Add prefix to examples in model_doc rst (#11226)

* Add prefix to examples in model_doc rst

* Apply suggestions from code review

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

docs/source/model_doc/bertgeneration.rst

@@ -38,22 +38,22 @@ Usage:
 
 .. code-block::
 
-    # leverage checkpoints for Bert2Bert model...
+    >>> # leverage checkpoints for Bert2Bert model...
-    # use BERT's cls token as BOS token and sep token as EOS token
+    >>> # use BERT's cls token as BOS token and sep token as EOS token
-    encoder = BertGenerationEncoder.from_pretrained("bert-large-uncased", bos_token_id=101, eos_token_id=102)
+    >>> encoder = BertGenerationEncoder.from_pretrained("bert-large-uncased", bos_token_id=101, eos_token_id=102)
-    # add cross attention layers and use BERT's cls token as BOS token and sep token as EOS token
+    >>> # add cross attention layers and use BERT's cls token as BOS token and sep token as EOS token
-    decoder = BertGenerationDecoder.from_pretrained("bert-large-uncased", add_cross_attention=True, is_decoder=True, bos_token_id=101, eos_token_id=102)
+    >>> decoder = BertGenerationDecoder.from_pretrained("bert-large-uncased", add_cross_attention=True, is_decoder=True, bos_token_id=101, eos_token_id=102)
-    bert2bert = EncoderDecoderModel(encoder=encoder, decoder=decoder)
+    >>> bert2bert = EncoderDecoderModel(encoder=encoder, decoder=decoder)
 
-    # create tokenizer...
+    >>> # create tokenizer...
-    tokenizer = BertTokenizer.from_pretrained("bert-large-uncased")
+    >>> tokenizer = BertTokenizer.from_pretrained("bert-large-uncased")
 
-    input_ids = tokenizer('This is a long article to summarize', add_special_tokens=False, return_tensors="pt").input_ids
+    >>> input_ids = tokenizer('This is a long article to summarize', add_special_tokens=False, return_tensors="pt").input_ids
-    labels = tokenizer('This is a short summary', return_tensors="pt").input_ids
+    >>> labels = tokenizer('This is a short summary', return_tensors="pt").input_ids
 
-    # train...
+    >>> # train...
-    loss = bert2bert(input_ids=input_ids, decoder_input_ids=labels, labels=labels).loss
+    >>> loss = bert2bert(input_ids=input_ids, decoder_input_ids=labels, labels=labels).loss
-    loss.backward()
+    >>> loss.backward()
 
 
 - Pretrained :class:`~transformers.EncoderDecoderModel` are also directly available in the model hub, e.g.,
@@ -61,15 +61,15 @@ Usage:
 
 .. code-block::
 
-    # instantiate sentence fusion model
+    >>> # instantiate sentence fusion model
-    sentence_fuser = EncoderDecoderModel.from_pretrained("google/roberta2roberta_L-24_discofuse")
+    >>> sentence_fuser = EncoderDecoderModel.from_pretrained("google/roberta2roberta_L-24_discofuse")
-    tokenizer = AutoTokenizer.from_pretrained("google/roberta2roberta_L-24_discofuse")
+    >>> tokenizer = AutoTokenizer.from_pretrained("google/roberta2roberta_L-24_discofuse")
 
-    input_ids = tokenizer('This is the first sentence. This is the second sentence.', add_special_tokens=False, return_tensors="pt").input_ids
+    >>> input_ids = tokenizer('This is the first sentence. This is the second sentence.', add_special_tokens=False, return_tensors="pt").input_ids
 
-    outputs = sentence_fuser.generate(input_ids)
+    >>> outputs = sentence_fuser.generate(input_ids)
 
-    print(tokenizer.decode(outputs[0]))
+    >>> print(tokenizer.decode(outputs[0]))
 
 
 Tips:

docs/source/model_doc/bertweet.rst

@@ -31,28 +31,28 @@ Example of use:
 
 .. code-block::
 
-    import torch
+    >>> import torch
-    from transformers import AutoModel, AutoTokenizer 
+    >>> from transformers import AutoModel, AutoTokenizer 
 
-    bertweet = AutoModel.from_pretrained("vinai/bertweet-base")
+    >>> bertweet = AutoModel.from_pretrained("vinai/bertweet-base")
 
-    # For transformers v4.x+: 
+    >>> # For transformers v4.x+: 
-    tokenizer = AutoTokenizer.from_pretrained("vinai/bertweet-base", use_fast=False)
+    >>> tokenizer = AutoTokenizer.from_pretrained("vinai/bertweet-base", use_fast=False)
 
-    # For transformers v3.x: 
+    >>> # For transformers v3.x: 
-    # tokenizer = AutoTokenizer.from_pretrained("vinai/bertweet-base")
+    >>> # tokenizer = AutoTokenizer.from_pretrained("vinai/bertweet-base")
 
