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/deta/configuration_deta.py → src/transformers/models/deprecated/deta/configuration_deta.py

@@ -14,9 +14,9 @@
 # limitations under the License.
 """DETA model configuration"""
 
-from ...configuration_utils import PretrainedConfig
-from ...utils import logging
-from ..auto import CONFIG_MAPPING
+from ....configuration_utils import PretrainedConfig
+from ....utils import logging
+from ...auto import CONFIG_MAPPING
 
 
 logger = logging.get_logger(__name__)

src/transformers/models/deta/image_processing_deta.py → src/transformers/models/deprecated/deta/image_processing_deta.py

@@ -19,9 +19,9 @@ from typing import Any, Callable, Dict, Iterable, List, Optional, Tuple, Union
 
 import numpy as np
 
-from ...feature_extraction_utils import BatchFeature
-from ...image_processing_utils import BaseImageProcessor, get_size_dict
-from ...image_transforms import (
+from ....feature_extraction_utils import BatchFeature
+from ....image_processing_utils import BaseImageProcessor, get_size_dict
+from ....image_transforms import (
     PaddingMode,
     center_to_corners_format,
     corners_to_center_format,
@@ -31,7 +31,7 @@ from ...image_transforms import (
     rgb_to_id,
     to_channel_dimension_format,
 )
-from ...image_utils import (
+from ....image_utils import (
     IMAGENET_DEFAULT_MEAN,
     IMAGENET_DEFAULT_STD,
     AnnotationFormat,
@@ -48,7 +48,7 @@ from ...image_utils import (
     validate_annotations,
     validate_preprocess_arguments,
 )
-from ...utils import (
+from ....utils import (
     is_flax_available,
     is_jax_tensor,
     is_tf_available,
@@ -59,7 +59,7 @@ from ...utils import (
     is_vision_available,
     logging,
 )
-from ...utils.generic import TensorType
+from ....utils.generic import TensorType
 
 
 if is_torch_available():

src/transformers/models/deta/modeling_deta.py → src/transformers/models/deprecated/deta/modeling_deta.py

@@ -28,8 +28,8 @@ from torch import Tensor, nn
 from torch.autograd import Function
 from torch.autograd.function import once_differentiable
 
-from ...activations import ACT2FN
-from ...file_utils import (
+from ....activations import ACT2FN
+from ....file_utils import (
     ModelOutput,
     add_start_docstrings,
     add_start_docstrings_to_model_forward,
@@ -38,12 +38,12 @@ from ...file_utils import (
     is_vision_available,
     replace_return_docstrings,
 )
-from ...modeling_attn_mask_utils import _prepare_4d_attention_mask
-from ...modeling_outputs import BaseModelOutput
-from ...modeling_utils import PreTrainedModel
-from ...pytorch_utils import meshgrid
-from ...utils import is_accelerate_available, is_ninja_available, is_torchvision_available, logging, requires_backends
-from ...utils.backbone_utils import load_backbone
+from ....modeling_attn_mask_utils import _prepare_4d_attention_mask
+from ....modeling_outputs import BaseModelOutput
+from ....modeling_utils import PreTrainedModel
+from ....pytorch_utils import meshgrid
+from ....utils import is_accelerate_available, is_ninja_available, is_torchvision_available, logging, requires_backends
+from ....utils.backbone_utils import load_backbone
 from .configuration_deta import DetaConfig
 
 

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

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

src/transformers/models/efficientformer/configuration_efficientformer.py → src/transformers/models/deprecated/efficientformer/configuration_efficientformer.py

@@ -16,8 +16,8 @@
 
 from typing import List
 
-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/efficientformer/image_processing_efficientformer.py → src/transformers/models/deprecated/efficientformer/image_processing_efficientformer.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_DEFAULT_MEAN,
     IMAGENET_DEFAULT_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/efficientformer/modeling_efficientformer.py → src/transformers/models/deprecated/efficientformer/modeling_efficientformer.py

@@ -23,10 +23,10 @@ import torch.utils.checkpoint
 from torch import nn
 from torch.nn import BCEWithLogitsLoss, CrossEntropyLoss, MSELoss
 
-from ...activations import ACT2FN
-from ...modeling_outputs import BaseModelOutput, BaseModelOutputWithPooling, ImageClassifierOutput
-from ...modeling_utils import PreTrainedModel
-from ...utils import (
+from ....activations import ACT2FN
+from ....modeling_outputs import BaseModelOutput, BaseModelOutputWithPooling, ImageClassifierOutput
+from ....modeling_utils import PreTrainedModel
+from ....utils import (
     ModelOutput,
     add_code_sample_docstrings,
     add_start_docstrings,

src/transformers/models/efficientformer/modeling_tf_efficientformer.py → src/transformers/models/deprecated/efficientformer/modeling_tf_efficientformer.py

