Reorganize repo (#8580)

* Put models in subfolders

* Styling

* Fix imports in tests

* More fixes in test imports

* Sneaky hidden imports

* Fix imports in doc files

* More sneaky imports

* Finish fixing tests

* Fix examples

* Fix path for copies

* More fixes for examples

* Fix dummy files

* More fixes for example

* More model import fixes

* Is this why you're unhappy GitHub?

* Fix imports in conver command

src/transformers/data/processors/squad.py

@@ -7,7 +7,7 @@ import numpy as np
 from tqdm import tqdm
 
 from ...file_utils import is_tf_available, is_torch_available
-from ...tokenization_bert import whitespace_tokenize
+from ...models.bert.tokenization_bert import whitespace_tokenize
 from ...tokenization_utils_base import BatchEncoding, PreTrainedTokenizerBase, TruncationStrategy
 from ...utils import logging
 from .utils import DataProcessor

src/transformers/modelcard.py

@@ -19,7 +19,6 @@ import copy
 import json
 import os
 
-from .configuration_auto import ALL_PRETRAINED_CONFIG_ARCHIVE_MAP
 from .file_utils import (
     CONFIG_NAME,
     MODEL_CARD_NAME,
@@ -29,6 +28,7 @@ from .file_utils import (
     hf_bucket_url,
     is_remote_url,
 )
+from .models.auto.configuration_auto import ALL_PRETRAINED_CONFIG_ARCHIVE_MAP
 from .utils import logging
 
 

src/transformers/models/albert/__init__.py

+# flake8: noqa
+# There's no way to ignore "F401 '...' imported but unused" warnings in this
+# module, but to preserve other warnings. So, don't check this module at all.
+
+from ...file_utils import is_sentencepiece_available, is_tf_available, is_tokenizers_available, is_torch_available
+from .configuration_albert import ALBERT_PRETRAINED_CONFIG_ARCHIVE_MAP, AlbertConfig
+
+
+if is_sentencepiece_available():
+    from .tokenization_albert import AlbertTokenizer
+
+if is_tokenizers_available():
+    from .tokenization_albert_fast import AlbertTokenizerFast
+
+if is_torch_available():
+    from .modeling_albert import (
+        ALBERT_PRETRAINED_MODEL_ARCHIVE_LIST,
+        AlbertForMaskedLM,
+        AlbertForMultipleChoice,
+        AlbertForPreTraining,
+        AlbertForQuestionAnswering,
+        AlbertForSequenceClassification,
+        AlbertForTokenClassification,
+        AlbertModel,
+        AlbertPreTrainedModel,
+        load_tf_weights_in_albert,
+    )
+
+if is_tf_available():
+    from .modeling_tf_albert import (
+        TF_ALBERT_PRETRAINED_MODEL_ARCHIVE_LIST,
+        TFAlbertForMaskedLM,
+        TFAlbertForMultipleChoice,
+        TFAlbertForPreTraining,
+        TFAlbertForQuestionAnswering,
+        TFAlbertForSequenceClassification,
+        TFAlbertForTokenClassification,
+        TFAlbertMainLayer,
+        TFAlbertModel,
+        TFAlbertPreTrainedModel,
+    )

src/transformers/configuration_albert.py → src/transformers/models/albert/configuration_albert.py

@@ -15,7 +15,7 @@
 # limitations under the License.
 """ ALBERT model configuration """
 
-from .configuration_utils import PretrainedConfig
+from ...configuration_utils import PretrainedConfig
 
 
 ALBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = {

src/transformers/modeling_albert.py → src/transformers/models/albert/modeling_albert.py

@@ -24,16 +24,15 @@ import torch
 import torch.nn as nn
 from torch.nn import CrossEntropyLoss, MSELoss
 
-from .activations import ACT2FN
-from .configuration_albert import AlbertConfig
-from .file_utils import (
+from ...activations import ACT2FN
+from ...file_utils import (
     ModelOutput,
     add_code_sample_docstrings,
     add_start_docstrings,
     add_start_docstrings_to_model_forward,
     replace_return_docstrings,
 )
-from .modeling_outputs import (
+from ...modeling_outputs import (
     BaseModelOutput,
     BaseModelOutputWithPooling,
     MaskedLMOutput,
@@ -42,13 +41,14 @@ from .modeling_outputs import (
     SequenceClassifierOutput,
     TokenClassifierOutput,
 )
-from .modeling_utils import (
+from ...modeling_utils import (
     PreTrainedModel,
     apply_chunking_to_forward,
     find_pruneable_heads_and_indices,
     prune_linear_layer,
 )
-from .utils import logging
+from ...utils import logging
+from .configuration_albert import AlbertConfig
 
 
 logger = logging.get_logger(__name__)
@@ -216,7 +216,7 @@ class AlbertEmbeddings(nn.Module):
         # position_ids (1, len position emb) is contiguous in memory and exported when serialized
         self.register_buffer("position_ids", torch.arange(config.max_position_embeddings).expand((1, -1)))
 
-    # Copied from transformers.modeling_bert.BertEmbeddings.forward
+    # Copied from transformers.models.bert.modeling_bert.BertEmbeddings.forward
     def forward(self, input_ids=None, token_type_ids=None, position_ids=None, inputs_embeds=None):
         if input_ids is not None:
             input_shape = input_ids.size()
@@ -266,7 +266,7 @@ class AlbertAttention(nn.Module):
         self.LayerNorm = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps)
         self.pruned_heads = set()
 
-    # Copied from transformers.modeling_bert.BertSelfAttention.transpose_for_scores
+    # Copied from transformers.models.bert.modeling_bert.BertSelfAttention.transpose_for_scores
     def transpose_for_scores(self, x):
         new_x_shape = x.size()[:-1] + (self.num_attention_heads, self.attention_head_size)
         x = x.view(*new_x_shape)

src/transformers/modeling_tf_albert.py → src/transformers/models/albert/modeling_tf_albert.py

@@ -21,9 +21,8 @@ from typing import Optional, Tuple
 
 import tensorflow as tf
 
-from .activations_tf import get_tf_activation
-from .configuration_albert import AlbertConfig
-from .file_utils import (
+from ...activations_tf import get_tf_activation
+from ...file_utils import (
     MULTIPLE_CHOICE_DUMMY_INPUTS,
     ModelOutput,
     add_code_sample_docstrings,
@@ -31,7 +30,7 @@ from .file_utils import (
     add_start_docstrings_to_model_forward,
     replace_return_docstrings,
 )
-from .modeling_tf_outputs import (
+from ...modeling_tf_outputs import (
     TFBaseModelOutput,
     TFBaseModelOutputWithPooling,
     TFMaskedLMOutput,
@@ -40,7 +39,7 @@ from .modeling_tf_outputs import (
     TFSequenceClassifierOutput,
     TFTokenClassifierOutput,
 )
-from .modeling_tf_utils import (
+from ...modeling_tf_utils import (
     TFMaskedLanguageModelingLoss,
     TFMultipleChoiceLoss,
     TFPreTrainedModel,
@@ -51,8 +50,9 @@ from .modeling_tf_utils import (
     keras_serializable,
     shape_list,
 )
-from .tokenization_utils import BatchEncoding
-from .utils import logging
+from ...tokenization_utils import BatchEncoding
+from ...utils import logging
+from .configuration_albert import AlbertConfig
 
 
 logger = logging.get_logger(__name__)

src/transformers/tokenization_albert.py → src/transformers/models/albert/tokenization_albert.py

