Ideas & society2024 · shared on Hacker News
Transformers are SSMs (Mamba-2)
Explore Transformers are SSMs (Mamba-2), 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.
Ydataminer ·
Zamba2-7B
282 points71 comments
Ydsalaj ·
State-space models can learn in-context by gradient descent
86 points58 comments
YPaulHoule ·
Breaking Quadratic Barriers: A Non-Attention LLM for Ultra-Long Context Horizons
70 points23 comments
Ymatt_d ·
FlashAttention-T: Towards Tensorized Attention
12 points0 comments
Yjasondavies ·
Transformers are SSMs (Mamba-2)
2 points0 comments