machelreid subformer issues

machelreid / subformer

The code for the Subformer, from the EMNLP 2021 Findings paper: "Subformer: Exploring Weight Sharing for Parameter Efficiency in Generative Transformers", by Machel Reid, Edison Marrese-Taylor, and Yutaka Matsuo

https://arxiv.org/abs/2101.00234

MIT License

14 stars 3 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Could you release the summary of CNN/Daily Mail decoded by the model?

#5 wxdwlai opened 2 years ago
0
Shared weights update during backpropagation

#4 qianlou opened 3 years ago
0
ModuleNotFoundError: No module named 'fairseq.data.multilingual_denoising_dataset'

#3 qianlou closed 3 years ago
5
How to reproduce the result of abstractive summarization?

#2 minjieyuan closed 3 years ago
4
Core codes for the sandwich weight sharing

#1 qianlou closed 3 years ago
2

machelreid / subformer

issues

Could you release the summary of CNN/Daily Mail decoded by the model?

Shared weights update during backpropagation

ModuleNotFoundError: No module named 'fairseq.data.multilingual_denoising_dataset'

How to reproduce the result of abstractive summarization?

Core codes for the sandwich weight sharing