Yong Zheng-Xin
Yong Zheng-Xin
@KhalidRmb @RishabhJain2018 I will create an issue and write unit tests for /apps/base/utils.py because #2054 couldn't pass the coverage tests.
@KhalidRmb Added unit tests for both functions `decode_data` and `encode_data` in /apps/base/utils.py #2107
Would integrate the current Berkeley Neural Parser into AllenNLP pipeline be a useful contribution? Would love to work on it!
@agururajvais please go ahead!
@desegura I notice that your forward and inverse models still have `.tar` suffix. You need to use `tar xvzf` to unzip the both `.tar.gz` model files.
Hi @salvaRC, thanks for the prompt reply! Quick follow-up on the Drive: I couldn't find the labeling function codes other than the existing label votes. Am I missing something?
I am working on this right now, but I ran into some weird GH issue (been Googling the whole day to debug it) where there's wikiann en templates in the...
@sbmaruf For the "Please review this [part](https://github.com/sbmaruf/Megatron-DeepSpeed/tree/c4-mc4-pre_processing/scripts/c4_mc4_processing#data-binarization-stat) carefully", is there any particular component to pay extra attention to? For instance, the reported figures?
I am interested in helping out with this. Currently running a prompt template of `Sentence: [sentence]. Is this [word] a [label]?` with inference on CoNLL03 with T0_p and T0_pp.
Referring to #21 .