@@ -22,8 +22,8 @@ from typing import List, Optional, Tuple
 
 import sentencepiece as spm
 
-from .tokenization_utils import PreTrainedTokenizer
-from .utils import logging
+from ...tokenization_utils import PreTrainedTokenizer
+from ...utils import logging
 
 
 logger = logging.get_logger(__name__)

src/transformers/tokenization_albert_fast.py → src/transformers/models/albert/tokenization_albert_fast.py

@@ -19,9 +19,9 @@ import os
 from shutil import copyfile
 from typing import List, Optional, Tuple
 
-from .file_utils import is_sentencepiece_available
-from .tokenization_utils_fast import PreTrainedTokenizerFast
-from .utils import logging
+from ...file_utils import is_sentencepiece_available
+from ...tokenization_utils_fast import PreTrainedTokenizerFast
+from ...utils import logging
 
 
 if is_sentencepiece_available():

src/transformers/models/auto/__init__.py

+# flake8: noqa
+# There's no way to ignore "F401 '...' imported but unused" warnings in this
+# module, but to preserve other warnings. So, don't check this module at all.
+
+from ...file_utils import is_tf_available, is_torch_available
+from .configuration_auto import ALL_PRETRAINED_CONFIG_ARCHIVE_MAP, CONFIG_MAPPING, AutoConfig
+from .tokenization_auto import TOKENIZER_MAPPING, AutoTokenizer
+
+
+if is_torch_available():
+    from .modeling_auto import (
+        MODEL_FOR_CAUSAL_LM_MAPPING,
+        MODEL_FOR_MASKED_LM_MAPPING,
+        MODEL_FOR_MULTIPLE_CHOICE_MAPPING,
+        MODEL_FOR_NEXT_SENTENCE_PREDICTION_MAPPING,
+        MODEL_FOR_PRETRAINING_MAPPING,
+        MODEL_FOR_QUESTION_ANSWERING_MAPPING,
+        MODEL_FOR_SEQ_TO_SEQ_CAUSAL_LM_MAPPING,
+        MODEL_FOR_SEQUENCE_CLASSIFICATION_MAPPING,
+        MODEL_FOR_TOKEN_CLASSIFICATION_MAPPING,
+        MODEL_MAPPING,
+        MODEL_WITH_LM_HEAD_MAPPING,
+        AutoModel,
+        AutoModelForCausalLM,
+        AutoModelForMaskedLM,
+        AutoModelForMultipleChoice,
+        AutoModelForNextSentencePrediction,
+        AutoModelForPreTraining,
+        AutoModelForQuestionAnswering,
+        AutoModelForSeq2SeqLM,
+        AutoModelForSequenceClassification,
+        AutoModelForTokenClassification,
+        AutoModelWithLMHead,
+    )
+
+if is_tf_available():
+    from .modeling_tf_auto import (
+        TF_MODEL_FOR_CAUSAL_LM_MAPPING,
+        TF_MODEL_FOR_MASKED_LM_MAPPING,
+        TF_MODEL_FOR_MULTIPLE_CHOICE_MAPPING,
+        TF_MODEL_FOR_NEXT_SENTENCE_PREDICTION_MAPPING,
+        TF_MODEL_FOR_PRETRAINING_MAPPING,
+        TF_MODEL_FOR_QUESTION_ANSWERING_MAPPING,
+        TF_MODEL_FOR_SEQ_TO_SEQ_CAUSAL_LM_MAPPING,
+        TF_MODEL_FOR_SEQUENCE_CLASSIFICATION_MAPPING,
+        TF_MODEL_FOR_TOKEN_CLASSIFICATION_MAPPING,
+        TF_MODEL_MAPPING,
+        TF_MODEL_WITH_LM_HEAD_MAPPING,
+        TFAutoModel,
+        TFAutoModelForCausalLM,
+        TFAutoModelForMaskedLM,
+        TFAutoModelForMultipleChoice,
+        TFAutoModelForPreTraining,
+        TFAutoModelForQuestionAnswering,
+        TFAutoModelForSeq2SeqLM,
+        TFAutoModelForSequenceClassification,
+        TFAutoModelForTokenClassification,
+        TFAutoModelWithLMHead,
+    )

src/transformers/configuration_auto.py → src/transformers/models/auto/configuration_auto.py

