Deprecate low use models (#30781)

* Deprecate models
- graphormer
- time_series_transformer
- xlm_prophetnet
- qdqbert
- nat
- ernie_m
- tvlt
- nezha
- mega
- jukebox
- vit_hybrid
- x_clip
- deta
- speech_to_text_2
- efficientformer
- realm
- gptsan_japanese

* Fix up

* Fix speech2text2 imports

* Make sure message isn't indented

* Fix docstrings

* Correctly map for deprecated models from model_type

* Uncomment out

* Add back time series transformer and x-clip

* Import fix and fix-up

* Fix up with updated ruff

src/transformers/models/qdqbert/__init__.py → src/transformers/models/deprecated/qdqbert/__init__.py

@@ -13,7 +13,7 @@
 # limitations under the License.
 from typing import TYPE_CHECKING
 
-from ...utils import OptionalDependencyNotAvailable, _LazyModule, is_torch_available
+from ....utils import OptionalDependencyNotAvailable, _LazyModule, is_torch_available
 
 
 _import_structure = {"configuration_qdqbert": ["QDQBertConfig"]}

src/transformers/models/qdqbert/configuration_qdqbert.py → src/transformers/models/deprecated/qdqbert/configuration_qdqbert.py

@@ -14,8 +14,8 @@
 # limitations under the License.
 """QDQBERT model 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/models/qdqbert/modeling_qdqbert.py → src/transformers/models/deprecated/qdqbert/modeling_qdqbert.py

@@ -25,8 +25,8 @@ import torch.utils.checkpoint
 from torch import nn
 from torch.nn import BCEWithLogitsLoss, CrossEntropyLoss, MSELoss
 
-from ...activations import ACT2FN
-from ...modeling_outputs import (
+from ....activations import ACT2FN
+from ....modeling_outputs import (
     BaseModelOutputWithPastAndCrossAttentions,
     BaseModelOutputWithPoolingAndCrossAttentions,
     CausalLMOutputWithCrossAttentions,
@@ -37,9 +37,9 @@ from ...modeling_outputs import (
     SequenceClassifierOutput,
     TokenClassifierOutput,
 )
-from ...modeling_utils import PreTrainedModel
-from ...pytorch_utils import find_pruneable_heads_and_indices, prune_linear_layer
-from ...utils import (
+from ....modeling_utils import PreTrainedModel
+from ....pytorch_utils import find_pruneable_heads_and_indices, prune_linear_layer
+from ....utils import (
     add_code_sample_docstrings,
     add_start_docstrings,
     add_start_docstrings_to_model_forward,

src/transformers/models/realm/__init__.py → src/transformers/models/deprecated/realm/__init__.py

@@ -13,7 +13,7 @@
 # limitations under the License.
 from typing import TYPE_CHECKING
 
-from ...utils import OptionalDependencyNotAvailable, _LazyModule, is_tokenizers_available, is_torch_available
+from ....utils import OptionalDependencyNotAvailable, _LazyModule, is_tokenizers_available, is_torch_available
 
 
 _import_structure = {

src/transformers/models/realm/configuration_realm.py → src/transformers/models/deprecated/realm/configuration_realm.py

@@ -14,8 +14,8 @@
 # limitations under the License.
 """REALM model 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/models/realm/modeling_realm.py → src/transformers/models/deprecated/realm/modeling_realm.py

@@ -23,16 +23,16 @@ import torch
 from torch import nn
 from torch.nn import CrossEntropyLoss
 
-from ...activations import ACT2FN
-from ...modeling_outputs import (
+from ....activations import ACT2FN
+from ....modeling_outputs import (
     BaseModelOutputWithPastAndCrossAttentions,
     BaseModelOutputWithPoolingAndCrossAttentions,
     MaskedLMOutput,
     ModelOutput,
 )
-from ...modeling_utils import PreTrainedModel
-from ...pytorch_utils import apply_chunking_to_forward, find_pruneable_heads_and_indices, prune_linear_layer
-from ...utils import add_start_docstrings, add_start_docstrings_to_model_forward, logging, replace_return_docstrings
+from ....modeling_utils import PreTrainedModel
+from ....pytorch_utils import apply_chunking_to_forward, find_pruneable_heads_and_indices, prune_linear_layer
+from ....utils import add_start_docstrings, add_start_docstrings_to_model_forward, logging, replace_return_docstrings
 from .configuration_realm import RealmConfig
 
