prathyusha-ut
10 models • 0 total models in database
Sort by:
qwen0.5_high_grpo_actor_step300
—
14
0
grpo_exp_c5_r1_s930451653_actor_step400
llama
13
0
grpo_exp_c4_r3_s458263775_actor_step400
llama
12
0
qwen0.5_full_junk_grpo_actor_step300
—
9
0
qwen0.5_control_grpo_actor_step300
—
8
0
grpo_exp_c3_r1_s742447337_actor_step400
llama
7
0
grpo_exp_c3_r3_s583256885_actor_step400
llama
6
0
grpo_exp_c4_r1_s604955402_actor_step400
llama
6
0
grpo_exp_c3_r2_s735266765_actor_step400
llama
5
0
grpo_exp_c4_r2_s129300818_actor_step400
llama
5
0