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.

examples/research_projects/distillation/grouped_batch_sampler.py

@@ -59,7 +59,7 @@ class GroupedBatchSampler(BatchSampler):
 
     def __init__(self, sampler, group_ids, batch_size):
         if not isinstance(sampler, Sampler):
-            raise ValueError(
+            raise TypeError(
                 "sampler should be an instance of torch.utils.data.Sampler, but got sampler={}".format(sampler)
             )
         self.sampler = sampler

examples/research_projects/tapex/wikisql_utils.py

@@ -48,7 +48,7 @@ def convert_to_float(value):
     if isinstance(value, int):
         return float(value)
     if not isinstance(value, str):
-        raise ValueError("Argument value is not a string. Can't parse it as float")
+        raise TypeError("Argument value is not a string. Can't parse it as float")
     sanitized = value
 
     try:
@@ -158,7 +158,7 @@ def _respect_conditions(table, row, conditions):
             cmp_value = _normalize_for_match(cmp_value)
 
         if not isinstance(table_value, type(cmp_value)):
-            raise ValueError("Type difference {} != {}".format(type(table_value), type(cmp_value)))
+            raise TypeError("Type difference {} != {}".format(type(table_value), type(cmp_value)))
 
         if not _compare(cond.operator, table_value, cmp_value):
             return False

src/transformers/agents/agent_types.py

@@ -107,7 +107,7 @@ class AgentImage(AgentType, ImageType):
         elif isinstance(value, np.ndarray):
             self._tensor = torch.tensor(value)
         else:
-            raise ValueError(f"Unsupported type for {self.__class__.__name__}: {type(value)}")
+            raise TypeError(f"Unsupported type for {self.__class__.__name__}: {type(value)}")
 
     def _ipython_display_(self, include=None, exclude=None):
         """

src/transformers/configuration_utils.py

@@ -1004,7 +1004,7 @@ class PretrainedConfig(PushToHubMixin):
             elif isinstance(old_v, float):
                 v = float(v)
             elif not isinstance(old_v, str):
-                raise ValueError(
+                raise TypeError(
                     f"You can only update int, float, bool or string values in the config, got {v} for key {k}"
                 )
 

src/transformers/data/processors/xnli.py

@@ -47,11 +47,11 @@ class XnliProcessor(DataProcessor):
             text_b = line[1]
             label = "contradiction" if line[2] == "contradictory" else line[2]
             if not isinstance(text_a, str):
-                raise ValueError(f"Training input {text_a} is not a string")
+                raise TypeError(f"Training input {text_a} is not a string")
             if not isinstance(text_b, str):
-                raise ValueError(f"Training input {text_b} is not a string")
+                raise TypeError(f"Training input {text_b} is not a string")
             if not isinstance(label, str):
-                raise ValueError(f"Training label {label} is not a string")
+                raise TypeError(f"Training label {label} is not a string")
             examples.append(InputExample(guid=guid, text_a=text_a, text_b=text_b, label=label))
         return examples
 
@@ -70,11 +70,11 @@ class XnliProcessor(DataProcessor):
             text_b = line[7]
             label = line[1]
             if not isinstance(text_a, str):
-                raise ValueError(f"Training input {text_a} is not a string")
+                raise TypeError(f"Training input {text_a} is not a string")
             if not isinstance(text_b, str):
-                raise ValueError(f"Training input {text_b} is not a string")
+                raise TypeError(f"Training input {text_b} is not a string")
             if not isinstance(label, str):
-                raise ValueError(f"Training label {label} is not a string")
+                raise TypeError(f"Training label {label} is not a string")
             examples.append(InputExample(guid=guid, text_a=text_a, text_b=text_b, label=label))
         return examples
 

src/transformers/generation/beam_constraints.py

@@ -156,7 +156,7 @@ class PhrasalConstraint(Constraint):
 
     def does_advance(self, token_id: int):
         if not isinstance(token_id, int):
-            raise ValueError(f"`token_id` has to be an `int`, but is {token_id} of type {type(token_id)}")
+            raise TypeError(f"`token_id` has to be an `int`, but is {token_id} of type {type(token_id)}")
 
