diff --git a/docs/source/model_doc/bertgeneration.rst b/docs/source/model_doc/bertgeneration.rst index 7c84338060..686b1b8386 100644 --- a/docs/source/model_doc/bertgeneration.rst +++ b/docs/source/model_doc/bertgeneration.rst @@ -38,22 +38,22 @@ Usage: .. code-block:: - # leverage checkpoints for Bert2Bert model... - # 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) - # 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) - bert2bert = EncoderDecoderModel(encoder=encoder, decoder=decoder) + >>> # leverage checkpoints for Bert2Bert model... + >>> # 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) + >>> # 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) + >>> bert2bert = EncoderDecoderModel(encoder=encoder, decoder=decoder) - # create tokenizer... - tokenizer = BertTokenizer.from_pretrained("bert-large-uncased") + >>> # create tokenizer... + >>> 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 - labels = tokenizer('This is a short summary', 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 - # train... - loss = bert2bert(input_ids=input_ids, decoder_input_ids=labels, labels=labels).loss - loss.backward() + >>> # train... + >>> loss = bert2bert(input_ids=input_ids, decoder_input_ids=labels, labels=labels).loss + >>> 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 - sentence_fuser = EncoderDecoderModel.from_pretrained("google/roberta2roberta_L-24_discofuse") - tokenizer = AutoTokenizer.from_pretrained("google/roberta2roberta_L-24_discofuse") + >>> # instantiate sentence fusion model + >>> sentence_fuser = EncoderDecoderModel.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: diff --git a/docs/source/model_doc/bertweet.rst b/docs/source/model_doc/bertweet.rst index b1d35d3a68..215746fca1 100644 --- a/docs/source/model_doc/bertweet.rst +++ b/docs/source/model_doc/bertweet.rst @@ -31,28 +31,28 @@ Example of use: .. code-block:: - import torch - from transformers import AutoModel, AutoTokenizer + >>> import torch + >>> from transformers import AutoModel, AutoTokenizer - bertweet = AutoModel.from_pretrained("vinai/bertweet-base") + >>> bertweet = AutoModel.from_pretrained("vinai/bertweet-base") - # For transformers v4.x+: - tokenizer = AutoTokenizer.from_pretrained("vinai/bertweet-base", use_fast=False) + >>> # For transformers v4.x+: + >>> tokenizer = AutoTokenizer.from_pretrained("vinai/bertweet-base", use_fast=False) - # For transformers v3.x: - # tokenizer = AutoTokenizer.from_pretrained("vinai/bertweet-base") + >>> # For transformers v3.x: + >>> # tokenizer = AutoTokenizer.from_pretrained("vinai/bertweet-base") - # INPUT TWEET IS ALREADY NORMALIZED! - line = "SC has first two presumptive cases of coronavirus , DHEC confirms HTTPURL via @USER :cry:" + >>> # INPUT TWEET IS ALREADY NORMALIZED! + >>> 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(): - features = bertweet(input_ids) # Models outputs are now tuples + >>> with torch.no_grad(): + ... features = bertweet(input_ids) # Models outputs are now tuples - ## With TensorFlow 2.0+: - # from transformers import TFAutoModel - # bertweet = TFAutoModel.from_pretrained("vinai/bertweet-base") + >>> # With TensorFlow 2.0+: + >>> # from transformers import TFAutoModel + >>> # bertweet = TFAutoModel.from_pretrained("vinai/bertweet-base") The original code can be found `here `__. diff --git a/docs/source/model_doc/herbert.rst b/docs/source/model_doc/herbert.rst index 2b94b957d1..8f237a21cc 100644 --- a/docs/source/model_doc/herbert.rst +++ b/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") - model = RobertaModel.from_pretrained("allegro/herbert-klej-cased-v1") + >>> tokenizer = HerbertTokenizer.from_pretrained("allegro/herbert-klej-cased-tokenizer-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') - outputs = model(encoded_input) + >>> encoded_input = tokenizer.encode("Kto ma lepszą sztukę, ma lepszy rząd – to jasne.", return_tensors='pt') + >>> outputs = model(encoded_input) - # HerBERT can also be loaded using AutoTokenizer and AutoModel: - import torch - from transformers import AutoModel, AutoTokenizer + >>> # HerBERT can also be loaded using AutoTokenizer and AutoModel: + >>> import torch + >>> from transformers import AutoModel, AutoTokenizer - tokenizer = AutoTokenizer.from_pretrained("allegro/herbert-klej-cased-tokenizer-v1") - model = AutoModel.from_pretrained("allegro/herbert-klej-cased-v1") + >>> tokenizer = AutoTokenizer.from_pretrained("allegro/herbert-klej-cased-tokenizer-v1") + >>> model = AutoModel.from_pretrained("allegro/herbert-klej-cased-v1") The original code can be found `here `__. diff --git a/docs/source/model_doc/phobert.rst b/docs/source/model_doc/phobert.rst index 95e12877a3..1d4958286a 100644 --- a/docs/source/model_doc/phobert.rst +++ b/docs/source/model_doc/phobert.rst @@ -31,23 +31,23 @@ Example of use: .. code-block:: - import torch - from transformers import AutoModel, AutoTokenizer + >>> import torch + >>> from transformers import AutoModel, AutoTokenizer - phobert = AutoModel.from_pretrained("vinai/phobert-base") - tokenizer = AutoTokenizer.from_pretrained("vinai/phobert-base") + >>> phobert = AutoModel.from_pretrained("vinai/phobert-base") + >>> tokenizer = AutoTokenizer.from_pretrained("vinai/phobert-base") - # INPUT TEXT MUST BE ALREADY WORD-SEGMENTED! - line = "Tôi là sinh_viên trường đại_học Công_nghệ ." + >>> # INPUT TEXT MUST BE ALREADY WORD-SEGMENTED! + >>> 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(): - features = phobert(input_ids) # Models outputs are now tuples + >>> with torch.no_grad(): + ... features = phobert(input_ids) # Models outputs are now tuples - ## With TensorFlow 2.0+: - # from transformers import TFAutoModel - # phobert = TFAutoModel.from_pretrained("vinai/phobert-base") + >>> # With TensorFlow 2.0+: + >>> # from transformers import TFAutoModel + >>> # phobert = TFAutoModel.from_pretrained("vinai/phobert-base") The original code can be found `here `__.