AI & machine learning2023 · shared on Hacker News
Efficient Streaming Language Models with Attention Sinks
Explore Efficient Streaming Language Models with Attention Sinks, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.
GO BEYOND THE ABSTRACT
The conversation around the idea.
Original Hacker News threads. Different perspectives, questions, and things worth thinking about.
Showing up to 100 related threads. A paper may appear in a comment rather than the original submission.
Links found in the discussion
Up to 50 recent source links, in HN item order.
Yachow ·
'Attention is all you need' coauthor says he's 'sick' of transformers
432 points224 comments
YZeljkoS ·
Task-specific LLM evals that do and don't work
182 points46 comments
Yshishirpatil ·
MemGPT – LLMs with self-editing memory for unbounded context
6 points0 comments
Yjxmorris12 ·
Efficient Streaming Language Models with Attention Sinks
5 points0 comments
YTheJCDenton ·
StreamingLLM: Efficient streaming technique enable infinite sequence lengths
2 points2 comments
Yog_kalu ·
Think Before You Speak: Training Language Models with Pause Tokens
2 points0 comments
Ycubie ·
Attention Sinks in LLMs for endless fluency
2 points2 comments
Ykelseyfrog ·
Efficient Streaming Language Models with Attention Sinks
1 points0 comments