@@ -17,43 +17,46 @@
 import re
 from collections import OrderedDict
 
-from .configuration_albert import ALBERT_PRETRAINED_CONFIG_ARCHIVE_MAP, AlbertConfig
-from .configuration_bart import BART_PRETRAINED_CONFIG_ARCHIVE_MAP, BartConfig
-from .configuration_bert import BERT_PRETRAINED_CONFIG_ARCHIVE_MAP, BertConfig
-from .configuration_bert_generation import BertGenerationConfig
-from .configuration_blenderbot import BLENDERBOT_PRETRAINED_CONFIG_ARCHIVE_MAP, BlenderbotConfig
-from .configuration_camembert import CAMEMBERT_PRETRAINED_CONFIG_ARCHIVE_MAP, CamembertConfig
-from .configuration_ctrl import CTRL_PRETRAINED_CONFIG_ARCHIVE_MAP, CTRLConfig
-from .configuration_deberta import DEBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP, DebertaConfig
-from .configuration_distilbert import DISTILBERT_PRETRAINED_CONFIG_ARCHIVE_MAP, DistilBertConfig
-from .configuration_dpr import DPR_PRETRAINED_CONFIG_ARCHIVE_MAP, DPRConfig
-from .configuration_electra import ELECTRA_PRETRAINED_CONFIG_ARCHIVE_MAP, ElectraConfig
-from .configuration_encoder_decoder import EncoderDecoderConfig
-from .configuration_flaubert import FLAUBERT_PRETRAINED_CONFIG_ARCHIVE_MAP, FlaubertConfig
-from .configuration_fsmt import FSMT_PRETRAINED_CONFIG_ARCHIVE_MAP, FSMTConfig
-from .configuration_funnel import FUNNEL_PRETRAINED_CONFIG_ARCHIVE_MAP, FunnelConfig
-from .configuration_gpt2 import GPT2_PRETRAINED_CONFIG_ARCHIVE_MAP, GPT2Config
-from .configuration_layoutlm import LAYOUTLM_PRETRAINED_CONFIG_ARCHIVE_MAP, LayoutLMConfig
-from .configuration_longformer import LONGFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP, LongformerConfig
-from .configuration_lxmert import LXMERT_PRETRAINED_CONFIG_ARCHIVE_MAP, LxmertConfig
-from .configuration_marian import MarianConfig
-from .configuration_mbart import MBART_PRETRAINED_CONFIG_ARCHIVE_MAP, MBartConfig
-from .configuration_mobilebert import MobileBertConfig
-from .configuration_openai import OPENAI_GPT_PRETRAINED_CONFIG_ARCHIVE_MAP, OpenAIGPTConfig
-from .configuration_pegasus import PegasusConfig
-from .configuration_prophetnet import PROPHETNET_PRETRAINED_CONFIG_ARCHIVE_MAP, ProphetNetConfig
-from .configuration_rag import RagConfig
-from .configuration_reformer import ReformerConfig
-from .configuration_retribert import RETRIBERT_PRETRAINED_CONFIG_ARCHIVE_MAP, RetriBertConfig
-from .configuration_roberta import ROBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP, RobertaConfig
-from .configuration_squeezebert import SQUEEZEBERT_PRETRAINED_CONFIG_ARCHIVE_MAP, SqueezeBertConfig
-from .configuration_t5 import T5_PRETRAINED_CONFIG_ARCHIVE_MAP, T5Config
-from .configuration_transfo_xl import TRANSFO_XL_PRETRAINED_CONFIG_ARCHIVE_MAP, TransfoXLConfig
-from .configuration_utils import PretrainedConfig
-from .configuration_xlm import XLM_PRETRAINED_CONFIG_ARCHIVE_MAP, XLMConfig
-from .configuration_xlm_prophetnet import XLM_PROPHETNET_PRETRAINED_CONFIG_ARCHIVE_MAP, XLMProphetNetConfig
-from .configuration_xlm_roberta import XLM_ROBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP, XLMRobertaConfig
-from .configuration_xlnet import XLNET_PRETRAINED_CONFIG_ARCHIVE_MAP, XLNetConfig
+from ...configuration_utils import PretrainedConfig
+from ..albert.configuration_albert import ALBERT_PRETRAINED_CONFIG_ARCHIVE_MAP, AlbertConfig
+from ..bart.configuration_bart import BART_PRETRAINED_CONFIG_ARCHIVE_MAP, BartConfig
+from ..bert.configuration_bert import BERT_PRETRAINED_CONFIG_ARCHIVE_MAP, BertConfig
+from ..bert_generation.configuration_bert_generation import BertGenerationConfig
+from ..blenderbot.configuration_blenderbot import BLENDERBOT_PRETRAINED_CONFIG_ARCHIVE_MAP, BlenderbotConfig
+from ..camembert.configuration_camembert import CAMEMBERT_PRETRAINED_CONFIG_ARCHIVE_MAP, CamembertConfig
+from ..ctrl.configuration_ctrl import CTRL_PRETRAINED_CONFIG_ARCHIVE_MAP, CTRLConfig
+from ..deberta.configuration_deberta import DEBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP, DebertaConfig
+from ..distilbert.configuration_distilbert import DISTILBERT_PRETRAINED_CONFIG_ARCHIVE_MAP, DistilBertConfig
+from ..dpr.configuration_dpr import DPR_PRETRAINED_CONFIG_ARCHIVE_MAP, DPRConfig
+from ..electra.configuration_electra import ELECTRA_PRETRAINED_CONFIG_ARCHIVE_MAP, ElectraConfig
+from ..encoder_decoder.configuration_encoder_decoder import EncoderDecoderConfig
+from ..flaubert.configuration_flaubert import FLAUBERT_PRETRAINED_CONFIG_ARCHIVE_MAP, FlaubertConfig
+from ..fsmt.configuration_fsmt import FSMT_PRETRAINED_CONFIG_ARCHIVE_MAP, FSMTConfig
+from ..funnel.configuration_funnel import FUNNEL_PRETRAINED_CONFIG_ARCHIVE_MAP, FunnelConfig
+from ..gpt2.configuration_gpt2 import GPT2_PRETRAINED_CONFIG_ARCHIVE_MAP, GPT2Config
+from ..layoutlm.configuration_layoutlm import LAYOUTLM_PRETRAINED_CONFIG_ARCHIVE_MAP, LayoutLMConfig
+from ..longformer.configuration_longformer import LONGFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP, LongformerConfig
+from ..lxmert.configuration_lxmert import LXMERT_PRETRAINED_CONFIG_ARCHIVE_MAP, LxmertConfig
+from ..marian.configuration_marian import MarianConfig
+from ..mbart.configuration_mbart import MBART_PRETRAINED_CONFIG_ARCHIVE_MAP, MBartConfig
+from ..mobilebert.configuration_mobilebert import MobileBertConfig
+from ..openai.configuration_openai import OPENAI_GPT_PRETRAINED_CONFIG_ARCHIVE_MAP, OpenAIGPTConfig
+from ..pegasus.configuration_pegasus import PegasusConfig
+from ..prophetnet.configuration_prophetnet import PROPHETNET_PRETRAINED_CONFIG_ARCHIVE_MAP, ProphetNetConfig
+from ..rag.configuration_rag import RagConfig
+from ..reformer.configuration_reformer import ReformerConfig
+from ..retribert.configuration_retribert import RETRIBERT_PRETRAINED_CONFIG_ARCHIVE_MAP, RetriBertConfig
+from ..roberta.configuration_roberta import ROBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP, RobertaConfig
+from ..squeezebert.configuration_squeezebert import SQUEEZEBERT_PRETRAINED_CONFIG_ARCHIVE_MAP, SqueezeBertConfig
+from ..t5.configuration_t5 import T5_PRETRAINED_CONFIG_ARCHIVE_MAP, T5Config
+from ..transfo_xl.configuration_transfo_xl import TRANSFO_XL_PRETRAINED_CONFIG_ARCHIVE_MAP, TransfoXLConfig
+from ..xlm.configuration_xlm import XLM_PRETRAINED_CONFIG_ARCHIVE_MAP, XLMConfig
+from ..xlm_prophetnet.configuration_xlm_prophetnet import (
+    XLM_PROPHETNET_PRETRAINED_CONFIG_ARCHIVE_MAP,
+    XLMProphetNetConfig,
+)
+from ..xlm_roberta.configuration_xlm_roberta import XLM_ROBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP, XLMRobertaConfig
+from ..xlnet.configuration_xlnet import XLNET_PRETRAINED_CONFIG_ARCHIVE_MAP, XLNetConfig
 
 
 ALL_PRETRAINED_CONFIG_ARCHIVE_MAP = dict(

src/transformers/modeling_auto.py → src/transformers/models/auto/modeling_auto.py

