Norm Tweaking: High-performance Low-bit Quantization of Large Language Models.
Liang LiQingyuan LiBo ZhangXiangxiang ChuPublished in: CoRR (2023)
Keyphrases
- language model
- language modeling
- probabilistic model
- n gram
- document retrieval
- speech recognition
- query expansion
- information retrieval
- language modelling
- uniform quantization
- test collection
- retrieval model
- document ranking
- smoothing methods
- statistical language models
- context sensitive
- vector space model
- ad hoc information retrieval
- word error rate
- language models for information retrieval
- document length
- term dependencies
- translation model
- passage retrieval
- relevance model
- error rate