[Docs] Fix spelling and grammar mistakes (#28825)

* Fix typos and grammar mistakes in docs and examples

* Fix typos in docstrings and comments

* Fix spelling of `tokenizer` in model tests

* Remove erroneous spaces in decorators

* Remove extra spaces in Markdown link texts

src/transformers/models/pix2struct/configuration_pix2struct.py

@@ -59,7 +59,7 @@ class Pix2StructTextConfig(PretrainedConfig):
         relative_attention_max_distance (`int`, *optional*, defaults to 128):
             The maximum distance of the longer sequences for the bucket separation.
         dropout_rate (`float`, *optional*, defaults to 0.1):
-            The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
         layer_norm_epsilon (`float`, *optional*, defaults to 1e-6):
             The epsilon used by the layer normalization layers.
         initializer_factor (`float`, *optional*, defaults to 1.0):
@@ -199,7 +199,7 @@ class Pix2StructVisionConfig(PretrainedConfig):
         layer_norm_eps (`float`, *optional*, defaults to 1e-06):
             The epsilon used by the layer normalization layers.
         dropout_rate (`float`, *optional*, defaults to 0.0):
-            The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
         attention_dropout (`float`, *optional*, defaults to 0.0):
             The dropout ratio for the attention probabilities.
         initializer_range (`float`, *optional*, defaults to 1e-10):

src/transformers/models/qdqbert/configuration_qdqbert.py

@@ -53,7 +53,7 @@ class QDQBertConfig(PretrainedConfig):
             The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
             `"relu"`, `"selu"` and `"gelu_new"` are supported.
         hidden_dropout_prob (`float`, *optional*, defaults to 0.1):
-            The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
         attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1):
             The dropout ratio for the attention probabilities.
         max_position_embeddings (`int`, *optional*, defaults to 512):

src/transformers/models/qwen2/tokenization_qwen2.py

@@ -88,7 +88,7 @@ class Qwen2Tokenizer(PreTrainedTokenizer):
     """
     Construct a Qwen2 tokenizer. Based on byte-level Byte-Pair-Encoding.
 
-    Same with GPT2Tokenzier, this tokenizer has been trained to treat spaces like parts of the tokens so a word will
+    Same with GPT2Tokenizer, this tokenizer has been trained to treat spaces like parts of the tokens so a word will
     be encoded differently whether it is at the beginning of the sentence (without space) or not:
 
     ```python

src/transformers/models/qwen2/tokenization_qwen2_fast.py

@@ -46,7 +46,7 @@ class Qwen2TokenizerFast(PreTrainedTokenizerFast):
     Construct a "fast" Qwen2 tokenizer (backed by HuggingFace's *tokenizers* library). Based on byte-level
     Byte-Pair-Encoding.
 
-    Same with GPT2Tokenzier, this tokenizer has been trained to treat spaces like parts of the tokens so a word will
+    Same with GPT2Tokenizer, this tokenizer has been trained to treat spaces like parts of the tokens so a word will
     be encoded differently whether it is at the beginning of the sentence (without space) or not:
 
     ```python

src/transformers/models/realm/configuration_realm.py

@@ -82,7 +82,7 @@ class RealmConfig(PretrainedConfig):
             The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
             `"relu"`, `"selu"` and `"gelu_new"` are supported.
         hidden_dropout_prob (`float`, *optional*, defaults to 0.1):
-            The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
         attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1):
             The dropout ratio for the attention probabilities.
         max_position_embeddings (`int`, *optional*, defaults to 512):

src/transformers/models/rembert/configuration_rembert.py

@@ -62,7 +62,7 @@ class RemBertConfig(PretrainedConfig):
             The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
             `"relu"`, `"selu"` and `"gelu_new"` are supported.
         hidden_dropout_prob (`float`, *optional*, defaults to 0):
-            The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
         attention_probs_dropout_prob (`float`, *optional*, defaults to 0):
             The dropout ratio for the attention probabilities.
         classifier_dropout_prob (`float`, *optional*, defaults to 0.1):

src/transformers/models/roc_bert/configuration_roc_bert.py

@@ -52,7 +52,7 @@ class RoCBertConfig(PretrainedConfig):
             The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
             `"relu"`, `"selu"` and `"gelu_new"` are supported.
         hidden_dropout_prob (`float`, *optional*, defaults to 0.1):
-            The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
         attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1):
             The dropout ratio for the attention probabilities.
         max_position_embeddings (`int`, *optional*, defaults to 512):