@@ -18,48 +18,10 @@
 import warnings
 from collections import OrderedDict
 
-from .configuration_auto import (
-    AlbertConfig,
-    AutoConfig,
-    BartConfig,
-    BertConfig,
-    BertGenerationConfig,
-    BlenderbotConfig,
-    CamembertConfig,
-    CTRLConfig,
-    DebertaConfig,
-    DistilBertConfig,
-    DPRConfig,
-    ElectraConfig,
-    EncoderDecoderConfig,
-    FlaubertConfig,
-    FSMTConfig,
-    FunnelConfig,
-    GPT2Config,
-    LayoutLMConfig,
-    LongformerConfig,
-    LxmertConfig,
-    MBartConfig,
-    MobileBertConfig,
-    OpenAIGPTConfig,
-    PegasusConfig,
-    ProphetNetConfig,
-    ReformerConfig,
-    RetriBertConfig,
-    RobertaConfig,
-    SqueezeBertConfig,
-    T5Config,
-    TransfoXLConfig,
-    XLMConfig,
-    XLMProphetNetConfig,
-    XLMRobertaConfig,
-    XLNetConfig,
-    replace_list_option_in_docstrings,
-)
-from .configuration_marian import MarianConfig
-from .configuration_utils import PretrainedConfig
-from .file_utils import add_start_docstrings
-from .modeling_albert import (
+from ...configuration_utils import PretrainedConfig
+from ...file_utils import add_start_docstrings
+from ...utils import logging
+from ..albert.modeling_albert import (
     AlbertForMaskedLM,
     AlbertForMultipleChoice,
     AlbertForPreTraining,
@@ -68,13 +30,13 @@ from .modeling_albert import (
     AlbertForTokenClassification,
     AlbertModel,
 )
-from .modeling_bart import (
+from ..bart.modeling_bart import (
     BartForConditionalGeneration,
     BartForQuestionAnswering,
     BartForSequenceClassification,
     BartModel,
 )
-from .modeling_bert import (
+from ..bert.modeling_bert import (
     BertForMaskedLM,
     BertForMultipleChoice,
     BertForNextSentencePrediction,
@@ -85,9 +47,9 @@ from .modeling_bert import (
     BertLMHeadModel,
     BertModel,
 )
-from .modeling_bert_generation import BertGenerationDecoder, BertGenerationEncoder
-from .modeling_blenderbot import BlenderbotForConditionalGeneration
-from .modeling_camembert import (
+from ..bert_generation.modeling_bert_generation import BertGenerationDecoder, BertGenerationEncoder
+from ..blenderbot.modeling_blenderbot import BlenderbotForConditionalGeneration
+from ..camembert.modeling_camembert import (
     CamembertForCausalLM,
     CamembertForMaskedLM,
     CamembertForMultipleChoice,
@@ -96,9 +58,9 @@ from .modeling_camembert import (
     CamembertForTokenClassification,
     CamembertModel,
 )
-from .modeling_ctrl import CTRLLMHeadModel, CTRLModel
-from .modeling_deberta import DebertaForSequenceClassification, DebertaModel
-from .modeling_distilbert import (
+from ..ctrl.modeling_ctrl import CTRLLMHeadModel, CTRLModel
+from ..deberta.modeling_deberta import DebertaForSequenceClassification, DebertaModel
+from ..distilbert.modeling_distilbert import (
     DistilBertForMaskedLM,
     DistilBertForMultipleChoice,
     DistilBertForQuestionAnswering,
@@ -106,8 +68,8 @@ from .modeling_distilbert import (
     DistilBertForTokenClassification,
     DistilBertModel,
 )
-from .modeling_dpr import DPRQuestionEncoder
-from .modeling_electra import (
+from ..dpr.modeling_dpr import DPRQuestionEncoder
+from ..electra.modeling_electra import (
     ElectraForMaskedLM,
     ElectraForMultipleChoice,
     ElectraForPreTraining,
@@ -116,8 +78,8 @@ from .modeling_electra import (
     ElectraForTokenClassification,
     ElectraModel,
 )
-from .modeling_encoder_decoder import EncoderDecoderModel
-from .modeling_flaubert import (
+from ..encoder_decoder.modeling_encoder_decoder import EncoderDecoderModel
+from ..flaubert.modeling_flaubert import (
     FlaubertForMultipleChoice,
     FlaubertForQuestionAnsweringSimple,
     FlaubertForSequenceClassification,
@@ -125,8 +87,8 @@ from .modeling_flaubert import (
     FlaubertModel,
     FlaubertWithLMHeadModel,
 )
-from .modeling_fsmt import FSMTForConditionalGeneration, FSMTModel
-from .modeling_funnel import (
+from ..fsmt.modeling_fsmt import FSMTForConditionalGeneration, FSMTModel
+from ..funnel.modeling_funnel import (
     FunnelForMaskedLM,
     FunnelForMultipleChoice,
     FunnelForPreTraining,
@@ -135,9 +97,9 @@ from .modeling_funnel import (
     FunnelForTokenClassification,
     FunnelModel,
 )
-from .modeling_gpt2 import GPT2ForSequenceClassification, GPT2LMHeadModel, GPT2Model
-from .modeling_layoutlm import LayoutLMForMaskedLM, LayoutLMForTokenClassification, LayoutLMModel
-from .modeling_longformer import (
+from ..gpt2.modeling_gpt2 import GPT2ForSequenceClassification, GPT2LMHeadModel, GPT2Model
+from ..layoutlm.modeling_layoutlm import LayoutLMForMaskedLM, LayoutLMForTokenClassification, LayoutLMModel
+from ..longformer.modeling_longformer import (
     LongformerForMaskedLM,
     LongformerForMultipleChoice,
     LongformerForQuestionAnswering,
