[configuration] remove redundant classmethod (#38812)

* remove redundant classmethod

* warning message, add space between words

* fix tests

* fix copies

src/transformers/configuration_utils.py

@@ -1199,6 +1199,42 @@ class PretrainedConfig(PushToHubMixin):
             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/aimv2/configuration_aimv2.py

@@ -280,17 +280,5 @@ class Aimv2Config(PretrainedConfig):
         self.logit_scale_init_value = logit_scale_init_value
         self.max_logit_scale = 100.0
 
-    @classmethod
-    def from_text_vision_configs(cls, text_config: Aimv2TextConfig, vision_config: Aimv2VisionConfig, **kwargs):
-        r"""
-        Instantiate a [`Aimv2Config`] (or a derived class) from aimv2 text model configuration and aimv2 vision
-        model configuration.
-
-        Returns:
-            [`Aimv2Config`]: An instance of a configuration object
-        """
-
-        return cls(text_config=text_config.to_dict(), vision_config=vision_config.to_dict(), **kwargs)
-
 
 __all__ = ["Aimv2Config", "Aimv2VisionConfig", "Aimv2TextConfig"]

src/transformers/models/align/configuration_align.py

@@ -327,17 +327,5 @@ class AlignConfig(PretrainedConfig):
         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 @@ class AltCLIPConfig(PretrainedConfig):
         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 @@ class BlipConfig(PretrainedConfig):
         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 @@ class BridgeTowerConfig(PretrainedConfig):
         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 @@ class ChineseCLIPConfig(PretrainedConfig):
         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 @@ class ClapConfig(PretrainedConfig):
         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 @@ class CLIPConfig(PretrainedConfig):
         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 @@ class CLIPSegConfig(PretrainedConfig):
         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 @@ class GroupViTConfig(PretrainedConfig):
         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/pix2struct/configuration_pix2struct.py

@@ -332,19 +332,5 @@ class Pix2StructConfig(PretrainedConfig):
 
         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 @@ class SiglipConfig(PretrainedConfig):
 
         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 @@ class Siglip2Config(PretrainedConfig):
 
         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 @@ class XCLIPConfig(PretrainedConfig):
         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 @@ class AlignModelTester:
         return config, input_ids, token_type_ids, input_mask, pixel_values
 
     def get_config(self):
-        return AlignConfig.from_text_vision_configs(
+        return AlignConfig(
-            self.text_model_tester.get_config(), self.vision_model_tester.get_config(), projection_dim=64
+            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 @@ class AltCLIPModelTester:
         return config, input_ids, attention_mask, pixel_values
 
     def get_config(self):
-        return AltCLIPConfig.from_text_vision_configs(
+        return AltCLIPConfig(
-            self.text_model_tester.get_config(), self.vision_model_tester.get_config(), projection_dim=64
+            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):

tests/models/blip/test_modeling_blip.py

@@ -381,8 +381,10 @@ class BlipModelTester:
         return config, input_ids, attention_mask, pixel_values
 
     def get_config(self):
-        return BlipConfig.from_text_vision_configs(
+        return BlipConfig(
-            self.text_model_tester.get_config(), self.vision_model_tester.get_config(), projection_dim=64
+            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):
@@ -664,8 +666,10 @@ class BlipTextRetrievalModelTester:
         return config, input_ids, attention_mask, pixel_values
 
     def get_config(self):
-        return BlipConfig.from_text_vision_configs(
+        return BlipConfig(
-            self.text_model_tester.get_config(), self.vision_model_tester.get_config(), projection_dim=64
+            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):
@@ -713,8 +717,10 @@ class BlipTextImageModelsModelTester:
         return config, input_ids, attention_mask, pixel_values
 
     def get_config(self):
-        return BlipConfig.from_text_vision_configs(
+        return BlipConfig(
-            self.text_model_tester.get_config(), self.vision_model_tester.get_config(), projection_dim=64
+            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):
@@ -761,8 +767,10 @@ class BlipVQAModelTester:
         return config, input_ids, attention_mask, pixel_values
 
     def get_config(self):
-        return BlipConfig.from_text_vision_configs(
+        return BlipConfig(
-            self.text_model_tester.get_config(), self.vision_model_tester.get_config(), projection_dim=64
+            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):