src/transformers/models/roformer/configuration_roformer.py

@@ -72,7 +72,7 @@ class RoFormerConfig(PretrainedConfig):
             The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
             `"relu"`, `"selu"` and `"gelu_new"` are supported.
         hidden_dropout_prob (`float`, *optional*, defaults to 0.1):
-            The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
         attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1):
             The dropout ratio for the attention probabilities.
         max_position_embeddings (`int`, *optional*, defaults to 1536):

src/transformers/models/seamless_m4t/configuration_seamless_m4t.py

@@ -223,7 +223,7 @@ class SeamlessM4TConfig(PretrainedConfig):
         variance_predictor_kernel_size (`int`, *optional*, defaults to 3):
             Kernel size of the duration predictor. Applies to the vocoder only.
         var_pred_dropout (`float`, *optional*, defaults to 0.5):
-            The dropout probabilitiy of the duration predictor. Applies to the vocoder only.
+            The dropout probability of the duration predictor. Applies to the vocoder only.
         vocoder_offset (`int`, *optional*, defaults to 4):
             Offset the unit token ids by this number to account for symbol tokens. Applies to the vocoder only.
 

src/transformers/models/seamless_m4t_v2/configuration_seamless_m4t_v2.py

@@ -183,7 +183,7 @@ class SeamlessM4Tv2Config(PretrainedConfig):
         t2u_variance_predictor_kernel_size (`int`, *optional*, defaults to 3):
             Kernel size of the convolutional layers of the text-to-unit's duration predictor.
         t2u_variance_pred_dropout (`float`, *optional*, defaults to 0.5):
-            The dropout probabilitiy of the text-to-unit's duration predictor.
+            The dropout probability of the text-to-unit's duration predictor.
 
          > Hifi-Gan Vocoder specific parameters
 
@@ -225,7 +225,7 @@ class SeamlessM4Tv2Config(PretrainedConfig):
         variance_predictor_kernel_size (`int`, *optional*, defaults to 3):
             Kernel size of the duration predictor. Applies to the vocoder only.
         var_pred_dropout (`float`, *optional*, defaults to 0.5):
-            The dropout probabilitiy of the duration predictor. Applies to the vocoder only.
+            The dropout probability of the duration predictor. Applies to the vocoder only.
         vocoder_offset (`int`, *optional*, defaults to 4):
             Offset the unit token ids by this number to account for symbol tokens. Applies to the vocoder only.
 

src/transformers/models/splinter/configuration_splinter.py

@@ -56,7 +56,7 @@ class SplinterConfig(PretrainedConfig):
             The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
             `"relu"`, `"selu"` and `"gelu_new"` are supported.
         hidden_dropout_prob (`float`, *optional*, defaults to 0.1):
-            The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
         attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1):
             The dropout ratio for the attention probabilities.
         max_position_embeddings (`int`, *optional*, defaults to 512):

src/transformers/models/timesformer/configuration_timesformer.py

@@ -57,7 +57,7 @@ class TimesformerConfig(PretrainedConfig):
             The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
             `"relu"`, `"selu"` and `"gelu_new"` are supported.
         hidden_dropout_prob (`float`, *optional*, defaults to 0.0):
-            The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
         attention_probs_dropout_prob (`float`, *optional*, defaults to 0.0):
             The dropout ratio for the attention probabilities.
         initializer_range (`float`, *optional*, defaults to 0.02):

src/transformers/models/tvlt/configuration_tvlt.py

@@ -64,7 +64,7 @@ class TvltConfig(PretrainedConfig):
             The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
             `"relu"`, `"selu"` and `"gelu_new"` are supported.
         hidden_dropout_prob (`float`, *optional*, defaults to 0.0):
-            The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
         attention_probs_dropout_prob (`float`, *optional*, defaults to 0.0):
             The dropout ratio for the attention probabilities.
         initializer_range (`float`, *optional*, defaults to 0.02):

src/transformers/models/unispeech/configuration_unispeech.py

@@ -68,7 +68,7 @@ class UniSpeechConfig(PretrainedConfig):
         feat_proj_dropout (`float`, *optional*, defaults to 0.0):
             The dropout probability for output of the feature encoder.
         feat_quantizer_dropout (`float`, *optional*, defaults to 0.0):
-            The dropout probabilitiy for the output of the feature encoder that's used by the quantizer.
+            The dropout probability for the output of the feature encoder that's used by the quantizer.
         final_dropout (`float`, *optional*, defaults to 0.1):
             The dropout probability for the final projection layer of [`UniSpeechForCTC`].
         layerdrop (`float`, *optional*, defaults to 0.1):

