News for hackers. Stuff that matters.
Re:LoRA Learns Less and Forgets Less by gregmac on Friday May 17, 2024 @10:22AM (#40390274)
This is "Low-Rank Adaptation", "a widely-used parameter-efficient finetuning method for large language models."

Not to be confused with LoRa ("long range") [1], an Internet of Things radio technology.

[1] https://en.wikipedia.org/wiki/LoRa

Re:LoRA Learns Less and Forgets Less by chaos_emergent on Friday May 17, 2024 @10:28AM (#40390329)
Isn’t this fairly obvious after a two second glance at the abstract