Fix typo in all model docs (#7714)

src/transformers/modeling_albert.py

@@ -539,7 +539,7 @@ ALBERT_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         token_type_ids (:obj:`torch.LongTensor` of shape :obj:`({0})`, `optional`):

src/transformers/modeling_bart.py

@@ -113,7 +113,7 @@ BART_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         decoder_input_ids (:obj:`torch.LongTensor` of shape :obj:`(batch_size, target_sequence_length)`, `optional`):

src/transformers/modeling_bert_generation.py

@@ -218,7 +218,7 @@ BERT_GENERATION_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         position_ids (:obj:`torch.LongTensor` of shape :obj:`({0})`, `optional`):
@@ -450,7 +450,7 @@ class BertGenerationDecoder(BertGenerationPreTrainedModel):
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
         labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Labels for computing the left-to-right language modeling loss (next word prediction).
             Indices should be in ``[-100, 0, ..., config.vocab_size]`` (see ``input_ids`` docstring)

src/transformers/modeling_ctrl.py

@@ -273,7 +273,7 @@ CTRL_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         token_type_ids (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):

src/transformers/modeling_distilbert.py

@@ -401,7 +401,7 @@ DISTILBERT_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         head_mask (:obj:`torch.FloatTensor` of shape :obj:`(num_heads,)` or :obj:`(num_layers, num_heads)`, `optional`):

src/transformers/modeling_dpr.py

@@ -358,7 +358,7 @@ DPR_ENCODERS_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         token_type_ids (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
@@ -403,7 +403,7 @@ DPR_READER_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         inputs_embeds (:obj:`torch.FloatTensor` of shape :obj:`(n_passages, sequence_length, hidden_size)`, `optional`):

src/transformers/modeling_electra.py

@@ -611,7 +611,7 @@ ELECTRA_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         token_type_ids (:obj:`torch.LongTensor` of shape :obj:`({0})`, `optional`):

src/transformers/modeling_encoder_decoder.py

@@ -74,7 +74,7 @@ ENCODER_DECODER_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         decoder_input_ids (:obj:`torch.LongTensor` of shape :obj:`(batch_size, target_sequence_length)`, `optional`):

src/transformers/modeling_flaubert.py

@@ -81,7 +81,7 @@ FLAUBERT_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         token_type_ids (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):

src/transformers/modeling_fsmt.py

@@ -224,7 +224,7 @@ FSMT_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         decoder_input_ids (:obj:`torch.LongTensor` of shape :obj:`(batch_size, target_sequence_length)`, `optional`):

src/transformers/modeling_funnel.py

@@ -857,7 +857,7 @@ FUNNEL_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         token_type_ids (:obj:`torch.LongTensor` of shape :obj:`({0})`, `optional`):

src/transformers/modeling_gpt2.py

@@ -429,7 +429,7 @@ GPT2_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         token_type_ids (:obj:`torch.LongTensor` of shape :obj:`(batch_size, input_ids_length)`, `optional`):

src/transformers/modeling_longformer.py

@@ -1018,7 +1018,7 @@ LONGFORMER_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         global_attention_mask (:obj:`torch.FloatTensor` of shape :obj:`({0})`, `optional`):

src/transformers/modeling_lxmert.py

@@ -848,7 +848,7 @@ LXMERT_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         visual_attention_mask (:obj:`torch.FloatTensor` of shape :obj:`({0})`, `optional`):
@@ -856,7 +856,7 @@ LXMERT_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         token_type_ids (:obj:`torch.LongTensor` of shape :obj:`({0})`, `optional`):

src/transformers/modeling_mmbt.py

@@ -123,7 +123,7 @@ MMBT_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         token_type_ids (`optional`) ``torch.LongTensor`` of shape ``(batch_size, sequence_length)``:
@@ -167,7 +167,7 @@ MMBT_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
         output_attentions (:obj:`bool`, `optional`):
             Whether or not to return the attentions tensors of all attention layers. See ``attentions`` under returned

src/transformers/modeling_mobilebert.py

@@ -756,7 +756,7 @@ MOBILEBERT_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         token_type_ids (:obj:`torch.LongTensor` of shape :obj:`({0})`, `optional`):
@@ -792,7 +792,7 @@ MOBILEBERT_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
         output_attentions (:obj:`bool`, `optional`):
             Whether or not to return the attentions tensors of all attention layers. See ``attentions`` under returned

src/transformers/modeling_openai.py

@@ -360,7 +360,7 @@ OPENAI_GPT_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         token_type_ids (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):

src/transformers/modeling_rag.py

@@ -406,7 +406,7 @@ RAG_FORWARD_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         encoder_outputs (:obj:`tuple(tuple(torch.FloatTensor)`, `optional`)
@@ -836,7 +836,7 @@ class RagSequenceForGeneration(RagPreTrainedModel):
                 Mask values selected in ``[0, 1]``:
 
                 - 1 for tokens that are **not masked**,
-                - 0 for tokens that are **maked**.
+                - 0 for tokens that are **masked**.
 
                 `What are attention masks? <../glossary.html#attention-mask>`__
             context_input_ids (:obj:`torch.LongTensor` of shape :obj:`(batch_size * config.n_docs, config.max_combined_length)`, `optional`, returned when `output_retrieved=True`):
@@ -1221,7 +1221,7 @@ class RagTokenForGeneration(RagPreTrainedModel):
                 Mask values selected in ``[0, 1]``:
 
                 - 1 for tokens that are **not masked**,
-                - 0 for tokens that are **maked**.
+                - 0 for tokens that are **masked**.
 
                 `What are attention masks? <../glossary.html#attention-mask>`__
             context_input_ids (:obj:`torch.LongTensor` of shape :obj:`(batch_size * config.n_docs, config.max_combined_length)`, `optional`, returned when `output_retrieved=True`):

src/transformers/modeling_reformer.py

@@ -1926,7 +1926,7 @@ REFORMER_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         position_ids (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):

src/transformers/modeling_retribert.py

@@ -185,7 +185,7 @@ class RetriBertModel(RetriBertPreTrainedModel):
                 Mask values selected in ``[0, 1]``:
 
                 - 1 for tokens that are **not masked**,
-                - 0 for tokens that are **maked**.
+                - 0 for tokens that are **masked**.
 
                 `What are attention masks? <../glossary.html#attention-mask>`__
             input_ids_doc (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`):