AlbertForMaskedLM,8
AlbertForQuestionAnswering,8
AllenaiLongformerBase,8
BartForCausalLM,8
BartForConditionalGeneration,4
BertForMaskedLM,32
BertForQuestionAnswering,32
BlenderbotForCausalLM,32
BlenderbotForConditionalGeneration,16
BlenderbotSmallForCausalLM,256
BlenderbotSmallForConditionalGeneration,128
CamemBert,32
DebertaForMaskedLM,32
DebertaForQuestionAnswering,32
DebertaV2ForMaskedLM,8
DebertaV2ForQuestionAnswering,8
DistilBertForMaskedLM,256
DistilBertForQuestionAnswering,512
DistillGPT2,32
ElectraForCausalLM,64
ElectraForQuestionAnswering,128
GPT2ForSequenceClassification,8
GPTJForCausalLM,1
GPTJForQuestionAnswering,1
GPTNeoForCausalLM,32
GPTNeoForSequenceClassification,32
GoogleFnet,32
LayoutLMForMaskedLM,32
LayoutLMForSequenceClassification,32
M2M100ForConditionalGeneration,64
MBartForCausalLM,8
MBartForConditionalGeneration,4
MT5ForConditionalGeneration,32
MegatronBertForCausalLM,16
MegatronBertForQuestionAnswering,16
MobileBertForMaskedLM,256
MobileBertForQuestionAnswering,256
OPTForCausalLM,4
PLBartForCausalLM,16
PLBartForConditionalGeneration,8
PegasusForCausalLM,128
PegasusForConditionalGeneration,64
RobertaForCausalLM,32
RobertaForQuestionAnswering,32
Speech2Text2ForCausalLM,1024
T5ForConditionalGeneration,8
T5Small,8
TrOCRForCausalLM,64
XGLMForCausalLM,32
XLNetLMHeadModel,16
YituTechConvBert,32