方法证据记录
LoRA and PEFT
LoRA (Low-Rank Adaptation), introduced by Hu et al. in 2022, and the broader family of parameter-efficient fine-tuning (PEFT) methods adapt large pretrained language models to new tasks by training only a small number of extra parameters instead of every weight in the model. This makes fine-tuning possible with far less GPU memory and compute while leaving the original model largely untouched.
源记录
引文逐字复制自方法源记录。这些引文不代表任何层级的验证。
Low-Rank Adaptation and Parameter-Efficient Fine-Tuning
分类方法记录 · ml-model / deep-learning
- Hu, E. J. et al. (2022). LoRA: Low-Rank Adaptation of Large Language Models. ICLR. · URL
- Lester, B. et al. (2021). The Power of Scale for Parameter-Efficient Prompt Tuning. EMNLP. · DOI 10.18653/v1/2021.emnlp-main.243
精选声明
声明已持久化到证据分类账中，每个声明都有自己的评估。
尚无精选声明
当分类账中没有声明时，此视图不会自行创建声明评估。
相关方法
从方法图中生成，显示为机器建议的关系 — 不推断任何证据声明。