 

src/transformers/models/realm/retrieval_realm.py → src/transformers/models/deprecated/realm/retrieval_realm.py

@@ -20,8 +20,8 @@ from typing import Optional, Union
 import numpy as np
 from huggingface_hub import hf_hub_download
 
-from ... import AutoTokenizer
-from ...utils import logging
+from .... import AutoTokenizer
+from ....utils import logging
 
 
 _REALM_BLOCK_RECORDS_FILENAME = "block_records.npy"

src/transformers/models/realm/tokenization_realm.py → src/transformers/models/deprecated/realm/tokenization_realm.py

@@ -19,9 +19,9 @@ import os
 import unicodedata
 from typing import List, Optional, Tuple
 
-from ...tokenization_utils import PreTrainedTokenizer, _is_control, _is_punctuation, _is_whitespace
-from ...tokenization_utils_base import BatchEncoding
-from ...utils import PaddingStrategy, logging
+from ....tokenization_utils import PreTrainedTokenizer, _is_control, _is_punctuation, _is_whitespace
+from ....tokenization_utils_base import BatchEncoding
+from ....utils import PaddingStrategy, logging
 
 
 logger = logging.get_logger(__name__)

src/transformers/models/realm/tokenization_realm_fast.py → src/transformers/models/deprecated/realm/tokenization_realm_fast.py

@@ -19,9 +19,9 @@ from typing import List, Optional, Tuple
 
 from tokenizers import normalizers
 
-from ...tokenization_utils_base import BatchEncoding
-from ...tokenization_utils_fast import PreTrainedTokenizerFast
-from ...utils import PaddingStrategy, logging
+from ....tokenization_utils_base import BatchEncoding
+from ....tokenization_utils_fast import PreTrainedTokenizerFast
+from ....utils import PaddingStrategy, logging
 from .tokenization_realm import RealmTokenizer
 
 

src/transformers/models/speech_to_text_2/__init__.py → src/transformers/models/deprecated/speech_to_text_2/__init__.py

@@ -13,7 +13,7 @@
 # limitations under the License.
 from typing import TYPE_CHECKING
 
-from ...utils import (
+from ....utils import (
     OptionalDependencyNotAvailable,
     _LazyModule,
     is_sentencepiece_available,

src/transformers/models/speech_to_text_2/configuration_speech_to_text_2.py → src/transformers/models/deprecated/speech_to_text_2/configuration_speech_to_text_2.py

@@ -14,8 +14,8 @@
 # limitations under the License.
 """Speech2Text model 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/models/speech_to_text_2/modeling_speech_to_text_2.py → src/transformers/models/deprecated/speech_to_text_2/modeling_speech_to_text_2.py

@@ -22,11 +22,11 @@ import torch
 from torch import nn
 from torch.nn import CrossEntropyLoss
 
-from ...activations import ACT2FN
-from ...modeling_attn_mask_utils import _prepare_4d_attention_mask, _prepare_4d_causal_attention_mask
-from ...modeling_outputs import BaseModelOutputWithPastAndCrossAttentions, CausalLMOutputWithCrossAttentions
-from ...modeling_utils import PreTrainedModel
-from ...utils import add_start_docstrings, logging, replace_return_docstrings
+from ....activations import ACT2FN
+from ....modeling_attn_mask_utils import _prepare_4d_attention_mask, _prepare_4d_causal_attention_mask
+from ....modeling_outputs import BaseModelOutputWithPastAndCrossAttentions, CausalLMOutputWithCrossAttentions
+from ....modeling_utils import PreTrainedModel
+from ....utils import add_start_docstrings, logging, replace_return_docstrings
 from .configuration_speech_to_text_2 import Speech2Text2Config
 
 

src/transformers/models/speech_to_text_2/processing_speech_to_text_2.py → src/transformers/models/deprecated/speech_to_text_2/processing_speech_to_text_2.py