@@ -20,13 +20,13 @@ from typing import Optional, Tuple, Union
 
 import tensorflow as tf
 
-from ...activations_tf import ACT2FN
-from ...modeling_tf_outputs import (
+from ....activations_tf import ACT2FN
+from ....modeling_tf_outputs import (
     TFBaseModelOutput,
     TFBaseModelOutputWithPooling,
     TFImageClassifierOutput,
 )
-from ...modeling_tf_utils import (
+from ....modeling_tf_utils import (
     TFPreTrainedModel,
     TFSequenceClassificationLoss,
     get_initializer,
@@ -34,8 +34,8 @@ from ...modeling_tf_utils import (
     keras_serializable,
     unpack_inputs,
 )
-from ...tf_utils import shape_list, stable_softmax
-from ...utils import (
+from ....tf_utils import shape_list, stable_softmax
+from ....utils import (
     ModelOutput,
     add_code_sample_docstrings,
     add_start_docstrings,

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

@@ -14,7 +14,7 @@
 from typing import TYPE_CHECKING
 
 # rely on isort to merge the imports
-from ...utils import OptionalDependencyNotAvailable, _LazyModule, is_sentencepiece_available, is_torch_available
+from ....utils import OptionalDependencyNotAvailable, _LazyModule, is_sentencepiece_available, is_torch_available
 
 
 _import_structure = {

src/transformers/models/ernie_m/configuration_ernie_m.py → src/transformers/models/deprecated/ernie_m/configuration_ernie_m.py

@@ -19,7 +19,7 @@ from __future__ import annotations
 
 from typing import Dict
 
-from ...configuration_utils import PretrainedConfig
+from ....configuration_utils import PretrainedConfig
 
 
 class ErnieMConfig(PretrainedConfig):

src/transformers/models/ernie_m/modeling_ernie_m.py → src/transformers/models/deprecated/ernie_m/modeling_ernie_m.py

@@ -22,8 +22,8 @@ import torch.utils.checkpoint
 from torch import nn, tensor
 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,
     MultipleChoiceModelOutput,
@@ -31,9 +31,9 @@ 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 add_code_sample_docstrings, add_start_docstrings, add_start_docstrings_to_model_forward, logging
+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, logging
 from .configuration_ernie_m import ErnieMConfig
 
 

src/transformers/models/ernie_m/tokenization_ernie_m.py → src/transformers/models/deprecated/ernie_m/tokenization_ernie_m.py

@@ -21,8 +21,8 @@ from typing import Any, Dict, 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/models/gptsan_japanese/__init__.py → src/transformers/models/deprecated/gptsan_japanese/__init__.py

@@ -14,7 +14,7 @@
 
 from typing import TYPE_CHECKING
 
-from ...utils import (
+from ....utils import (
     OptionalDependencyNotAvailable,
     _LazyModule,
     is_flax_available,

src/transformers/models/gptsan_japanese/configuration_gptsan_japanese.py → src/transformers/models/deprecated/gptsan_japanese/configuration_gptsan_japanese.py

@@ -14,8 +14,8 @@
 # limitations under the License.
 """GPTSAN-japanese 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/gptsan_japanese/modeling_gptsan_japanese.py → src/transformers/models/deprecated/gptsan_japanese/modeling_gptsan_japanese.py

@@ -20,10 +20,10 @@ from typing import List, Optional, Tuple, Union
 import torch
 import torch.nn as nn
 
-from ...activations import ACT2FN
-from ...modeling_outputs import MoECausalLMOutputWithPast, MoEModelOutputWithPastAndCrossAttentions
-from ...modeling_utils import PreTrainedModel
-from ...utils import (
+from ....activations import ACT2FN
+from ....modeling_outputs import MoECausalLMOutputWithPast, MoEModelOutputWithPastAndCrossAttentions
+from ....modeling_utils import PreTrainedModel
+from ....utils import (
     DUMMY_INPUTS,
     DUMMY_MASK,
     add_start_docstrings,

src/transformers/models/gptsan_japanese/tokenization_gptsan_japanese.py → src/transformers/models/deprecated/gptsan_japanese/tokenization_gptsan_japanese.py

@@ -22,8 +22,8 @@ from typing import List, Optional, Tuple, Union
 
 import numpy as np
 
-from ...tokenization_utils import PreTrainedTokenizer
-from ...tokenization_utils_base import (
+from ....tokenization_utils import PreTrainedTokenizer
+from ....tokenization_utils_base import (
     BatchEncoding,
     PreTokenizedInput,
     PreTokenizedInputPair,
@@ -31,7 +31,7 @@ from ...tokenization_utils_base import (
     TextInputPair,
     TruncationStrategy,
 )
-from ...utils import PaddingStrategy, logging
+from ....utils import PaddingStrategy, logging
 
 
 logger = logging.get_logger(__name__)