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(
-                f"adapter_config should be an instance of PeftConfig. Got {type(adapter_config)} instead."
-            )
+            raise TypeError(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)}."
             )