         if self.completed:
             return False
@@ -165,7 +165,7 @@ class PhrasalConstraint(Constraint):
 
     def update(self, token_id: int):
         if not isinstance(token_id, int):
-            raise ValueError(f"`token_id` has to be an `int`, but is {token_id} of type {type(token_id)}")
+            raise TypeError(f"`token_id` has to be an `int`, but is {token_id} of type {type(token_id)}")
 
         stepped = False
         completed = False
@@ -300,7 +300,7 @@ class DisjunctiveConstraint(Constraint):
 
     def does_advance(self, token_id: int):
         if not isinstance(token_id, int):
-            raise ValueError(f"`token_id` is supposed to be type `int`, but is {token_id} of type {type(token_id)}")
+            raise TypeError(f"`token_id` is supposed to be type `int`, but is {token_id} of type {type(token_id)}")
 
         next_tokens = self.trie.next_tokens(self.current_seq)
 
@@ -308,7 +308,7 @@ class DisjunctiveConstraint(Constraint):
 
     def update(self, token_id: int):
         if not isinstance(token_id, int):
-            raise ValueError(f"`token_id` is supposed to be type `int`, but is {token_id} of type {type(token_id)}")
+            raise TypeError(f"`token_id` is supposed to be type `int`, but is {token_id} of type {type(token_id)}")
 
         stepped = False
         completed = False
@@ -432,7 +432,7 @@ class ConstraintListState:
 
     def add(self, token_id: int):
         if not isinstance(token_id, int):
-            raise ValueError(f"`token_id` should be an `int`, but is `{token_id}`.")
+            raise TypeError(f"`token_id` should be an `int`, but is `{token_id}`.")
 
         complete, stepped = False, False
 

src/transformers/generation/utils.py

@@ -4281,7 +4281,7 @@ def _split(data, full_batch_size: int, split_size: int = None):
                 for i in range(0, full_batch_size, split_size)
             ]
     else:
-        raise ValueError(f"Unexpected attribute type: {type(data)}")
+        raise TypeError(f"Unexpected attribute type: {type(data)}")
 
 
 def _split_model_inputs(
@@ -4388,7 +4388,7 @@ def stack_model_outputs(model_outputs: List[ModelOutput]) -> ModelOutput:
             # If the elements are integers or floats, return a tensor
             return torch.tensor(data)
         else:
-            raise ValueError(f"Unexpected attribute type: {type(data[0])}")
+            raise TypeError(f"Unexpected attribute type: {type(data[0])}")
 
     # Use a dictionary comprehension to gather attributes from all objects and concatenate them
     concatenated_data = {

src/transformers/image_processing_base.py

@@ -544,7 +544,7 @@ class ImageProcessingMixin(PushToHubMixin):
             response.raise_for_status()
             return Image.open(BytesIO(response.content))
         else:
-            raise ValueError(f"only a single or a list of entries is supported but got type={type(image_url_or_urls)}")
+            raise TypeError(f"only a single or a list of entries is supported but got type={type(image_url_or_urls)}")
 
 
 ImageProcessingMixin.push_to_hub = copy_func(ImageProcessingMixin.push_to_hub)

src/transformers/image_transforms.py

@@ -75,7 +75,7 @@ def to_channel_dimension_format(
         `np.ndarray`: The image with the channel dimension set to `channel_dim`.
     """
     if not isinstance(image, np.ndarray):
-        raise ValueError(f"Input image must be of type np.ndarray, got {type(image)}")
+        raise TypeError(f"Input image must be of type np.ndarray, got {type(image)}")
 
     if input_channel_dim is None:
         input_channel_dim = infer_channel_dimension_format(image)
@@ -121,7 +121,7 @@ def rescale(
         `np.ndarray`: The rescaled image.
     """
     if not isinstance(image, np.ndarray):
-        raise ValueError(f"Input image must be of type np.ndarray, got {type(image)}")
+        raise TypeError(f"Input image must be of type np.ndarray, got {type(image)}")
 
     rescaled_image = image * scale
     if data_format is not None:
@@ -453,7 +453,7 @@ def center_crop(
     return_numpy = True if return_numpy is None else return_numpy
 
