Jiahao Zhang PRO

zjhhhh

1

·

AI & ML interests

None yet

Recent Activity

updated a dataset about 1 month ago

zjhhhh/fixed-n-rb-offset-marginrl-qwen3-4b-base-polaris53k-offset512-token-mean-1epoch-rollouts

updated a model about 1 month ago

zjhhhh/fixed-n-rb-offset-marginrl-qwen3-4b-base-polaris53k-offset512-token-mean-1epoch-step_208

published a model about 1 month ago

zjhhhh/fixed-n-rb-offset-marginrl-qwen3-4b-base-polaris53k-offset512-token-mean-1epoch-step_208

View all activity

Organizations

None yet

zjhhhh 's datasets 4,384

zjhhhh/fixed-n-rb-offset-marginrl-qwen3-4b-base-polaris53k-offset512-token-mean-1epoch-rollouts

Viewer • Updated Sep 15 • 852k • 23

zjhhhh/f-cov-offset512-qwen3-1.7b-base-math12k-49fbccca-rollouts

Viewer • Updated Sep 15 • 614k • 15

zjhhhh/fixed-n-rb-offset512-qwen3-1.7b-base-math12k-8be8236f-rollouts

Viewer • Updated Sep 14 • 614k • 14

zjhhhh/f-cov-offset256-qwen3-1.7b-base-math12k-d72a4f5d-rollouts

Viewer • Updated Sep 14 • 614k • 20 • 2

zjhhhh/fixed-n-rb-offset256-qwen3-1.7b-base-math12k-754f8ca2-rollouts

Viewer • Updated Sep 12 • 614k • 15

zjhhhh/er_cost_marginrl_r1_distill_1.5b_compression_n16_b512_32k_lr1e-6_kl0_seed42-rollouts

Viewer • Updated Sep 12 • 51.2k • 26

zjhhhh/compression_dataset

Viewer • Updated Sep 10 • 3.2k • 41

zjhhhh/fixed-n-rb-er-cost-marginrl-qwen3-1.7b-base-math12k-token-mean-run2-rollouts

Viewer • Updated Sep 6 • 840k • 16

zjhhhh/fixed-n-rb-cost-aware-marginrl-qwen3-1.7b-base-math12k-token-mean-rerun-rollouts

Viewer • Updated Sep 5 • 942k • 129

zjhhhh/fixed-n-rb-er-cost-marginrl-qwen3-1.7b-base-math12k-token-mean-fixed-q0p8-run2-rollouts

Viewer • Updated Aug 24 • 942k • 12

zjhhhh/DeepScaleR-Qwen3-1.7B-2k-strategy-error-200

Viewer • Updated Jul 29 • 200 • 11

zjhhhh/game_qwen2.5_rlcf_viswavi__qwen2.5_rlcf

Viewer • Updated Jul 25 • 500 • 6

zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_rlcf_worst_expand_tokenized_gap_ratio_0.17_logprob

Viewer • Updated Jul 24 • 41.4k • 52

zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_rlcf_worst_expand_tokenized_gap_ratio_0.17

Viewer • Updated Jul 24 • 41.4k • 29

zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_preprocessed

Viewer • Updated Jul 24 • 41k • 46

zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_rescaled

Viewer • Updated Jul 24 • 50.1k • 6

zjhhhh/game_qwen2.5_rlcf_base

Viewer • Updated Jul 24 • 500 • 14

zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_42

Viewer • Updated Jul 24 • 700 • 6

zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_45

Viewer • Updated Jul 24 • 700 • 21

zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_43

Viewer • Updated Jul 24 • 700 • 7

zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_48

Viewer • Updated Jul 24 • 700 • 9

zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_40

Viewer • Updated Jul 24 • 700 • 6

zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_41

Viewer • Updated Jul 24 • 700 • 5

zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_37

Viewer • Updated Jul 24 • 700 • 5

zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_46

Viewer • Updated Jul 24 • 700 • 8

zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_33

Viewer • Updated Jul 24 • 700 • 5

zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_36

Viewer • Updated Jul 24 • 700 • 5

zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_34

Viewer • Updated Jul 24 • 700 • 8

zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_44

Viewer • Updated Jul 24 • 700 • 8

zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_35

Viewer • Updated Jul 24 • 700 • 6