1AlbertForMaskedLM,8 2AlbertForQuestionAnswering,8 3AllenaiLongformerBase,8 4BartForCausalLM,8 5BartForConditionalGeneration,4 6BertForMaskedLM,32 7BertForQuestionAnswering,32 8BlenderbotForCausalLM,32 9BlenderbotForConditionalGeneration,16 10BlenderbotSmallForCausalLM,256 11BlenderbotSmallForConditionalGeneration,128 12CamemBert,32 13DebertaForMaskedLM,32 14DebertaForQuestionAnswering,32 15DebertaV2ForMaskedLM,8 16DebertaV2ForQuestionAnswering,8 17DistilBertForMaskedLM,256 18DistilBertForQuestionAnswering,512 19DistillGPT2,32 20ElectraForCausalLM,64 21ElectraForQuestionAnswering,128 22GPT2ForSequenceClassification,8 23GPTJForCausalLM,1 24GPTJForQuestionAnswering,1 25GPTNeoForCausalLM,32 26GPTNeoForSequenceClassification,32 27GoogleFnet,32 28LayoutLMForMaskedLM,32 29LayoutLMForSequenceClassification,32 30M2M100ForConditionalGeneration,64 31MBartForCausalLM,8 32MBartForConditionalGeneration,4 33MT5ForConditionalGeneration,32 34MegatronBertForCausalLM,16 35MegatronBertForQuestionAnswering,16 36MobileBertForMaskedLM,256 37MobileBertForQuestionAnswering,256 38OPTForCausalLM,4 39PLBartForCausalLM,16 40PLBartForConditionalGeneration,8 41PegasusForCausalLM,128 42PegasusForConditionalGeneration,64 43RobertaForCausalLM,32 44RobertaForQuestionAnswering,32 45Speech2Text2ForCausalLM,1024 46T5ForConditionalGeneration,8 47T5Small,8 48TrOCRForCausalLM,64 49XGLMForCausalLM,32 50XLNetLMHeadModel,16 51YituTechConvBert,32 52