MultiRL

non-profit

AI & ML interests

None defined yet.

Recent Activity

KimSHine updated a model about 19 hours ago

MultiRL/qwen3_1.7b_easy_rl_ours_adv_fixed_gamma_1_98_gem_ms_seq_is

KimSHine published a model about 19 hours ago

MultiRL/qwen3_1.7b_easy_rl_ours_adv_fixed_gamma_1_98_gem_ms_seq_is

KimSHine updated a model 1 day ago

MultiRL/qwen3_1.7b_easy_rl_ours_adv_fixed_gamma_1_98_mask_only

View all activity

MultiRL 's models 90

MultiRL/qwen3_1.7b_easy_rl_ours_adv_fixed_gamma_1_98_gem_ms_seq_is

2B • Updated about 19 hours ago • 50

MultiRL/qwen3_1.7b_easy_rl_ours_adv_fixed_gamma_1_98_mask_only

2B • Updated 1 day ago • 104

MultiRL/qwen3_1.7b_easy_rl_ours_adv_fixed_gamma_995_98_ori_norm

2B • Updated 5 days ago • 152

MultiRL/qwen3_1.7b_easy_rl_ours_adv_fixed_gamma_995_98

2B • Updated 7 days ago • 6

MultiRL/qwen3_1.7b_sft_final_easy_reinforce_ours_adv_fixed_gamma_0.9

2B • Updated 9 days ago • 277

MultiRL/qwen3_1.7b_easy_rl_old_adv_fixed_gamma_1

2B • Updated 10 days ago • 109

MultiRL/qwen3_1.7b_easy_rl_fixed_gamma_1

2B • Updated 13 days ago • 135

MultiRL/qwen3_1.7b_easy_rl_old_adv_final_fixed_sequence_max_token_norm_batch_128

2B • Updated 14 days ago • 46

MultiRL/qwen3_1.7b_medium_rl_ours_adv_final_fixed_sequence_gamma_1

2B • Updated 14 days ago • 14

MultiRL/qwen3_1.7b_medium_rl_ours_adv_fixed_sequence_from_epoch_3

2B • Updated 15 days ago • 6

MultiRL/qwen3_1.7b_easy_rl_ours_adv_final_fixed_sequence_max_token_norm

2B • Updated 15 days ago • 7

MultiRL/qwen3_1.7b_easy_rl_ours_adv_fixed_sequence_batch_128

2B • Updated 16 days ago • 1.1k

MultiRL/qwen3_1.7b_easy_rl_ours_adv_fixed_sequence_epoch_3

2B • Updated 16 days ago • 173

MultiRL/qwen3_1.7b_easy_rl_ours_adv_fixed_token

2B • Updated 17 days ago • 89

MultiRL/qwen3_1.7b_easy_rl_gamma_1_step_40

2B • Updated 18 days ago • 94

MultiRL/qwen3_4b_easy_rl_our_adv_final

4B • Updated 20 days ago • 1.92k

MultiRL/qwen3_1.7b_easy_rl_final_group_norm

2B • Updated 20 days ago • 92

MultiRL/qwen3_1.7b_easy_rl_final_gamma_1

2B • Updated 24 days ago • 2.93k

MultiRL/qwen3_4b_base_easy_rl_final

4B • Updated 24 days ago • 138

MultiRL/qwen3_4b_base_sft_final

4B • Updated 25 days ago • 612

MultiRL/qwen3_4b_easy_rl_new

4B • Updated 26 days ago • 1.2k

MultiRL/qwen3_1.7b_easy_rl_gspo

2B • Updated 26 days ago • 109

MultiRL/qwen3_4b_sft_new

4B • Updated 27 days ago • 836

MultiRL/qwen3_1.7b_easy_rl_final_step120

2B • Updated 27 days ago • 3.69k

MultiRL/qwen3_4b_medium_rl_final

4B • Updated 27 days ago • 2.05k

MultiRL/qwen3_4b_sft_one_act

4B • Updated 28 days ago • 359

MultiRL/qwen3_1.7b_easy_rl_reinforce_ori

2B • Updated 28 days ago • 19

MultiRL/qwen3_1.7b_easy_rl_reinforce_alpha_0.5

2B • Updated 28 days ago • 105

MultiRL/qwen3_1.7b_easy_rl_reinforce_alpha_1

2B • Updated 28 days ago • 105

MultiRL/qwen3_1.7b_easy_rl_reinforce_alpha_0

2B • Updated 28 days ago • 103