LoftQ: LoRA-Fine-Tuning-aware Quantization for Large Language Models.
Yixiao LiYifan YuChen LiangNikos KarampatziakisPengcheng HeWeizhu ChenTuo ZhaoPublished in: ICLR (2024)
Keyphrases
- fine tuning
- language model
- agent technology
- language modeling
- document retrieval
- viable alternative
- probabilistic model
- speech recognition
- information retrieval
- n gram
- retrieval model
- language modelling
- software agents
- test collection
- smoothing methods
- statistical language models
- context sensitive
- query expansion
- ad hoc information retrieval
- electronic commerce
- distributed systems
- relevance model
- language model for information retrieval
- fine tuned
- machine learning
- translation model
- document ranking
- multi agent systems
- pseudo relevance feedback
- vector space model
- multiagent systems
- mobile agents
- passage retrieval
- document length
- okapi bm
- intelligent agents