Weiyu Sun

SWY666 's models 73

Sort:  Recently updated

SWY666/Best13-topk-double-Qwen-Go_official

3B • Updated Apr 24, 2025

SWY666/GRPO_Best3_Linear_topk_4096_official

3B • Updated Apr 24, 2025

SWY666/GRPO_Best1

3B • Updated Apr 23, 2025

SWY666/GRPO_Best3

3B • Updated Apr 22, 2025

SWY666/GRPO_BestN3_double_pure

3B • Updated Apr 20, 2025

SWY666/GRPO_Best13_double_pure

3B • Updated Apr 19, 2025

SWY666/SimPO_adjusted_Best1_Qwen-Go

3B • Updated Apr 17, 2025 • 1

SWY666/SimPO_adjusted_Best3_4096_Qwen-Go

3B • Updated Apr 16, 2025 • 1

SWY666/GRPO_BestN3_double

3B • Updated Apr 16, 2025

SWY666/GRPO_BestN3_Linear_topk_820

3B • Updated Apr 14, 2025

SWY666/GRPO_Best13_double

3B • Updated Apr 10, 2025 • 68

SWY666/GRPO_Best13_Linear_topk_820

3B • Updated Apr 10, 2025

SWY666/SimPO_adjusted_Best3_410_Qwen-Go-temp-1

3B • Updated Apr 6, 2025

SWY666/SimPO_adjusted_Best3_410_Qwen-Go-temp-0p9

3B • Updated Apr 6, 2025

SWY666/SimPO_adjusted_Best3_4096_Qwen-Go-temp-1

3B • Updated Apr 5, 2025

SWY666/SimPO_adjusted_Nemotron_205_Qwen-Go

3B • Updated Apr 5, 2025 • 1

SWY666/SimPO_adjusted_Nemotron_820_Qwen-Go

3B • Updated Apr 4, 2025 • 1

SWY666/SimPO_adjusted_Nemotron_8192_Qwen-Go-origin

3B • Updated Apr 2, 2025

SWY666/SimPO_adjusted_Nemotron_8192_Qwen-Go

3B • Updated Apr 2, 2025

SWY666/SimPO_adjusted_Best1_819_Qwen-Go

3B • Updated Mar 25, 2025 • 1

SWY666/SimPO_adjusted_Best1_204_Qwen-Go

3B • Updated Mar 23, 2025 • 1

SWY666/SimPO_adjusted_Best3_51_Qwen-Go

3B • Updated Mar 23, 2025 • 1

SWY666/SimPO_adjusted_Best1_8192_Qwen-Go

3B • Updated Mar 22, 2025 • 1

SWY666/SimPO_adjusted_Best3_200_Qwen-Go

3B • Updated Mar 22, 2025 • 1

SWY666/SimPO_adjusted_Best13_Qwen-Go-2

3B • Updated Mar 5, 2025 • 1

SWY666/SimPO_adjusted_Best13_Qwen-Go

3B • Updated Feb 25, 2025 • 1

SWY666/SimPO_adjusted_Best3_Qwen-Go

3B • Updated Feb 24, 2025 • 1

SWY666/SimPO_adjusted_Best3_Qwen-bd1

3B • Updated Feb 22, 2025

SWY666/SimPO_adjusted_Best3_Qwen-debug-2

3B • Updated Feb 22, 2025 • 1

SWY666/SimPO_adjusted_Best3_Qwen-debug

3B • Updated Feb 22, 2025 • 1