     if not isinstance(image, np.ndarray):
-        raise ValueError(f"Input image must be of type np.ndarray, got {type(image)}")
+        raise TypeError(f"Input image must be of type np.ndarray, got {type(image)}")
 
     if not isinstance(size, Iterable) or len(size) != 2:
         raise ValueError("size must have 2 elements representing the height and width of the output image")

src/transformers/image_utils.py

@@ -377,7 +377,7 @@ def load_image(image: Union[str, "PIL.Image.Image"], timeout: Optional[float] =
     elif isinstance(image, PIL.Image.Image):
         image = image
     else:
-        raise ValueError(
+        raise TypeError(
             "Incorrect format used for image. Should be an url linking to an image, a base64 string, a local path, or a PIL image."
         )
     image = PIL.ImageOps.exif_transpose(image)

src/transformers/integrations/awq.py

@@ -199,7 +199,7 @@ def get_modules_to_fuse(model, quantization_config):
             The quantization configuration to use.
     """
     if not isinstance(model, PreTrainedModel):
-        raise ValueError(f"The model should be an instance of `PreTrainedModel`, got {model.__class__.__name__}")
+        raise TypeError(f"The model should be an instance of `PreTrainedModel`, got {model.__class__.__name__}")
 
     # Always default to `quantization_config.modules_to_fuse`
     if quantization_config.modules_to_fuse is not None:

src/transformers/integrations/peft.py

@@ -262,9 +262,7 @@ class PeftAdapterMixin:
             raise ValueError(f"Adapter with name {adapter_name} already exists. Please use a different name.")
 
         if not isinstance(adapter_config, PeftConfig):
-            raise ValueError(
+            raise TypeError(f"adapter_config should be an instance of PeftConfig. Got {type(adapter_config)} instead.")
-                f"adapter_config should be an instance of PeftConfig. Got {type(adapter_config)} instead."
-            )
 
         # Retrieve the name or path of the model, one could also use self.config._name_or_path
         # but to be consistent with what we do in PEFT: https://github.com/huggingface/peft/blob/6e783780ca9df3a623992cc4d1d665001232eae0/src/peft/mapping.py#L100

src/transformers/modeling_tf_utils.py

@@ -1209,7 +1209,7 @@ class TFPreTrainedModel(keras.Model, TFModelUtilsMixin, TFGenerationMixin, PushT
     def __init__(self, config, *inputs, **kwargs):
         super().__init__(*inputs, **kwargs)
         if not isinstance(config, PretrainedConfig):
-            raise ValueError(
+            raise TypeError(
                 f"Parameter config in `{self.__class__.__name__}(config)` should be an instance of class "
                 "`PretrainedConfig`. To create a model from a pretrained model use "
                 f"`model = {self.__class__.__name__}.from_pretrained(PRETRAINED_MODEL_NAME)`"

src/transformers/models/align/modeling_align.py

@@ -1418,13 +1418,13 @@ class AlignModel(AlignPreTrainedModel):
         super().__init__(config)
 
         if not isinstance(config.text_config, AlignTextConfig):
-            raise ValueError(
+            raise TypeError(
                 "config.text_config is expected to be of type AlignTextConfig but is of type"
                 f" {type(config.text_config)}."
             )
 
         if not isinstance(config.vision_config, AlignVisionConfig):
-            raise ValueError(
+            raise TypeError(
                 "config.vision_config is expected to be of type AlignVisionConfig but is of type"
                 f" {type(config.vision_config)}."
             )

src/transformers/models/altclip/modeling_altclip.py

@@ -1466,12 +1466,12 @@ class AltCLIPModel(AltCLIPPreTrainedModel):
         super().__init__(config)
 
         if not isinstance(config.vision_config, AltCLIPVisionConfig):
-            raise ValueError(
+            raise TypeError(
                 "config.vision_config is expected to be of type AltCLIPVisionConfig but is of type"
                 f" {type(config.vision_config)}."
             )
         if not isinstance(config.text_config, AltCLIPTextConfig):
-            raise ValueError(
+            raise TypeError(
                 "config.text_config is expected to be of type AltCLIPTextConfig but is of type"
                 f" {type(config.text_config)}."
             )

src/transformers/models/bark/processing_bark.py

@@ -211,7 +211,7 @@ class BarkProcessor(ProcessorMixin):
                 raise ValueError(f"Voice preset unrecognized, missing {key} as a key.")
 
