Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling.
Xiuying WeiYunchen ZhangYuhang LiXiangguo ZhangRuihao GongJinyang GuoXianglong LiuPublished in: CoRR (2023)
Keyphrases
- language model
- language modeling
- document retrieval
- n gram
- probabilistic model
- speech recognition
- information retrieval
- query expansion
- statistical language models
- language modelling
- retrieval model
- smoothing methods
- document ranking
- context sensitive
- language models for information retrieval
- test collection
- ad hoc information retrieval
- translation model
- word error rate
- error rate
- language model for information retrieval
- okapi bm
- term dependencies
- vector space model