[<class 'transformers.modeling_transfo_xl.AdaptiveEmbedding'>, <class 'transformers.modeling_albert.AlbertForMaskedLM'>, <class 'transformers.modeling_albert.AlbertForMultipleChoice'>, <class 'transformers.modeling_albert.AlbertForPreTraining'>, <class 'transformers.modeling_albert.AlbertForQuestionAnswering'>, <class 'transformers.modeling_albert.AlbertForSequenceClassification'>, <class 'transformers.modeling_albert.AlbertForTokenClassification'>, <class 'transformers.modeling_albert.AlbertModel'>, <class 'transformers.modeling_albert.AlbertPreTrainedModel'>, <class 'transformers.modeling_auto.AutoModel'>, <class 'transformers.modeling_auto.AutoModelForCausalLM'>, <class 'transformers.modeling_auto.AutoModelForMaskedLM'>, <class 'transformers.modeling_auto.AutoModelForMultipleChoice'>, <class 'transformers.modeling_auto.AutoModelForPreTraining'>, <class 'transformers.modeling_auto.AutoModelForQuestionAnswering'>, <class 'transformers.modeling_auto.AutoModelForSeq2SeqLM'>, <class 'transformers.modeling_auto.AutoModelForSequenceClassification'>, <class 'transformers.modeling_auto.AutoModelForTokenClassification'>, <class 'transformers.modeling_auto.AutoModelWithLMHead'>, <class 'transformers.modeling_bart.BartForConditionalGeneration'>, <class 'transformers.modeling_bart.BartForQuestionAnswering'>, <class 'transformers.modeling_bart.BartForSequenceClassification'>, <class 'transformers.modeling_bart.BartModel'>, <class 'transformers.modeling_bert.BertForMaskedLM'>, <class 'transformers.modeling_bert.BertForMultipleChoice'>, <class 'transformers.modeling_bert.BertForNextSentencePrediction'>, <class 'transformers.modeling_bert.BertForPreTraining'>, <class 'transformers.modeling_bert.BertForQuestionAnswering'>, <class 'transformers.modeling_bert.BertForSequenceClassification'>, <class 'transformers.modeling_bert.BertForTokenClassification'>, <class 'transformers.modeling_bert_generation.BertGenerationDecoder'>, <class 'transformers.modeling_bert_generation.BertGenerationEncoder'>, <class 'transformers.modeling_bert.BertLMHeadModel'>, <class 'transformers.modeling_bert.BertLayer'>, <class 'transformers.modeling_bert.BertModel'>, <class 'transformers.modeling_bert.BertPreTrainedModel'>, <class 'transformers.modeling_blenderbot.BlenderbotForConditionalGeneration'>, <class 'transformers.modeling_ctrl.CTRLLMHeadModel'>, <class 'transformers.modeling_ctrl.CTRLModel'>, <class 'transformers.modeling_ctrl.CTRLPreTrainedModel'>, <class 'transformers.modeling_camembert.CamembertForCausalLM'>, <class 'transformers.modeling_camembert.CamembertForMaskedLM'>, <class 'transformers.modeling_camembert.CamembertForMultipleChoice'>, <class 'transformers.modeling_camembert.CamembertForQuestionAnswering'>, <class 'transformers.modeling_camembert.CamembertForSequenceClassification'>, <class 'transformers.modeling_camembert.CamembertForTokenClassification'>, <class 'transformers.modeling_camembert.CamembertModel'>, <class 'transformers.modeling_utils.Conv1D'>, <class 'transformers.modeling_dpr.DPRContextEncoder'>, <class 'transformers.modeling_dpr.DPRPretrainedContextEncoder'>, <class 'transformers.modeling_dpr.DPRPretrainedQuestionEncoder'>, <class 'transformers.modeling_dpr.DPRPretrainedReader'>, <class 