fix: Fixed raising `TypeError` instead of `ValueError` for invalid type (#32111)

* Raised TypeError instead of ValueError for invalid types.

* Updated formatting using ruff.

* Retrieved few changes.

* Retrieved few changes.

* Updated tests accordingly.

src/transformers/models/clap/modeling_clap.py

@@ -1928,13 +1928,13 @@ class ClapModel(ClapPreTrainedModel):
         super().__init__(config)
 
         if not isinstance(config.text_config, ClapTextConfig):
-            raise ValueError(
+            raise TypeError(
                 "config.text_config is expected to be of type ClapTextConfig but is of type"
                 f" {type(config.text_config)}."
             )
 
         if not isinstance(config.audio_config, ClapAudioConfig):
-            raise ValueError(
+            raise TypeError(
                 "config.audio_config is expected to be of type ClapAudioConfig but is of type"
                 f" {type(config.audio_config)}."
             )

src/transformers/models/clip/modeling_clip.py

@@ -1119,13 +1119,13 @@ class CLIPModel(CLIPPreTrainedModel):
         super().__init__(config)
 
         if not isinstance(config.text_config, CLIPTextConfig):
-            raise ValueError(
+            raise TypeError(
                 "config.text_config is expected to be of type CLIPTextConfig but is of type"
                 f" {type(config.text_config)}."
             )
 
         if not isinstance(config.vision_config, CLIPVisionConfig):
-            raise ValueError(
+            raise TypeError(
                 "config.vision_config is expected to be of type CLIPVisionConfig but is of type"
                 f" {type(config.vision_config)}."
             )

src/transformers/models/clip/modeling_tf_clip.py

@@ -825,13 +825,13 @@ class TFCLIPMainLayer(keras.layers.Layer):
         super().__init__(**kwargs)
 
         if not isinstance(config.text_config, CLIPTextConfig):
-            raise ValueError(
+            raise TypeError(
                 "config.text_config is expected to be of type CLIPTextConfig but is of type"
                 f" {type(config.text_config)}."
             )
 
         if not isinstance(config.vision_config, CLIPVisionConfig):
-            raise ValueError(
+            raise TypeError(
                 "config.vision_config is expected to be of type CLIPVisionConfig but is of type"
                 f" {type(config.vision_config)}."
             )

src/transformers/models/clipseg/modeling_clipseg.py

@@ -924,13 +924,13 @@ class CLIPSegModel(CLIPSegPreTrainedModel):
         super().__init__(config)
 
         if not isinstance(config.text_config, CLIPSegTextConfig):
-            raise ValueError(
+            raise TypeError(
                 "config.text_config is expected to be of type CLIPSegTextConfig but is of type"
                 f" {type(config.text_config)}."
             )
 
         if not isinstance(config.vision_config, CLIPSegVisionConfig):
-            raise ValueError(
+            raise TypeError(
                 "config.vision_config is expected to be of type CLIPSegVisionConfig but is of type"
                 f" {type(config.vision_config)}."
             )

src/transformers/models/clvp/modeling_clvp.py

@@ -1513,19 +1513,19 @@ class ClvpModelForConditionalGeneration(ClvpPreTrainedModel):
         super().__init__(config)
 
         if not isinstance(config.text_config, ClvpEncoderConfig):
-            raise ValueError(
+            raise TypeError(
                 "config.text_config is expected to be of type `ClvpEncoderConfig` but is of type"
                 f" {type(config.text_config)}."
             )
 
         if not isinstance(config.speech_config, ClvpEncoderConfig):
-            raise ValueError(
+            raise TypeError(
                 "config.speech_config is expected to be of type `ClvpEncoderConfig` but is of type"
                 f" {type(config.speech_config)}."
             )
 
         if not isinstance(config.decoder_config, ClvpDecoderConfig):
-            raise ValueError(
+            raise TypeError(
                 "config.decoder_config is expected to be of type `ClvpDecoderConfig` but is of type"
                 f" {type(config.decoder_config)}."
             )

