Integer or Floating Point? New Outlooks for Low-Bit Quantization on Large Language Models.
Yijia ZhangLingran ZhaoShijie CaoWenqiang WangTing CaoFan YangMao YangShanghang ZhangNingyi XuPublished in: CoRR (2023)
Keyphrases
- floating point
- language model
- language modeling
- n gram
- probabilistic model
- document retrieval
- fixed point
- information retrieval
- speech recognition
- uniform quantization
- context sensitive
- language modelling
- retrieval model
- query expansion
- statistical language models
- sparse matrices
- test collection
- language models for information retrieval
- pseudo relevance feedback
- document ranking
- instruction set
- query terms
- floating point arithmetic
- language model for information retrieval
- smoothing methods
- vector space model
- query specific
- okapi bm
- statistical language modeling
- graphical models