lcastricato

60fps training data goes a long way ;)

Medium is going to bc cc by sa nc 4.0. We may reevaluate in the future and make it more lenient. Small is meant to be the model for builders and hackers.

Hi,

Louis here. CEO of overworld. Happy to answer questions :)

I'm team lead at Carper. This is correct. It's also just a project one of our engineers did over the course of a few days, so very low risk.

We will swap the base model out for StableLM as soon as we can and iterate from there. We just thought the community would enjoy this research artifact :)

We're doing some stuff with NVIDIA right now that I can't talk about yet. Super exciting though.

FYI they don't compare to trlX bc trlX is roughly just as fast. Similarly, they put trl in the worst light possible (trl is actually must faster than they claim.)

I am a soon to be computational narratology PhD student. I decided to take it upon myself to try to increase public awareness of narratology (Its a cool field, more people should know about it!)

As such, I decided to start a blog series about formally analyzing plot holes and showing how these plot holes become apparent in the topological features of an embedded narrative. This directly correlates with my PhD thesis (creating a DNN to automatically detect plot holes in narratives, and suggest ways to fix them) so I thought I'd be a prime candidate for writing a blog about it!

Rebuttals are more than welcome btw! I will happily write a follow up piece :)