Janghwan Lee

large language model (3) model compression (3) model quantization (2) post-training quantization (2) reinforcement learning from human feedback (1) language model (1) parameter-efficient fine-tuning (1) low-rank adaptation (1) inference efficiency (1) weight quantization (1) error compensation (1) activation outlier (1) activation quantization (1) 2-bit inference (1) 2-bit quantization (1) floating-point format (1) quantization error compensation (1) direct preference optimization (1) knowledge distillation (1) preference alignment (1)