LowRA enables LoRA fine-tuning with base weights at 1.15 to 4 bits per parameter, outperforming QLoRA and LoftQ at equal bit widths and matching their accuracy at lower bit widths.
Punica: Multi-tenant lora serving
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits
LowRA enables LoRA fine-tuning with base weights at 1.15 to 4 bits per parameter, outperforming QLoRA and LoftQ at equal bit widths and matching their accuracy at lower bit widths.