2 papers
cs.CL2024
APT: Adaptive Pruning and Tuning Pretrained Language Models for Efficient Training and Inference
Bowen Zhao, Hannaneh Hajishirzi, Qingqing Cao
Fine-tuning and inference with large Language Models (LM) are generally known to be expensive. Parameter-efficient fine-tuning over pretrained LMs reduces training memory by updati…
cs.CL2023
BTR: Binary Token Representations for Efficient Retrieval Augmented Language Models
Qingqing Cao, Sewon Min, Yizhong Wang +1
Retrieval augmentation addresses many critical problems in large language models such as hallucination, staleness, and privacy leaks. However, running retrieval-augmented language…