src/transformers/models/deberta_v2/tokenization_deberta_v2.py

@@ -518,4 +518,4 @@ def convert_to_unicode(text):
     elif isinstance(text, bytes):
         return text.decode("utf-8", "ignore")
     else:
-        raise ValueError(f"Unsupported string type: {type(text)}")
+        raise TypeError(f"Unsupported string type: {type(text)}")

src/transformers/models/depth_anything/modeling_depth_anything.py

@@ -298,7 +298,7 @@ class DepthAnythingNeck(nn.Module):
                 List of hidden states from the backbone.
         """
         if not isinstance(hidden_states, (tuple, list)):
-            raise ValueError("hidden_states should be a tuple or list of tensors")
+            raise TypeError("hidden_states should be a tuple or list of tensors")
 
         if len(hidden_states) != len(self.config.neck_hidden_sizes):
             raise ValueError("The number of hidden states should be equal to the number of neck hidden sizes.")

src/transformers/models/dpt/modeling_dpt.py

@@ -1002,7 +1002,7 @@ class DPTNeck(nn.Module):
                 List of hidden states from the backbone.
         """
         if not isinstance(hidden_states, (tuple, list)):
-            raise ValueError("hidden_states should be a tuple or list of tensors")
+            raise TypeError("hidden_states should be a tuple or list of tensors")
 
         if len(hidden_states) != len(self.config.neck_hidden_sizes):
             raise ValueError("The number of hidden states should be equal to the number of neck hidden sizes.")

src/transformers/models/esm/openfold_utils/chunk_utils.py

@@ -32,7 +32,7 @@ def _fetch_dims(tree: Union[dict, list, tuple, torch.Tensor]) -> List[Tuple[int,
     elif isinstance(tree, torch.Tensor):
         shapes.append(tree.shape)
     else:
-        raise ValueError("Not supported")
+        raise TypeError("Not supported")
 
     return shapes
 
@@ -302,7 +302,7 @@ def chunk_layer(
             else:
                 out[i : i + chunk_size] = output_chunk
         else:
-            raise ValueError("Not supported")
+            raise TypeError("Not supported")
 
         i += chunk_size
 

src/transformers/models/esm/openfold_utils/residue_constants.py

@@ -394,7 +394,7 @@ def map_structure_with_atom_order(in_list: list, first_call: bool = True) -> lis
         elif isinstance(in_list[i], str):
             in_list[i] = atom_order[in_list[i]]
         else:
-            raise ValueError("Unexpected type when mapping nested lists!")
+            raise TypeError("Unexpected type when mapping nested lists!")
     return in_list
 
 

src/transformers/models/esm/openfold_utils/tensor_utils.py

@@ -134,7 +134,7 @@ def tree_map(fn, tree, leaf_type):
         return fn(tree)
     else:
         print(type(tree))
-        raise ValueError("Not supported")
+        raise TypeError("Not supported")
 
 
 tensor_tree_map = partial(tree_map, leaf_type=torch.Tensor)

src/transformers/models/flava/modeling_flava.py

@@ -1181,19 +1181,19 @@ class FlavaModel(FlavaPreTrainedModel):
         super().__init__(config)
 
         if not isinstance(config.text_config, FlavaTextConfig):
-            raise ValueError(
+            raise TypeError(
                 "config.text_config is expected to be of type FlavaTextConfig but is of type"
                 f" {type(config.text_config)}."
             )
 
         if not isinstance(config.image_config, FlavaImageConfig):
-            raise ValueError(
+            raise TypeError(
                 "config.image_config is expected to be of type FlavaImageConfig but is of type"
                 f" {type(config.image_config)}."
             )
 
