[configuration] remove redundant classmethod

src/transformers/configuration_utils.py

@@ -1157,6 +1157,42 @@ def get_text_config(self, decoder=False) -> "PretrainedConfig":
             config_to_return = self
         return config_to_return
 
+    @classmethod
+    def from_text_vision_configs(cls, text_config, vision_config, **kwargs):
+        r"""
+        Instantiate a model config (or a derived class) from text model configuration and vision model
+        configuration.
+
+        Returns:
+            [`PreTrainedConfig`]: An instance of a configuration object
+        """
+
+        warnings.warn(
+            "The `from_text_vision_configs` method is deprecated and will be removed in v4.60 of Transformers. Please instantiate "
+            "the config class directly with `MyConfig(text_config=text_config, vision_config=vision_config, **kwargs)` instead.",
+            FutureWarning,
+        )
+
+        return cls(text_config=text_config.to_dict(), vision_config=vision_config.to_dict(), **kwargs)
+
+    @classmethod
+    def from_text_audio_configs(cls, text_config, audio_config, **kwargs):
+        r"""
+        Instantiate a model config (or a derived class) from text model configuration and audio model
+        configuration.
+
+        Returns:
+            [`PreTrainedConfig`]: An instance of a configuration object
+        """
+
+        warnings.warn(
+            "The `from_text_audio_configs` method is deprecated and will be removed in v4.60 of Transformers. Please instantiate "
+            "the config class directly with `MyConfig(text_config=text_config, audio_config=audio_config, **kwargs)` instead.",
+            FutureWarning,
+        )
+
+        return cls(text_config=text_config.to_dict(), audio_config=audio_config.to_dict(), **kwargs)
+
 
 def get_configuration_file(configuration_files: list[str]) -> str:
     """

src/transformers/models/align/configuration_align.py

@@ -333,17 +333,5 @@ def __init__(
         self.temperature_init_value = temperature_init_value
         self.initializer_range = initializer_range
 
-    @classmethod
-    def from_text_vision_configs(cls, text_config: AlignTextConfig, vision_config: AlignVisionConfig, **kwargs):
-        r"""
-        Instantiate a [`AlignConfig`] (or a derived class) from align text model configuration and align vision model
-        configuration.
-
-        Returns:
-            [`AlignConfig`]: An instance of a configuration object
-        """
-
-        return cls(text_config=text_config.to_dict(), vision_config=vision_config.to_dict(), **kwargs)
-
 
 __all__ = ["AlignTextConfig", "AlignVisionConfig", "AlignConfig"]

src/transformers/models/altclip/configuration_altclip.py

@@ -368,17 +368,5 @@ def __init__(
         self.logit_scale_init_value = logit_scale_init_value
         self.initializer_factor = 1.0
 
-    @classmethod
-    def from_text_vision_configs(cls, text_config: AltCLIPTextConfig, vision_config: AltCLIPVisionConfig, **kwargs):
-        r"""
-        Instantiate a [`AltCLIPConfig`] (or a derived class) from altclip text model configuration and altclip vision
-        model configuration.
-
-        Returns:
-            [`AltCLIPConfig`]: An instance of a configuration object
-        """
-
-        return cls(text_config=text_config.to_dict(), vision_config=vision_config.to_dict(), **kwargs)
-
 
 __all__ = ["AltCLIPTextConfig", "AltCLIPVisionConfig", "AltCLIPConfig"]

src/transformers/models/blip/configuration_blip.py

@@ -313,17 +313,5 @@ def __init__(
         self.image_text_hidden_size = image_text_hidden_size
         self.label_smoothing = label_smoothing
 
-    @classmethod
-    def from_text_vision_configs(cls, text_config: BlipTextConfig, vision_config: BlipVisionConfig, **kwargs):
-        r"""
-        Instantiate a [`BlipConfig`] (or a derived class) from blip text model configuration and blip vision model
-        configuration.
-
-        Returns:
-            [`BlipConfig`]: An instance of a configuration object
-        """
-
-        return cls(text_config=text_config.to_dict(), vision_config=vision_config.to_dict(), **kwargs)
-
 
