zjhhhh/fixed-n-rb-capped-cost-aware-marginrl-qwen3-1.7b-base-math12k-cap8-token-mean-step_150
Updated
Jiahao Zhang PRO
zjhhhh
AI & ML interests
None yet
Recent Activity
published a model 1 minute ago
zjhhhh/fixed-n-rb-capped-cost-aware-marginrl-qwen3-1.7b-base-math12k-cap8-token-mean-step_150 updated a model 1 minute ago
zjhhhh/fixed-n-rb-capped-cost-aware-marginrl-qwen3-1.7b-base-math12k-cap8-token-mean-step_100 published a model 2 minutes ago
zjhhhh/fixed-n-rb-capped-cost-aware-marginrl-qwen3-1.7b-base-math12k-cap8-token-mean-step_100Organizations
None yet
models 693
zjhhhh/fixed-n-rb-capped-cost-aware-marginrl-qwen3-1.7b-base-math12k-cap8-token-mean-step_100
Updated
zjhhhh/fixed-n-rb-capped-cost-aware-marginrl-qwen3-1.7b-base-math12k-cap8-token-mean-step_50
Updated
zjhhhh/fixed-n-rb-er-cost-marginrl-qwen3-1.7b-base-math12k-token-mean-from-maxrl-step100-plus50-step_50
Updated
zjhhhh/fixed-n-rb-er-cost-marginrl-success-gated-qwen3-1.7b-base-math12k-token-mean-step_230
Updated
zjhhhh/fixed-n-rb-er-cost-marginrl-success-gated-qwen3-1.7b-base-math12k-token-mean-step_200
Updated
zjhhhh/fixed-n-rb-er-cost-marginrl-success-gated-qwen3-1.7b-base-math12k-token-mean-step_150
Updated
zjhhhh/fixed-n-rb-er-cost-marginrl-success-gated-qwen3-1.7b-base-math12k-token-mean-step_100
Updated
zjhhhh/fixed-n-rb-er-cost-marginrl-success-gated-qwen3-1.7b-base-math12k-token-mean-step_50
Updated
zjhhhh/efficient-reasoning-qwen3-1.7b-base-math12k-step_150
Updated
datasets 4,374
zjhhhh/DeepScaleR-Qwen3-1.7B-2k-strategy-error-200
Viewer • Updated • 200 • 471
zjhhhh/game_qwen2.5_rlcf_viswavi__qwen2.5_rlcf
Viewer • Updated • 500 • 50
zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_rlcf_worst_expand_tokenized_gap_ratio_0.17_logprob
Viewer • Updated • 41.4k • 62
zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_rlcf_worst_expand_tokenized_gap_ratio_0.17
Viewer • Updated • 41.4k • 53
zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_preprocessed
Viewer • Updated • 41k • 48
zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_rescaled
Viewer • Updated • 50.1k • 52
zjhhhh/game_qwen2.5_rlcf_base
Viewer • Updated • 500 • 42
zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_42
Viewer • Updated • 700 • 47
zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_45
Viewer • Updated • 700 • 40
zjhhhh/7b_iter2_rlcf_worst_rerun_0.17_vec_rlcf_scores_43
Viewer • Updated • 700 • 46