Many settings affect the outputs in interesting ways, but that's half the fun. These LoRAs are very lightly trained; more training may or may not help. The competitions are also performed using zero-shot text guessing, and if Facebook said it, you can bet that's actually Meta AI saying it, and they are leaders in the field. Source: about 1 year ago

You should look at the entire niche of MAE-related papers, that's quite exciting, and the neuroscience-inspired stream of stuff like Barlow Twins. As well, the official Facebook AI blog is surprisingly good coverage of much of the interesting un/semi-supervised DL research FAIR does, and worth going through. Source: almost 2 years ago

I am looking to work with 1 or 2 people on a https://hackr.io/ clone. Source: 11 months ago

I know a better place, Https://hackr.io. Source: over 1 year ago

Https://hackr.io/ has countless resources. Source: almost 2 years ago

For future situations when you want to find the best resource for X, you can check out hackr.io. It is a community driven database of resources where members upvote learning material they have tried and liked. The best way to find out what the best thing for you is to see for yourself regardless of what other's experiences may be. Source: about 2 years ago

Hackr.io https://hackr.io/ platform allows you to register and learn courses for free. There are multiple courses from different sources available on the website, a sizeable amount of people post lectures on the website. Although, there is a voting system whereby courses that get the most votes from users get upvoted to the top. There's also a filter available on the site that you can use to push down courses... - Source: dev.to / over 2 years ago