Abhishek Bisht

icon indicating a website link https://llamasearch.uk icon indicating an email [email protected]

icon company @causaly icon location london icon location I'm an Engg with a passion for building ideas into reality , especially when people find them useful 🦙

Results 4 comments of Abhishek Bisht

AttributeError: module 'tensorflow.contrib.seq2seq' has no attribute 'prepare_attention'

I am also having the same issue, do I need to downgrade(as i am having tf version '1.3.0') the tf version? or there is some other solution to this issue?

Predictions in raw data

@GuillermoJaca for prediction you can directly use your fine tune model in huggingface transformer pipeline, some sample code below for you reference: ``` from transformers import AutoTokenizer, AutoModelForTokenClassification from transformers...

In XFUND dataset why B-QUESTION", "B-ANSWER", "B-HEADER", "I-ANSWER", "I-QUESTION", "I-HEADER

@ChidanandKumarVimaan , This is 'BIO' tagging scheme (for token classification or NER task) , So each tag has "**B**egin" , "**I**nside", "**O**ther" , So in total 7 classes.

Truncated response -- repro code

we do face this issues , any workaround