zjhhhh/Qwen7b_multi_perprompt_iter1_44000
Viewer • Updated • 2k • 4
Jiahao Zhang
zjhhhh
AI & ML interests
None yet
Recent Activity
updated a dataset 5 days ago
zjhhhh/rltf-feedback-distillation-toy-50q-4r published a dataset 5 days ago
zjhhhh/rltf-feedback-distillation-toy-50q-4r updated a model about 2 months ago
zjhhhh/rltf-dapo-sd-smoke-gs31Organizations
None yet
zjhhhh/Qwen7b_multi_perprompt_iter1_16000
Preview • Updated • 3
zjhhhh/Qwen7b_multi_perprompt_iter1_26000
Viewer • Updated • 2k • 3
zjhhhh/Qwen7b_multi_perprompt_iter1_36000
Viewer • Updated • 2k • 3
zjhhhh/Qwen7b_multi_perprompt_iter1_50000
Viewer • Updated • 1.07k • 4
zjhhhh/7b_iter1_preprocessed_mean_beta_1.0_multi_noexpand_tokenized_gap_ratio_0.8_logprob
Viewer • Updated • 34.9k • 4
zjhhhh/7b_iter1_preprocessed_mean_beta_1.0_multi_noexpand_tokenized_gap_ratio_0.9_logprob
Preview • Updated • 3
zjhhhh/7b_iter1_mean_beta_1.0_multi_expand_tokenized_gap_ratio_0.34_logprob
Viewer • Updated • 87.5k • 5
zjhhhh/7b_iter1_preprocessed_mean_beta_1.0_multi_noexpand_tokenized_logprob
Viewer • Updated • 43.4k • 4
zjhhhh/7b_iter1_mean_beta_1.0_multi_expand_tokenized_gap_ratio_0.1_logprob
Viewer • Updated • 27.7k • 4
zjhhhh/7b_iter1_preprocessed_mean_beta_1.0_multi_noexpand_tokenized_gap_ratio_0.9
Viewer • Updated • 39.1k • 3
zjhhhh/7b_iter1_preprocessed_mean_beta_1.0_multi_noexpand_tokenized_gap_ratio_0.8
Viewer • Updated • 34.9k • 4
zjhhhh/7b_iter1_mean_beta_1.0_multi_expand_tokenized_gap_ratio_0.34
Viewer • Updated • 87.5k • 3
zjhhhh/7b_iter1_mean_beta_1.0_multi_expand_tokenized_gap_ratio_0.1
Viewer • Updated • 27.7k • 4
zjhhhh/iter2_7b_min_0.17_final_adversary_min_expand_ver2_tokenized_gap_ratio_0.17_logprob
Viewer • Updated • 41.6k • 4
zjhhhh/iter2_7b_min_0.17_final_adversary_min_expand_ver2_tokenized_gap_ratio_0.17
Viewer • Updated • 41.6k • 4
zjhhhh/iter2_7b_min_0.17_final_adversary_min_expand_ver2_tokenized
Viewer • Updated • 241k • 4
zjhhhh/iter2_7b_min_0.17_final_adversary_preprocessed
Viewer • Updated • 41.3k • 4
zjhhhh/iter2_7b_min_gap_0.17_final_scores_adversary_rescaled
Viewer • Updated • 50.1k • 3
zjhhhh/iter2_7b_min_gap_0.17_final_scores_base_42
Viewer • Updated • 700 • 4
zjhhhh/iter2_7b_min_gap_0.17_final_scores_adversary_40
Viewer • Updated • 700 • 4
zjhhhh/iter2_7b_min_gap_0.17_final_scores_base_40
Viewer • Updated • 700 • 3
zjhhhh/iter2_7b_min_gap_0.17_final_scores_adversary_43
Viewer • Updated • 700 • 4
zjhhhh/iter2_7b_min_gap_0.17_final_scores_base_43
Viewer • Updated • 700 • 4
zjhhhh/iter2_7b_min_gap_0.17_final_scores_adversary_45
Viewer • Updated • 700 • 3
zjhhhh/iter2_7b_min_gap_0.17_final_scores_base_45
Viewer • Updated • 700 • 4
zjhhhh/iter2_7b_min_gap_0.17_final_scores_adversary_37
Viewer • Updated • 700 • 4
zjhhhh/iter2_7b_min_gap_0.17_final_scores_base_37
Viewer • Updated • 700 • 3
zjhhhh/iter2_7b_min_gap_0.17_final_scores_adversary_46
Viewer • Updated • 700 • 4
zjhhhh/iter2_7b_min_gap_0.17_final_scores_base_46
Viewer • Updated • 700 • 4