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/graphormer/__init__.py → src/transformers/models/deprecated/graphormer/__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/graphormer/collating_graphormer.py → src/transformers/models/deprecated/graphormer/collating_graphormer.py

@@ -6,7 +6,7 @@ from typing import Any, Dict, List, Mapping
 import numpy as np
 import torch
 
-from ...utils import is_cython_available, requires_backends
+from ....utils import is_cython_available, requires_backends
 
 
 if is_cython_available():

src/transformers/models/graphormer/configuration_graphormer.py → src/transformers/models/deprecated/graphormer/configuration_graphormer.py

@@ -14,8 +14,8 @@
 # limitations under the License.
 """Graphormer 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/graphormer/modeling_graphormer.py → src/transformers/models/deprecated/graphormer/modeling_graphormer.py

@@ -21,13 +21,13 @@ import torch
 import torch.nn as nn
 from torch.nn import BCEWithLogitsLoss, CrossEntropyLoss, MSELoss
 
-from ...activations import ACT2FN
-from ...modeling_outputs import (
+from ....activations import ACT2FN
+from ....modeling_outputs import (
     BaseModelOutputWithNoAttention,
     SequenceClassifierOutput,
 )
-from ...modeling_utils import PreTrainedModel
-from ...utils import logging
+from ....modeling_utils import PreTrainedModel
+from ....utils import logging
 from .configuration_graphormer import GraphormerConfig
 
 

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

@@ -14,7 +14,7 @@
 
 from typing import TYPE_CHECKING
 
-from ...utils import OptionalDependencyNotAvailable, _LazyModule, is_torch_available
+from ....utils import OptionalDependencyNotAvailable, _LazyModule, is_torch_available
 
 
 _import_structure = {

src/transformers/models/jukebox/configuration_jukebox.py → src/transformers/models/deprecated/jukebox/configuration_jukebox.py

@@ -17,8 +17,8 @@
 import os
 from typing import List, Union
 
-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/jukebox/modeling_jukebox.py → src/transformers/models/deprecated/jukebox/modeling_jukebox.py

@@ -24,10 +24,10 @@ import torch.nn.functional as F
 from torch import nn
 from torch.nn import LayerNorm as FusedLayerNorm
 
-from ...activations import ACT2FN
-from ...modeling_utils import PreTrainedModel
-from ...utils import add_start_docstrings, logging
-from ...utils.logging import tqdm
+from ....activations import ACT2FN
+from ....modeling_utils import PreTrainedModel
+from ....utils import add_start_docstrings, logging
+from ....utils.logging import tqdm
 from .configuration_jukebox import ATTENTION_PATTERNS, JukeboxConfig, JukeboxPriorConfig, JukeboxVQVAEConfig
 
 

src/transformers/models/jukebox/tokenization_jukebox.py → src/transformers/models/deprecated/jukebox/tokenization_jukebox.py

@@ -24,10 +24,10 @@ from typing import Any, Dict, List, Optional, Tuple, Union
 import numpy as np
 import regex
 
-from ...tokenization_utils import AddedToken, PreTrainedTokenizer
-from ...tokenization_utils_base import BatchEncoding
-from ...utils import TensorType, is_flax_available, is_tf_available, is_torch_available, logging
-from ...utils.generic import _is_jax, _is_numpy
+from ....tokenization_utils import AddedToken, PreTrainedTokenizer
+from ....tokenization_utils_base import BatchEncoding
+from ....utils import TensorType, is_flax_available, is_tf_available, is_torch_available, logging
+from ....utils.generic import _is_jax, _is_numpy
 
 
 logger = logging.get_logger(__name__)

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

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

src/transformers/models/mega/configuration_mega.py → src/transformers/models/deprecated/mega/configuration_mega.py

@@ -17,9 +17,9 @@
 from collections import OrderedDict
 from typing import Mapping
 