             if not isinstance(voice_preset[key], np.ndarray):
-                raise ValueError(f"{key} voice preset must be a {str(self.preset_shape[key])}D ndarray.")
+                raise TypeError(f"{key} voice preset must be a {str(self.preset_shape[key])}D ndarray.")
 
             if len(voice_preset[key].shape) != self.preset_shape[key]:
                 raise ValueError(f"{key} voice preset must be a {str(self.preset_shape[key])}D ndarray.")

src/transformers/models/blip/modeling_blip.py

@@ -755,13 +755,13 @@ class BlipModel(BlipPreTrainedModel):
         super().__init__(config)
 
         if not isinstance(config.text_config, BlipTextConfig):
-            raise ValueError(
+            raise TypeError(
                 "config.text_config is expected to be of type BlipTextConfig but is of type"
                 f" {type(config.text_config)}."
             )
 
         if not isinstance(config.vision_config, BlipVisionConfig):
-            raise ValueError(
+            raise TypeError(
                 "config.vision_config is expected to be of type BlipVisionConfig but is of type"
                 f" {type(config.vision_config)}."
             )

src/transformers/models/blip/modeling_tf_blip.py

@@ -794,13 +794,13 @@ class TFBlipMainLayer(keras.layers.Layer):
         super().__init__(*args, **kwargs)
 
         if not isinstance(config.text_config, BlipTextConfig):
-            raise ValueError(
+            raise TypeError(
                 "config.text_config is expected to be of type BlipTextConfig but is of type"
                 f" {type(config.text_config)}."
             )
 
         if not isinstance(config.vision_config, BlipVisionConfig):
-            raise ValueError(
+            raise TypeError(
                 "config.vision_config is expected to be of type BlipVisionConfig but is of type"
                 f" {type(config.vision_config)}."
             )

src/transformers/models/chameleon/processing_chameleon.py

@@ -113,7 +113,7 @@ class ChameleonProcessor(ProcessorMixin):
         if isinstance(text, str):
             text = [text]
         elif not isinstance(text, list) and not isinstance(text[0], str):
-            raise ValueError("Invalid input text. Please provide a string, or a list of strings")
+            raise TypeError("Invalid input text. Please provide a string, or a list of strings")
 
         # Replace the image token with the expanded image token sequence
         prompt_strings = []

src/transformers/models/chinese_clip/modeling_chinese_clip.py

@@ -1341,13 +1341,13 @@ class ChineseCLIPModel(ChineseCLIPPreTrainedModel):
         super().__init__(config)
 
         if not isinstance(config.text_config, ChineseCLIPTextConfig):
-            raise ValueError(
+            raise TypeError(
                 "config.text_config is expected to be of type ChineseCLIPTextConfig but is of type"
                 f" {type(config.text_config)}."
             )
 
         if not isinstance(config.vision_config, ChineseCLIPVisionConfig):
-            raise ValueError(
+            raise TypeError(
                 "config.vision_config is expected to be of type ChineseCLIPVisionConfig but is of type"
                 f" {type(config.vision_config)}."
             )

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)}."
             )

src/transformers/models/owlvit/modeling_owlvit.py

@@ -998,13 +998,13 @@ class OwlViTModel(OwlViTPreTrainedModel):
         super().__init__(config)
 
         if not isinstance(config.text_config, OwlViTTextConfig):
-            raise ValueError(
+            raise TypeError(
                 "config.text_config is expected to be of type OwlViTTextConfig but is of type"
                 f" {type(config.text_config)}."
             )
 
         if not isinstance(config.vision_config, OwlViTVisionConfig):
-            raise ValueError(
+            raise TypeError(
                 "config.vision_config is expected to be of type OwlViTVisionConfig but is of type"
                 f" {type(config.vision_config)}."
             )

src/transformers/models/rag/retrieval_rag.py

@@ -204,7 +204,7 @@ class HFIndexBase(Index):
 
