RPTQ: Reorder-based Post-training Quantization for Large Language Models.
Zhihang YuanLin NiuJiawei LiuWenyu LiuXinggang WangYuzhang ShangGuangyu SunQiang WuJiaxiang WuBingzhe WuPublished in: CoRR (2023)
Keyphrases
- language model
- language modeling
- n gram
- probabilistic model
- document retrieval
- information retrieval
- speech recognition
- statistical language models
- language modelling
- retrieval model
- test collection
- query expansion
- ad hoc information retrieval
- context sensitive
- relevance model
- language models for information retrieval
- training set
- text retrieval
- vector space model
- translation model
- query specific
- document length
- language model for information retrieval
- ad hoc retrieval
- pseudo relevance feedback
- decision trees