@@ -145,10 +107,10 @@ from .modeling_longformer import (
     LongformerForTokenClassification,
     LongformerModel,
 )
-from .modeling_lxmert import LxmertForPreTraining, LxmertForQuestionAnswering, LxmertModel
-from .modeling_marian import MarianMTModel
-from .modeling_mbart import MBartForConditionalGeneration
-from .modeling_mobilebert import (
+from ..lxmert.modeling_lxmert import LxmertForPreTraining, LxmertForQuestionAnswering, LxmertModel
+from ..marian.modeling_marian import MarianMTModel
+from ..mbart.modeling_mbart import MBartForConditionalGeneration
+from ..mobilebert.modeling_mobilebert import (
     MobileBertForMaskedLM,
     MobileBertForMultipleChoice,
     MobileBertForNextSentencePrediction,
@@ -158,23 +120,23 @@ from .modeling_mobilebert import (
     MobileBertForTokenClassification,
     MobileBertModel,
 )
-from .modeling_openai import OpenAIGPTForSequenceClassification, OpenAIGPTLMHeadModel, OpenAIGPTModel
-from .modeling_pegasus import PegasusForConditionalGeneration
-from .modeling_prophetnet import ProphetNetForCausalLM, ProphetNetForConditionalGeneration, ProphetNetModel
-from .modeling_rag import (  # noqa: F401 - need to import all RagModels to be in globals() function
+from ..openai.modeling_openai import OpenAIGPTForSequenceClassification, OpenAIGPTLMHeadModel, OpenAIGPTModel
+from ..pegasus.modeling_pegasus import PegasusForConditionalGeneration
+from ..prophetnet.modeling_prophetnet import ProphetNetForCausalLM, ProphetNetForConditionalGeneration, ProphetNetModel
+from ..rag.modeling_rag import (  # noqa: F401 - need to import all RagModels to be in globals() function
     RagModel,
     RagSequenceForGeneration,
     RagTokenForGeneration,
 )
-from .modeling_reformer import (
+from ..reformer.modeling_reformer import (
     ReformerForMaskedLM,
     ReformerForQuestionAnswering,
     ReformerForSequenceClassification,
     ReformerModel,
     ReformerModelWithLMHead,
 )
-from .modeling_retribert import RetriBertModel
-from .modeling_roberta import (
+from ..retribert.modeling_retribert import RetriBertModel
+from ..roberta.modeling_roberta import (
     RobertaForCausalLM,
     RobertaForMaskedLM,
     RobertaForMultipleChoice,
@@ -183,7 +145,7 @@ from .modeling_roberta import (
     RobertaForTokenClassification,
     RobertaModel,
 )
-from .modeling_squeezebert import (
+from ..squeezebert.modeling_squeezebert import (
     SqueezeBertForMaskedLM,
     SqueezeBertForMultipleChoice,
     SqueezeBertForQuestionAnswering,
@@ -191,9 +153,9 @@ from .modeling_squeezebert import (
     SqueezeBertForTokenClassification,
     SqueezeBertModel,
 )
-from .modeling_t5 import T5ForConditionalGeneration, T5Model
-from .modeling_transfo_xl import TransfoXLLMHeadModel, TransfoXLModel
-from .modeling_xlm import (
+from ..t5.modeling_t5 import T5ForConditionalGeneration, T5Model
+from ..transfo_xl.modeling_transfo_xl import TransfoXLLMHeadModel, TransfoXLModel
+from ..xlm.modeling_xlm import (
     XLMForMultipleChoice,
     XLMForQuestionAnsweringSimple,
     XLMForSequenceClassification,
@@ -201,12 +163,12 @@ from .modeling_xlm import (
     XLMModel,
     XLMWithLMHeadModel,
 )
-from .modeling_xlm_prophetnet import (
+from ..xlm_prophetnet.modeling_xlm_prophetnet import (
     XLMProphetNetForCausalLM,
     XLMProphetNetForConditionalGeneration,
     XLMProphetNetModel,
 )
-from .modeling_xlm_roberta import (
+from ..xlm_roberta.modeling_xlm_roberta import (
     XLMRobertaForCausalLM,
     XLMRobertaForMaskedLM,
     XLMRobertaForMultipleChoice,
@@ -215,7 +177,7 @@ from .modeling_xlm_roberta import (
     XLMRobertaForTokenClassification,
     XLMRobertaModel,
 )
-from .modeling_xlnet import (
+from ..xlnet.modeling_xlnet import (
     XLNetForMultipleChoice,
     XLNetForQuestionAnsweringSimple,
     XLNetForSequenceClassification,
@@ -223,7 +185,45 @@ from .modeling_xlnet import (
     XLNetLMHeadModel,
     XLNetModel,
 )
-from .utils import logging
+from .configuration_auto import (
+    AlbertConfig,
+    AutoConfig,
+    BartConfig,
+    BertConfig,
+    BertGenerationConfig,
+    BlenderbotConfig,
+    CamembertConfig,
+    CTRLConfig,
+    DebertaConfig,
+    DistilBertConfig,
+    DPRConfig,
+    ElectraConfig,
+    EncoderDecoderConfig,
+    FlaubertConfig,
+    FSMTConfig,
+    FunnelConfig,
+    GPT2Config,
+    LayoutLMConfig,
+    LongformerConfig,
+    LxmertConfig,
+    MarianConfig,
+    MBartConfig,
+    MobileBertConfig,
+    OpenAIGPTConfig,
+    PegasusConfig,
+    ProphetNetConfig,
+    ReformerConfig,
+    RetriBertConfig,
+    RobertaConfig,
+    SqueezeBertConfig,
+    T5Config,
+    TransfoXLConfig,
+    XLMConfig,
+    XLMProphetNetConfig,
+    XLMRobertaConfig,
+    XLNetConfig,
+    replace_list_option_in_docstrings,
+)
 
