zjhhhh/iter2_7b_multi_gap_0.17_scores_adversary_11
Viewer • Updated • 700 • 7
Jiahao Zhang
zjhhhh
AI & ML interests
None yet
Recent Activity
updated a dataset 7 days ago
zjhhhh/DeepScaleR-Qwen3-1.7B-rl-whole published a dataset 7 days ago
zjhhhh/DeepScaleR-Qwen3-1.7B-rl-whole updated a dataset 7 days ago
zjhhhh/DeepScaleR-Autoresearch-responses-ver1Organizations
None yet
zjhhhh/iter2_7b_multi_gap_0.17_scores_base_11
Viewer • Updated • 700 • 6
zjhhhh/iter2_7b_multi_gap_0.17_scores_base_8
Viewer • Updated • 700 • 5
zjhhhh/generation_for_iter2_7b_multi_gap_0.17_filtered
Viewer • Updated • 50.1k • 6
zjhhhh/generation_for_iter2_7b_multi_gap_0.17_part2_filtered
Viewer • Updated • 12.5k • 7
zjhhhh/generation_for_iter2_7b_multi_gap_0.17_part1_filtered
Viewer • Updated • 12.5k • 5
zjhhhh/generation_for_iter2_7b_multi_gap_0.17_part4_filtered
Viewer • Updated • 12.5k • 6
zjhhhh/generation_for_iter2_7b_multi_gap_0.17_part3_filtered
Viewer • Updated • 12.5k • 6
zjhhhh/generation_for_iter2_7b_multi_gap_0.17_part4
Viewer • Updated • 12.8k • 6
zjhhhh/generation_for_iter2_7b_multi_gap_0.17_part3
Viewer • Updated • 12.8k • 6
zjhhhh/generation_for_iter2_7b_multi_gap_0.17_part2
Viewer • Updated • 12.8k • 7
zjhhhh/generation_for_iter2_7b_multi_gap_0.17_part1
Viewer • Updated • 12.8k • 7
zjhhhh/generation_for_iter2_7b_multi_gap_0.17
Viewer • Updated • 51.1k • 7
zjhhhh/Qwen7b_multi_gap_0.17_iter1_generation
Viewer • Updated • 51.1k • 7
zjhhhh/game_7b_zjhhhh__7b_iter2_multi_0.17_eta_1e4_step_322_final
Viewer • Updated • 500 • 8
zjhhhh/game_3b_zjhhhh__iter2_ver2_pad_adversary_min_step_367_final
Viewer • Updated • 500 • 7
zjhhhh/game_3b_zjhhhh__iter2_multi_adversary_step_367_final
Viewer • Updated • 500 • 7
zjhhhh/game_7b_zjhhhh__7b_iter2_minmin_step_301
Viewer • Updated • 500 • 7
zjhhhh/game_7b_zjhhhh__7b_fullcheck_gap_0.17_iter2_eta_1e2_step_322_final
Viewer • Updated • 500 • 8
zjhhhh/game_3b_zjhhhh__3b_rerun_rlcf_iter2_step_396_final
Viewer • Updated • 500 • 7
zjhhhh/game_3b_zjhhhh__iter2_fullcheck_multi_adversary_eta_1e3_step_367_final
Viewer • Updated • 500 • 7
zjhhhh/game_7b_zjhhhh__7b_rlcf_gap_0.17_iter2_step_335_final
Viewer • Updated • 500 • 7
zjhhhh/game_7b_viswavi__qwen2.5_rlcf
Viewer • Updated • 500 • 5
zjhhhh/game_3b_base
Viewer • Updated • 500 • 6
zjhhhh/game_7b_base
Viewer • Updated • 500 • 6
zjhhhh/3b_iter2_rlcf_scores_rlcf_expand_tokenized_gap_ratio_0.22_logprob
Viewer • Updated • 51.6k • 4
zjhhhh/3b_iter2_rlcf_scores_rlcf_expand_tokenized_gap_ratio_0.22
Viewer • Updated • 51.6k • 8
zjhhhh/3b_iter2_rlcf_scores_rlcf_expand_tokenized
Viewer • Updated • 232k • 6
zjhhhh/3b_iter2_rlcf_scores_preprocessed
Viewer • Updated • 39.6k • 9
zjhhhh/3b_iter2_rlcf_scores
Viewer • Updated • 50.1k • 7