mzio/aprm-sft_genthinkact-ENtextworld_treasure_hunter-GEaprm_qwen3_ap-SE42-RE0-ap1-b0000
Viewer
• Updated
• 3.2k • 10
Michael Zhang
mzio
AI & ML interests
None yet
Recent Activity
updated
a dataset about 12 hours ago
mzio/sc_synthetic_regenerate_c500_q5_gpt-41-mini_v17 published
a dataset about 12 hours ago
mzio/sc_synthetic_regenerate_c500_q5_gpt-41-mini_v17 updated
a dataset about 12 hours ago
mzio/sc_synthetic_regenerate_c10_q5_gpt-41-mini_v17_smoke Organizations
mzio/sft-ENtextworld_cooking_game-GEaprm_qwen3_ap-SE42-RE1
Viewer
• Updated
• 1.26k • 11
mzio/sft-ENtextworld_treasure_hunter-GEaprm_qwen3_ap-SE42-RE1
Viewer
• Updated
• 400 • 11
mzio/sft-ENtextworld_coin_collector-GEaprm_qwen3_ap-SE42-RE1
Viewer
• Updated
• 400 • 11
mzio/sft-ENtextworld_cooking_game-GEaprm_qwen3_ap-SE42-RE0
Viewer
• Updated
• 1.26k • 10
mzio/sft-ENtextworld_treasure_hunter-GEaprm_qwen3_ap-SE42-RE0
Viewer
• Updated
• 400 • 10
mzio/sft-ENtextworld_coin_collector-GEaprm_qwen3_ap-SE42-RE0
Viewer
• Updated
• 400 • 12
mzio/aprm_sft_thought_action_rollouts-ENhotpotqa_mc_gpt5_gen4s_GEaprm_qwen3_ap_SE42_RE4-ap1_best_0020
Viewer
• Updated
• 1.59k • 11
mzio/aprm_sft_thought_action_rollouts-ENhotpotqa_mc_gpt5_gen4s_GEaprm_qwen3_ap_SE42_RE4-ap1_0019
Viewer
• Updated
• 1.59k • 11
mzio/aprm_sft_thought_action_rollouts-ENhotpotqa_mc_default_GEaprm_qwen3_ap_SE42_RE5-ap1_best_0040
Viewer
• Updated
• 12.7k • 10
mzio/aprm_sft_thought_action_rollouts-ENhotpotqa_mc_default_GEaprm_qwen3_ap_SE42_RE5-ap1_0039
Viewer
• Updated
• 12.7k • 12
mzio/act_prm-gpt5_low-hotpotqa_mc_gpt5_gen-v2397-tools
Viewer
• Updated
• 2.4k • 12
mzio/act_prm-gpt5_low-hotpotqa_mc_gpt5_gen-v5-tools
Viewer
• Updated
• 5 • 10
mzio/rb_last-cql-mc_oai_gpt5_low-ec_hotpotqa_mc_gpt5-ds_train-spp1-gbs1-s42-r_0-v5649-tools
Viewer
• Updated
• 5.65k • 11
mzio/hotpotqa_mc-llama3_2_3b_inst-full_obs-tools-v546
Viewer
• Updated
• 546 • 9
mzio/hotpotqa_mc-llama3_2_3b_inst-full_obs-tools-v1082
Viewer
• Updated
• 1.08k • 8
mzio/hotpotqa_mc-llama3_2_3b_inst-full_obs_v1082
Viewer
• Updated
• 1.08k • 9
mzio/aprm_sft_thought_action_rollouts-act_prm_browsecomp_100_hide_obs_aprm_qwen3_ap_42_2-ap_rl0020
Viewer
• Updated
• 9.91k • 28
mzio/aprm_sft_thought_action_rollouts-act_prm_browsecomp_100_hide_obs_aprm_qwen3_ap_42_2-ap_rl0010
Viewer
• Updated
• 9.91k • 24
mzio/aprm_sft_thought_action_rollouts-act_prm_browsecomp_100_hide_obs_aprm_qwen3_ap_42_2-ap_rl0000
Viewer
• Updated
• 9.91k • 24
mzio/aprm_sft_thought_action_rollouts-act_prm_browsecomp_100_hide_obs_aprm_qwen3_ap_42_1-ap_rl0000
Viewer
• Updated
• 9.91k • 23
mzio/aprm_sft-act_prm_hotpotqa_mc_250_aprm_qwen3_ap_42_0-0080
Viewer
• Updated
• 1.02k • 10
mzio/aprm_sft-act_prm_browsecomp_100_aprm_qwen3_ap_42_debug-0020
Viewer
• Updated
• 2.12k • 22
mzio/aprm_sft-act_prm_hotpotqa_mc_250_aprm_qwen3_ap_nobandit_42_0-0070
Viewer
• Updated
• 4.06k • 6
mzio/aprm_sft-act_prm_hotpotqa_mc_250_aprm_qwen3_ap_42_0-0070
Viewer
• Updated
• 4.06k • 10
mzio/aprm_sft-act_prm_hotpotqa_mc_250_aprm_qwen3_ap_nobandit_42_0-0060
Viewer
• Updated
• 1.02k • 9
mzio/aprm_sft-act_prm_hotpotqa_mc_250_aprm_qwen3_ap_42_0-0060
Viewer
• Updated
• 1.02k • 10
mzio/aprm_sft-act_prm_browsecomp_100_aprm_qwen3_ap_42_debug-0010
Viewer
• Updated
• 7.2k • 31
mzio/aprm_sft-act_prm_hotpotqa_mc_250_aprm_qwen3_ap_nobandit_42_0-0050
Viewer
• Updated
• 4.06k • 9
mzio/aprm_sft-act_prm_hotpotqa_mc_250_aprm_qwen3_ap_42_0-0050
Viewer
• Updated
• 4.06k • 9