QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models.
Yuhui XuLingxi XieXiaotao GuXin ChenHeng ChangHengheng ZhangZhengsu ChenXiaopeng ZhangQi TianPublished in: CoRR (2023)
Keyphrases
- language model
- low rank
- agent technology
- passage retrieval
- language modeling
- linear combination
- matrix factorization
- missing data
- singular value decomposition
- convex optimization
- low rank matrix
- probabilistic model
- matrix completion
- question answering
- n gram
- semi supervised
- information retrieval
- document retrieval
- test collection
- high dimensional data
- retrieval model
- rank minimization
- smoothing methods
- high order
- query expansion
- query terms
- relevance model
- vector space model
- nearest neighbor
- cross lingual
- trace norm