'transformers.modeling_dpr.DPRQuestionEncoder'>, <class 'transformers.modeling_dpr.DPRReader'>, <class 'transformers.modeling_deberta.DebertaForSequenceClassification'>, <class 'transformers.modeling_deberta.DebertaModel'>, <class 'transformers.modeling_deberta.DebertaPreTrainedModel'>, <class 'transformers.modeling_distilbert.DistilBertForMaskedLM'>, <class 'transformers.modeling_distilbert.DistilBertForMultipleChoice'>, <class 'transformers.modeling_distilbert.DistilBertForQuestionAnswering'>, <class 'transformers.modeling_distilbert.DistilBertForSequenceClassification'>, <class 'transformers.modeling_distilbert.DistilBertForTokenClassification'>, <class 'transformers.modeling_distilbert.DistilBertModel'>, <class 'transformers.modeling_distilbert.DistilBertPreTrainedModel'>, <class 'transformers.modeling_electra.ElectraForMaskedLM'>, <class 'transformers.modeling_electra.ElectraForMultipleChoice'>, <class 'transformers.modeling_electra.ElectraForPreTraining'>, <class 'transformers.modeling_electra.ElectraForQuestionAnswering'>, <class 'transformers.modeling_electra.ElectraForSequenceClassification'>, <class 'transformers.modeling_electra.ElectraForTokenClassification'>, <class 'transformers.modeling_electra.ElectraModel'>, <class 'transformers.modeling_electra.ElectraPreTrainedModel'>, <class 'transformers.modeling_encoder_decoder.EncoderDecoderModel'>, <class 'transformers.modeling_fsmt.FSMTForConditionalGeneration'>, <class 'transformers.modeling_fsmt.FSMTModel'>, <class 'transformers.modeling_flaubert.FlaubertForMultipleChoice'>, <class 'transformers.modeling_flaubert.FlaubertForQuestionAnswering'>, <class 'transformers.modeling_flaubert.FlaubertForQuestionAnsweringSimple'>, <class 'transformers.modeling_flaubert.FlaubertForSequenceClassification'>, <class 'transformers.modeling_flaubert.FlaubertForTokenClassification'>, <class 'transformers.modeling_flaubert.FlaubertModel'>, <class 'transformers.modeling_flaubert.FlaubertWithLMHeadModel'>, <class 'transformers.modeling_funnel.FunnelBaseModel'>, <class 'transformers.modeling_funnel.FunnelForMaskedLM'>, <class 'transformers.modeling_funnel.FunnelForMultipleChoice'>, <class 'transformers.modeling_funnel.FunnelForPreTraining'>, <class 'transformers.modeling_funnel.FunnelForQuestionAnswering'>, <class 'transformers.modeling_funnel.FunnelForSequenceClassification'>, <class 'transformers.modeling_funnel.FunnelForTokenClassification'>, <class 'transformers.modeling_funnel.FunnelModel'>, <class 'transformers.modeling_gpt2.GPT2DoubleHeadsModel'>, <class 'transformers.modeling_gpt2.GPT2ForSequenceClassification'>, <class 'transformers.modeling_gpt2.GPT2LMHeadModel'>, <class 'transformers.modeling_gpt2.GPT2Model'>, <class 'transformers.modeling_gpt2.GPT2PreTrainedModel'>, <class 'transformers.modeling_layoutlm.LayoutLMForMaskedLM'>, <class 'transformers.modeling_layoutlm.LayoutLMForTokenClassification'>, <class 'transformers.modeling_layoutlm.LayoutLMModel'>, <class 'transformers.modeling_longformer.LongformerForMaskedLM'>, <class 'transformers.modeling_longformer.LongformerForMultipleChoice'>, <class 'transformers.modeling_longformer.LongformerForQuestionAnswering'>, <class 'transformers.modeling_longformer.LongformerForSequenceClassification'>, <class 