Sasha Rush
@srush_nlp
Professor, Programmer in NYC.
Cornell Tech, Hugging Face 🤗
https://t.co/cZl0wTfqGz
ID:4558314927
http://rush-nlp.com 21-12-2015 15:46:59
6,1K Tweets
51,6K Followers
464 Following
Excited to share Penzai, a JAX research toolkit from Google DeepMind for building, editing, and visualizing neural networks! Penzai makes it easy to see model internals and lets you inject custom logic anywhere.
Check it out on GitHub: github.com/google-deepmin…
Sasha Rush Somehow the disentangled arch also makes the gradients cleaner and 'interpretable'
✨Excited to finally drop our new paper: SSMs “look like” RNNs, but we show their statefulness is an illusion🪄🐇
Current SSMs cannot express basic state tracking, but a minimal change fixes this! 👀
w/ jackson petty, Ashish Sabharwal
arxiv.org/abs/2404.08819