mismatch experiment on MoE models and corresponding configurations for tis/mis.
-
zhuohaoli/Qwen3-30B-A3B-Base-DRPO-tis-config3
Text Generation • 31B • Updated • 3 -
zhuohaoli/Qwen3-30B-A3B-Base-DRPO-tis-config1
Text Generation • 31B • Updated • 2 -
zhuohaoli/Qwen3-30B-A3B-Base-DRPO-tis-config2
Text Generation • 31B • Updated • 2 -
zhuohaoli/Qwen3-30B-A3B-Base-DRPO-tis-config4
Text Generation • 31B • Updated • 2