[doc] :obj: hunt (#14954)

* redo sans examples

* style

src/transformers/models/vision_encoder_decoder/modeling_vision_encoder_decoder.py

@@ -260,7 +260,7 @@ class VisionEncoderDecoderModel(PreTrainedModel):
         the model, you need to first set it back in training mode with `model.train()`.
 
         Params:
-            encoder_pretrained_model_name_or_path (:obj: *str*, *optional*):
+            encoder_pretrained_model_name_or_path (`str`, *optional*):
                 Information necessary to initiate the image encoder. Can be either:
 
                     - A string, the *model id* of a pretrained model hosted inside a model repo on huggingface.co. An
@@ -272,7 +272,7 @@ class VisionEncoderDecoderModel(PreTrainedModel):
                       `config` argument. This loading path is slower than converting the TensorFlow checkpoint in a
                       PyTorch model using the provided conversion scripts and loading the PyTorch model afterwards.
 
-            decoder_pretrained_model_name_or_path (:obj: *str*, *optional*, defaults to `None`):
+            decoder_pretrained_model_name_or_path (`str`, *optional*, defaults to `None`):
                 Information necessary to initiate the text decoder. Can be either:
 
                     - A string, the *model id* of a pretrained model hosted inside a model repo on huggingface.co.

src/transformers/models/vision_text_dual_encoder/modeling_flax_vision_text_dual_encoder.py

@@ -403,7 +403,7 @@ class FlaxVisionTextDualEncoderModel(FlaxPreTrainedModel):
     ) -> FlaxPreTrainedModel:
         """
         Params:
-            vision_model_name_or_path (:obj: *str*, *optional*, defaults to `None`):
+            vision_model_name_or_path (`str`, *optional*, defaults to `None`):
                 Information necessary to initiate the vision model. Can be either:
 
                     - A string, the *model id* of a pretrained model hosted inside a model repo on huggingface.co.
@@ -416,7 +416,7 @@ class FlaxVisionTextDualEncoderModel(FlaxPreTrainedModel):
                       loading path is slower than converting the PyTorch checkpoint in a Flax model using the provided
                       conversion scripts and loading the Flax model afterwards.
 
-            text_model_name_or_path (:obj: *str*, *optional*):
+            text_model_name_or_path (`str`, *optional*):
                 Information necessary to initiate the text model. Can be either:
 
                     - A string, the *model id* of a pretrained model hosted inside a model repo on huggingface.co.

src/transformers/models/vision_text_dual_encoder/modeling_vision_text_dual_encoder.py

@@ -404,7 +404,7 @@ class VisionTextDualEncoderModel(PreTrainedModel):
     ) -> PreTrainedModel:
         """
         Params:
-            vision_model_name_or_path (:obj: *str*, *optional*, defaults to `None`):
+            vision_model_name_or_path (`str`, *optional*, defaults to `None`):
                 Information necessary to initiate the vision model. Can be either:
 
                     - A string, the *model id* of a pretrained model hosted inside a model repo on huggingface.co.
@@ -417,7 +417,7 @@ class VisionTextDualEncoderModel(PreTrainedModel):
                       loading path is slower than converting the PyTorch checkpoint in a Flax model using the provided
                       conversion scripts and loading the Flax model afterwards.
 
-            text_model_name_or_path (:obj: *str*, *optional*):
+            text_model_name_or_path (`str`, *optional*):
                 Information necessary to initiate the text model. Can be either:
 
                     - A string, the *model id* of a pretrained model hosted inside a model repo on huggingface.co.

src/transformers/models/wav2vec2/configuration_wav2vec2.py

@@ -73,7 +73,7 @@ class Wav2Vec2Config(PretrainedConfig):
         feat_extract_activation (`str, `optional`, defaults to `"gelu"`):
             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 (obj:*float*, *optional*, defaults to 0.0):
+        feat_quantizer_dropout (`float`, *optional*, defaults to 0.0):
             The dropout probabilitiy for quantized feature extractor states.
         conv_dim (`Tuple[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

src/transformers/models/wavlm/configuration_wavlm.py

@@ -72,7 +72,7 @@ class WavLMConfig(PretrainedConfig):
         feat_extract_activation (`str, `optional`, defaults to `"gelu"`):
             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 (obj:*float*, *optional*, defaults to 0.0):
+        feat_quantizer_dropout (`float`, *optional*, defaults to 0.0):
             The dropout probabilitiy for quantized feature extractor states.
         conv_dim (`Tuple[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

src/transformers/models/xlnet/modeling_tf_xlnet.py

@@ -512,15 +512,15 @@ class TFXLNetMainLayer(tf.keras.layers.Layer):
             curr_out = curr_out[: self.reuse_len]
 
         if self.mem_len is None or self.mem_len == 0:
-            # If :obj:`use_mems` is active but no `mem_len` is defined, the model behaves like GPT-2 at inference time
+            # If `use_mems` is active but no `mem_len` is defined, the model behaves like GPT-2 at inference time
             # and returns all of the past and current hidden states.
             cutoff = 0
         else:
-            # If :obj:`use_mems` is active and `mem_len` is defined, the model returns the last `mem_len` hidden
+            # If `use_mems` is active and `mem_len` is defined, the model returns the last `mem_len` hidden
             # states. This is the preferred setting for training and long-form generation.
             cutoff = -self.mem_len
         if prev_mem is None:
-            # if :obj:`use_mems` is active and `mem_len` is defined, the model
+            # if `use_mems` is active and `mem_len` is defined, the model
             new_mem = curr_out[cutoff:]
         else:
             new_mem = tf.concat([prev_mem, curr_out], 0)[cutoff:]