 
 # Add modeling imports here

src/transformers/modeling_flax_auto.py → src/transformers/models/auto/modeling_flax_auto.py

@@ -17,11 +17,11 @@
 
 from collections import OrderedDict
 
+from ...configuration_utils import PretrainedConfig
+from ...utils import logging
+from ..bert.modeling_flax_bert import FlaxBertModel
+from ..roberta.modeling_flax_roberta import FlaxRobertaModel
 from .configuration_auto import AutoConfig, BertConfig, RobertaConfig
-from .configuration_utils import PretrainedConfig
-from .modeling_flax_bert import FlaxBertModel
-from .modeling_flax_roberta import FlaxRobertaModel
-from .utils import logging
 
 
 logger = logging.get_logger(__name__)

src/transformers/modeling_tf_auto.py → src/transformers/models/auto/modeling_tf_auto.py

@@ -18,38 +18,10 @@
 import warnings
 from collections import OrderedDict
 
-from .configuration_auto import (
-    AlbertConfig,
-    AutoConfig,
-    BartConfig,
-    BertConfig,
-    CamembertConfig,
-    CTRLConfig,
-    DistilBertConfig,
-    ElectraConfig,
-    FlaubertConfig,
-    FunnelConfig,
-    GPT2Config,
-    LongformerConfig,
-    LxmertConfig,
-    MobileBertConfig,
-    OpenAIGPTConfig,
-    RobertaConfig,
-    T5Config,
-    TransfoXLConfig,
-    XLMConfig,
-    XLMRobertaConfig,
-    XLNetConfig,
-    replace_list_option_in_docstrings,
-)
-from .configuration_blenderbot import BlenderbotConfig
-from .configuration_dpr import DPRConfig
-from .configuration_marian import MarianConfig
-from .configuration_mbart import MBartConfig
-from .configuration_pegasus import PegasusConfig
-from .configuration_utils import PretrainedConfig
-from .file_utils import add_start_docstrings
-from .modeling_tf_albert import (
+from ...configuration_utils import PretrainedConfig
+from ...file_utils import add_start_docstrings
+from ...utils import logging
+from ..albert.modeling_tf_albert import (
     TFAlbertForMaskedLM,
     TFAlbertForMultipleChoice,
     TFAlbertForPreTraining,
@@ -58,8 +30,8 @@ from .modeling_tf_albert import (
     TFAlbertForTokenClassification,
     TFAlbertModel,
 )
-from .modeling_tf_bart import TFBartForConditionalGeneration, TFBartModel
-from .modeling_tf_bert import (
+from ..bart.modeling_tf_bart import TFBartForConditionalGeneration, TFBartModel
+from ..bert.modeling_tf_bert import (
     TFBertForMaskedLM,
     TFBertForMultipleChoice,
     TFBertForNextSentencePrediction,
@@ -70,8 +42,8 @@ from .modeling_tf_bert import (
     TFBertLMHeadModel,
     TFBertModel,
 )
-from .modeling_tf_blenderbot import TFBlenderbotForConditionalGeneration
-from .modeling_tf_camembert import (
+from ..blenderbot.modeling_tf_blenderbot import TFBlenderbotForConditionalGeneration
+from ..camembert.modeling_tf_camembert import (
     TFCamembertForMaskedLM,
     TFCamembertForMultipleChoice,
     TFCamembertForQuestionAnswering,
@@ -79,8 +51,8 @@ from .modeling_tf_camembert import (
     TFCamembertForTokenClassification,
     TFCamembertModel,
 )
-from .modeling_tf_ctrl import TFCTRLLMHeadModel, TFCTRLModel
-from .modeling_tf_distilbert import (
+from ..ctrl.modeling_tf_ctrl import TFCTRLLMHeadModel, TFCTRLModel
+from ..distilbert.modeling_tf_distilbert import (
     TFDistilBertForMaskedLM,
     TFDistilBertForMultipleChoice,
     TFDistilBertForQuestionAnswering,
@@ -88,8 +60,8 @@ from .modeling_tf_distilbert import (
     TFDistilBertForTokenClassification,
     TFDistilBertModel,
 )
-from .modeling_tf_dpr import TFDPRQuestionEncoder
-from .modeling_tf_electra import (
+from ..dpr.modeling_tf_dpr import TFDPRQuestionEncoder
+from ..electra.modeling_tf_electra import (
     TFElectraForMaskedLM,
     TFElectraForMultipleChoice,
     TFElectraForPreTraining,
@@ -98,7 +70,7 @@ from .modeling_tf_electra import (
     TFElectraForTokenClassification,
     TFElectraModel,
 )
-from .modeling_tf_flaubert import (
+from ..flaubert.modeling_tf_flaubert import (
     TFFlaubertForMultipleChoice,
     TFFlaubertForQuestionAnsweringSimple,
     TFFlaubertForSequenceClassification,
@@ -106,7 +78,7 @@ from .modeling_tf_flaubert import (
     TFFlaubertModel,
     TFFlaubertWithLMHeadModel,
 )
-from .modeling_tf_funnel import (
+from ..funnel.modeling_tf_funnel import (
     TFFunnelForMaskedLM,
     TFFunnelForMultipleChoice,
     TFFunnelForPreTraining,
@@ -115,12 +87,16 @@ from .modeling_tf_funnel import (
     TFFunnelForTokenClassification,
     TFFunnelModel,
 )
-from .modeling_tf_gpt2 import TFGPT2LMHeadModel, TFGPT2Model
-from .modeling_tf_longformer import TFLongformerForMaskedLM, TFLongformerForQuestionAnswering, TFLongformerModel
-from .modeling_tf_lxmert import TFLxmertForPreTraining, TFLxmertModel
-from .modeling_tf_marian import TFMarianMTModel
-from .modeling_tf_mbart import TFMBartForConditionalGeneration
-from .modeling_tf_mobilebert import (
+from ..gpt2.modeling_tf_gpt2 import TFGPT2LMHeadModel, TFGPT2Model
+from ..longformer.modeling_tf_longformer import (
+    TFLongformerForMaskedLM,
+    TFLongformerForQuestionAnswering,
+    TFLongformerModel,
+)
+from ..lxmert.modeling_tf_lxmert import TFLxmertForPreTraining, TFLxmertModel
+from ..marian.modeling_tf_marian import TFMarianMTModel
+from ..mbart.modeling_tf_mbart import TFMBartForConditionalGeneration
+from ..mobilebert.modeling_tf_mobilebert import (
     TFMobileBertForMaskedLM,
     TFMobileBertForMultipleChoice,
     TFMobileBertForNextSentencePrediction,
@@ -130,9 +106,9 @@ from .modeling_tf_mobilebert import (
     TFMobileBertForTokenClassification,
     TFMobileBertModel,
 )
-from .modeling_tf_openai import TFOpenAIGPTLMHeadModel, TFOpenAIGPTModel
-from .modeling_tf_pegasus import TFPegasusForConditionalGeneration
-from .modeling_tf_roberta import (
+from ..openai.modeling_tf_openai import TFOpenAIGPTLMHeadModel, TFOpenAIGPTModel
+from ..pegasus.modeling_tf_pegasus import TFPegasusForConditionalGeneration
+from ..roberta.modeling_tf_roberta import (
     TFRobertaForMaskedLM,
     TFRobertaForMultipleChoice,
     TFRobertaForQuestionAnswering,
@@ -140,9 +116,9 @@ from .modeling_tf_roberta import (
     TFRobertaForTokenClassification,
     TFRobertaModel,
 )
-from .modeling_tf_t5 import TFT5ForConditionalGeneration, TFT5Model
-from .modeling_tf_transfo_xl import TFTransfoXLLMHeadModel, TFTransfoXLModel
-from .modeling_tf_xlm import (
+from ..t5.modeling_tf_t5 import TFT5ForConditionalGeneration, TFT5Model
+from ..transfo_xl.modeling_tf_transfo_xl import TFTransfoXLLMHeadModel, TFTransfoXLModel
+from ..xlm.modeling_tf_xlm import (
     TFXLMForMultipleChoice,
     TFXLMForQuestionAnsweringSimple,
     TFXLMForSequenceClassification,
@@ -150,7 +126,7 @@ from .modeling_tf_xlm import (
     TFXLMModel,
     TFXLMWithLMHeadModel,
 )
-from .modeling_tf_xlm_roberta import (
+from ..xlm_roberta.modeling_tf_xlm_roberta import (
     TFXLMRobertaForMaskedLM,
     TFXLMRobertaForMultipleChoice,
     TFXLMRobertaForQuestionAnswering,
@@ -158,7 +134,7 @@ from .modeling_tf_xlm_roberta import (
     TFXLMRobertaForTokenClassification,
     TFXLMRobertaModel,
 )
-from .modeling_tf_xlnet import (
+from ..xlnet.modeling_tf_xlnet import (
     TFXLNetForMultipleChoice,
     TFXLNetForQuestionAnsweringSimple,
     TFXLNetForSequenceClassification,
@@ -166,7 +142,35 @@ from .modeling_tf_xlnet import (
     TFXLNetLMHeadModel,
     TFXLNetModel,
 )
-from .utils import logging
+from .configuration_auto import (
+    AlbertConfig,
+    AutoConfig,
+    BartConfig,
+    BertConfig,
+    BlenderbotConfig,
+    CamembertConfig,
+    CTRLConfig,
+    DistilBertConfig,
+    DPRConfig,
+    ElectraConfig,
+    FlaubertConfig,
+    FunnelConfig,
+    GPT2Config,
+    LongformerConfig,
+    LxmertConfig,
+    MarianConfig,
+    MBartConfig,
+    MobileBertConfig,
+    OpenAIGPTConfig,
+    PegasusConfig,
+    RobertaConfig,
+    T5Config,
+    TransfoXLConfig,
+    XLMConfig,
+    XLMRobertaConfig,
+    XLNetConfig,
+    replace_list_option_in_docstrings,
+)
 
 
 # Add modeling imports here

src/transformers/tokenization_auto.py → src/transformers/models/auto/tokenization_auto.py