     def _check_dataset_format(self, with_index: bool):
         if not isinstance(self.dataset, Dataset):
-            raise ValueError(f"Dataset should be a datasets.Dataset object, but got {type(self.dataset)}")
+            raise TypeError(f"Dataset should be a datasets.Dataset object, but got {type(self.dataset)}")
         if len({"title", "text", "embeddings"} - set(self.dataset.column_names)) > 0:
             raise ValueError(
                 "Dataset should be a dataset with the following columns: "

src/transformers/models/siglip/modeling_siglip.py

@@ -1202,13 +1202,13 @@ class SiglipModel(SiglipPreTrainedModel):
         super().__init__(config)
 
         if not isinstance(config.text_config, SiglipTextConfig):
-            raise ValueError(
+            raise TypeError(
                 "config.text_config is expected to be of type SiglipTextConfig but is of type"
                 f" {type(config.text_config)}."
             )
 
         if not isinstance(config.vision_config, SiglipVisionConfig):
-            raise ValueError(
+            raise TypeError(
                 "config.vision_config is expected to be of type SiglipVisionConfig but is of type"
                 f" {type(config.vision_config)}."
             )

src/transformers/models/udop/configuration_udop.py

@@ -135,7 +135,7 @@ class UdopConfig(PretrainedConfig):
         self.patch_size = patch_size
         self.num_channels = num_channels
         if not isinstance(relative_bias_args, list):
-            raise ValueError("`relative_bias_args` should be a list of dictionaries.")
+            raise TypeError("`relative_bias_args` should be a list of dictionaries.")
         self.relative_bias_args = relative_bias_args
 
         act_info = self.feed_forward_proj.split("-")

src/transformers/models/wav2vec2_with_lm/processing_wav2vec2_with_lm.py

@@ -92,7 +92,7 @@ class Wav2Vec2ProcessorWithLM(ProcessorMixin):
 
         super().__init__(feature_extractor, tokenizer)
         if not isinstance(decoder, BeamSearchDecoderCTC):
-            raise ValueError(f"`decoder` has to be of type {BeamSearchDecoderCTC.__class__}, but is {type(decoder)}")
+            raise TypeError(f"`decoder` has to be of type {BeamSearchDecoderCTC.__class__}, but is {type(decoder)}")
 
         if feature_extractor.__class__.__name__ not in ["Wav2Vec2FeatureExtractor", "SeamlessM4TFeatureExtractor"]:
             raise ValueError(

src/transformers/models/x_clip/modeling_x_clip.py

@@ -1242,13 +1242,13 @@ class XCLIPModel(XCLIPPreTrainedModel):
         super().__init__(config)
 
         if not isinstance(config.text_config, XCLIPTextConfig):
-            raise ValueError(
+            raise TypeError(
                 "config.text_config is expected to be of type XCLIPTextConfig but is of type"
                 f" {type(config.text_config)}."
             )
 
         if not isinstance(config.vision_config, XCLIPVisionConfig):
-            raise ValueError(
+            raise TypeError(
                 "config.vision_config is expected to be of type XCLIPVisionConfig but is of type"
                 f" {type(config.vision_config)}."
             )

src/transformers/models/zoedepth/modeling_zoedepth.py

@@ -334,7 +334,7 @@ class ZoeDepthNeck(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/pipelines/audio_classification.py

@@ -190,7 +190,7 @@ class AudioClassificationPipeline(Pipeline):
                 ).numpy()
 
         if not isinstance(inputs, np.ndarray):
-            raise ValueError("We expect a numpy ndarray as input")
+            raise TypeError("We expect a numpy ndarray as input")
         if len(inputs.shape) != 1:
             raise ValueError("We expect a single channel audio input for AudioClassificationPipeline")
 

src/transformers/pipelines/automatic_speech_recognition.py

@@ -406,7 +406,7 @@ class AutomaticSpeechRecognitionPipeline(ChunkPipeline):
                 # of the original length in the stride so we can cut properly.
                 stride = (inputs.shape[0], int(round(stride[0] * ratio)), int(round(stride[1] * ratio)))
         if not isinstance(inputs, np.ndarray):
-            raise ValueError(f"We expect a numpy ndarray as input, got `{type(inputs)}`")
+            raise TypeError(f"We expect a numpy ndarray as input, got `{type(inputs)}`")
         if len(inputs.shape) != 1:
             raise ValueError("We expect a single channel audio input for AutomaticSpeechRecognitionPipeline")
 