src/transformers/models/xlnet/modeling_xlnet.py

@@ -1000,15 +1000,15 @@ class XLNetModel(XLNetPreTrainedModel):
             curr_out = curr_out[: self.reuse_len]
 
         if self.mem_len is None or self.mem_len == 0:
-            # If :obj:`use_mems` is active but no `mem_len` is defined, the model behaves like GPT-2 at inference time
+            # If `use_mems` is active but no `mem_len` is defined, the model behaves like GPT-2 at inference time
             # and returns all of the past and current hidden states.
             cutoff = 0
         else:
-            # If :obj:`use_mems` is active and `mem_len` is defined, the model returns the last `mem_len` hidden
+            # If `use_mems` is active and `mem_len` is defined, the model returns the last `mem_len` hidden
             # states. This is the preferred setting for training and long-form generation.
             cutoff = -self.mem_len
         if prev_mem is None:
-            # if :obj:`use_mems` is active and `mem_len` is defined, the model
+            # if `use_mems` is active and `mem_len` is defined, the model
             new_mem = curr_out[cutoff:]
         else:
             new_mem = torch.cat([prev_mem, curr_out], dim=0)[cutoff:]

src/transformers/trainer.py

@@ -2466,7 +2466,7 @@ class Trainer:
         ignore_keys: Optional[List[str]] = None,
     ) -> Tuple[Optional[torch.Tensor], Optional[torch.Tensor], Optional[torch.Tensor]]:
         """
-        Perform an evaluation step on `model` using obj:*inputs*.
+        Perform an evaluation step on `model` using `inputs`.
 
         Subclass and override to inject custom behavior.
 

src/transformers/trainer_pt_utils.py

@@ -226,8 +226,8 @@ def torch_distributed_zero_first(local_rank: int):
 
 class DistributedSamplerWithLoop(DistributedSampler):
     """
-    Like a :obj:torch.utils.data.distributed.DistributedSampler` but loops at the end back to the beginning of the
-    shuffled samples to make each process have a round multiple of batch_size samples.
+    Like a torch.utils.data.distributed.DistributedSampler` but loops at the end back to the beginning of the shuffled
+    samples to make each process have a round multiple of batch_size samples.
 
     Args:
         dataset (`torch.utils.data.Dataset`):

src/transformers/trainer_seq2seq.py

@@ -126,7 +126,7 @@ class Seq2SeqTrainer(Trainer):
         ignore_keys: Optional[List[str]] = None,
     ) -> Tuple[Optional[float], Optional[torch.Tensor], Optional[torch.Tensor]]:
         """
-        Perform an evaluation step on `model` using obj:*inputs*.
+        Perform an evaluation step on `model` using `inputs`.
 
         Subclass and override to inject custom behavior.
 

src/transformers/training_args.py

@@ -175,8 +175,8 @@ class TrainingArguments:
         logging_steps (`int`, *optional*, defaults to 500):
             Number of update steps between two logs if `logging_strategy="steps"`.
         logging_nan_inf_filter (`bool`, *optional*, defaults to `True`):
-            Whether to filter `nan` and `inf` losses for logging. If set to obj:`True` the loss of every step that is
-            `nan` or `inf` is filtered and the average loss of the current logging window is taken instead.
+            Whether to filter `nan` and `inf` losses for logging. If set to `True` the loss of every step that is `nan`
+            or `inf` is filtered and the average loss of the current logging window is taken instead.
 
             <Tip>
 

tests/test_doc_samples.py

@@ -45,11 +45,11 @@ class TestCodeExamples(unittest.TestCase):
         the doctests in those files
 
         Args:
-            directory (:obj:`Path`): Directory containing the files
-            identifier (:obj:`str`): Will parse files containing this
-            ignore_files (:obj:`List[str]`): List of files to skip
-            n_identifier (:obj:`str` or :obj:`List[str]`): Will not parse files containing this/these identifiers.
-            only_modules (:obj:`bool`): Whether to only analyze modules
+            directory (`Path`): Directory containing the files
+            identifier (`str`): Will parse files containing this
+            ignore_files (`List[str]`): List of files to skip
+            n_identifier (`str` or `List[str]`): Will not parse files containing this/these identifiers.
+            only_modules (`bool`): Whether to only analyze modules
         """
         files = [file for file in os.listdir(directory) if os.path.isfile(os.path.join(directory, file))]
 

tests/test_modeling_xlnet.py

@@ -556,7 +556,7 @@ class XLNetModelTest(ModelTesterMixin, GenerationTesterMixin, unittest.TestCase)
         self.model_tester.create_and_check_xlnet_base_model(*config_and_inputs)
 
     def test_xlnet_base_model_use_mems(self):
-        # checking that in auto-regressive mode, :obj:`use_mems` gives the same results
+        # checking that in auto-regressive mode, `use_mems` gives the same results
         self.model_tester.set_seed()
         config_and_inputs = self.model_tester.prepare_config_and_inputs()
         self.model_tester.create_and_check_xlnet_model_use_mems(*config_and_inputs)