Remove deprecated (#8604)

* Remove old deprecated arguments

Co-authored-by: LysandreJik <lysandre.debut@reseau.eseo.fr>

* Remove needless imports

* Fix tests

Co-authored-by: LysandreJik <lysandre.debut@reseau.eseo.fr>

src/transformers/models/roberta/modeling_roberta.py

@@ -16,7 +16,6 @@
 """PyTorch RoBERTa model. """
 
 import math
-import warnings
 
 import torch
 import torch.nn as nn
@@ -872,7 +871,6 @@ class RobertaForMaskedLM(RobertaPreTrainedModel):
         output_attentions=None,
         output_hidden_states=None,
         return_dict=None,
-        **kwargs
     ):
         r"""
         labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
@@ -882,13 +880,6 @@ class RobertaForMaskedLM(RobertaPreTrainedModel):
         kwargs (:obj:`Dict[str, any]`, optional, defaults to `{}`):
             Used to hide legacy arguments that have been deprecated.
         """
-        if "masked_lm_labels" in kwargs:
-            warnings.warn(
-                "The `masked_lm_labels` argument is deprecated and will be removed in a future version, use `labels` instead.",
-                FutureWarning,
-            )
-            labels = kwargs.pop("masked_lm_labels")
-        assert kwargs == {}, f"Unexpected keyword arguments: {list(kwargs.keys())}."
         return_dict = return_dict if return_dict is not None else self.config.use_return_dict
 
         outputs = self.roberta(

src/transformers/models/roberta/tokenization_roberta.py

@@ -14,7 +14,6 @@
 # limitations under the License.
 """Tokenization classes for RoBERTa."""
 
-import warnings
 from typing import List, Optional
 
 from ...tokenization_utils import AddedToken
@@ -251,13 +250,6 @@ class RobertaTokenizer(GPT2Tokenizer):
         return len(cls + token_ids_0 + sep + sep + token_ids_1 + sep) * [0]
 
     def prepare_for_tokenization(self, text, is_split_into_words=False, **kwargs):
-        if "is_pretokenized" in kwargs:
-            warnings.warn(
-                "`is_pretokenized` is deprecated and will be removed in a future version, use `is_split_into_words` instead.",
-                FutureWarning,
-            )
-            is_split_into_words = kwargs.pop("is_pretokenized")
-
         add_prefix_space = kwargs.pop("add_prefix_space", self.add_prefix_space)
         if (is_split_into_words or add_prefix_space) and (len(text) > 0 and not text[0].isspace()):
             text = " " + text