Add return_dict option to be compatible to llama

DRSY / EMO

[ICLR 2024]EMO: Earth Mover Distance Optimization for Auto-Regressive Language Modeling(https://arxiv.org/abs/2310.04691)

114 stars 14 forks source link

Closed xufangzhi closed 1 year ago

xufangzhi commented 1 year ago

Compatible to the output format of the forward function in modeling_llama (when return_dict is True)