def main():
parser = argparse.ArgumentParser()
# Required parameters
parser.add_argument("--bert_model_dir",
default=config.bert_model_dir,
type=str,
help="Bert pre-trained model dir")
args = parser.parse_args()
nlp = pipeline(
'fill-mask',
model=args.bert_model_dir,
tokenizer=args.bert_model_dir,
device=0, # gpu device id
)
i = nlp('hi lili, What is the name of the [MASK] ?')
print(i)
i = nlp('今天[MASK]情很好')
print(i)
i = nlp('少先队员[MASK]该为老人让座')
print(i)
i = nlp('[MASK]七学习是人工智能领遇最能体现智能的一个分知')
print(i)
i = nlp('机[MASK]学习是人工智能领遇最能体现智能的一个分知')
print(i)
def main():
parser = argparse.ArgumentParser()
# Required parameters
parser.add_argument("--bert_model_dir",
default=os.path.join(
pwd_path,
'../data/bert_models/chinese_finetuned_lm/'),
type=str,
help="Bert pre-trained model dir")
args = parser.parse_args()
nlp = pipeline('fill-mask',
model=args.bert_model_dir,
tokenizer=args.bert_model_dir)
i = nlp('hi lili, What is the name of the [MASK] ?')
print(i)
i = nlp('今天[MASK]情很好')
print(i)
i = nlp('少先队员[MASK]该为老人让座')
print(i)
i = nlp('[MASK]七学习是人工智能领遇最能体现智能的一个分知')
print(i)
i = nlp('机[MASK]学习是人工智能领遇最能体现智能的一个分知')
print(i)
def __init__(self, d_model_dir=D_model_dir, g_model_dir=G_model_dir):
super(ElectraCorrector, self).__init__()
self.name = 'electra_corrector'
t1 = time.time()
self.g_model = pipeline("fill-mask",
model=g_model_dir,
tokenizer=g_model_dir)
self.d_model = ElectraForPreTraining.from_pretrained(d_model_dir)
if self.g_model:
self.mask = self.g_model.tokenizer.mask_token
logger.debug('Loaded electra model: %s, spend: %.3f s.' %
(g_model_dir, time.time() - t1))
def __init__(self, bert_model_dir=config.bert_model_dir):
super(BertCorrector, self).__init__()
self.name = 'bert_corrector'
t1 = time.time()
self.model = pipeline(
'fill-mask',
model=bert_model_dir,
tokenizer=bert_model_dir,
device=0, # gpu device id
)
if self.model:
self.mask = self.model.tokenizer.mask_token
logger.debug('Loaded bert model: %s, spend: %.3f s.' % (bert_model_dir, time.time() - t1))
def fill_mask_demo():
nlp = pipeline(
"fill-mask",
model=G_model_dir,
tokenizer=G_model_dir
)
print(nlp.tokenizer.mask_token)
print(
nlp(f"HuggingFace is creating a {nlp.tokenizer.mask_token} that the community uses to solve NLP tasks.")
)
i = nlp('hi, What is your [MASK] ?')
print(i)
i = nlp('今天[MASK]情很好')
print(i)
def __init__(self,
bert_model_dir=os.path.join(
pwd_path, '../data/bert_models/chinese_finetuned_lm/')):
super(BertCorrector, self).__init__()
self.name = 'bert_corrector'
t1 = time.time()
self.model = pipeline(
'fill-mask',
model=bert_model_dir,
tokenizer=bert_model_dir,
device=0, # gpu device id
)
if self.model:
self.mask = self.model.tokenizer.mask_token
logger.debug('Loaded bert model: %s, spend: %.3f s.' %
(bert_model_dir, time.time() - t1))
