zjhhhh/fixed-n-rb-er-cost-marginrl-qwen3-1.7b-base-math12k-token-mean-fixed-q0p8-run2-rollouts
Viewer • Updated • 942k • 301
Jiahao Zhang PRO
zjhhhh
AI & ML interests
None yet
Recent Activity
updated a model about 15 hours ago
zjhhhh/maxrl-qwen3-0.6b-polaris-4-8-2epochs-step_100 published a model about 15 hours ago
zjhhhh/maxrl-qwen3-0.6b-polaris-4-8-2epochs-step_100 updated a model about 15 hours ago
zjhhhh/maxrl-qwen3-0.6b-polaris-4-8-2epochs-step_50Organizations
None yet
zjhhhh/DeepScaleR-Qwen3-1.7B-2k-strategy-error-200
Viewer • Updated • 200 • 399
zjhhhh/game_qwen2.5_rlcf_viswavi__qwen2.5_rlcf
Viewer • Updated • 500 • 7
zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_rlcf_worst_expand_tokenized_gap_ratio_0.17_logprob
Viewer • Updated • 41.4k • 23
zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_rlcf_worst_expand_tokenized_gap_ratio_0.17
Viewer • Updated • 41.4k • 19
zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_preprocessed
Viewer • Updated • 41k • 15
zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_rescaled
Viewer • Updated • 50.1k • 19
zjhhhh/game_qwen2.5_rlcf_base
Viewer • Updated • 500 • 11
zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_42
Viewer • Updated • 700 • 15
zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_45
Viewer • Updated • 700 • 6
zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_43
Viewer • Updated • 700 • 11
zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_48
Viewer • Updated • 700 • 9
zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_40
Viewer • Updated • 700 • 9
zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_41
Viewer • Updated • 700 • 12
zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_37
Viewer • Updated • 700 • 11
zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_46
Viewer • Updated • 700 • 5
zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_33
Viewer • Updated • 700 • 8
zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_36
Viewer • Updated • 700 • 14
zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_34
Viewer • Updated • 700 • 8
zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_44
Viewer • Updated • 700 • 13
zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_35
Viewer • Updated • 700 • 12
zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_47
Viewer • Updated • 700 • 7
zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_32
Viewer • Updated • 700 • 8
zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_38
Viewer • Updated • 700 • 11
zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_62
Viewer • Updated • 700 • 10
zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_66
Viewer • Updated • 700 • 9
zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_63
Viewer • Updated • 700 • 7
zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_55
Viewer • Updated • 700 • 8
zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_39
Viewer • Updated • 700 • 8
zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_54
Viewer • Updated • 700 • 7