SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Merge branch 'master' into conditional-generation

Browse Source
This commit is contained in:
Thomas Wolf
2019-10-30 16:40:35 +01:00
committed by GitHub
parent 3cf2020c6b 079bfb32fb
commit 228cdd6a6e
87 changed files with 5059 additions and 719 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
transformers/modeling_bert.py
View File

@@ -46,6 +46,8 @@ BERT_PRETRAINED_MODEL_ARCHIVE_MAP = {
'bert-large-uncased-whole-word-masking-finetuned-squad': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-whole-word-masking-finetuned-squad-pytorch_model.bin",
'bert-large-cased-whole-word-masking-finetuned-squad': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-cased-whole-word-masking-finetuned-squad-pytorch_model.bin",
'bert-base-cased-finetuned-mrpc': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-cased-finetuned-mrpc-pytorch_model.bin",
'bert-base-german-dbmdz-cased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-german-dbmdz-cased-pytorch_model.bin",
'bert-base-german-dbmdz-uncased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-german-dbmdz-uncased-pytorch_model.bin",
}
@@ -1194,12 +1196,16 @@ class BertForQuestionAnswering(BertPreTrainedModel):
Examples::
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
model = BertForQuestionAnswering.from_pretrained('bert-base-uncased')
input_ids = torch.tensor(tokenizer.encode("Hello, my dog is cute")).unsqueeze(0) # Batch size 1
start_positions = torch.tensor([1])
end_positions = torch.tensor([3])
outputs = model(input_ids, start_positions=start_positions, end_positions=end_positions)
loss, start_scores, end_scores = outputs[:2]
model = BertForQuestionAnswering.from_pretrained('bert-large-uncased-whole-word-masking-finetuned-squad')
question, text = "Who was Jim Henson?", "Jim Henson was a nice puppet"
input_text = "[CLS] " + question + " [SEP] " + text + " [SEP]"
input_ids = tokenizer.encode(input_text)
token_type_ids = [0 if i <= input_ids.index(102) else 1 for i in range(len(input_ids))]
start_scores, end_scores = model(torch.tensor([input_ids]), token_type_ids=torch.tensor([token_type_ids]))
all_tokens = tokenizer.convert_ids_to_tokens(input_ids)
print(' '.join(all_tokens[torch.argmax(start_scores) : torch.argmax(end_scores)+1]))
# a nice puppet
"""
def __init__(self, config):