Zero-Order Optimization for LLM Fine-Tuning via Learnable Direction Sampling
arXiv:2602.13659v1 Announce Type: new Abstract: Fine-tuning large pretrained language models (LLMs) is a cornerstone of modern NLP, yet its growing memory demands (driven by backpropagation …
Valery Parfenov, Grigoriy Evseev, Andrey Veprikov, Nikolay Bushkov, Stanislav Moiseev, Aleksandr Beznosikov
조회수 35회