from transformers import BertTokenizerFast tokenizer = BertTokenizerFast("./vocab.txt", unk_token="<unk>", sep_token="</s>", cls_token="<s>", pad_token="<pad>", mask_token="[MASK]" ) features = pipeline( "feature-extraction", model="./model", …

How to specify sequence length when using "feature-extraction"

poli April 27, 2021, 10:12pm 3

I’m getting the following error: IndexError: index out of range in self

Topic		Replies	Views
Truncating sequence -- within a pipeline Beginners	7	5869	May 3, 2024
Out of index error in pipeline Beginners	9	6526	June 22, 2022
Predictions with pipeline fails to truncate test set 🤗Transformers	0	181	January 23, 2024
Tokenizer behaviour with pipeline 🤗Tokenizers	0	930	August 1, 2023
Truncate the seq. not working 🤗Transformers	0	838	August 17, 2022