LoRA (Low-Rank Adaptation) fine-tunes LLMs by updating low-rank matrices in attention layers while freezing most weights. It reduces memory and computational costs. arxiv.org/pdf/2106.09685

Show Post

Looks like a book or a very long review paper! Can you share the link?

Show Post

Entropy is one of those formulas that many of us learn, swallow whole, and even use regularly without really understanding. (E.g., where does that “log” come from? Are there other possible formulas?) Yet there's an intuitive & almost inevitable way to arrive at this expression.

Show Post

A big THANK YOU to each and every one of the participants, presenters, tutorials, and local organizers for making the third Learning on Graphs conference @logconference.bsky.social possible! 💙

Show Post

*A Journey into PyTorch, the Ecosystem, and Deep Learning Compilers* Great seminar by @lantiga.bsky.social on the compiler's ecosystem and the recent Thunder framework by LightningAI! I have uploaded slides, video, & notebooks publicly. 🙂 www.sscardapane.it/seminars/pyt...

Show Post