@@ -17,6 +17,37 @@
 
 from collections import OrderedDict
 
+from ...configuration_utils import PretrainedConfig
+from ...file_utils import is_sentencepiece_available, is_tokenizers_available
+from ...utils import logging
+from ..bart.tokenization_bart import BartTokenizer
+from ..bert.tokenization_bert import BertTokenizer
+from ..bert_japanese.tokenization_bert_japanese import BertJapaneseTokenizer
+from ..bertweet.tokenization_bertweet import BertweetTokenizer
+from ..blenderbot.tokenization_blenderbot import BlenderbotSmallTokenizer
+from ..ctrl.tokenization_ctrl import CTRLTokenizer
+from ..deberta.tokenization_deberta import DebertaTokenizer
+from ..distilbert.tokenization_distilbert import DistilBertTokenizer
+from ..dpr.tokenization_dpr import DPRQuestionEncoderTokenizer
+from ..electra.tokenization_electra import ElectraTokenizer
+from ..flaubert.tokenization_flaubert import FlaubertTokenizer
+from ..fsmt.tokenization_fsmt import FSMTTokenizer
+from ..funnel.tokenization_funnel import FunnelTokenizer
+from ..gpt2.tokenization_gpt2 import GPT2Tokenizer
+from ..herbert.tokenization_herbert import HerbertTokenizer
+from ..layoutlm.tokenization_layoutlm import LayoutLMTokenizer
+from ..longformer.tokenization_longformer import LongformerTokenizer
+from ..lxmert.tokenization_lxmert import LxmertTokenizer
+from ..mobilebert.tokenization_mobilebert import MobileBertTokenizer
+from ..openai.tokenization_openai import OpenAIGPTTokenizer
+from ..phobert.tokenization_phobert import PhobertTokenizer
+from ..prophetnet.tokenization_prophetnet import ProphetNetTokenizer
+from ..rag.tokenization_rag import RagTokenizer
+from ..retribert.tokenization_retribert import RetriBertTokenizer
+from ..roberta.tokenization_roberta import RobertaTokenizer
+from ..squeezebert.tokenization_squeezebert import SqueezeBertTokenizer
+from ..transfo_xl.tokenization_transfo_xl import TransfoXLTokenizer
+from ..xlm.tokenization_xlm import XLMTokenizer
 from .configuration_auto import (
     AlbertConfig,
     AutoConfig,
@@ -57,51 +88,20 @@ from .configuration_auto import (
     XLNetConfig,
     replace_list_option_in_docstrings,
 )
-from .configuration_utils import PretrainedConfig
-from .file_utils import is_sentencepiece_available, is_tokenizers_available
-from .tokenization_bart import BartTokenizer
-from .tokenization_bert import BertTokenizer
-from .tokenization_bert_japanese import BertJapaneseTokenizer
-from .tokenization_bertweet import BertweetTokenizer
-from .tokenization_blenderbot import BlenderbotSmallTokenizer
-from .tokenization_ctrl import CTRLTokenizer
-from .tokenization_deberta import DebertaTokenizer
-from .tokenization_distilbert import DistilBertTokenizer
-from .tokenization_dpr import DPRQuestionEncoderTokenizer
-from .tokenization_electra import ElectraTokenizer
-from .tokenization_flaubert import FlaubertTokenizer
-from .tokenization_fsmt import FSMTTokenizer
-from .tokenization_funnel import FunnelTokenizer
-from .tokenization_gpt2 import GPT2Tokenizer
-from .tokenization_herbert import HerbertTokenizer
-from .tokenization_layoutlm import LayoutLMTokenizer
-from .tokenization_longformer import LongformerTokenizer
-from .tokenization_lxmert import LxmertTokenizer
-from .tokenization_mobilebert import MobileBertTokenizer
-from .tokenization_openai import OpenAIGPTTokenizer
-from .tokenization_phobert import PhobertTokenizer
-from .tokenization_prophetnet import ProphetNetTokenizer
-from .tokenization_rag import RagTokenizer
-from .tokenization_retribert import RetriBertTokenizer
-from .tokenization_roberta import RobertaTokenizer
-from .tokenization_squeezebert import SqueezeBertTokenizer
-from .tokenization_transfo_xl import TransfoXLTokenizer
-from .tokenization_xlm import XLMTokenizer
-from .utils import logging
 
 
 if is_sentencepiece_available():
-    from .tokenization_albert import AlbertTokenizer
-    from .tokenization_bert_generation import BertGenerationTokenizer
-    from .tokenization_camembert import CamembertTokenizer
-    from .tokenization_marian import MarianTokenizer
-    from .tokenization_mbart import MBartTokenizer
-    from .tokenization_pegasus import PegasusTokenizer
-    from .tokenization_reformer import ReformerTokenizer
-    from .tokenization_t5 import T5Tokenizer
-    from .tokenization_xlm_prophetnet import XLMProphetNetTokenizer
-    from .tokenization_xlm_roberta import XLMRobertaTokenizer
-    from .tokenization_xlnet import XLNetTokenizer
+    from ..albert.tokenization_albert import AlbertTokenizer
+    from ..bert_generation.tokenization_bert_generation import BertGenerationTokenizer
+    from ..camembert.tokenization_camembert import CamembertTokenizer
+    from ..marian.tokenization_marian import MarianTokenizer
+    from ..mbart.tokenization_mbart import MBartTokenizer
+    from ..pegasus.tokenization_pegasus import PegasusTokenizer
+    from ..reformer.tokenization_reformer import ReformerTokenizer
+    from ..t5.tokenization_t5 import T5Tokenizer
+    from ..xlm_prophetnet.tokenization_xlm_prophetnet import XLMProphetNetTokenizer
+    from ..xlm_roberta.tokenization_xlm_roberta import XLMRobertaTokenizer
+    from ..xlnet.tokenization_xlnet import XLNetTokenizer
 else:
     AlbertTokenizer = None
     BertGenerationTokenizer = None
@@ -116,30 +116,30 @@ else:
     XLMProphetNetTokenizer = None
 
