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

While KotlinDL seems to be a good solution by Jetbrains, I would personally stick to Java frameworks like DL4J for a better community support and likely more features. Source: almost 3 years ago

Would recommend taking a look at dl4j: https://deeplearning4j.org. Source: about 3 years ago

We use DeepLearning4j in this chapter because it is written in Java and easy to use with Clojure. In a later chapter we will use the Clojure library libpython-clj to access other deep learning-based tools like the Hugging Face Transformer models for question answering systems as well as the spaCy Python library for NLP. Source: about 3 years ago

FastAPI. Or even simpler: DL4J, to be used in Java when we need to communicate with the rest of the applications in real time. Source: about 3 years ago