tests/models/bridgetower/test_modeling_bridgetower.py

@@ -203,9 +203,9 @@ class BridgeTowerModelTester:
         return (config, input_ids, attention_mask, pixel_values, pixel_mask)
 
     def get_config(self):
-        return BridgeTowerConfig.from_text_vision_configs(
+        return BridgeTowerConfig(
-            text_config=self.text_model_tester.get_config(),
+            text_config=self.text_model_tester.get_config().to_dict(),
-            vision_config=self.vision_model_tester.get_config(),
+            vision_config=self.vision_model_tester.get_config().to_dict(),
             share_cross_modal_transformer_layers=self.share_cross_modal_transformer_layers,
             share_link_tower_layers=self.share_link_tower_layers,
             link_tower_type=self.link_tower_type,

tests/models/chinese_clip/test_modeling_chinese_clip.py

@@ -515,8 +515,10 @@ class ChineseCLIPModelTester:
         return config, input_ids, token_type_ids, attention_mask, pixel_values
 
     def get_config(self):
-        return ChineseCLIPConfig.from_text_vision_configs(
+        return ChineseCLIPConfig(
-            self.text_model_tester.get_config(), self.vision_model_tester.get_config(), projection_dim=64
+            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/clap/test_modeling_clap.py

@@ -459,8 +459,10 @@ class ClapModelTester:
         return config, input_ids, attention_mask, input_features
 
     def get_config(self):
-        return ClapConfig.from_text_audio_configs(
+        return ClapConfig(
-            self.text_model_tester.get_config(), self.audio_model_tester.get_config(), projection_dim=64
+            text_config=self.text_model_tester.get_config().to_dict(),
+            audio_config=self.audio_model_tester.get_config().to_dict(),
+            projection_dim=64,
         )
 
     def create_and_check_model(self, config, input_ids, attention_mask, input_features):

tests/models/clip/test_modeling_clip.py

@@ -502,8 +502,10 @@ class CLIPModelTester:
         return config, input_ids, attention_mask, pixel_values
 
     def get_config(self):
-        return CLIPConfig.from_text_vision_configs(
+        return CLIPConfig(
-            self.text_model_tester.get_config(), self.vision_model_tester.get_config(), projection_dim=64
+            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):

tests/models/clipseg/test_modeling_clipseg.py

@@ -374,9 +374,9 @@ class CLIPSegModelTester:
         return config, input_ids, attention_mask, pixel_values
 
     def get_config(self):
-        return CLIPSegConfig.from_text_vision_configs(
+        return CLIPSegConfig(
-            self.text_model_tester.get_config(),
+            text_config=self.text_model_tester.get_config().to_dict(),
-            self.vision_model_tester.get_config(),
+            vision_config=self.vision_model_tester.get_config().to_dict(),
             projection_dim=64,
             reduce_dim=32,
             extract_layers=self.extract_layers,

tests/models/efficientloftr/test_modeling_efficientloftr.py

@@ -216,7 +216,7 @@ class EfficientLoFTRModelTest(ModelTesterMixin, unittest.TestCase):
 
             self.assertListEqual(
                 list(hidden_states[0].shape[-2:]),
-                [self.model_tester.image_height // 2, self.model_tester.image_width // 2],
+                [self.model_tester.image_height, self.model_tester.image_width],
             )
 
         config, inputs_dict = self.model_tester.prepare_config_and_inputs_for_common()

tests/models/groupvit/test_modeling_groupvit.py

@@ -497,8 +497,10 @@ class GroupViTModelTester:
         return config, input_ids, attention_mask, pixel_values
 
     def get_config(self):
-        return GroupViTConfig.from_text_vision_configs(
+        return GroupViTConfig(
-            self.text_model_tester.get_config(), self.vision_model_tester.get_config(), projection_dim=64
+            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):

tests/models/owlv2/test_modeling_owlv2.py

@@ -375,7 +375,11 @@ class Owlv2ModelTester:
         return config, input_ids, attention_mask, pixel_values
 
     def get_config(self):
-        return Owlv2Config.from_text_vision_configs(self.text_config, self.vision_config, projection_dim=64)
+        return Owlv2Config(
+            text_config=self.text_config,
+            vision_config=self.vision_config,
+            projection_dim=64,
+        )
 
