MultiRL/qwen3_1.7b_easy_rl_ours_adv_fixed_geo_ms_token_tis
2B
•
Updated
MultiRL
non-profit
AI & ML interests
None defined yet.
Recent Activity
View all activity
models
94
MultiRL/qwen3_1.7b_easy_rl_ours_adv_fixed_gamma_1_98_geo_ms_6epoch
2B
•
Updated
•
8
MultiRL/qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5
2B
•
Updated
•
6
MultiRL/qwen3_1.7b_easy_rl_ours_adv_fixed_gamma_1_98_geo_ms_token_tis
2B
•
Updated
•
187
MultiRL/qwen3_1.7b_easy_rl_ours_adv_fixed_gamma_1_98_gem_ms_seq_is
2B
•
Updated
•
372
MultiRL/qwen3_1.7b_easy_rl_ours_adv_fixed_gamma_1_98_mask_only
2B
•
Updated
•
250
MultiRL/qwen3_1.7b_easy_rl_ours_adv_fixed_gamma_995_98_ori_norm
2B
•
Updated
•
160
MultiRL/qwen3_1.7b_easy_rl_ours_adv_fixed_gamma_995_98
2B
•
Updated
•
6
MultiRL/qwen3_1.7b_sft_final_easy_reinforce_ours_adv_fixed_gamma_0.9
2B
•
Updated
•
386
MultiRL/qwen3_1.7b_easy_rl_old_adv_fixed_gamma_1
2B
•
Updated
•
234
datasets
32
MultiRL/new_sudoku_benchmark_900
Updated
MultiRL/new_sudoku_many
Viewer
•
Updated
•
790
MultiRL/hard_short
Viewer
•
Updated
•
100
MultiRL/easy_tooshort
Viewer
•
Updated
•
420
MultiRL/easy_toolong
Viewer
•
Updated
•
150
MultiRL/final_sudoku_medium_rl_hint
Viewer
•
Updated
•
640
MultiRL/final_sudoku_sft_C_hint
Viewer
•
Updated
•
800
MultiRL/final_sudoku_easy_rl_hint
Viewer
•
Updated
•
320
MultiRL/final_sudoku_benchmark_hint
Viewer
•
Updated
•
515
•
12
MultiRL/rush_hour_benchmark
Viewer
•
Updated
•
150
•
31