 if is_tokenizers_available():
-    from .tokenization_albert_fast import AlbertTokenizerFast
-    from .tokenization_bart_fast import BartTokenizerFast
-    from .tokenization_bert_fast import BertTokenizerFast
-    from .tokenization_camembert_fast import CamembertTokenizerFast
-    from .tokenization_distilbert_fast import DistilBertTokenizerFast
-    from .tokenization_dpr_fast import DPRQuestionEncoderTokenizerFast
-    from .tokenization_electra_fast import ElectraTokenizerFast
-    from .tokenization_funnel_fast import FunnelTokenizerFast
-    from .tokenization_gpt2_fast import GPT2TokenizerFast
-    from .tokenization_herbert_fast import HerbertTokenizerFast
-    from .tokenization_layoutlm_fast import LayoutLMTokenizerFast
-    from .tokenization_longformer_fast import LongformerTokenizerFast
-    from .tokenization_lxmert_fast import LxmertTokenizerFast
-    from .tokenization_mbart_fast import MBartTokenizerFast
-    from .tokenization_mobilebert_fast import MobileBertTokenizerFast
-    from .tokenization_openai_fast import OpenAIGPTTokenizerFast
-    from .tokenization_pegasus_fast import PegasusTokenizerFast
-    from .tokenization_reformer_fast import ReformerTokenizerFast
-    from .tokenization_retribert_fast import RetriBertTokenizerFast
-    from .tokenization_roberta_fast import RobertaTokenizerFast
-    from .tokenization_squeezebert_fast import SqueezeBertTokenizerFast
-    from .tokenization_t5_fast import T5TokenizerFast
-    from .tokenization_xlm_roberta_fast import XLMRobertaTokenizerFast
-    from .tokenization_xlnet_fast import XLNetTokenizerFast
+    from ..albert.tokenization_albert_fast import AlbertTokenizerFast
+    from ..bart.tokenization_bart_fast import BartTokenizerFast
+    from ..bert.tokenization_bert_fast import BertTokenizerFast
+    from ..camembert.tokenization_camembert_fast import CamembertTokenizerFast
+    from ..distilbert.tokenization_distilbert_fast import DistilBertTokenizerFast
+    from ..dpr.tokenization_dpr_fast import DPRQuestionEncoderTokenizerFast
+    from ..electra.tokenization_electra_fast import ElectraTokenizerFast
+    from ..funnel.tokenization_funnel_fast import FunnelTokenizerFast
+    from ..gpt2.tokenization_gpt2_fast import GPT2TokenizerFast
+    from ..herbert.tokenization_herbert_fast import HerbertTokenizerFast
+    from ..layoutlm.tokenization_layoutlm_fast import LayoutLMTokenizerFast
+    from ..longformer.tokenization_longformer_fast import LongformerTokenizerFast
+    from ..lxmert.tokenization_lxmert_fast import LxmertTokenizerFast
+    from ..mbart.tokenization_mbart_fast import MBartTokenizerFast
+    from ..mobilebert.tokenization_mobilebert_fast import MobileBertTokenizerFast
+    from ..openai.tokenization_openai_fast import OpenAIGPTTokenizerFast
+    from ..pegasus.tokenization_pegasus_fast import PegasusTokenizerFast
+    from ..reformer.tokenization_reformer_fast import ReformerTokenizerFast
+    from ..retribert.tokenization_retribert_fast import RetriBertTokenizerFast
+    from ..roberta.tokenization_roberta_fast import RobertaTokenizerFast
+    from ..squeezebert.tokenization_squeezebert_fast import SqueezeBertTokenizerFast
+    from ..t5.tokenization_t5_fast import T5TokenizerFast
+    from ..xlm_roberta.tokenization_xlm_roberta_fast import XLMRobertaTokenizerFast
+    from ..xlnet.tokenization_xlnet_fast import XLNetTokenizerFast
 else:
     AlbertTokenizerFast = None
     BartTokenizerFast = None

src/transformers/models/bart/__init__.py

+# flake8: noqa
+# There's no way to ignore "F401 '...' imported but unused" warnings in this
+# module, but to preserve other warnings. So, don't check this module at all.
+
+from ...file_utils import is_tf_available, is_tokenizers_available, is_torch_available
+from .configuration_bart import BartConfig
+from .tokenization_bart import BartTokenizer
+
+
+if is_tokenizers_available():
+    from .tokenization_bart_fast import BartTokenizerFast
+
+if is_torch_available():
+    from .modeling_bart import (
+        BART_PRETRAINED_MODEL_ARCHIVE_LIST,
+        BartForConditionalGeneration,
+        BartForQuestionAnswering,
+        BartForSequenceClassification,
+        BartModel,
+        PretrainedBartModel,
+    )
+
+if is_tf_available():
+    from .modeling_tf_bart import TFBartForConditionalGeneration, TFBartModel

src/transformers/configuration_bart.py → src/transformers/models/bart/configuration_bart.py

@@ -14,8 +14,8 @@
 # limitations under the License.
 """ BART configuration """
 
-from .configuration_utils import PretrainedConfig
-from .utils import logging
+from ...configuration_utils import PretrainedConfig
+from ...utils import logging
 
 
 logger = logging.get_logger(__name__)

src/transformers/convert_bart_original_pytorch_checkpoint_to_pytorch.py → src/transformers/models/bart/convert_bart_original_pytorch_checkpoint_to_pytorch.py

@@ -30,7 +30,7 @@ from transformers import (
     BartModel,
     BartTokenizer,
 )
-from transformers.modeling_bart import _make_linear_from_emb
+from transformers.models.bart.modeling_bart import _make_linear_from_emb
 from transformers.utils import logging
 
 

src/transformers/modeling_bart.py → src/transformers/models/bart/modeling_bart.py

@@ -24,16 +24,15 @@ import torch.nn.functional as F
 from torch import Tensor, nn
 from torch.nn import CrossEntropyLoss
 
-from .activations import ACT2FN
-from .configuration_bart import BartConfig
-from .file_utils import (
+from ...activations import ACT2FN
+from ...file_utils import (
     add_code_sample_docstrings,
     add_end_docstrings,
     add_start_docstrings,
     add_start_docstrings_to_model_forward,
     replace_return_docstrings,
 )
-from .modeling_outputs import (
+from ...modeling_outputs import (
     BaseModelOutput,
     BaseModelOutputWithPastAndCrossAttentions,
     Seq2SeqLMOutput,
@@ -41,8 +40,9 @@ from .modeling_outputs import (
     Seq2SeqQuestionAnsweringModelOutput,
     Seq2SeqSequenceClassifierOutput,
 )
-from .modeling_utils import PreTrainedModel
-from .utils import logging
+from ...modeling_utils import PreTrainedModel
+from ...utils import logging
+from .configuration_bart import BartConfig
 
 
 logger = logging.get_logger(__name__)

src/transformers/modeling_tf_bart.py → src/transformers/models/bart/modeling_tf_bart.py

@@ -24,13 +24,17 @@ import tensorflow as tf
 from tensorflow import Tensor
 from tensorflow.keras.layers import Dense, Layer, LayerNormalization
 
-from .activations_tf import ACT2FN
-from .configuration_bart import BartConfig
-from .file_utils import add_start_docstrings, add_start_docstrings_to_model_forward, replace_return_docstrings
-from .modeling_tf_outputs import TFBaseModelOutput, TFBaseModelOutputWithPast, TFSeq2SeqLMOutput, TFSeq2SeqModelOutput
+from ...activations_tf import ACT2FN
+from ...file_utils import add_start_docstrings, add_start_docstrings_to_model_forward, replace_return_docstrings
+from ...modeling_tf_outputs import (
+    TFBaseModelOutput,
+    TFBaseModelOutputWithPast,
+    TFSeq2SeqLMOutput,
+    TFSeq2SeqModelOutput,
+)
 
 # Public API
-from .modeling_tf_utils import (
+from ...modeling_tf_utils import (
     DUMMY_INPUTS,
     TFPreTrainedModel,
     TFSharedEmbeddings,
@@ -39,8 +43,9 @@ from .modeling_tf_utils import (
     keras_serializable,
     shape_list,
 )
-from .tokenization_utils_base import BatchEncoding
-from .utils import logging
+from ...tokenization_utils_base import BatchEncoding
+from ...utils import logging
+from .configuration_bart import BartConfig
 
 
 _CONFIG_FOR_DOC = "BartConfig"