'transformers.modeling_longformer.LongformerForTokenClassification'>, <class 'transformers.modeling_longformer.LongformerModel'>, <class 'transformers.modeling_longformer.LongformerSelfAttention'>, <class 'transformers.modeling_lxmert.LxmertEncoder'>, <class 'transformers.modeling_lxmert.LxmertForPreTraining'>, <class 'transformers.modeling_lxmert.LxmertForQuestionAnswering'>, <class 'transformers.modeling_lxmert.LxmertModel'>, <class 'transformers.modeling_lxmert.LxmertPreTrainedModel'>, <class 'transformers.modeling_lxmert.LxmertVisualFeatureEncoder'>, <class 'transformers.modeling_lxmert.LxmertXLayer'>, <class 'transformers.modeling_mbart.MBartForConditionalGeneration'>, <class 'transformers.modeling_mmbt.MMBTForClassification'>, <class 'transformers.modeling_mmbt.MMBTModel'>, <class 'transformers.modeling_marian.MarianMTModel'>, <class 'transformers.modeling_mobilebert.MobileBertForMaskedLM'>, <class 'transformers.modeling_mobilebert.MobileBertForMultipleChoice'>, <class 'transformers.modeling_mobilebert.MobileBertForNextSentencePrediction'>, <class 'transformers.modeling_mobilebert.MobileBertForPreTraining'>, <class 'transformers.modeling_mobilebert.MobileBertForQuestionAnswering'>, <class 'transformers.modeling_mobilebert.MobileBertForSequenceClassification'>, <class 'transformers.modeling_mobilebert.MobileBertForTokenClassification'>, <class 'transformers.modeling_mobilebert.MobileBertLayer'>, <class 'transformers.modeling_mobilebert.MobileBertModel'>, <class 'transformers.modeling_mobilebert.MobileBertPreTrainedModel'>, <class 'transformers.modeling_mmbt.ModalEmbeddings'>, <class 'transformers.modeling_openai.OpenAIGPTDoubleHeadsModel'>, <class 'transformers.modeling_openai.OpenAIGPTForSequenceClassification'>, <class 'transformers.modeling_openai.OpenAIGPTLMHeadModel'>, <class 'transformers.modeling_openai.OpenAIGPTModel'>, <class 'transformers.modeling_openai.OpenAIGPTPreTrainedModel'>, <class 'transformers.modeling_pegasus.PegasusForConditionalGeneration'>, <class 'transformers.modeling_utils.PreTrainedModel'>, <class 'transformers.modeling_bart.PretrainedBartModel'>, <class 'transformers.modeling_fsmt.PretrainedFSMTModel'>, <class 'transformers.modeling_prophetnet.ProphetNetDecoder'>, <class 'transformers.modeling_prophetnet.ProphetNetEncoder'>, <class 'transformers.modeling_prophetnet.ProphetNetForCausalLM'>, <class 'transformers.modeling_prophetnet.ProphetNetForConditionalGeneration'>, <class 'transformers.modeling_prophetnet.ProphetNetModel'>, <class 'transformers.modeling_prophetnet.ProphetNetPreTrainedModel'>, <class 'transformers.modeling_rag.RagModel'>, <class 'transformers.modeling_rag.RagSequenceForGeneration'>, <class 'transformers.modeling_rag.RagTokenForGeneration'>, <class 'transformers.modeling_reformer.ReformerAttention'>, <class 'transformers.modeling_reformer.ReformerForMaskedLM'>, <class 'transformers.modeling_reformer.ReformerForQuestionAnswering'>, <class 'transformers.modeling_reformer.ReformerForSequenceClassification'>, <class 'transformers.modeling_reformer.ReformerLayer'>, <class 'transformers.modeling_reformer.ReformerModel'>, <class 'transformers.modeling_reformer.ReformerModelWithLMHead'>, <class 'transformers.modeling_retribert.RetriBertModel'>, <class 