happynew111/NEW_qwen2_5_MATH_1_5b_grpo_reg_beta_0.1_gspo_bce_4
Viewer • Updated • 1 • 2
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 • 6
happynew111/NEW_qwen2_5_MATH_1_5b_grpo_reg_beta_0.1_gspo_bce_2
Viewer • Updated • 1 • 10
happynew111/NEW_qwen2_5_MATH_1_5b_grpo_reg_beta_0.1_gspo_bce_1
Viewer • Updated • 1 • 6
happynew111/NEW_qwen2_5_MATH_1_5b_grpo_reg_beta_0.1_gpg_bce_5
Viewer • Updated • 1 • 7
happynew111/NEW_qwen2_5_MATH_1_5b_grpo_reg_beta_0.1_gpg_bce_4
Viewer • Updated • 1 • 9
happynew111/NEW_qwen2_5_MATH_1_5b_grpo_reg_beta_0.1_gpg_bce_3
Viewer • Updated • 1 • 2
happynew111/NEW_qwen2_5_MATH_1_5b_grpo_reg_beta_0.1_gpg_bce_2
Viewer • Updated • 1 • 6
happynew111/NEW_qwen2_5_MATH_1_5b_grpo_reg_beta_0.1_gpg_bce_1
Viewer • Updated • 1 • 11
happynew111/haotian_data-GPS-AR-Lopti-master
Preview • Updated • 172
happynew111/haotian_data-GPS-Model
Updated • 3
happynew111/haotian_data-GPS-CCGSPG_for_me
Updated • 2
happynew111/haotian_data-GPS-CCGSPG_for_me_second
Updated • 2
happynew111/haotian_data-GPS-GAINRL-main
Updated • 2
happynew111/haotian_data-GPS-lm-evaluation-harness
Updated • 997
happynew111/haotian_data-GPS-verl-main-CL
Updated • 140
happynew111/haotian_data-GPS-verl-main
Viewer • Updated • 13.5k • 2
happynew111/MATH_BS_BCE_train_json
Viewer • Updated • 8.97M • 4
happynew111/MATH_BS_BCE_valid_log_json
Viewer • Updated • 1.51M • 21
happynew111/AR_train_json
Viewer • Updated • 12.5k • 2
happynew111/AR_valid_log_json
Preview • Updated • 2
happynew111/MATH_train_json
Viewer • Updated • 7 • 6
happynew111/MATH_valid_log_json
Updated • 2