new_epoch2
8B • Updated • 3
talzoomanzoo/eurus_member3_new_epoch1
Updated • 3
talzoomanzoo/eurus_member3_new_epoch0
8B • Updated • 6
talzoomanzoo/eurus_member2_new_epoch2
8B • Updated • 3