src/transformers/pipelines/zero_shot_audio_classification.py

@@ -114,7 +114,7 @@ class ZeroShotAudioClassificationPipeline(Pipeline):
             audio = ffmpeg_read(audio, self.feature_extractor.sampling_rate)
 
         if not isinstance(audio, np.ndarray):
-            raise ValueError("We expect a numpy ndarray as input")
+            raise TypeError("We expect a numpy ndarray as input")
         if len(audio.shape) != 1:
             raise ValueError("We expect a single channel audio input for ZeroShotAudioClassificationPipeline")
 

src/transformers/processing_utils.py

@@ -356,7 +356,7 @@ class ProcessorMixin(PushToHubMixin):
                 proper_class = getattr(transformers_module, class_name)
 
             if not isinstance(arg, proper_class):
-                raise ValueError(
+                raise TypeError(
                     f"Received a {type(arg).__name__} for argument {attribute_name}, but a {class_name} was expected."
                 )
 

src/transformers/tokenization_utils.py

@@ -474,7 +474,7 @@ class PreTrainedTokenizer(PreTrainedTokenizerBase):
         # Always raise an error if string because users should define the behavior
         for index, token in value.items():
             if not isinstance(token, (str, AddedToken)) or not isinstance(index, int):
-                raise ValueError(
+                raise TypeError(
                     f"The provided `added_tokens_decoder` has an element of type {index.__class__, token.__class__}, should be a dict of {int, Union[AddedToken, str]}"
                 )
 

src/transformers/utils/quantization_config.py

@@ -405,7 +405,7 @@ class BitsAndBytesConfig(QuantizationConfigMixin):
     @load_in_4bit.setter
     def load_in_4bit(self, value: bool):
         if not isinstance(value, bool):
-            raise ValueError("load_in_4bit must be a boolean")
+            raise TypeError("load_in_4bit must be a boolean")
 
         if self.load_in_8bit and value:
             raise ValueError("load_in_4bit and load_in_8bit are both True, but only one can be used at the same time")
@@ -418,7 +418,7 @@ class BitsAndBytesConfig(QuantizationConfigMixin):
     @load_in_8bit.setter
     def load_in_8bit(self, value: bool):
         if not isinstance(value, bool):
-            raise ValueError("load_in_8bit must be a boolean")
+            raise TypeError("load_in_8bit must be a boolean")
 
         if self.load_in_4bit and value:
             raise ValueError("load_in_4bit and load_in_8bit are both True, but only one can be used at the same time")
@@ -429,30 +429,30 @@ class BitsAndBytesConfig(QuantizationConfigMixin):
         Safety checker that arguments are correct - also replaces some NoneType arguments with their default values.
         """
         if not isinstance(self.load_in_4bit, bool):
-            raise ValueError("load_in_4bit must be a boolean")
+            raise TypeError("load_in_4bit must be a boolean")
 
         if not isinstance(self.load_in_8bit, bool):
-            raise ValueError("load_in_8bit must be a boolean")
+            raise TypeError("load_in_8bit must be a boolean")
 
         if not isinstance(self.llm_int8_threshold, float):
-            raise ValueError("llm_int8_threshold must be a float")
+            raise TypeError("llm_int8_threshold must be a float")
 
         if self.llm_int8_skip_modules is not None and not isinstance(self.llm_int8_skip_modules, list):
-            raise ValueError("llm_int8_skip_modules must be a list of strings")
+            raise TypeError("llm_int8_skip_modules must be a list of strings")
         if not isinstance(self.llm_int8_enable_fp32_cpu_offload, bool):
-            raise ValueError("llm_int8_enable_fp32_cpu_offload must be a boolean")
+            raise TypeError("llm_int8_enable_fp32_cpu_offload must be a boolean")
 
         if not isinstance(self.llm_int8_has_fp16_weight, bool):
-            raise ValueError("llm_int8_has_fp16_weight must be a boolean")
+            raise TypeError("llm_int8_has_fp16_weight must be a boolean")
 