         if not isinstance(config.multimodal_config, FlavaMultimodalConfig):
-            raise ValueError(
+            raise TypeError(
                 "config.multimodal_config is expected to be of type FlavaMultimodalConfig but "
                 + f"is of type {type(config.multimodal_config)}."
             )

src/transformers/models/groupvit/modeling_groupvit.py

@@ -1302,13 +1302,13 @@ class GroupViTModel(GroupViTPreTrainedModel):
         super().__init__(config)
 
         if not isinstance(config.text_config, GroupViTTextConfig):
-            raise ValueError(
+            raise TypeError(
                 "config.text_config is expected to be of type GroupViTTextConfig but is of type"
                 f" {type(config.text_config)}."
             )
 
         if not isinstance(config.vision_config, GroupViTVisionConfig):
-            raise ValueError(
+            raise TypeError(
                 "config.vision_config is expected to be of type GroupViTVisionConfig but is of type"
                 f" {type(config.vision_config)}."
             )

src/transformers/models/groupvit/modeling_tf_groupvit.py

@@ -1443,13 +1443,13 @@ class TFGroupViTMainLayer(keras.layers.Layer):
         super().__init__(**kwargs)
 
         if not isinstance(config.text_config, GroupViTTextConfig):
-            raise ValueError(
+            raise TypeError(
                 "config.text_config is expected to be of type GroupViTTextConfig but is of type"
                 f" {type(config.text_config)}."
             )
 
         if not isinstance(config.vision_config, GroupViTVisionConfig):
-            raise ValueError(
+            raise TypeError(
                 "config.vision_config is expected to be of type GroupViTVisionConfig but is of type"
                 f" {type(config.vision_config)}."
             )

src/transformers/models/llava_next/image_processing_llava_next.py

@@ -513,7 +513,7 @@ class LlavaNextImageProcessor(BaseImageProcessor):
             List[np.array]: A list of NumPy arrays containing the processed image patches.
         """
         if not isinstance(grid_pinpoints, list):
-            raise ValueError("grid_pinpoints must be a list of possible resolutions.")
+            raise TypeError("grid_pinpoints must be a list of possible resolutions.")
 
         possible_resolutions = grid_pinpoints
 

src/transformers/models/llava_next/modeling_llava_next.py

@@ -60,12 +60,12 @@ def get_anyres_image_grid_shape(image_size, grid_pinpoints, patch_size):
         tuple: The shape of the image patch grid in the format (width, height).
     """
     if not isinstance(grid_pinpoints, list):
-        raise ValueError("grid_pinpoints should be a list of tuples or lists")
+        raise TypeError("grid_pinpoints should be a list of tuples or lists")
 
     # ! VERY IMPORTANT if image_size is tensor, must convert to into tuple, otherwise it will cause wrong calculate
     if not isinstance(image_size, (list, tuple)):
         if not isinstance(image_size, (torch.Tensor, np.ndarray)):
-            raise ValueError(
+            raise TypeError(
                 f"image_size invalid type: {type(image_size)} not valid, should be either list, tuple, np.ndarray or tensor"
             )
         image_size = image_size.tolist()
@@ -91,12 +91,12 @@ def image_size_to_num_patches(image_size, grid_pinpoints, patch_size: int):
         int: the number of patches
     """
     if not isinstance(grid_pinpoints, list):
-        raise ValueError("grid_pinpoints should be a list of tuples or lists")
+        raise TypeError("grid_pinpoints should be a list of tuples or lists")
 
     # ! VERY IMPORTANT if image_size is tensor, must convert to into tuple, otherwise it will cause wrong calculate
     if not isinstance(image_size, (list, tuple)):
         if not isinstance(image_size, (torch.Tensor, np.ndarray)):
-            raise ValueError(f"image_size invalid type {type(image_size)} with value {image_size}")
+            raise TypeError(f"image_size invalid type {type(image_size)} with value {image_size}")
         image_size = image_size.tolist()
 
     best_resolution = select_best_resolution(image_size, grid_pinpoints)

src/transformers/models/llava_next_video/modeling_llava_next_video.py

@@ -66,12 +66,12 @@ def get_anyres_image_grid_shape(image_size, grid_pinpoints, patch_size):
         tuple: The shape of the image patch grid in the format (width, height).
     """
     if not isinstance(grid_pinpoints, list):
-        raise ValueError("grid_pinpoints should be a list of tuples or lists")
+        raise TypeError("grid_pinpoints should be a list of tuples or lists")
 
