Clean-up deprecated code (#33446)

* update

* update modeling

src/transformers/models/fuyu/configuration_fuyu.py

@@ -14,8 +14,6 @@
 # limitations under the License.
 """Fuyu model configuration"""
 
-import warnings
-
 from ...configuration_utils import PretrainedConfig
 from ...utils import logging
 from ..auto import CONFIG_MAPPING
@@ -207,20 +205,3 @@ def _rope_scaling_validation(self):
             )
         if rope_scaling_factor is None or not isinstance(rope_scaling_factor, float) or rope_scaling_factor <= 1.0:
             raise ValueError(f"`rope_scaling`'s factor field must be a float > 1, got {rope_scaling_factor}")
-
-    @property
-    def vocab_size(self):
-        warnings.warn(
-            "The `vocab_size` attribute is deprecated and will be removed in v4.44, Please use `text_config.vocab_size` instead.",
-            FutureWarning,
-        )
-        return self._vocab_size
-
-    @vocab_size.setter
-    def vocab_size(self, value):
-        self._vocab_size = value
-
-    def to_dict(self):
-        output = super().to_dict()
-        output.pop("_vocab_size", None)
-        return output

src/transformers/models/fuyu/modeling_fuyu.py

@@ -183,15 +183,6 @@ def get_decoder(self):
     def tie_weights(self):
         return self.language_model.tie_weights()
 
-    def resize_token_embeddings(self, new_num_tokens: Optional[int] = None, pad_to_multiple_of=None) -> nn.Embedding:
-        # TODO: config.vocab_size is deprecated and will be removed in v4.43.
-        # `resize_token_embeddings` should work from `modeling_utils.py``
-        model_embeds = self.language_model.resize_token_embeddings(new_num_tokens, pad_to_multiple_of)
-        self.config.text_config.vocab_size = model_embeds.num_embeddings
-        self.config.vocab_size = model_embeds.num_embeddings
-        self.vocab_size = model_embeds.num_embeddings
-        return model_embeds
-
     def gather_continuous_embeddings(
         self,
         word_embeddings: torch.Tensor,
@@ -254,8 +245,8 @@ def forward(
         r"""
         labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
                 Labels for computing the masked language modeling loss. Indices should either be in `[0, ...,
-                config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
-                (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`.
+                config.text_config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
+                (masked), the loss is only computed for the tokens with labels in `[0, ..., config.text_config.vocab_size]`.
 
         Returns:
 

src/transformers/models/paligemma/configuration_paligemma.py

@@ -141,20 +141,7 @@ def ignore_index(self):
     def ignore_index(self, value):
         self._ignore_index = value
 
-    @property
-    def vocab_size(self):
-        warnings.warn(
-            "The `vocab_size` attribute is deprecated and will be removed in v4.44, Please use `text_config.vocab_size` instead.",
-            FutureWarning,
-        )
-        return self._vocab_size
-
-    @vocab_size.setter
-    def vocab_size(self, value):
-        self._vocab_size = value
-
     def to_dict(self):
         output = super().to_dict()
-        output.pop("_vocab_size", None)
         output.pop("_ignore_index", None)
         return output

src/transformers/models/paligemma/modeling_paligemma.py

@@ -53,7 +53,7 @@ class PaliGemmaCausalLMOutputWithPast(ModelOutput):
     Args:
         loss (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided):
             Language modeling loss (for next-token prediction).
-        logits (`torch.FloatTensor` of shape `(batch_size, sequence_length, config.vocab_size)`):
+        logits (`torch.FloatTensor` of shape `(batch_size, sequence_length, config.text_config.vocab_size)`):
             Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
         past_key_values (`tuple(tuple(torch.FloatTensor))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`):
             Tuple of `tuple(torch.FloatTensor)` of length `config.n_layers`, with each tuple having 2 tensors of shape
@@ -283,15 +283,6 @@ def get_decoder(self):
     def tie_weights(self):
         return self.language_model.tie_weights()
 
-    def resize_token_embeddings(self, new_num_tokens: Optional[int] = None, pad_to_multiple_of=None) -> nn.Embedding:
-        # TODO: config.vocab_size is deprecated and will be removed in v4.43.
-        # `resize_token_embeddings` should work from `modeling_utils.py``
-        model_embeds = self.language_model.resize_token_embeddings(new_num_tokens, pad_to_multiple_of)
-        self.config.text_config.vocab_size = model_embeds.num_embeddings
-        self.config.vocab_size = model_embeds.num_embeddings
-        self.vocab_size = model_embeds.num_embeddings
-        return model_embeds
-
     def _update_causal_mask(
         self, attention_mask, token_type_ids, inputs_embeds, past_key_values, cache_position, is_training: bool = False
     ):
@@ -362,8 +353,8 @@ def forward(
         Args:
             labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
                 Labels for computing the masked language modeling loss. Indices should either be in `[0, ...,
-                config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
-                (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`.
+                config.text_config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
+                (masked), the loss is only computed for the tokens with labels in `[0, ..., config.text_config.vocab_size]`.
 
             num_logits_to_keep (`int`, *optional*):
                 Calculate logits for the last `num_logits_to_keep` tokens. If `0`, calculate logits for all