mzio/aprm-tw-treasure-hunter-medium-gpt5m_med-gs4-s0-train
Viewer • Updated • 4.4k • 23
Michael Zhang PRO
mzio
AI & ML interests
None yet
Recent Activity
updated a dataset 21 days ago
mzio/astra-bench-gpt5m-b-n300-0401 published a dataset 21 days ago
mzio/astra-bench-gpt5m-b-n300-0401 updated a dataset 21 days ago
mzio/astra-bench-gpt5m-b-n200-0401Organizations
mzio/aprm-sft_thinkact-Eaprm_tw_tr_medium_hi-Gaprm_qw3_ap_nobandit-S42-R0-ap1-best-train_all-b08
Viewer • Updated • 244 • 18
mzio/aprm-sft_thinkact-Eaprm_tw_tr_medium_hi-Gaprm_qwen3_ap-S42-R0-ap1-train_all-b070
Viewer • Updated • 244 • 16
mzio/aprm-tw-treasure-hunter-easy-gpt5m_med-gs4-s0-train
Viewer • Updated • 1.15k • 46
mzio/aprm-sft_thinkact-Eaprm_tw_tr_hard_hi-Gaprm_qwen3_ap-S42-R0-ap1-train_all-b070
Viewer • Updated • 244 • 16
mzio/aprm-finqa_reasoning-gpt5_med-gs4-s0-r2-train
Viewer • Updated • 4.3k • 24
mzio/tw-sft-cooking-game-hard-hi
Viewer • Updated • 620 • 19
mzio/tw-sft-cooking-game-medium-hi
Viewer • Updated • 620 • 19
mzio/tw-sft-cooking-game-easy-hi
Viewer • Updated • 620 • 18
mzio/aprm-sft_thinkact-Eaprm_tw_tr_hard_hi-Gaprm_qwen3_ap_nobandit-S42-R0-ap1-train_all-b070
Viewer • Updated • 244 • 16
mzio/aprm-sft_thinkact-Eaprm_tw_tr_medium_hi-Gaprm_qw3_ap_nobandit-S42-R0-ap1-best-train_all-b07
Viewer • Updated • 244 • 18
mzio/aprm-sft_thinkact-Eaprm_tw_tr_medium_hi-Gaprm_qwen3_ap-S42-R0-ap1-train_all-b060
Viewer • Updated • 244 • 17
mzio/aprm-sft_thinkact-Eaprm_tw_tr_hard_hi-Gaprm_qwen3_ap-S42-R0-ap1-train_all-b060
Viewer • Updated • 244 • 16
mzio/aprm-sft_thinkact-Eaprm_tw_tr_hard_hi-Gaprm_qwen3_ap_nobandit-S42-R0-ap1-train_all-b060
Viewer • Updated • 244 • 18
mzio/aprm-sft_thinkact-Eaprm_tw_tr_medium_hi-Gaprm_qwen3_ap_nobandit-S42-R0-ap1-train_all-b060
Viewer • Updated • 244 • 13
mzio/aprm-sft_thinkact-Eaprm_tw_tr_medium_hi-Gaprm_qwen3_ap-S42-R0_ns4-ap1-train_all-b010
Viewer • Updated • 244 • 15
mzio/aprm-finqa_reasoning-gpt5m_med-gs4-s0-r2-train
Viewer • Updated • 3.69k • 43
mzio/aprm-sft_thinkact-Eaprm_tw_tr_medium_hi-Gaprm_qwen3_ap-S42-R0-ap1-best-train_all-b050
Viewer • Updated • 244 • 17
mzio/aprm-sft_thinkact-Eaprm_tw_tr_hard_hi-Gaprm_qwen3_ap-S42-R0-ap1-train_all-b050
Viewer • Updated • 244 • 18
mzio/aprm-sft_thinkact-Eaprm_tw_tr_hard_hi-Gaprm_qw3_ap_nobandit-S42-R0-ap1-best-train_all-b050
Viewer • Updated • 244 • 20
mzio/aprm-sft_thinkact-Eaprm_tw_tr_medium_hi-Gaprm_qw3_ap_nobandit-S42-R0-ap1-best-train_all-b05
Viewer • Updated • 244 • 15
mzio/aprm-sft_thinkact-Eaprm_tw_tr_medium_hi-Gaprm_qwen3_ap-S42-R0-ap1-train_all-b050
Viewer • Updated • 244 • 20
mzio/aprm-sft_thinkact-Eaprm_tw_tr_medium_hi-Gaprm_qwen3_ap-S42-R0-ap1-train_all-b040
Viewer • Updated • 244 • 16
mzio/aprm-sft_thinkact-Eaprm_tw_tr_hard_hi-Gaprm_qwen3_ap-S42-R0-ap1-train_all-b040
Viewer • Updated • 244 • 17
mzio/aprm-sft_thinkact-Eaprm_tw_tr_hard_hi-Gaprm_qwen3_ap_nobandit-S42-R0-ap1-train_all-b040
Viewer • Updated • 244 • 15
mzio/aprm-sft_thinkact-Eaprm_tw_tr_medium_hi-Gaprm_qwen3_ap_nobandit-S42-R0-ap1-train_all-b040
Viewer • Updated • 244 • 18
mzio/aprm-finqa_reasoning-gpt5m_med-gs8-s0-r1-train
Viewer • Updated • 3k • 20
mzio/aprm-sft_thinkact-Eaprm_tw_tr_medium_hi-Gaprm_qwen3_ap-S42-R0-ap1-train_all-b030
Viewer • Updated • 244 • 16
mzio/aprm-sft_thinkact-Eaprm_tw_tr_hard_hi-Gaprm_qwen3_ap-S42-R0-ap1-train_all-b030
Viewer • Updated • 244 • 20
mzio/aprm-sft_thinkact-Eaprm_tw_tr_hard_hi-Gaprm_qwen3_ap_nobandit-S42-R0-ap1-train_all-b030
Viewer • Updated • 244 • 20