def test_tokens_to_text(self):
tokenizer = SentencePieceTokenizer("./tests/data/m_common.model")
text = "[CLS] a b c [MASK] e f [SEP] g h i [SEP]"
tokens = tokenizer.text_to_tokens(text)
result = tokenizer.tokens_to_text(tokens)
self.assertTrue(text == result)
def test_add_special_tokens(self):
tokenizer = SentencePieceTokenizer("./tests/data/m_common.model")
special_tokens = ["[CLS]", "[MASK]", "[SEP]"]
tokenizer.add_special_tokens(special_tokens)
self.assertTrue(tokenizer.vocab_size == tokenizer.original_vocab_size +
len(special_tokens))
def test_text_to_tokens(self):
tokenizer = SentencePieceTokenizer("./tests/data/m_common.model")
special_tokens = nemo_nlp.data.tokenizers.MODEL_SPECIAL_TOKENS['bert']
tokenizer.add_special_tokens(special_tokens)
text = "[CLS] a b c [MASK] e f [SEP] g h i [SEP]"
tokens = tokenizer.text_to_tokens(text)
self.assertTrue(len(tokens) == len(text.split()))
self.assertTrue(tokens.count("[CLS]") == 1)
self.assertTrue(tokens.count("[MASK]") == 1)
self.assertTrue(tokens.count("[SEP]") == 2)
def test_text_to_ids(self):
tokenizer = SentencePieceTokenizer("./tests/data/m_common.model")
special_tokens = ["[CLS]", "[MASK]", "[SEP]"]
tokenizer.add_special_tokens(special_tokens)
text = "[CLS] a b c [MASK] e f [SEP] g h i [SEP]"
ids = tokenizer.text_to_ids(text)
self.assertTrue(len(ids) == len(text.split()))
self.assertTrue(ids.count(tokenizer.special_tokens["[CLS]"]) == 1)
self.assertTrue(ids.count(tokenizer.special_tokens["[MASK]"]) == 1)
self.assertTrue(ids.count(tokenizer.special_tokens["[SEP]"]) == 2)
def test_ids_to_text(self):
tokenizer = SentencePieceTokenizer("./tests/data/m_common.model")
special_tokens = nemo_nlp.data.tokenizers.MODEL_SPECIAL_TOKENS['bert']
tokenizer.add_special_tokens(special_tokens)
text = "[CLS] a b c [MASK] e f [SEP] g h i [SEP]"
ids = tokenizer.text_to_ids(text)
result = tokenizer.ids_to_text(ids)
self.assertTrue(text == result)
def test_ids_to_tokens(self):
tokenizer = SentencePieceTokenizer("./tests/data/m_common.model")
special_tokens = nemo_nlp.data.tokenizers.MODEL_SPECIAL_TOKENS['bert']
tokenizer.add_special_tokens(special_tokens)
text = "[CLS] a b c [MASK] e f [SEP] g h i [SEP]"
tokens = tokenizer.text_to_tokens(text)
ids = tokenizer.tokens_to_ids(tokens)
result = tokenizer.ids_to_tokens(ids)
self.assertTrue(len(result) == len(tokens))
for i in range(len(result)):
self.assertTrue(result[i] == tokens[i])
def test_ids_to_text(self):
tokenizer = SentencePieceTokenizer("./tests/data/m_common.model")
special_tokens = ["[CLS]", "[MASK]", "[SEP]"]
tokenizer.add_special_tokens(special_tokens)
text = "[CLS] a b c [MASK] e f [SEP] g h i [SEP]"
ids = tokenizer.text_to_ids(text)
result = tokenizer.ids_to_text(ids)
self.assertTrue(text == result)
def test_ids_to_tokens(self):
tokenizer = SentencePieceTokenizer("./tests/data/m_common.model")
special_tokens = ["[CLS]", "[MASK]", "[SEP]"]
tokenizer.add_special_tokens(special_tokens)
text = "[CLS] a b c [MASK] e f [SEP] g h i [SEP]"
tokens = tokenizer.text_to_tokens(text)
ids = tokenizer.tokens_to_ids(tokens)
result = tokenizer.ids_to_tokens(ids)
self.assertTrue(len(result) == len(tokens))
for i in range(len(result)):
self.assertTrue(result[i] == tokens[i])
def test_add_special_tokens(self):
tokenizer = SentencePieceTokenizer("./tests/data/m_common.model")
special_tokens = nemo_nlp.data.tokenizers.MODEL_SPECIAL_TOKENS['bert']
tokenizer.add_special_tokens(special_tokens)
self.assertTrue(tokenizer.vocab_size == tokenizer.original_vocab_size + len(set(special_tokens.values())))
output_file = f'{nf.work_dir}/output.txt'
if args.bert_checkpoint is None:
""" Use this if you're using a standard BERT model.
To see the list of pretrained models, call:
nemo_nlp.nm.trainables.huggingface.BERT.list_pretrained_models()
"""
tokenizer = NemoBertTokenizer(args.pretrained_bert_model)
model = nemo_nlp.nm.trainables.huggingface.BERT(pretrained_model_name=args.pretrained_bert_model)
else:
""" Use this if you're using a BERT model that you pre-trained yourself.
"""
if args.tokenizer == "sentencepiece":
special_tokens = nemo_nlp.utils.MODEL_SPECIAL_TOKENS['bert']
tokenizer = SentencePieceTokenizer(model_path=args.tokenizer_model)
elif args.tokenizer == "nemobert":
tokenizer = NemoBertTokenizer(args.pretrained_bert_model)
else:
raise ValueError(f"received unexpected tokenizer '{args.tokenizer}'")
if args.bert_config is not None:
with open(args.bert_config) as json_file:
config = json.load(json_file)
model = nemo_nlp.nm.trainables.huggingface.BERT(**config)
else:
model = nemo_nlp.nm.trainables.huggingface.BERT(pretrained_model_name=args.pretrained_bert_model)
model.restore_from(args.bert_checkpoint)
logging.info(f"Model restored from {args.bert_checkpoint}")
hidden_size = model.hidden_size
output_file = f'{nf.work_dir}/output.txt'
if args.bert_checkpoint is None:
""" Use this if you're using a standard BERT model.
To see the list of pretrained models, call:
nemo_nlp.huggingface.BERT.list_pretrained_models()
"""
tokenizer = NemoBertTokenizer(args.pretrained_bert_model)
model = nemo_nlp.nm.trainables.huggingface.BERT(
pretrained_model_name=args.pretrained_bert_model)
else:
""" Use this if you're using a BERT model that you pre-trained yourself.
"""
if args.tokenizer == "sentencepiece":
special_tokens = nemo_nlp.utils.MODEL_SPECIAL_TOKENS['bert']
tokenizer = SentencePieceTokenizer(model_path=args.tokenizer_model,
special_tokens=special_tokens)
elif args.tokenizer == "nemobert":
tokenizer = NemoBertTokenizer(args.pretrained_bert_model)
else:
raise ValueError(f"received unexpected tokenizer '{args.tokenizer}'")
if args.bert_config is not None:
with open(args.bert_config) as json_file:
config = json.load(json_file)
model = nemo_nlp.nm.trainables.huggingface.BERT(**config)
else:
model = nemo_nlp.nm.trainables.huggingface.BERT(
pretrained_model_name=args.pretrained_bert_model)
model.restore_from(args.bert_checkpoint)
logging.info(f"Model restored from {args.bert_checkpoint}")
