RADLADS
@radlads_llm
Rapid Attention Distillation to Linear Attention Decoders at Scale.
by @picocreator
arxiv.org/pdf/2505.03005
huggingface.co/papers/2505.03…
ID: 1845176025954820096
https://radlads.info/ 12-10-2024 18:53:52
7 Tweet
61 Followers
2 Following