-    # INPUT TWEET IS ALREADY NORMALIZED!
+    >>> # INPUT TWEET IS ALREADY NORMALIZED!
-    line = "SC has first two presumptive cases of coronavirus , DHEC confirms HTTPURL via @USER :cry:"
+    >>> line = "SC has first two presumptive cases of coronavirus , DHEC confirms HTTPURL via @USER :cry:"
 
-    input_ids = torch.tensor([tokenizer.encode(line)])
+    >>> input_ids = torch.tensor([tokenizer.encode(line)])
 
-    with torch.no_grad():
+    >>> with torch.no_grad():
-        features = bertweet(input_ids)  # Models outputs are now tuples
+    ...     features = bertweet(input_ids)  # Models outputs are now tuples
 
-    ## With TensorFlow 2.0+:
+    >>> # With TensorFlow 2.0+:
-    # from transformers import TFAutoModel
+    >>> # from transformers import TFAutoModel
-    # bertweet = TFAutoModel.from_pretrained("vinai/bertweet-base")
+    >>> # bertweet = TFAutoModel.from_pretrained("vinai/bertweet-base")
 
 
 The original code can be found `here <https://github.com/VinAIResearch/BERTweet>`__.

docs/source/model_doc/herbert.rst

@@ -40,20 +40,20 @@ Examples of use:
 
 .. code-block::
 
-    from transformers import HerbertTokenizer, RobertaModel
+    >>> from transformers import HerbertTokenizer, RobertaModel
 
-    tokenizer = HerbertTokenizer.from_pretrained("allegro/herbert-klej-cased-tokenizer-v1")
+    >>> tokenizer = HerbertTokenizer.from_pretrained("allegro/herbert-klej-cased-tokenizer-v1")
-    model = RobertaModel.from_pretrained("allegro/herbert-klej-cased-v1")
+    >>> model = RobertaModel.from_pretrained("allegro/herbert-klej-cased-v1")
 
-    encoded_input = tokenizer.encode("Kto ma lepszą sztukę, ma lepszy rząd – to jasne.", return_tensors='pt')
+    >>> encoded_input = tokenizer.encode("Kto ma lepszą sztukę, ma lepszy rząd – to jasne.", return_tensors='pt')
-    outputs = model(encoded_input)
+    >>> outputs = model(encoded_input)
 
-    # HerBERT can also be loaded using AutoTokenizer and AutoModel:
+    >>> # HerBERT can also be loaded using AutoTokenizer and AutoModel:
-    import torch
+    >>> import torch
-    from transformers import AutoModel, AutoTokenizer
+    >>> from transformers import AutoModel, AutoTokenizer
 
-    tokenizer = AutoTokenizer.from_pretrained("allegro/herbert-klej-cased-tokenizer-v1")
+    >>> tokenizer = AutoTokenizer.from_pretrained("allegro/herbert-klej-cased-tokenizer-v1")
-    model = AutoModel.from_pretrained("allegro/herbert-klej-cased-v1")
+    >>> model = AutoModel.from_pretrained("allegro/herbert-klej-cased-v1")
 
 
 The original code can be found `here <https://github.com/allegro/HerBERT>`__.

docs/source/model_doc/phobert.rst

@@ -31,23 +31,23 @@ Example of use:
 
 .. code-block::
 
-    import torch
+    >>> import torch
-    from transformers import AutoModel, AutoTokenizer
+    >>> from transformers import AutoModel, AutoTokenizer
 
-    phobert = AutoModel.from_pretrained("vinai/phobert-base")
+    >>> phobert = AutoModel.from_pretrained("vinai/phobert-base")
-    tokenizer = AutoTokenizer.from_pretrained("vinai/phobert-base")
+    >>> tokenizer = AutoTokenizer.from_pretrained("vinai/phobert-base")
 
-    # INPUT TEXT MUST BE ALREADY WORD-SEGMENTED!
+    >>> # INPUT TEXT MUST BE ALREADY WORD-SEGMENTED!
-    line = "Tôi là sinh_viên trường đại_học Công_nghệ ."
+    >>> line = "Tôi là sinh_viên trường đại_học Công_nghệ ."
 
-    input_ids = torch.tensor([tokenizer.encode(line)])
+    >>> input_ids = torch.tensor([tokenizer.encode(line)])
 
-    with torch.no_grad():
+    >>> with torch.no_grad():
-        features = phobert(input_ids)  # Models outputs are now tuples
+    ...     features = phobert(input_ids)  # Models outputs are now tuples
 
-    ## With TensorFlow 2.0+:
+    >>> # With TensorFlow 2.0+:
-    # from transformers import TFAutoModel
+    >>> # from transformers import TFAutoModel
-    # phobert = TFAutoModel.from_pretrained("vinai/phobert-base")
+    >>> # phobert = TFAutoModel.from_pretrained("vinai/phobert-base")
 
 
 The original code can be found `here <https://github.com/VinAIResearch/PhoBERT>`__.