cosmiasstash.bsky.social
@cosmiasstash.bsky.social
i designed my ponysona months before Maud Pie appeared and people asked about it
September 11, 2025 at 11:24 PM
it's a reaction image used like "No bro, [why would you do this?]"
To find a lot more, search "不是哥们"
January 16, 2025 at 9:39 PM
Yi Tay etc disagree:
www.yitay.net/blog/model-a...
2024-07-16

> BERT-style models pretty much deprecated at this point because there is a strictly better alternative... if the decoder was getting in the way... yanking out the encoder performed just as competitive as a BERT encoder.
What happened to BERT & T5? On Transformer Encoders, PrefixLM and Denoising Objectives — Yi Tay
A Blogpost series about Model Architectures Part 1: What happened to BERT and T5? Thoughts on Transformer Encoders, PrefixLM and Denoising objectives
www.yitay.net
December 20, 2024 at 11:05 PM
I'd like to know how does it compare with T5?

P.S.: I'm the author of Wikipedia BERT and T5 and basically all the Transformer-related pages. If you have comments about how the pages can be improved I can do it.

(Yes ULMFit had already been on the BERT page)
December 20, 2024 at 2:03 AM