[HN Gopher] X-Transformers: A fully-featured transformer with ex... ___________________________________________________________________ X-Transformers: A fully-featured transformer with experimental features Author : blackcat201 Score : 31 points Date : 2021-05-08 17:38 UTC (5 hours ago) (HTM) web link (github.com) (TXT) w3m dump (github.com) | krick wrote: | That's really cool. Now I need a bunch of pre-trained models for | this... | shayankh wrote: | absolutely fucking amazing | argvargc wrote: | Unfortunately for me, I genuinely thought this was going to be a | DIY robot build that could disguise itself as something else. | giords wrote: | *for us | mrfusion wrote: | Explain like I'm a first year CS major? | thesehands wrote: | Transformers suffer from a quadratic bottleneck when | calculating attention. Much work has been done investigating | where memory can be saved by being more explicit on which | attentions to calculate. This repo implements transformers with | noted improvements | erik_seaberg wrote: | It's a kind of machine learning model: | https://medium.com/inside-machine-learning/what-is-a-transfo... | adontz wrote: | I have expected to see a 3D model for Optimus Prime. | fao_ wrote: | As others have mentioned, anything obscure like this should | literally come with a Wikipedia (or other such) link to explain | what it is, what it does. This is the primary problem with small | project READMEs, imo. They assume you're already familiar with | them and know what the hell they are. Like, take Ironhide: | https://github.com/MrMEEE/ironhide Optimus Support for | Linux Through VirtualGL - PPA version also available | | That's... great. So it's doing something with GL, and it's | running on Linux, but uhhh. my branch of the | original bumblebee project.. | | What is Optimus? What is Bumblebee? The trick of it is that it | links to a blog where neither of these terms are ever explained. | Maybe it's to just look impressive on someone's CV? How could I | even tell the difference? | | Likewise for this project, all you need in the README is one line | that's like: X-Transformers is a re- | implementation of Machine Learning Transformers that has been | built based on experimental Arxiv papers | | It's a one-line fix but it'll stop people like me being confused | as to whether or not you're implementing a new HTTP header | nerdponx wrote: | I would agree if this were some kind of public release | announcement. | | Would you say the same about an experimental programming | language based on a bunch of recent PLT/CS research? | | That's pretty much what this is, but for machine learning. It's | not meant to be "for the public", it's effectively research. | enchiridion wrote: | We're talking 2-3 sentences to explain what's going on. | | A researcher releasing work publicly on github is presumably | doing so too spread the ideas. | skybrian wrote: | Sure, they have some audience in mind, but not necessarily | us. There are a lot of documents that are public but are | meant for a specialized audience. If they were meant for | the general public, they'd be written very differently. | | Sharing a link on Hacker News is effectively taking it out | of context and sometimes it's up to us to add that context | back in. The author doesn't owe it to us. ___________________________________________________________________ (page generated 2021-05-08 23:00 UTC)