AlbertForMaskedLM,4
AlbertForQuestionAnswering,4
AllenaiLongformerBase,4
BartForCausalLM,4
BartForConditionalGeneration,2
BertForMaskedLM,16
BertForQuestionAnswering,16
BigBird,32
BlenderbotForCausalLM,32
BlenderbotSmallForCausalLM,64
BlenderbotSmallForConditionalGeneration,64
CamemBert,16
DebertaForMaskedLM,32
DebertaForQuestionAnswering,8
DebertaV2ForMaskedLM,16
DebertaV2ForQuestionAnswering,2
DistilBertForMaskedLM,128
DistilBertForQuestionAnswering,256
DistillGPT2,16
ElectraForCausalLM,8
ElectraForQuestionAnswering,8
GoogleFnet,16
GPT2ForSequenceClassification,4
LayoutLMForMaskedLM,16
LayoutLMForSequenceClassification,16
M2M100ForConditionalGeneration,16
MBartForCausalLM,4
MBartForConditionalGeneration,2
MegatronBertForCausalLM,4
MegatronBertForQuestionAnswering,8
MobileBertForMaskedLM,64
MobileBertForQuestionAnswering,64
MT5ForConditionalGeneration,16
OPTForCausalLM,2
PegasusForCausalLM,32
PegasusForConditionalGeneration,32
PLBartForCausalLM,8
PLBartForConditionalGeneration,4
RobertaForCausalLM,16
RobertaForQuestionAnswering,16
Speech2Text2ForCausalLM,32
T5ForConditionalGeneration,4
T5Small,1
TrOCRForCausalLM,32
XGLMForCausalLM,8
XLNetLMHeadModel,8
YituTechConvBert,16