 __all__ = ["BlipConfig", "BlipTextConfig", "BlipVisionConfig"]

src/transformers/models/bridgetower/configuration_bridgetower.py

@@ -304,16 +304,5 @@ def __init__(
         self.text_config = BridgeTowerTextConfig(**text_config)
         self.vision_config = BridgeTowerVisionConfig(**vision_config)
 
-    @classmethod
-    def from_text_vision_configs(
-        cls, text_config: BridgeTowerTextConfig, vision_config: BridgeTowerVisionConfig, **kwargs
-    ):
-        r"""
-        Instantiate a [`BridgeTowerConfig`] (or a derived class) from BridgeTower text model configuration. Returns:
-            [`BridgeTowerConfig`]: An instance of a configuration object
-        """
-
-        return cls(text_config=text_config.to_dict(), vision_config=vision_config.to_dict(), **kwargs)
-
 
 __all__ = ["BridgeTowerConfig", "BridgeTowerTextConfig", "BridgeTowerVisionConfig"]

src/transformers/models/chinese_clip/configuration_chinese_clip.py

@@ -373,18 +373,6 @@ def __init__(
         self.initializer_factor = 1.0
         self.initializer_range = 0.02
 
-    @classmethod
-    def from_text_vision_configs(
-        cls, text_config: ChineseCLIPTextConfig, vision_config: ChineseCLIPVisionConfig, **kwargs
-    ):
-        r"""
-        Instantiate a [`ChineseCLIPConfig`] (or a derived class) from Chinese-CLIP text model configuration and
-        Chinese-CLIP vision model configuration. Returns:
-            [`ChineseCLIPConfig`]: An instance of a configuration object
-        """
-
-        return cls(text_config=text_config.to_dict(), vision_config=vision_config.to_dict(), **kwargs)
-
 
 class ChineseCLIPOnnxConfig(OnnxConfig):
     @property

src/transformers/models/clap/configuration_clap.py

@@ -378,17 +378,5 @@ def __init__(
         self.initializer_factor = initializer_factor
         self.num_hidden_layers = self.text_config.num_hidden_layers + len(self.audio_config.depths)
 
-    @classmethod
-    def from_text_audio_configs(cls, text_config: ClapTextConfig, audio_config: ClapAudioConfig, **kwargs):
-        r"""
-        Instantiate a [`ClapConfig`] (or a derived class) from clap text model configuration and clap audio model
-        configuration.
-
-        Returns:
-            [`ClapConfig`]: An instance of a configuration object
-        """
-
-        return cls(text_config=text_config.to_dict(), audio_config=audio_config.to_dict(), **kwargs)
-
 
 __all__ = ["ClapAudioConfig", "ClapConfig", "ClapTextConfig"]

src/transformers/models/clip/configuration_clip.py

@@ -361,18 +361,6 @@ def __init__(
         self.logit_scale_init_value = logit_scale_init_value
         self.initializer_factor = 1.0
 
-    @classmethod
-    def from_text_vision_configs(cls, text_config: CLIPTextConfig, vision_config: CLIPVisionConfig, **kwargs):
-        r"""
-        Instantiate a [`CLIPConfig`] (or a derived class) from clip text model configuration and clip vision model
-        configuration.
-
-        Returns:
-            [`CLIPConfig`]: An instance of a configuration object
-        """
-
-        return cls(text_config=text_config.to_dict(), vision_config=vision_config.to_dict(), **kwargs)
-
 
 class CLIPOnnxConfig(OnnxConfig):
     @property

src/transformers/models/clipseg/configuration_clipseg.py

@@ -380,17 +380,5 @@ def __init__(
         self.initializer_factor = 1.0
         self.use_complex_transposed_convolution = use_complex_transposed_convolution
 
