Ian Wu

HerrHruby 's models 46

Sort:  Recently updated

HerrHruby/online_pope_rl_800_4_steps_2_samples_omit_initial_thinking_step_2_step_96

4B • Updated Nov 7 • 2

HerrHruby/online_acemath_rl_4b_inst_hard_16k_thinking_no_summ_2_steps_2_samples_4b_base_buggy_step_80

4B • Updated Nov 7 • 3

HerrHruby/online_acemath_rl_4b_inst_hard_with_dishsoap_curr_trained_90_steps_3_steps_2_samples_60_steps

4B • Updated Nov 2 • 32

HerrHruby/online_acemath_rl_4b_inst_hard_with_dishsoap_curr_trained_90_steps_3_steps_2_samples_20_steps

4B • Updated Nov 2 • 3

HerrHruby/online_acemath_rl_4b_inst_hard_16k_thinking_no_summ_4_steps_2_samples_step_200

4B • Updated Oct 29 • 3

HerrHruby/online_acemath_rl_4b_inst_hard_16k_thinking_no_summ_4_steps_2_samples_step_100

4B • Updated Oct 28 • 4

HerrHruby/offline_acemath_rl_4b_inst_hard_16k_thinking_no_summ_step_120

4B • Updated Oct 26 • 3

HerrHruby/online_acemath_rl_4b_inst_hard_16k_thinking_no_summ_step_120

4B • Updated Oct 21 • 5

HerrHruby/online_acemath_rl_4b_inst_hard_16k_thinking_vanilla_like_step_90

4B • Updated Oct 21 • 3

HerrHruby/online_acemath_rl_4b_inst_hard_16k_thinking_no_summ_thinking_step_90

4B • Updated Oct 21 • 167

HerrHruby/acemath_rl_4b_inst_hard_2_steps_complete_16k_thinking_step_50

4B • Updated Oct 19 • 8

HerrHruby/interventions_e3_prefix_RL_intervention_only_qwen3_1p7b

2B • Updated Sep 22 • 5

HerrHruby/sft_qwen2.5_1.5b_countdown_3_4_verification_19k_500_steps

2B • Updated Sep 9 • 4

HerrHruby/sft_qwen2.5_1.5b_countdown_3_4_verification_19k_400_steps

2B • Updated Sep 9 • 4

HerrHruby/sft_qwen2.5_1.5b_countdown_3_4_verification_19k_300_steps

2B • Updated Sep 9 • 4

HerrHruby/sft_qwen2.5_1.5b_countdown_verification_16k_400_steps

2B • Updated Sep 8 • 4