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

Fix #1686

Browse Source
This commit is contained in:
thomwolf
2019-11-05 09:38:00 +01:00
parent d2e2577dd3
commit f1e4db2aa8
1 changed files with 4 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
transformers/modeling_openai.py
View File

@@ -565,9 +565,12 @@ class OpenAIGPTDoubleHeadsModel(OpenAIGPTPreTrainedModel):
tokenizer = OpenAIGPTTokenizer.from_pretrained('openai-gpt') tokenizer = OpenAIGPTTokenizer.from_pretrained('openai-gpt')
model = OpenAIGPTDoubleHeadsModel.from_pretrained('openai-gpt') model = OpenAIGPTDoubleHeadsModel.from_pretrained('openai-gpt')
tokenizer.add_special_tokens({'cls_token': '[CLS]'}) # Add a [CLS] to the vocabulary (we should train it also!) tokenizer.add_special_tokens({'cls_token': '[CLS]'}) # Add a [CLS] to the vocabulary (we should train it also!)
model.resize_token_embeddings(len(tokenizer))
choices = ["Hello, my dog is cute [CLS]", "Hello, my cat is cute [CLS]"] choices = ["Hello, my dog is cute [CLS]", "Hello, my cat is cute [CLS]"]
input_ids = torch.tensor([tokenizer.encode(s) for s in choices]).unsqueeze(0) # Batch size 1, 2 choices input_ids = torch.tensor([tokenizer.encode(s) for s in choices]).unsqueeze(0) # Batch size 1, 2 choices
mc_token_ids = torch.tensor([input_ids.size(-1), input_ids.size(-1)]).unsqueeze(0) # Batch size 1 mc_token_ids = torch.tensor([input_ids.size(-1)-1, input_ids.size(-1)-1]).unsqueeze(0) # Batch size 1
outputs = model(input_ids, mc_token_ids=mc_token_ids) outputs = model(input_ids, mc_token_ids=mc_token_ids)
lm_prediction_scores, mc_prediction_scores = outputs[:2] lm_prediction_scores, mc_prediction_scores = outputs[:2]