Result of new doc style with fixes (huggingface#17015)

* Result of new doc style with fixes

* Add last two files

* Bump hf-doc-builder

Author: sgugger

docs/source/en/model_doc/bert-generation.mdx

@@ -49,7 +49,7 @@ Usage:
 
 >>> input_ids = tokenizer(
 ...     "This is a long article to summarize", add_special_tokens=False, return_tensors="pt"
->>> ).input_ids
+... ).input_ids
 >>> labels = tokenizer("This is a short summary", return_tensors="pt").input_ids
 
 >>> # train...
@@ -67,7 +67,7 @@ Usage:
 
 >>> input_ids = tokenizer(
 ...     "This is the first sentence. This is the second sentence.", add_special_tokens=False, return_tensors="pt"
->>> ).input_ids
+... ).input_ids
 
 >>> outputs = sentence_fuser.generate(input_ids)
 

docs/source/en/model_doc/luke.mdx

@@ -97,7 +97,7 @@ Example:
 >>> entities = [
 ...     "Beyoncé",
 ...     "Los Angeles",
->>> ]  # Wikipedia entity titles corresponding to the entity mentions "Beyoncé" and "Los Angeles"
+... ]  # Wikipedia entity titles corresponding to the entity mentions "Beyoncé" and "Los Angeles"
 >>> entity_spans = [(0, 7), (17, 28)]  # character-based entity spans corresponding to "Beyoncé" and "Los Angeles"
 >>> inputs = tokenizer(text, entities=entities, entity_spans=entity_spans, add_prefix_space=True, return_tensors="pt")
 >>> outputs = model(**inputs)

setup.py

@@ -111,7 +111,7 @@
     "ftfy",
     "fugashi>=1.0",
     "GitPython<3.1.19",
-    "hf-doc-builder>=0.2.0",
+    "hf-doc-builder>=0.3.0",
     "huggingface-hub>=0.1.0,<1.0",
     "importlib_metadata",
     "ipadic>=1.0.0,<2.0",

src/transformers/dependency_versions_table.py

@@ -18,7 +18,7 @@
     "ftfy": "ftfy",
     "fugashi": "fugashi>=1.0",
     "GitPython": "GitPython<3.1.19",
-    "hf-doc-builder": "hf-doc-builder>=0.2.0",
+    "hf-doc-builder": "hf-doc-builder>=0.3.0",
     "huggingface-hub": "huggingface-hub>=0.1.0,<1.0",
     "importlib_metadata": "importlib_metadata",
     "ipadic": "ipadic>=1.0.0,<2.0",

src/transformers/models/encoder_decoder/modeling_encoder_decoder.py

@@ -457,7 +457,7 @@ def forward(
         >>> tokenizer = BertTokenizer.from_pretrained("bert-base-uncased")
         >>> model = EncoderDecoderModel.from_encoder_decoder_pretrained(
         ...     "bert-base-uncased", "bert-base-uncased"
-        >>> )  # initialize Bert2Bert from pre-trained checkpoints
+        ... )  # initialize Bert2Bert from pre-trained checkpoints
 
         >>> # training
         >>> model.config.decoder_start_token_id = tokenizer.cls_token_id

src/transformers/models/encoder_decoder/modeling_tf_encoder_decoder.py

@@ -528,7 +528,7 @@ def call(
         >>> # forward
         >>> input_ids = tokenizer.encode(
         ...     "Hello, my dog is cute", add_special_tokens=True, return_tensors="tf"
-        >>> )  # Batch size 1
+        ... )  # Batch size 1
         >>> outputs = model(input_ids=input_ids, decoder_input_ids=input_ids)
 
         >>> # training

src/transformers/models/gpt2/modeling_tf_gpt2.py

@@ -1061,7 +1061,7 @@ def call(
 
         >>> embedding_layer = model.resize_token_embeddings(
         ...     len(tokenizer)
-        >>> )  # Update the model embeddings with the new vocabulary size
+        ... )  # Update the model embeddings with the new vocabulary size
 
         >>> choices = ["Hello, my dog is cute [CLS]", "Hello, my cat is cute [CLS]"]
         >>> encoded_choices = [tokenizer.encode(s) for s in choices]

src/transformers/models/imagegpt/modeling_imagegpt.py

@@ -1000,7 +1000,7 @@ def forward(
         >>> samples = output[:, 1:].cpu().detach().numpy()
         >>> samples_img = [
         ...     np.reshape(np.rint(127.5 * (clusters[s] + 1.0)), [n_px, n_px, 3]).astype(np.uint8) for s in samples
-        >>> ]  # convert color cluster tokens back to pixels
+        ... ]  # convert color cluster tokens back to pixels
         >>> f, axes = plt.subplots(1, batch_size, dpi=300)
 
         >>> for img, ax in zip(samples_img, axes):

src/transformers/models/longformer/modeling_longformer.py

@@ -1634,18 +1634,18 @@ def forward(
 
         >>> attention_mask = torch.ones(
         ...     input_ids.shape, dtype=torch.long, device=input_ids.device
-        >>> )  # initialize to local attention
+        ... )  # initialize to local attention
         >>> global_attention_mask = torch.zeros(
         ...     input_ids.shape, dtype=torch.long, device=input_ids.device
-        >>> )  # initialize to global attention to be deactivated for all tokens
+        ... )  # initialize to global attention to be deactivated for all tokens
         >>> global_attention_mask[
         ...     :,
         ...     [
         ...         1,
         ...         4,
         ...         21,
         ...     ],
-        >>> ] = 1  # Set global attention to random tokens for the sake of this example
+        ... ] = 1  # Set global attention to random tokens for the sake of this example
         >>> # Usually, set global attention based on the task. For example,
         >>> # classification: the <s> token
         >>> # QA: question tokens
@@ -2025,7 +2025,7 @@ def forward(
         >>> answer_tokens = all_tokens[torch.argmax(start_logits) : torch.argmax(end_logits) + 1]
         >>> answer = tokenizer.decode(
         ...     tokenizer.convert_tokens_to_ids(answer_tokens)
-        >>> )  # remove space prepending space token
+        ... )  # remove space prepending space token
         ```"""
         return_dict = return_dict if return_dict is not None else self.config.use_return_dict
 

src/transformers/models/luke/modeling_luke.py

@@ -953,11 +953,11 @@ def forward(
         >>> entities = [
         ...     "Beyoncé",
         ...     "Los Angeles",
-        >>> ]  # Wikipedia entity titles corresponding to the entity mentions "Beyoncé" and "Los Angeles"
+        ... ]  # Wikipedia entity titles corresponding to the entity mentions "Beyoncé" and "Los Angeles"
         >>> entity_spans = [
         ...     (0, 7),
         ...     (17, 28),
-        >>> ]  # character-based entity spans corresponding to "Beyoncé" and "Los Angeles"
+        ... ]  # character-based entity spans corresponding to "Beyoncé" and "Los Angeles"
 
         >>> encoding = tokenizer(
         ...     text, entities=entities, entity_spans=entity_spans, add_prefix_space=True, return_tensors="pt"
@@ -1435,7 +1435,7 @@ def forward(
         >>> entity_spans = [
         ...     (0, 7),
         ...     (17, 28),
-        >>> ]  # character-based entity spans corresponding to "Beyoncé" and "Los Angeles"
+        ... ]  # character-based entity spans corresponding to "Beyoncé" and "Los Angeles"
         >>> inputs = tokenizer(text, entity_spans=entity_spans, return_tensors="pt")
         >>> outputs = model(**inputs)
         >>> logits = outputs.logits