zjhhhh/Qwen7b_min_iter2_16000
Viewer • Updated • 2k • 7
Jiahao Zhang
zjhhhh
AI & ML interests
None yet
Recent Activity
updated a dataset 2 days ago
zjhhhh/DeepScaleR-Qwen3-1.7B-2k-strategy-error-200 published a dataset 2 days ago
zjhhhh/DeepScaleR-Qwen3-1.7B-2k-strategy-error-200 updated a dataset 7 days ago
zjhhhh/game_qwen2.5_rlcf_viswavi__qwen2.5_rlcfOrganizations
None yet
zjhhhh/Qwen7b_min_iter2_44000
Viewer • Updated • 2k • 9
zjhhhh/Qwen7b_min_iter2_8000
Viewer • Updated • 2k • 6
zjhhhh/Qwen7b_min_iter2_0
Viewer • Updated • 2k • 6
zjhhhh/Qwen7b_min_iter2_30000
Viewer • Updated • 2k • 7
zjhhhh/Qwen7b_min_iter2_36000
Viewer • Updated • 2k • 6
zjhhhh/Qwen7b_min_iter2_26000
Viewer • Updated • 2k • 5
zjhhhh/Qwen7b_min_iter2_6000
Viewer • Updated • 2k • 5
zjhhhh/Qwen7b_min_iter2_2000
Viewer • Updated • 2k • 5
zjhhhh/Qwen7b_min_iter2_50000
Viewer • Updated • 1.07k • 6
zjhhhh/7b_iter1_preprocessed_mean_beta_1.0_multi_noexpand_tokenized_gap_ratio_0.6_logprob
Viewer • Updated • 26.3k • 7
zjhhhh/iter2_7b_multi_adversary_mean_beta_1.0_multi_expand_tokenized_gap_ratio_0.22_logprob
Viewer • Updated • 54.4k • 8
zjhhhh/iter2_7b_multi_adversary_mean_beta_1.0_multi_expand_tokenized_gap_ratio_0.22
Viewer • Updated • 54.4k • 5
zjhhhh/iter2_7b_multi_adversary_mean_beta_1.0_multi_expand_tokenized
Viewer • Updated • 244k • 10
zjhhhh/iter2_7b_multi_adversary_preprocessed
Viewer • Updated • 41.9k • 7
zjhhhh/7b_iter1_min_expand_ver2_tokenized_gap_ratio_0.17_logprob
Viewer • Updated • 45.7k • 7
zjhhhh/iter2_7b_multi_scores_adversary_rescaled
Viewer • Updated • 50.1k • 7
zjhhhh/7b_iter1_min_expand_ver2_tokenized_gap_ratio_0.17
Viewer • Updated • 45.7k • 7
zjhhhh/7b_iter1_min_expand_ver2_tokenized_gap_ratio_0.17_mean_beta_1.0_multi_noexpand_tokenized
Viewer • Updated • 56.9k • 7
zjhhhh/7b_iter1_preprocessed_mean_beta_1.0_multi_noexpand_tokenized_gap_ratio_0.6
Viewer • Updated • 26.3k • 7
zjhhhh/7b_iter1_preprocessed_mean_beta_1.0_multi_noexpand_tokenized_gap_ratio_0.5
Viewer • Updated • 22.1k • 8
zjhhhh/iter2_7b_multi_scores_adversary_42
Viewer • Updated • 700 • 6
zjhhhh/iter2_7b_multi_scores_base_42
Viewer • Updated • 700 • 6
zjhhhh/iter2_7b_multi_scores_adversary_45
Viewer • Updated • 700 • 5
zjhhhh/iter2_7b_multi_scores_base_45
Viewer • Updated • 700 • 4
zjhhhh/iter2_7b_multi_scores_adversary_40
Viewer • Updated • 700 • 5
zjhhhh/iter2_7b_multi_scores_base_40
Viewer • Updated • 700 • 5
zjhhhh/iter2_7b_multi_scores_adversary_43
Viewer • Updated • 700 • 5
zjhhhh/iter2_7b_multi_scores_base_43
Viewer • Updated • 700 • 5
zjhhhh/iter2_7b_multi_scores_adversary_37
Viewer • Updated • 700 • 6