Sanya Roy 's starred repositories
RWKV-LM
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
some-assembly-required
đź“– An approachable introduction to Assembly.
ForumMagnum
The development repository for LessWrong2 and the EA Forum, based on Vulcan JS
probability-games
Given that the only thing we know about a weighted coin is the probability of getting either side, how good can we get at guessing?
Sleep-Utilities
Some automated programs to help with catching zzzz's
astronoodles.github.io
PERSONAL WEBSITE
cs76-chess-tournament
The winning chess AI submission! ~1550 ELO Lichess
MIT-6.00.1x
Introduction to Computer Science and Programming in Python.
MIT-6.00.2x
Introduction to computational thinking and data science