Recover-LoRA for Aggressive Quantization: Reclaiming Accuracy in 2-Bit Language Models via Low-Rank Adaptation with Knowledge Distillation on Synthetic Data 文章

ArXiv CS.AI2026-06-04NEWSen作者: Devleena Das, Rajeev Patwari, Elliott Delaye, Ashish Sirasao
查看原文 →
关系图谱

Recover-LoRA for Aggressive Quantization: Reclaiming Accuracy in 2-Bit Language Models via Low-Rank Adaptation with Knowledge Distillation on Synthetic Data · 相关技术

相关技术

GateUpRecover-LoRA