mzio/aprm-sft_thinkact-Eaprm_tw_tr_easy_gpt5m-Gaprm_qwen3_ap-S0-Rgpt5m_hd_0-ap1-train_all-b070
Viewer • Updated • 348
Michael Zhang
mzio
AI & ML interests
None yet
Recent Activity
updated a dataset 43 minutes ago
mzio/aprm-sft_thinkact-Eaprm_tw_tr_easy_gpt5m-Gaprm_qwen3_ap-S0-Rgpt5m_hd_0-ap1-train_all-b070 published a dataset 43 minutes ago
mzio/aprm-sft_thinkact-Eaprm_tw_tr_easy_gpt5m-Gaprm_qwen3_ap-S0-Rgpt5m_hd_0-ap1-train_all-b070 updated a dataset about 1 hour ago
mzio/aprm-sft_thinkact-Efinqa_reasoning-Gaprm_qwen3_ap-S1-Rfinqa_aprm_0-ap1-train_all-b040Organizations
mzio/aprm-sft_thinkact-Efinqa_reasoning-Gaprm_qwen3_ap-S1-Rfinqa_aprm_0-ap1-train_all-b040
Viewer • Updated • 508
mzio/aprm-sft_thinkact-Eaprm_tw_tr_easy_gpt5m-Gaprm_qwen3_ap-S0-Rgpt5m_hd_0-ap1-train_all-b060
Viewer • Updated • 348
mzio/aprm-sft_thinkact-Efinqa_reasoning-Gaprm_qw3_ap-S1-Rfinqa_aprm_1_mc-ap1-best-train_all-b030
Viewer • Updated • 508
mzio/aprm-sft_thinkact-Eaprm_tw_cc_easy_gpt5m-Gaprm_qwen3_ap-S0-Rgpt5m_0-ap1-train_all-b030
Viewer • Updated • 1.17k
mzio/aprm-sft_thinkact-Eaprm_tw_tr_easy_gpt5m-Gaprm_qw3_ap-S0-Rgpt5m_hd_0-ap1-best-train_all-b05
Viewer • Updated • 348
mzio/aprm-sft_genthinkact-Eaprm_tw_tr_easy_gpt5m-Gaprm_qw3_ap-S0-Rgpt5m_0-ap1_best-train_all-b09
Viewer • Updated • 348
mzio/aprm-sft_thinkact-Eaprm_tw_tr_easy_gpt5m-Gaprm_qwen3_ap-S0-Rgpt5m_0-ap1-train_all-b099
Viewer • Updated • 348
mzio/aprm-sft_thinkact-Efinqa_reasoning-Gaprm_qwen3_ap-S1-Rfinqa_aprm_0-ap1-train_all-b030
Preview • Updated
mzio/aprm-sft_thinkact-Eaprm_tw_tr_easy_gpt5m-Gaprm_qwen3_ap-S0-Rgpt5m_hd_0-ap1-train_all-b040
Viewer • Updated • 348
mzio/aprm-sft_thinkact-Eaprm_tw_tr_easy_gpt5m-Gaprm_qwen3_ap-S0-Rgpt5m_0-ap1-train_all-b090
Viewer • Updated • 348
mzio/aprm-sft_thinkact-Eaprm_tw_tr_easy_gpt5m-Gaprm_qwen3_ap-S0-Rgpt5m_hd_0-ap1-train_all-b030
Viewer • Updated • 348
mzio/aprm-sft_thinkact-Eaprm_tw_tr_easy_gpt5m-Gaprm_qwen3_ap-S0-Rgpt5m_0-ap1-train_all-b080
Viewer • Updated • 348 • 3
mzio/aprm-sft_thinkact-Efinqa_reasoning-Gaprm_qw3_ap-S1-Rfinqa_aprm_1_mc-ap1-best-train_all-b020
Viewer • Updated • 508 • 3
mzio/aprm-sft_thinkact-Eaprm_tw_cc_easy_gpt5m-Gaprm_qwen3_ap-S0-Rgpt5m_0-ap1-best-train_all-b020
Viewer • Updated • 1.17k • 4
mzio/aprm-sft_thinkact-Eaprm_tw_tr_easy_gpt5m-Gaprm_qw3_ap-S0-Rgpt5m_hd_0-ap1-best-train_all-b02
Viewer • Updated • 348 • 2
mzio/aprm-sft_thinkact-Eaprm_tw_tr_easy_gpt5m-Gaprm_qwen3_ap-S0-Rgpt5m_0-ap1-train_all-b070
Viewer • Updated • 348 • 3
mzio/aprm-sft_thinkact-Efinqa_reasoning-Gaprm_qwen3_ap-S1-Rfinqa_aprm_0-ap1-train_all-b020
Viewer • Updated • 508 • 2
mzio/aprm-tau2-airline-gpt5m_med-gs4-s0-train
Viewer • Updated • 2.73k • 19
mzio/aprm-sft_thinkact-Eaprm_tw_tr_easy_gpt5m-Gaprm_qwen3_ap-S0-Rgpt5m_hd_0-ap1-train_all-b010
Viewer • Updated • 348 • 3
mzio/aprm-sft_thinkact-Eaprm_tw_tr_easy_gpt5m-Gaprm_qwen3_ap-S0-Rgpt5m_0-ap1-train_all-b060
Viewer • Updated • 348 • 3
mzio/aprm-sft_thinkact-Eaprm_tw_tr_easy_gpt5m-Gaprm_qwen3_ap-S0-Rgpt5m_0-ap1-best-train_all-b050
Viewer • Updated • 348 • 3
mzio/aprm-sft_genthinkact-Eaprm_tw_tr_medium_hi-Gaprm_qw3_ap-S42-R1_ns4_alo0-ap1_best-train_all
Viewer • Updated • 244 • 2
mzio/aprm-sft_thinkact-Eaprm_tw_tr_medium_hi-Gaprm_qwen3_ap-S42-R1_ns4_alo0-ap1-train_all-b099
Viewer • Updated • 244 • 2
mzio/aprm-sft_thinkact-Efinqa_reasoning-Gaprm_qw3_ap-S1-Rfinqa_aprm_1_mc-ap1-best-train_all-b010
Viewer • Updated • 508 • 3
mzio/aprm-tau2-retail-gpt5m_med-gs8-s0-train
Viewer • Updated • 7.27k • 6
mzio/aprm-sft_thinkact-Eaprm_tw_tr_medium_hi-Gaprm_qwen3_ap-S42-R1_ns4_alo0-ap1-train_all-b090
Viewer • Updated • 244 • 3
mzio/aprm-sft_thinkact-Eaprm_tw_tr_easy_gpt5m-Gaprm_qwen3_ap-S0-Rgpt5m_0-ap1-train_all-b040
Viewer • Updated • 348 • 5
mzio/aprm-sft_thinkact-Eaprm_tw_cc_easy_gpt5m-Gaprm_qwen3_ap-S0-Rgpt5m_0-ap1-train_all-b010
Viewer • Updated • 1.17k • 5
mzio/aprm-sft_thinkact-Eaprm_tw_tr_medium_hi-Gaprm_qwen3_ap-S42-R1_ns4_alo0-ap1-train_all-b080
Viewer • Updated • 244 • 8