CURLoRA v3

What's New:
Conducting more experiments with GPT2 model and integrating the results in the paper and adding the experiment code.

Key Features:
Implementation of the CURLoRA approach. Leveraging modified CUR matrix decomposition for stable LLM continual fine-tuning and catastrophic forgetting mitigation.
Comparing LoRA vs CURLoRA in LLMs continual learning and catastrophic forgetting using multiple tasks/datasets

Contents:
Code: Source code for the CURLoRA research.
Paper: Research paper detailing the methodology, math, theoretical analysis, and experimental results of CURLoRA.

Contributors:
Muhammad Fawi