-from ...configuration_utils import PretrainedConfig
-from ...onnx import OnnxConfig
-from ...utils import logging
+from ....configuration_utils import PretrainedConfig
+from ....onnx import OnnxConfig
+from ....utils import logging
 
 
 logger = logging.get_logger(__name__)

src/transformers/models/mega/modeling_mega.py → src/transformers/models/deprecated/mega/modeling_mega.py

@@ -23,8 +23,8 @@ 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 (
     BaseModelOutputWithPoolingAndCrossAttentions,
     CausalLMOutputWithCrossAttentions,
     MaskedLMOutput,
@@ -33,9 +33,9 @@ from ...modeling_outputs import (
     SequenceClassifierOutput,
     TokenClassifierOutput,
 )
-from ...modeling_utils import PreTrainedModel
-from ...pytorch_utils import ALL_LAYERNORM_LAYERS
-from ...utils import (
+from ....modeling_utils import PreTrainedModel
+from ....pytorch_utils import ALL_LAYERNORM_LAYERS
+from ....utils import (
     add_code_sample_docstrings,
     add_start_docstrings,
     add_start_docstrings_to_model_forward,

src/transformers/models/nat/__init__.py → src/transformers/models/deprecated/nat/__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_nat": ["NatConfig"]}

src/transformers/models/nat/configuration_nat.py → src/transformers/models/deprecated/nat/configuration_nat.py

@@ -14,9 +14,9 @@
 # limitations under the License.
 """Neighborhood Attention Transformer model configuration"""
 
-from ...configuration_utils import PretrainedConfig
-from ...utils import logging
-from ...utils.backbone_utils import BackboneConfigMixin, get_aligned_output_features_output_indices
+from ....configuration_utils import PretrainedConfig
+from ....utils import logging
+from ....utils.backbone_utils import BackboneConfigMixin, get_aligned_output_features_output_indices
 
 
 logger = logging.get_logger(__name__)

src/transformers/models/nat/modeling_nat.py → src/transformers/models/deprecated/nat/modeling_nat.py

@@ -23,11 +23,11 @@ import torch.utils.checkpoint
 from torch import nn
 from torch.nn import BCEWithLogitsLoss, CrossEntropyLoss, MSELoss
 
-from ...activations import ACT2FN
-from ...modeling_outputs import BackboneOutput
-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 BackboneOutput
+from ....modeling_utils import PreTrainedModel
+from ....pytorch_utils import find_pruneable_heads_and_indices, prune_linear_layer
+from ....utils import (
     ModelOutput,
     OptionalDependencyNotAvailable,
     add_code_sample_docstrings,
@@ -38,7 +38,7 @@ from ...utils import (
     replace_return_docstrings,
     requires_backends,
 )
-from ...utils.backbone_utils import BackboneMixin
+from ....utils.backbone_utils import BackboneMixin
 from .configuration_nat import NatConfig
 
 

src/transformers/models/nezha/__init__.py → src/transformers/models/deprecated/nezha/__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/nezha/configuration_nezha.py → src/transformers/models/deprecated/nezha/configuration_nezha.py

-from ... import PretrainedConfig
+from .... import PretrainedConfig
 
 
 class NezhaConfig(PretrainedConfig):

src/transformers/models/nezha/modeling_nezha.py → src/transformers/models/deprecated/nezha/modeling_nezha.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,
     MaskedLMOutput,
@@ -36,9 +36,9 @@ from ...modeling_outputs import (
     SequenceClassifierOutput,
     TokenClassifierOutput,
 )
-from ...modeling_utils import PreTrainedModel
-from ...pytorch_utils import apply_chunking_to_forward, find_pruneable_heads_and_indices, prune_linear_layer
-from ...utils import (
+from ....modeling_utils import PreTrainedModel
+from ....pytorch_utils import apply_chunking_to_forward, find_pruneable_heads_and_indices, prune_linear_layer
+from ....utils import (
     ModelOutput,
     add_code_sample_docstrings,
     add_start_docstrings,