Ian Wu's picture

Ian Wu

HerrHruby

·

AI & ML interests

None yet

Recent Activity

updated a dataset 2 days ago

AI-Math-TCS/tcs_papers_v1

published a dataset 2 days ago

AI-Math-TCS/tcs_papers_v1

updated a dataset 3 days ago

HerrHruby/scout_idx1024to2048_guided_branch_viz20

View all activity

Organizations

HerrHruby 's models 61

HerrHruby/offline_acemath_rl_30b_inst_hard_16k_filtered_with_dishsoap_curr_3_steps_2_samples_step_120

31B • Updated Dec 29, 2025 • 1

HerrHruby/offline_acemath_rl_30b_inst_hard_16k_filtered_with_dishsoap_curr_3_steps_2_samples_step_100

31B • Updated Dec 29, 2025 • 1

HerrHruby/offline_acemath_rl_30b_inst_hard_16k_filtered_with_dishsoap_curr_3_steps_2_samples_step_60

31B • Updated Dec 27, 2025 • 1

HerrHruby/online_acemath_rl_30b_inst_hard_16k_filtered_no_summ_3_steps_2_samples_step_80

31B • Updated Dec 24, 2025 • 1

HerrHruby/online_acemath_rl_30b_inst_hard_16k_no_summ_2_steps_2_samples_step_80_high_ent

31B • Updated Dec 19, 2025 • 1

HerrHruby/vanilla_grpo_acemath_rl_30b_async_inst_16k_step_130

31B • Updated Dec 8, 2025

HerrHruby/vanilla_grpo_acemath_rl_30b_inst_16k_step_130

31B • Updated Dec 7, 2025 • 1

HerrHruby/vanilla_grpo_acemath_rl_4b_inst_16k_step_180

4B • Updated Nov 29, 2025 • 4

HerrHruby/offline_acemath_rl_4b_inst_hard_with_dishsoap_16k_no_summ_curr_3_steps_2_samples_step_170

4B • Updated Nov 29, 2025 • 2

HerrHruby/offline_acemath_rl_4b_inst_hard_with_dishsoap_16k_no_summ_curr_3_steps_2_samples_step_120

4B • Updated Nov 28, 2025

HerrHruby/vanilla_grpo_acemath_rl_4b_inst_32k_step_180

4B • Updated Nov 27, 2025

HerrHruby/offline_acemath_rl_4b_inst_hard_with_dishsoap_16k_no_summ_curr_omit_step_150

4B • Updated Nov 26, 2025 • 1

HerrHruby/online_acemath_rl_4b_inst_hard_16k_no_summ_3_steps_2_samples_step_120

4B • Updated Nov 24, 2025 • 1

HerrHruby/offline_acemath_rl_4b_inst_hard_with_dishsoap_16k_no_summ_curr_step_180

4B • Updated Nov 23, 2025 • 1

HerrHruby/offline_acemath_rl_4b_inst_hard_with_dishsoap_16k_no_summ_curr_step_60

4B • Updated Nov 22, 2025

HerrHruby/offline_acemath_rl_4b_inst_hard_with_dishsoap_small_16k_thinking_no_summ_curr_step_100

4B • Updated Nov 13, 2025 • 1

HerrHruby/offline_acemath_rl_4b_inst_hard_with_dishsoap_small_16k_thinking_no_summ_curr_step_70

4B • Updated Nov 13, 2025 • 2

HerrHruby/online_acemath_rl_4b_hard_16k_thinking_no_summ_2_steps_2_samples_4b_base_028_clip_step_110

4B • Updated Nov 12, 2025 • 2

HerrHruby/online_acemath_rl_4b_hard_16k_thinking_no_summ_2_steps_2_samples_4b_base_027_clip_step_90

4B • Updated Nov 11, 2025 • 1

HerrHruby/online_pope_rl_800_4_steps_2_samples_omit_initial_thinking_step_2_step_140

4B • Updated Nov 9, 2025

HerrHruby/online_pope_rl_800_4_steps_2_samples_omit_initial_thinking_step_2_step_96

4B • Updated Nov 7, 2025 • 1

HerrHruby/online_acemath_rl_4b_inst_hard_16k_thinking_no_summ_2_steps_2_samples_4b_base_buggy_step_80

4B • Updated Nov 7, 2025 • 2

HerrHruby/online_acemath_rl_4b_inst_hard_with_dishsoap_curr_trained_90_steps_3_steps_2_samples_60_steps

4B • Updated Nov 2, 2025 • 1

HerrHruby/online_acemath_rl_4b_inst_hard_with_dishsoap_curr_trained_90_steps_3_steps_2_samples_20_steps

4B • Updated Nov 2, 2025 • 2

HerrHruby/online_acemath_rl_4b_inst_hard_16k_thinking_no_summ_4_steps_2_samples_step_200

4B • Updated Oct 29, 2025 • 3

HerrHruby/online_acemath_rl_4b_inst_hard_16k_thinking_no_summ_4_steps_2_samples_step_100

4B • Updated Oct 28, 2025 • 1

HerrHruby/offline_acemath_rl_4b_inst_hard_16k_thinking_no_summ_step_120

4B • Updated Oct 26, 2025 • 1

HerrHruby/online_acemath_rl_4b_inst_hard_16k_thinking_no_summ_step_120

4B • Updated Oct 21, 2025 • 1

HerrHruby/online_acemath_rl_4b_inst_hard_16k_thinking_vanilla_like_step_90

4B • Updated Oct 21, 2025 • 2

HerrHruby/online_acemath_rl_4b_inst_hard_16k_thinking_no_summ_thinking_step_90

4B • Updated Oct 21, 2025 • 1