From 74755c89b92e0c0c027221c13fd034afed4d2136 Mon Sep 17 00:00:00 2001 From: Lysandre Date: Mon, 6 Jan 2020 14:41:53 +0100 Subject: [PATCH] Example snippet for BertForQuestionAnswering --- src/transformers/modeling_bert.py | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/src/transformers/modeling_bert.py b/src/transformers/modeling_bert.py index 8e4526620f..96c5c94d9d 100644 --- a/src/transformers/modeling_bert.py +++ b/src/transformers/modeling_bert.py @@ -1392,8 +1392,7 @@ class BertForQuestionAnswering(BertPreTrainedModel): tokenizer = BertTokenizer.from_pretrained('bert-base-uncased') 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) + input_ids = tokenizer.encode(question, 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)