-    @classmethod
-    def from_text_vision_configs(cls, text_config: CLIPSegTextConfig, vision_config: CLIPSegVisionConfig, **kwargs):
-        r"""
-        Instantiate a [`CLIPSegConfig`] (or a derived class) from clipseg text model configuration and clipseg vision
-        model configuration.
-
-        Returns:
-            [`CLIPSegConfig`]: An instance of a configuration object
-        """
-
-        return cls(text_config=text_config.to_dict(), vision_config=vision_config.to_dict(), **kwargs)
-
 
 __all__ = ["CLIPSegConfig", "CLIPSegTextConfig", "CLIPSegVisionConfig"]

src/transformers/models/groupvit/configuration_groupvit.py

@@ -357,18 +357,6 @@ def __init__(
         self.initializer_factor = 1.0
         self.output_segmentation = False
 
-    @classmethod
-    def from_text_vision_configs(cls, text_config: GroupViTTextConfig, vision_config: GroupViTVisionConfig, **kwargs):
-        r"""
-        Instantiate a [`GroupViTConfig`] (or a derived class) from groupvit text model configuration and groupvit
-        vision model configuration.
-
-        Returns:
-            [`GroupViTConfig`]: An instance of a configuration object
-        """
-
-        return cls(text_config=text_config.to_dict(), vision_config=vision_config.to_dict(), **kwargs)
-
 
 class GroupViTOnnxConfig(OnnxConfig):
     @property

src/transformers/models/owlv2/configuration_owlv2.py

@@ -14,7 +14,7 @@
 # limitations under the License.
 """OWLv2 model configuration"""
 
-from typing import TYPE_CHECKING, Dict
+from typing import TYPE_CHECKING
 
 
 if TYPE_CHECKING:
@@ -270,20 +270,5 @@ def __init__(
         self.return_dict = return_dict
         self.initializer_factor = 1.0
 
-    @classmethod
-    def from_text_vision_configs(cls, text_config: Dict, vision_config: Dict, **kwargs):
-        r"""
-        Instantiate a [`Owlv2Config`] (or a derived class) from owlv2 text model configuration and owlv2 vision
-        model configuration.
-
-        Returns:
-            [`Owlv2Config`]: An instance of a configuration object
-        """
-        config_dict = {}
-        config_dict["text_config"] = text_config
-        config_dict["vision_config"] = vision_config
-
-        return cls.from_dict(config_dict, **kwargs)
-
 
 __all__ = ["Owlv2Config", "Owlv2TextConfig", "Owlv2VisionConfig"]

src/transformers/models/owlvit/configuration_owlvit.py

@@ -16,7 +16,7 @@
 
 from collections import OrderedDict
 from collections.abc import Mapping
-from typing import TYPE_CHECKING, Any, Dict, Optional
+from typing import TYPE_CHECKING, Any, Optional
 
 
 if TYPE_CHECKING:
@@ -271,21 +271,6 @@ def __init__(
         self.return_dict = return_dict
         self.initializer_factor = 1.0
 
-    @classmethod
-    def from_text_vision_configs(cls, text_config: Dict, vision_config: Dict, **kwargs):
-        r"""
-        Instantiate a [`OwlViTConfig`] (or a derived class) from owlvit text model configuration and owlvit vision
-        model configuration.
-
-        Returns:
-            [`OwlViTConfig`]: An instance of a configuration object
-        """
-        config_dict = {}
-        config_dict["text_config"] = text_config
-        config_dict["vision_config"] = vision_config
-
-        return cls.from_dict(config_dict, **kwargs)
-
 
 class OwlViTOnnxConfig(OnnxConfig):
     @property

src/transformers/models/pix2struct/configuration_pix2struct.py

@@ -332,19 +332,5 @@ def __init__(
 
         self.is_vqa = is_vqa
 
-    @classmethod
-    def from_text_vision_configs(
-        cls, text_config: Pix2StructTextConfig, vision_config: Pix2StructVisionConfig, **kwargs
-    ):
-        r"""
-        Instantiate a [`Pix2StructConfig`] (or a derived class) from pix2struct text model configuration and pix2struct
-        vision model configuration.
-
-        Returns:
-            [`Pix2StructConfig`]: An instance of a configuration object
-        """
-
-        return cls(text_config=text_config.to_dict(), vision_config=vision_config.to_dict(), **kwargs)
-
 
