Hwijeen Ahn

output of bidirectional LSTM

1

First of all, thanks for your great tutorial on pytorch! It's a great tip for beginners. I have a question about the way you use the output of a bidirectional...

Airline pops up on BufWritePost event.

1

Hi,  thank you for the great plugin. One little thing that gets on my nerve is that airline plugin pops up whenever...

Slow dataloading with big datasets issue persists

42

Hi, I reported too slow data fetching when data is large(#2210) a couple of weeks ago, and @lhoestq referred me to the fix (#2122). However, the problem seems to persist....

How about supporting alternatives to fine-tuning?

9

Hi, thank you for the great library. Recently, many algorithms are proposed to replace fine-tuning as it incurs too many burdens, especially with huge models like GPT3. Examples include [P-tuning](https://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=&ved=2ahUKEwjA2dbKqM3xAhXzKaYKHfRiDDwQFjABegQIBxAD&url=https%3A%2F%2Farxiv.org%2Fabs%2F2103.10385&usg=AOvVaw3jtXvJ-0GWxlJmIFjVpd9M)...

`datasets.map` multi processing much slower than single processing

14

Hi, thank you for the great library. I've been using datasets to pretrain language models, and it often involves datasets as large as ~70G. My data preparation step is roughly...