     def create_and_check_model(self, config, input_ids, attention_mask, pixel_values):
         model = Owlv2Model(config).to(torch_device).eval()
@@ -589,7 +593,11 @@ class Owlv2ForObjectDetectionTester:
         return config, pixel_values, input_ids, attention_mask
 
     def get_config(self):
-        return Owlv2Config.from_text_vision_configs(self.text_config, self.vision_config, projection_dim=64)
+        return Owlv2Config(
+            text_config=self.text_config,
+            vision_config=self.vision_config,
+            projection_dim=64,
+        )
 
     def create_and_check_model(self, config, pixel_values, input_ids, attention_mask):
         model = Owlv2ForObjectDetection(config).to(torch_device).eval()

tests/models/owlvit/test_modeling_owlvit.py

@@ -371,7 +371,11 @@ class OwlViTModelTester:
         return config, input_ids, attention_mask, pixel_values
 
     def get_config(self):
-        return OwlViTConfig.from_text_vision_configs(self.text_config, self.vision_config, projection_dim=64)
+        return OwlViTConfig(
+            text_config=self.text_config,
+            vision_config=self.vision_config,
+            projection_dim=64,
+        )
 
     def create_and_check_model(self, config, input_ids, attention_mask, pixel_values):
         model = OwlViTModel(config).to(torch_device).eval()
@@ -583,7 +587,11 @@ class OwlViTForObjectDetectionTester:
         return config, pixel_values, input_ids, attention_mask
 
     def get_config(self):
-        return OwlViTConfig.from_text_vision_configs(self.text_config, self.vision_config, projection_dim=64)
+        return OwlViTConfig(
+            text_config=self.text_config,
+            vision_config=self.vision_config,
+            projection_dim=64,
+        )
 
     def create_and_check_model(self, config, pixel_values, input_ids, attention_mask):
         model = OwlViTForObjectDetection(config).to(torch_device).eval()

tests/models/pix2struct/test_modeling_pix2struct.py

@@ -383,7 +383,11 @@ class Pix2StructModelTester:
         return config, input_ids, attention_mask, flattened_patches
 
     def get_config(self, text_config, vision_config):
-        return Pix2StructConfig.from_text_vision_configs(text_config, vision_config, projection_dim=64)
+        return Pix2StructConfig(
+            text_config=self.text_model_tester.get_config().to_dict(),
+            vision_config=self.vision_model_tester.get_config().to_dict(),
+            projection_dim=64,
+        )
 
     def prepare_config_and_inputs_for_common(self):
         config_and_inputs = self.prepare_config_and_inputs()

tests/models/siglip/test_modeling_siglip.py

@@ -428,9 +428,9 @@ class SiglipModelTester:
         return config, input_ids, attention_mask, pixel_values
 
     def get_config(self):
-        return SiglipConfig.from_text_vision_configs(
+        return SiglipConfig(
-            self.text_model_tester.get_config(),
+            text_config=self.text_model_tester.get_config().to_dict(),
-            self.vision_model_tester.get_config(),
+            vision_config=self.vision_model_tester.get_config().to_dict(),
         )
 
     def create_and_check_model(self, config, input_ids, attention_mask, pixel_values):

tests/models/siglip2/test_modeling_siglip2.py

@@ -514,9 +514,9 @@ class Siglip2ModelTester:
         return config, input_ids, attention_mask, pixel_values, pixel_attention_mask, spatial_shapes
 
     def get_config(self):
-        return Siglip2Config.from_text_vision_configs(
+        return Siglip2Config(
-            self.text_model_tester.get_config(),
+            text_config=self.text_model_tester.get_config().to_dict(),
-            self.vision_model_tester.get_config(),
+            vision_config=self.vision_model_tester.get_config().to_dict(),
         )
 
     def create_and_check_model(

tests/models/x_clip/test_modeling_x_clip.py

@@ -493,9 +493,9 @@ class XCLIPModelTester:
         return config, input_ids, attention_mask, pixel_values
 
     def get_config(self):
-        return XCLIPConfig.from_text_vision_configs(
+        return XCLIPConfig(
-            self.text_model_tester.get_config(),
+            text_config=self.text_model_tester.get_config().to_dict(),
-            self.vision_model_tester.get_config(),
+            vision_config=self.vision_model_tester.get_config().to_dict(),
             projection_dim=self.projection_dim,
         )