'transformers.modeling_retribert.RetriBertPreTrainedModel'>, <class 'transformers.modeling_roberta.RobertaForCausalLM'>, <class 'transformers.modeling_roberta.RobertaForMaskedLM'>, <class 'transformers.modeling_roberta.RobertaForMultipleChoice'>, <class 'transformers.modeling_roberta.RobertaForQuestionAnswering'>, <class 'transformers.modeling_roberta.RobertaForSequenceClassification'>, <class 'transformers.modeling_roberta.RobertaForTokenClassification'>, <class 'transformers.modeling_roberta.RobertaModel'>, <class 'transformers.modeling_squeezebert.SqueezeBertForMaskedLM'>, <class 'transformers.modeling_squeezebert.SqueezeBertForMultipleChoice'>, <class 'transformers.modeling_squeezebert.SqueezeBertForQuestionAnswering'>, <class 'transformers.modeling_squeezebert.SqueezeBertForSequenceClassification'>, <class 'transformers.modeling_squeezebert.SqueezeBertForTokenClassification'>, <class 'transformers.modeling_squeezebert.SqueezeBertModel'>, <class 'transformers.modeling_squeezebert.SqueezeBertModule'>, <class 'transformers.modeling_squeezebert.SqueezeBertPreTrainedModel'>, <class 'transformers.modeling_t5.T5ForConditionalGeneration'>, <class 'transformers.modeling_t5.T5Model'>, <class 'transformers.modeling_t5.T5PreTrainedModel'>, <class 'transformers.modeling_transfo_xl.TransfoXLLMHeadModel'>, <class 'transformers.modeling_transfo_xl.TransfoXLModel'>, <class 'transformers.modeling_transfo_xl.TransfoXLPreTrainedModel'>, <class 'transformers.modeling_xlm.XLMForMultipleChoice'>, <class 'transformers.modeling_xlm.XLMForQuestionAnswering'>, <class 'transformers.modeling_xlm.XLMForQuestionAnsweringSimple'>, <class 'transformers.modeling_xlm.XLMForSequenceClassification'>, <class 'transformers.modeling_xlm.XLMForTokenClassification'>, <class 'transformers.modeling_xlm.XLMModel'>, <class 'transformers.modeling_xlm.XLMPreTrainedModel'>, <class 'transformers.modeling_xlm_prophetnet.XLMProphetNetDecoder'>, <class 'transformers.modeling_xlm_prophetnet.XLMProphetNetEncoder'>, <class 'transformers.modeling_xlm_prophetnet.XLMProphetNetForCausalLM'>, <class 'transformers.modeling_xlm_prophetnet.XLMProphetNetForConditionalGeneration'>, <class 'transformers.modeling_xlm_prophetnet.XLMProphetNetModel'>, <class 'transformers.modeling_xlm_roberta.XLMRobertaForCausalLM'>, <class 'transformers.modeling_xlm_roberta.XLMRobertaForMaskedLM'>, <class 'transformers.modeling_xlm_roberta.XLMRobertaForMultipleChoice'>, <class 'transformers.modeling_xlm_roberta.XLMRobertaForQuestionAnswering'>, <class 'transformers.modeling_xlm_roberta.XLMRobertaForSequenceClassification'>, <class 'transformers.modeling_xlm_roberta.XLMRobertaForTokenClassification'>, <class 'transformers.modeling_xlm_roberta.XLMRobertaModel'>, <class 'transformers.modeling_xlm.XLMWithLMHeadModel'>, <class 'transformers.modeling_xlnet.XLNetForMultipleChoice'>, <class 'transformers.modeling_xlnet.XLNetForQuestionAnswering'>, <class 'transformers.modeling_xlnet.XLNetForQuestionAnsweringSimple'>, <class 'transformers.modeling_xlnet.XLNetForSequenceClassification'>, <class 'transformers.modeling_xlnet.XLNetForTokenClassification'>, <class 'transformers.modeling_xlnet.XLNetLMHeadModel'>, <class 'transformers.modeling_xlnet.XLNetModel'>, <class 'transformers.modeling_xlnet.XLNetPreTrainedModel'>]