         if self.bnb_4bit_compute_dtype is not None and not isinstance(self.bnb_4bit_compute_dtype, torch.dtype):
-            raise ValueError("bnb_4bit_compute_dtype must be torch.dtype")
+            raise TypeError("bnb_4bit_compute_dtype must be torch.dtype")
 
         if not isinstance(self.bnb_4bit_quant_type, str):
-            raise ValueError("bnb_4bit_quant_type must be a string")
+            raise TypeError("bnb_4bit_quant_type must be a string")
 
         if not isinstance(self.bnb_4bit_use_double_quant, bool):
-            raise ValueError("bnb_4bit_use_double_quant must be a boolean")
+            raise TypeError("bnb_4bit_use_double_quant must be a boolean")
 
         if self.load_in_4bit and not version.parse(importlib.metadata.version("bitsandbytes")) >= version.parse(
             "0.39.0"
@@ -957,13 +957,13 @@ class AqlmConfig(QuantizationConfigMixin):
         Safety checker that arguments are correct - also replaces some NoneType arguments with their default values.
         """
         if not isinstance(self.in_group_size, int):
-            raise ValueError("in_group_size must be a float")
+            raise TypeError("in_group_size must be a float")
         if not isinstance(self.out_group_size, int):
-            raise ValueError("out_group_size must be a float")
+            raise TypeError("out_group_size must be a float")
         if not isinstance(self.num_codebooks, int):
-            raise ValueError("num_codebooks must be a float")
+            raise TypeError("num_codebooks must be a float")
         if not isinstance(self.nbits_per_codebook, int):
-            raise ValueError("nbits_per_codebook must be a float")
+            raise TypeError("nbits_per_codebook must be a float")
 
         if self.linear_weights_not_to_quantize is not None and not isinstance(
             self.linear_weights_not_to_quantize, list

tests/agents/test_tools_common.py

@@ -60,7 +60,7 @@ def output_type(output):
     elif isinstance(output, (torch.Tensor, AgentAudio)):
         return "audio"
     else:
-        raise ValueError(f"Invalid output: {output}")
+        raise TypeError(f"Invalid output: {output}")
 
 
 @is_agent_test

tests/models/luke/test_tokenization_luke.py

@@ -188,7 +188,7 @@ class LukeTokenizerTest(TokenizerTesterMixin, unittest.TestCase):
         with self.assertRaises(ValueError):
             tokenizer(sentence, entities=tuple(entities), entity_spans=spans)
 
-        with self.assertRaises(ValueError):
+        with self.assertRaises(TypeError):
             tokenizer(sentence, entities=entities, entity_spans=tuple(spans))
 
         with self.assertRaises(ValueError):

tests/models/mluke/test_tokenization_mluke.py

@@ -151,7 +151,7 @@ class MLukeTokenizerTest(TokenizerTesterMixin, unittest.TestCase):
         with self.assertRaises(ValueError):
             tokenizer(sentence, entities=tuple(entities), entity_spans=spans)
 
-        with self.assertRaises(ValueError):
+        with self.assertRaises(TypeError):
             tokenizer(sentence, entities=entities, entity_spans=tuple(spans))
 
         with self.assertRaises(ValueError):

tests/pipelines/test_pipelines_feature_extraction.py

@@ -171,7 +171,7 @@ class FeatureExtractionPipelineTests(unittest.TestCase):
         elif isinstance(input_, float):
             return 0
         else:
-            raise ValueError("We expect lists of floats, nothing else")
+            raise TypeError("We expect lists of floats, nothing else")
         return shape
 
     def get_test_pipeline(self, model, tokenizer, processor, torch_dtype="float32"):

tests/test_pipeline_mixin.py

@@ -145,7 +145,7 @@ class PipelineTesterMixin:
         if not isinstance(model_architectures, tuple):
             model_architectures = (model_architectures,)
         if not isinstance(model_architectures, tuple):
-            raise ValueError(f"`model_architectures` must be a tuple. Got {type(model_architectures)} instead.")
+            raise TypeError(f"`model_architectures` must be a tuple. Got {type(model_architectures)} instead.")
 
         for model_architecture in model_architectures:
             model_arch_name = model_architecture.__name__