     # ! VERY IMPORTANT if image_size is tensor, must convert to into tuple, otherwise it will cause wrong calculate
     if not isinstance(image_size, (list, tuple)):
         if not isinstance(image_size, (torch.Tensor, np.ndarray)):
-            raise ValueError(
+            raise TypeError(
                 f"image_size invalid type: {type(image_size)} not valid, should be either list, tuple, np.ndarray or tensor"
             )
         image_size = image_size.tolist()
@@ -97,12 +97,12 @@ def image_size_to_num_patches(image_size, grid_pinpoints, patch_size: int):
         int: the number of patches
     """
     if not isinstance(grid_pinpoints, list):
-        raise ValueError("grid_pinpoints should be a list of tuples or lists")
+        raise TypeError("grid_pinpoints should be a list of tuples or lists")
 
     # ! VERY IMPORTANT if image_size is tensor, must convert to into tuple, otherwise it will cause wrong calculate
     if not isinstance(image_size, (list, tuple)):
         if not isinstance(image_size, (torch.Tensor, np.ndarray)):
-            raise ValueError(f"image_size invalid type {type(image_size)} with value {image_size}")
+            raise TypeError(f"image_size invalid type {type(image_size)} with value {image_size}")
         image_size = image_size.tolist()
 
     best_resolution = select_best_resolution(image_size, grid_pinpoints)

src/transformers/models/luke/tokenization_luke.py

@@ -889,7 +889,7 @@ class LukeTokenizer(PreTrainedTokenizer):
 
     def _check_entity_input_format(self, entities: Optional[EntityInput], entity_spans: Optional[EntitySpanInput]):
         if not isinstance(entity_spans, list):
-            raise ValueError("entity_spans should be given as a list")
+            raise TypeError("entity_spans should be given as a list")
         elif len(entity_spans) > 0 and not isinstance(entity_spans[0], tuple):
             raise ValueError(
                 "entity_spans should be given as a list of tuples containing the start and end character indices"

src/transformers/models/mluke/tokenization_mluke.py

@@ -721,7 +721,7 @@ class MLukeTokenizer(PreTrainedTokenizer):
     # Copied from transformers.models.luke.tokenization_luke.LukeTokenizer._check_entity_input_format
     def _check_entity_input_format(self, entities: Optional[EntityInput], entity_spans: Optional[EntitySpanInput]):
         if not isinstance(entity_spans, list):
-            raise ValueError("entity_spans should be given as a list")
+            raise TypeError("entity_spans should be given as a list")
         elif len(entity_spans) > 0 and not isinstance(entity_spans[0], tuple):
             raise ValueError(
                 "entity_spans should be given as a list of tuples containing the start and end character indices"

src/transformers/models/owlv2/modeling_owlv2.py

@@ -1015,13 +1015,13 @@ class Owlv2Model(Owlv2PreTrainedModel):
         super().__init__(config)
 
         if not isinstance(config.text_config, Owlv2TextConfig):
-            raise ValueError(
+            raise TypeError(
                 "config.text_config is expected to be of type Owlv2TextConfig but is of type"
                 f" {type(config.text_config)}."
             )
 
         if not isinstance(config.vision_config, Owlv2VisionConfig):
-            raise ValueError(
+            raise TypeError(
                 "config.vision_config is expected to be of type Owlv2VisionConfig but is of type"
                 f" {type(config.vision_config)}."
             )