Can we use
ElectraForMaskedLM for causal language modeling?
BertForMaskedLM was split into and
BertForMaskedLM, one model for causal LM, one for masked LM.
Is ELECTRA’s Masked LM class can be applied for causal LM?
Or is there a separate class?
Or is it not possible to use ELECTRA as Causal LM in the first place?
Thank you in advance.