 __all__ = ["Pix2StructConfig", "Pix2StructTextConfig", "Pix2StructVisionConfig"]

src/transformers/models/siglip/configuration_siglip.py

@@ -253,17 +253,5 @@ def __init__(self, text_config=None, vision_config=None, **kwargs):
 
         self.initializer_factor = 1.0
 
-    @classmethod
-    def from_text_vision_configs(cls, text_config: SiglipTextConfig, vision_config: SiglipVisionConfig, **kwargs):
-        r"""
-        Instantiate a [`SiglipConfig`] (or a derived class) from siglip text model configuration and siglip vision
-        model configuration.
-
-        Returns:
-            [`SiglipConfig`]: An instance of a configuration object
-        """
-
-        return cls(text_config=text_config.to_dict(), vision_config=vision_config.to_dict(), **kwargs)
-
 
 __all__ = ["SiglipConfig", "SiglipTextConfig", "SiglipVisionConfig"]

src/transformers/models/siglip2/configuration_siglip2.py

@@ -261,17 +261,5 @@ def __init__(self, text_config=None, vision_config=None, **kwargs):
 
         self.initializer_factor = 1.0
 
-    @classmethod
-    def from_text_vision_configs(cls, text_config: Siglip2TextConfig, vision_config: Siglip2VisionConfig, **kwargs):
-        r"""
-        Instantiate a [`Siglip2Config`] (or a derived class) from siglip2 text model configuration and siglip2 vision
-        model configuration.
-
-        Returns:
-            [`Siglip2Config`]: An instance of a configuration object
-        """
-
-        return cls(text_config=text_config.to_dict(), vision_config=vision_config.to_dict(), **kwargs)
-
 
 __all__ = ["Siglip2Config", "Siglip2TextConfig", "Siglip2VisionConfig"]

src/transformers/models/x_clip/configuration_x_clip.py

@@ -365,17 +365,5 @@ def __init__(
         self.logit_scale_init_value = logit_scale_init_value
         self.initializer_factor = 1.0
 
-    @classmethod
-    def from_text_vision_configs(cls, text_config: XCLIPTextConfig, vision_config: XCLIPVisionConfig, **kwargs):
-        r"""
-        Instantiate a [`XCLIPConfig`] (or a derived class) from xclip text model configuration and xclip vision model
-        configuration.
-
-        Returns:
-            [`XCLIPConfig`]: An instance of a configuration object
-        """
-
-        return cls(text_config=text_config.to_dict(), vision_config=vision_config.to_dict(), **kwargs)
-
 
 __all__ = ["XCLIPConfig", "XCLIPTextConfig", "XCLIPVisionConfig"]

tests/models/align/test_modeling_align.py

@@ -408,8 +408,10 @@ def prepare_config_and_inputs(self):
         return config, input_ids, token_type_ids, input_mask, pixel_values
 
     def get_config(self):
-        return AlignConfig.from_text_vision_configs(
-            self.text_model_tester.get_config(), self.vision_model_tester.get_config(), projection_dim=64
+        return AlignConfig(
+            text_config=self.text_model_tester.get_config().to_dict(),
+            vision_config=self.vision_model_tester.get_config().to_dict(),
+            projection_dim=64,
         )
 
     def create_and_check_model(self, config, input_ids, token_type_ids, attention_mask, pixel_values):

tests/models/altclip/test_modeling_altclip.py

@@ -376,8 +376,10 @@ def prepare_config_and_inputs(self):
         return config, input_ids, attention_mask, pixel_values
 
     def get_config(self):
-        return AltCLIPConfig.from_text_vision_configs(
-            self.text_model_tester.get_config(), self.vision_model_tester.get_config(), projection_dim=64
+        return AltCLIPConfig(
+            text_config=self.text_model_tester.get_config().to_dict(),
+            vision_config=self.vision_model_tester.get_config().to_dict(),
+            projection_dim=64,
         )
 
     def create_and_check_model(self, config, input_ids, attention_mask, pixel_values):