@@ -19,7 +19,7 @@ Speech processor class for Speech2Text2
 import warnings
 from contextlib import contextmanager
 
-from ...processing_utils import ProcessorMixin
+from ....processing_utils import ProcessorMixin
 
 
 class Speech2Text2Processor(ProcessorMixin):

src/transformers/models/speech_to_text_2/tokenization_speech_to_text_2.py → src/transformers/models/deprecated/speech_to_text_2/tokenization_speech_to_text_2.py

@@ -18,8 +18,8 @@ import json
 import os
 from typing import Dict, List, Optional, Tuple
 
-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/models/tvlt/__init__.py → src/transformers/models/deprecated/tvlt/__init__.py

@@ -17,7 +17,7 @@
 # limitations under the License.
 from typing import TYPE_CHECKING
 
-from ...utils import (
+from ....utils import (
     OptionalDependencyNotAvailable,
     _LazyModule,
     is_torch_available,

src/transformers/models/tvlt/configuration_tvlt.py → src/transformers/models/deprecated/tvlt/configuration_tvlt.py

@@ -14,8 +14,8 @@
 # limitations under the License.
 """TVLT model 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/models/tvlt/feature_extraction_tvlt.py → src/transformers/models/deprecated/tvlt/feature_extraction_tvlt.py

@@ -19,9 +19,9 @@ from typing import List, Optional, Union
 
 import numpy as np
 
-from ...audio_utils import mel_filter_bank, spectrogram, window_function
-from ...feature_extraction_sequence_utils import BatchFeature, SequenceFeatureExtractor
-from ...utils import TensorType, logging
+from ....audio_utils import mel_filter_bank, spectrogram, window_function
+from ....feature_extraction_sequence_utils import BatchFeature, SequenceFeatureExtractor
+from ....utils import TensorType, logging
 
 
 logger = logging.get_logger(__name__)

src/transformers/models/tvlt/image_processing_tvlt.py → src/transformers/models/deprecated/tvlt/image_processing_tvlt.py

@@ -18,13 +18,13 @@ from typing import Dict, List, Optional, Union
 
 import numpy as np
 
-from ...image_processing_utils import BaseImageProcessor, BatchFeature, get_size_dict
-from ...image_transforms import (
+from ....image_processing_utils import BaseImageProcessor, BatchFeature, get_size_dict
+from ....image_transforms import (
     get_resize_output_image_size,
     resize,
     to_channel_dimension_format,
 )
-from ...image_utils import (
+from ....image_utils import (
     IMAGENET_STANDARD_MEAN,
     IMAGENET_STANDARD_STD,
     ChannelDimension,
@@ -38,7 +38,7 @@ from ...image_utils import (
     validate_kwargs,
     validate_preprocess_arguments,
 )
-from ...utils import TensorType, logging
+from ....utils import TensorType, logging
 
 
 logger = logging.get_logger(__name__)

src/transformers/models/tvlt/modeling_tvlt.py → src/transformers/models/deprecated/tvlt/modeling_tvlt.py

@@ -25,11 +25,11 @@ import torch.utils.checkpoint
 from torch import nn
 from torch.nn import BCEWithLogitsLoss, CrossEntropyLoss, MSELoss
 
-from ...activations import ACT2FN
-from ...modeling_outputs import BaseModelOutput, SequenceClassifierOutput
-from ...modeling_utils import PreTrainedModel
-from ...pytorch_utils import find_pruneable_heads_and_indices, prune_linear_layer
-from ...utils import (
+from ....activations import ACT2FN
+from ....modeling_outputs import BaseModelOutput, SequenceClassifierOutput
+from ....modeling_utils import PreTrainedModel
+from ....pytorch_utils import find_pruneable_heads_and_indices, prune_linear_layer
+from ....utils import (
     ModelOutput,
     add_start_docstrings,
     add_start_docstrings_to_model_forward,

src/transformers/models/tvlt/processing_tvlt.py → src/transformers/models/deprecated/tvlt/processing_tvlt.py

@@ -16,7 +16,7 @@
 Processor class for TVLT.
 """
 
-from ...processing_utils import ProcessorMixin
+from ....processing_utils import ProcessorMixin
 
 
 class TvltProcessor(ProcessorMixin):