happynew111/NEW_qwen2_5_MATH_1_5b_grpo_reg_beta_0.1_gspo_bce_4
Viewer • Updated • 1 • 15
Liu
happynew111
AI & ML interests
None yet
Organizations
None yet
happynew111/NEW_qwen2_5_MATH_1_5b_grpo_reg_beta_0.1_gspo_bce_3
Viewer • Updated • 1 • 14
happynew111/NEW_qwen2_5_MATH_1_5b_grpo_reg_beta_0.1_gspo_bce_2
Viewer • Updated • 1 • 16
happynew111/NEW_qwen2_5_MATH_1_5b_grpo_reg_beta_0.1_gspo_bce_1
Viewer • Updated • 1 • 17
happynew111/NEW_qwen2_5_MATH_1_5b_grpo_reg_beta_0.1_gpg_bce_5
Viewer • Updated • 1 • 13
happynew111/NEW_qwen2_5_MATH_1_5b_grpo_reg_beta_0.1_gpg_bce_4
Viewer • Updated • 1 • 19
happynew111/NEW_qwen2_5_MATH_1_5b_grpo_reg_beta_0.1_gpg_bce_3
Viewer • Updated • 1 • 16
happynew111/NEW_qwen2_5_MATH_1_5b_grpo_reg_beta_0.1_gpg_bce_2
Viewer • Updated • 1 • 22
happynew111/NEW_qwen2_5_MATH_1_5b_grpo_reg_beta_0.1_gpg_bce_1
Viewer • Updated • 1 • 12
happynew111/haotian_data-GPS-AR-Lopti-master
Preview • Updated • 152
happynew111/haotian_data-GPS-Model
Updated • 19
happynew111/haotian_data-GPS-CCGSPG_for_me
Updated • 16
happynew111/haotian_data-GPS-CCGSPG_for_me_second
Updated • 18
happynew111/haotian_data-GPS-GAINRL-main
Updated • 16
happynew111/haotian_data-GPS-lm-evaluation-harness
Updated • 701
happynew111/haotian_data-GPS-verl-main-CL
Updated • 572
happynew111/haotian_data-GPS-verl-main
Viewer • Updated • 13.5k • 23
happynew111/MATH_BS_BCE_train_json
Viewer • Updated • 8.97M • 13
happynew111/MATH_BS_BCE_valid_log_json
Viewer • Updated • 1.51M • 18
happynew111/AR_train_json
Viewer • Updated • 12.5k • 13
happynew111/AR_valid_log_json
Preview • Updated • 12
happynew111/MATH_train_json
Viewer • Updated • 7 • 15
happynew111/MATH_valid_log_json
Updated • 6