HerrHruby/offline_acemath_rl_30b_inst_hard_16k_filtered_with_dishsoap_curr_3_steps_2_samples_step_140
31B
•
Updated
Ian Wu
HerrHruby
·
AI & ML interests
None yet
Recent Activity
updated
a dataset
about 1 hour ago
HerrHruby/30b_trained_80
published
a dataset
about 1 hour ago
HerrHruby/30b_trained_80
updated
a dataset
about 1 hour ago
HerrHruby/30b_trained_60
Organizations
models
46
HerrHruby/offline_acemath_rl_30b_inst_hard_16k_filtered_with_dishsoap_curr_3_steps_2_samples_step_130
31B
•
Updated
•
3
HerrHruby/offline_acemath_rl_30b_inst_hard_16k_filtered_with_dishsoap_curr_3_steps_2_samples_step_120
31B
•
Updated
•
5
HerrHruby/offline_acemath_rl_30b_inst_hard_16k_filtered_with_dishsoap_curr_3_steps_2_samples_step_100
31B
•
Updated
•
6
HerrHruby/offline_acemath_rl_30b_inst_hard_16k_filtered_with_dishsoap_curr_3_steps_2_samples_step_80
31B
•
Updated
•
8
HerrHruby/offline_acemath_rl_30b_inst_hard_16k_filtered_with_dishsoap_curr_3_steps_2_samples_step_60
31B
•
Updated
•
11
HerrHruby/online_acemath_rl_30b_inst_hard_16k_filtered_no_summ_3_steps_2_samples_step_80
31B
•
Updated
•
410
HerrHruby/online_acemath_rl_30b_inst_hard_16k_no_summ_2_steps_2_samples_step_80_high_ent
31B
•
Updated
•
16
HerrHruby/vanilla_grpo_acemath_rl_30b_async_inst_16k_step_130
31B
•
Updated
•
11
HerrHruby/vanilla_grpo_acemath_rl_30b_inst_16k_step_130
31B
•
Updated
•
13
datasets
35
HerrHruby/30b_trained_80
Viewer
•
Updated
•
3.2k
HerrHruby/30b_trained_60
Viewer
•
Updated
•
3.2k
HerrHruby/acemath_rl_30b_a3b_inst_hard_filtered_with_dishsoap
Viewer
•
Updated
•
3.28k
•
3
HerrHruby/fs_gptoss_20b
Viewer
•
Updated
•
800
•
7
HerrHruby/fs_gptoss_120b
Viewer
•
Updated
•
800
•
5
HerrHruby/answerbench_gptoss
Viewer
•
Updated
•
1.6k
•
7
HerrHruby/acemath_rl_30b_a3b_inst_hard_filtered
Viewer
•
Updated
•
2.25k
•
10
HerrHruby/acemath_rl_30b_a3b_inst_hard
Viewer
•
Updated
•
2.49k
•
25
HerrHruby/hmmt_25_nov
Viewer
•
Updated
•
30
•
7
HerrHruby/pope_acemath_mix_rl_372
Viewer
•
Updated
•
500
•
17