Outlier Suppression+: Accurate quantization of large language models by equivalent and effective shifting and scaling.
Xiuying WeiYunchen ZhangYuhang LiXiangguo ZhangRuihao GongJinyang GuoXianglong LiuPublished in: EMNLP (2023)
Keyphrases
- language model
- language modeling
- probabilistic model
- language modelling
- speech recognition
- n gram
- statistical language models
- test collection
- retrieval model
- query expansion
- document retrieval
- information retrieval
- ad hoc information retrieval
- smoothing methods
- language models for information retrieval
- document length
- document ranking
- translation model
- pseudo relevance feedback
- context sensitive
- machine learning