Tuesday, February 6, 2024

New best story on Hacker News: Beyond self-attention: How a small language model predicts the next token

Beyond self-attention: How a small language model predicts the next token
463 by tplrbv | 85 comments on Hacker News.


-
Labels:

New best story on Hacker News: Astra can read and write weights to improve Qwen

Astra can read and write weights to improve Qwen 708 by dbreunig | 211 comments on Hacker News.