src/transformers/models/unispeech_sat/configuration_unispeech_sat.py

@@ -69,7 +69,7 @@ class UniSpeechSatConfig(PretrainedConfig):
         feat_proj_dropout (`float`, *optional*, defaults to 0.0):
             The dropout probability for output of the feature encoder.
         feat_quantizer_dropout (`float`, *optional*, defaults to 0.0):
-            The dropout probabilitiy for the output of the feature encoder that's used by the quantizer.
+            The dropout probability for the output of the feature encoder that's used by the quantizer.
         final_dropout (`float`, *optional*, defaults to 0.1):
             The dropout probability for the final projection layer of [`UniSpeechSatForCTC`].
         layerdrop (`float`, *optional*, defaults to 0.1):

src/transformers/models/videomae/configuration_videomae.py

@@ -58,7 +58,7 @@ class VideoMAEConfig(PretrainedConfig):
             The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
             `"relu"`, `"selu"` and `"gelu_new"` are supported.
         hidden_dropout_prob (`float`, *optional*, defaults to 0.0):
-            The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
         attention_probs_dropout_prob (`float`, *optional*, defaults to 0.0):
             The dropout ratio for the attention probabilities.
         initializer_range (`float`, *optional*, defaults to 0.02):

src/transformers/models/vilt/configuration_vilt.py

@@ -59,7 +59,7 @@ class ViltConfig(PretrainedConfig):
             The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
             `"relu"`, `"selu"` and `"gelu_new"` are supported.
         hidden_dropout_prob (`float`, *optional*, defaults to 0.0):
-            The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
         attention_probs_dropout_prob (`float`, *optional*, defaults to 0.0):
             The dropout ratio for the attention probabilities.
         initializer_range (`float`, *optional*, defaults to 0.02):

src/transformers/models/visual_bert/configuration_visual_bert.py

@@ -71,7 +71,7 @@ class VisualBertConfig(PretrainedConfig):
             The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
             `"relu"`, `"selu"` and `"gelu_new"` are supported.
         hidden_dropout_prob (`float`, *optional*, defaults to 0.1):
-            The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
         attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1):
             The dropout ratio for the attention probabilities.
         max_position_embeddings (`int`, *optional*, defaults to 512):

src/transformers/models/vit_mae/configuration_vit_mae.py

@@ -50,7 +50,7 @@ class ViTMAEConfig(PretrainedConfig):
             The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
             `"relu"`, `"selu"` and `"gelu_new"` are supported.
         hidden_dropout_prob (`float`, *optional*, defaults to 0.0):
-            The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
         attention_probs_dropout_prob (`float`, *optional*, defaults to 0.0):
             The dropout ratio for the attention probabilities.
         initializer_range (`float`, *optional*, defaults to 0.02):

src/transformers/models/wav2vec2/configuration_wav2vec2.py

@@ -82,7 +82,7 @@ class Wav2Vec2Config(PretrainedConfig):
             The non-linear activation function (function or string) in the 1D convolutional layers of the feature
             extractor. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` are supported.
         feat_quantizer_dropout (`float`, *optional*, defaults to 0.0):
-            The dropout probabilitiy for quantized feature encoder states.
+            The dropout probability for quantized feature encoder states.
         conv_dim (`Tuple[int]` or `List[int]`, *optional*, defaults to `(512, 512, 512, 512, 512, 512, 512)`):
             A tuple of integers defining the number of input and output channels of each 1D convolutional layer in the
             feature encoder. The length of *conv_dim* defines the number of 1D convolutional layers.
@@ -140,7 +140,7 @@ class Wav2Vec2Config(PretrainedConfig):
         contrastive_logits_temperature (`float`, *optional*, defaults to 0.1):
             The temperature *kappa* in the contrastive loss.
         feat_quantizer_dropout (`float`, *optional*, defaults to 0.0):
-            The dropout probabilitiy for the output of the feature encoder that's used by the quantizer.
+            The dropout probability for the output of the feature encoder that's used by the quantizer.
         num_negatives (`int`, *optional*, defaults to 100):
             Number of negative samples for the contrastive loss.
         codevector_dim (`int`, *optional*, defaults to 256):