klotz: sebastian reschka* + mora* + parameter-efficient fine-tuning* + pretraining* + memory* + microsoft research* + lora* + continual pretraining*

0 bookmark(s) - Sort by: Date ↓ / Title / - Bookmarks from other users for this tag

  1. This paper proposes a new method called MoRA for parameter-efficient fine-tuning of large language models (LLMs). The proposed method, MoRA, employs a square matrix to achieve high-rank updating, maintaining the same number of trainable parameters. The paper suggests that low-rank updating, as implemented in LoRA, may limit the ability of LLMs to effectively learn and memorize new knowledge. MoRA outperforms LoRA on memory-intensive tasks and achieves comparable performance on other tasks.

Top of the page

First / Previous / Next / Last / Page 1 of 0 SemanticScuttle - klotz.me: Tags: sebastian reschka + mora + parameter-efficient fine-tuning + pretraining + memory + microsoft research + lora + continual pretraining

About - Propulsed by SemanticScuttle