HerrHruby/offline_acemath_rl_4b_inst_hard_with_dishsoap_small_16k_thinking_no_summ_curr_step_100
4B
•
Updated
•
11
Ian Wu
HerrHruby
·
AI & ML interests
None yet
Recent Activity
updated
a model
about 10 hours ago
HerrHruby/offline_acemath_rl_4b_inst_hard_with_dishsoap_small_16k_thinking_no_summ_curr_step_100
published
a model
about 11 hours ago
HerrHruby/offline_acemath_rl_4b_inst_hard_with_dishsoap_small_16k_thinking_no_summ_curr_step_100
updated
a model
1 day ago
HerrHruby/offline_acemath_rl_4b_inst_hard_with_dishsoap_small_16k_thinking_no_summ_curr_step_70
Organizations
HerrHruby/offline_acemath_rl_4b_inst_hard_with_dishsoap_small_16k_thinking_no_summ_curr_step_70
4B
•
Updated
•
28
HerrHruby/online_acemath_rl_4b_hard_16k_thinking_no_summ_2_steps_2_samples_4b_base_028_clip_step_110
4B
•
Updated
•
64
HerrHruby/online_acemath_rl_4b_hard_16k_thinking_no_summ_2_steps_2_samples_4b_base_027_clip_step_90
4B
•
Updated
•
18
HerrHruby/online_pope_rl_800_4_steps_2_samples_omit_initial_thinking_step_2_step_140
4B
•
Updated
•
16
HerrHruby/online_pope_rl_800_4_steps_2_samples_omit_initial_thinking_step_2_step_96
4B
•
Updated
•
3
HerrHruby/online_acemath_rl_4b_inst_hard_16k_thinking_no_summ_2_steps_2_samples_4b_base_buggy_step_80
4B
•
Updated
•
11
HerrHruby/online_acemath_rl_4b_inst_hard_with_dishsoap_curr_trained_90_steps_3_steps_2_samples_60_steps
4B
•
Updated
•
135
HerrHruby/online_acemath_rl_4b_inst_hard_with_dishsoap_curr_trained_90_steps_3_steps_2_samples_20_steps
4B
•
Updated
•
12
HerrHruby/online_acemath_rl_4b_inst_hard_16k_thinking_no_summ_4_steps_2_samples_step_200
4B
•
Updated
•
16
HerrHruby/online_acemath_rl_4b_inst_hard_16k_thinking_no_summ_4_steps_2_samples_step_100
4B
•
Updated
•
25
HerrHruby/offline_acemath_rl_4b_inst_hard_16k_thinking_no_summ_step_120
4B
•
Updated
•
18
HerrHruby/online_acemath_rl_4b_inst_hard_16k_thinking_no_summ_step_120
4B
•
Updated
•
20
HerrHruby/online_acemath_rl_4b_inst_hard_16k_thinking_vanilla_like_step_90
4B
•
Updated
•
66
HerrHruby/online_acemath_rl_4b_inst_hard_16k_thinking_no_summ_thinking_step_90
4B
•
Updated
•
664
HerrHruby/acemath_rl_4b_inst_hard_2_steps_complete_16k_thinking_step_50
4B
•
Updated
•
16
HerrHruby/2k_hard_5_05_8_steps_e2e_explore_small_boxed_all_bonus_pos_turn_num_2_mbzs_stable_230_steps
2B
•
Updated
•
20
HerrHruby/2k_hard_5_05_8_steps_e2e_explore_small_boxed_all_bonus_pos_turn_num_2_mbzs_stable_170_steps
2B
•
Updated
•
12
HerrHruby/2k_hard_5_05_8_steps_e2e_explore_small_boxed_all_bonus_pos_turn_num_2_mbzs_stable_130_steps
2B
•
Updated
•
4
HerrHruby/2k_hard_5_05_8_steps_e2e_explore_bonus_pos_RL_step_80
2B
•
Updated
•
2
HerrHruby/interventions_e3_prefix_RL_intervention_only_qwen3_1p7b
2B
•
Updated
•
3
HerrHruby/2k_hard_5_05_8_steps_e2e_RL_step_100
2B
•
Updated
•
1
HerrHruby/sft_qwen_3_1p7b_reasoning_cache_e2e_1p7b_deepscaler_16k_18k_2048_toks_560_steps
2B
•
Updated
•
2
HerrHruby/2k_hard_8_steps_e2e_RL_step_200
2B
•
Updated
•
1
HerrHruby/sft_qwen_3_1p7b_reasoning_cache_e2e_deepscaler_16k_38k_2048_toks_2100_steps
2B
•
Updated
•
2
HerrHruby/sft_qwen_3_1p7b_reasoning_cache_e2e_deepscaler_16k_2048_toks_560_steps
2B
•
Updated
•
8
HerrHruby/sft_qwen_3_1p7b_reasoning_cache_e2e_deepscaler_16k_2048_toks_400_steps
2B
•
Updated
•
6
HerrHruby/sft_qwen_3_1p7b_reasoning_cache_seq_sft_16k_1024_toks_1500_steps
2B
•
Updated
HerrHruby/sft_qwen2.5_1.5b_countdown_3_4_verification_19k_500_steps
2B
•
Updated
•
43
HerrHruby/sft_qwen2.5_1.5b_countdown_3_4_verification_19k_400_steps
2B
•
Updated
•
1