Tootfinder

One week to go with last places up for grabs! Join us at DINAcon 2024 next week in Bern to hear about:
💠 AI in Parliament: A Roadmap for the Parliamentary Library { Jacqueline Kucera }
🌸 How can large language models be used for sustainable procurement? { Marcel Gygli, Luca Rolshoven }
🌿 Source code sovereignty: local alternatives for an independent digital future { Tobias Brunner }
🧑‍⚖️ My workshop on open source contracts with Simon Schlauri
🌃

CH Open DINAcon 2024 in Bern | Wissenschaft und Technik
Veranstaltung am 21.11.2024 in Bern. Die DINAcon ist ein Event für digitale Nachhaltigkeit unter dem Motto "Zukunftsmodelle für eine digi

Excited about the new xLSTM model release. There are many well-though designs compared to transformers: recurrence (which should allows composability), gating (like Mamba & LSTM which is based on, which allows time complexity independent of the input size), state tracking (unlike Mamba & transformers). For now, these advantage aren’t apparent on benchmarks, but most training techniques are secrets, and the recent advances of LLMs evidenced that they matter a lot.