AI & ML interests
None yet
Organizations
None yet
models 39
happynew111/haotian_data-GPS-verl-main
Updated
happynew111/MATH_valid_log_json
Updated
happynew111/NEW_qwen2_5_MATH_1_5b_grpo_reg_gspo_third_time
Updated
happynew111/NEW_qwen2_5_MATH_1_5b_grpo_reg_gspo_second_time
Updated
happynew111/NEW_qwen2_5_MATH_1_5b_grpo_reg_gspo_5_time
Updated
happynew111/NEW_qwen2_5_MATH_1_5b_grpo_reg_gspo_4_time
Updated
happynew111/NEW_qwen2_5_MATH_1_5b_grpo_reg_gspo
Updated
happynew111/NEW_qwen2_5_MATH_1_5b_grpo_reg_gpg_third
Updated
happynew111/NEW_qwen2_5_MATH_1_5b_grpo_reg_gpg_second
Updated
happynew111/NEW_qwen2_5_MATH_1_5b_grpo_reg_gpg_5
Updated
datasets 53
happynew111/NEW_qwen2_5_MATH_1_5b_grpo_AR_Lopti_follow_kk_bce_5
Viewer
• Updated • 1 • 18
happynew111/NEW_qwen2_5_MATH_1_5b_grpo_AR_Lopti_follow_kk_bce_4
Viewer
• Updated • 1 • 13
happynew111/NEW_qwen2_5_MATH_1_5b_grpo_AR_Lopti_follow_kk_bce_3
Viewer
• Updated • 1 • 9
happynew111/NEW_qwen2_5_MATH_1_5b_grpo_AR_Lopti_follow_kk_bce_2
Viewer
• Updated • 1 • 16
happynew111/NEW_qwen2_5_MATH_1_5b_grpo_AR_Lopti_follow_kk_bce_1
Viewer
• Updated • 1 • 6
happynew111/ADARFT-advantage_plots_valid
Viewer
• Updated • 49 • 17
Updated • 46
happynew111/qwen2_5_MATH_1_5b_grpo_baseline_rollout_4
Viewer
• Updated • 1 • 18
happynew111/NEW_qwen2_5_MATH_1_5b_grpo_reg_beta_1_ccpo_bce_pos_1_neg_1
Updated • 11
happynew111/NEW_qwen2_5_MATH_1_5b_grpo_reg_beta_1_ccpo_bce_1
Updated • 25