Active filters: SWY666
SWY666/SimPO_adjusted_Best3_4096_Qwen-Go-temp-1
3B • Updated • 2
SWY666/SimPO_adjusted_Best3_410_Qwen-Go-temp-1
3B • Updated • 3
SWY666/SimPO_adjusted_Best3_410_Qwen-Go-temp-0p9
3B • Updated • 2
SWY666/GRPO_Best13_double
3B • Updated • 2
SWY666/GRPO_Best13_Linear_topk_820
3B • Updated • 2
SWY666/GRPO_BestN3_Linear_topk_820
3B • Updated • 2
SWY666/GRPO_BestN3_double
3B • Updated • 2
SWY666/GRPO_Best13_double_pure
3B • Updated • 5
SWY666/GRPO_Best13_Linear_topk_820_official
3B • Updated • 4
SWY666/GRPO_BestN3_double_pure
3B • Updated • 2
3B • Updated • 2
SWY666/GRPO_Best1_Linear_topk_820_official
3B • Updated • 2
3B • Updated • 2
SWY666/Best13-topk-double-Qwen-Go_official
3B • Updated • 3
SWY666/GRPO_Best1_Linear_topk_8192_official
3B • Updated • 3
SWY666/GRPO_Best3_Linear_topk_4096_official
3B • Updated • 3
SWY666/GRPO_Best1_Linear_topk_205_official
3B • Updated • 1
SWY666/GRPO_Best13_Linear_topk_205_official
3B • Updated • 2
SWY666/GRPO_Best3_Linear_topk_205_official
3B • Updated • 4
SWY666/GRPO_Best13_Linear_topk_1620_official
3B • Updated • 2
SWY666/GRPO_Best13_topk_double_official_new
3B • Updated • 2
SWY666/Best3_Linear_topk_1640_official_new
3B • Updated • 2
SWY666/Best13_L_1620_official_new
3B • Updated • 2
3B • Updated • 5
SWY666/Best13_L_3280_official_new
Updated
3B • Updated • 2
SWY666/Best13_820_c_distance
3B • Updated • 2
SWY666/Nemotron_official_0
3B • Updated • 5
SWY666/Nemotron_official_topk_8192
3B • Updated • 2
SWY666/Best2_official_topk_4608
3B • Updated • 8