QQQ: Quality Quattuor-Bit Quantization for Large Language Models.
Ying ZhangPeng ZhangMincong HuangJingyang XiangYujie WangChao WangYineng ZhangLei YuChuan LiuWei LinPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- n gram
- probabilistic model
- information retrieval
- statistical language models
- document retrieval
- language modelling
- speech recognition
- query expansion
- test collection
- retrieval model
- language models for information retrieval
- translation model
- ad hoc information retrieval
- smoothing methods
- query terms
- context sensitive
- document ranking
- language model for information retrieval
- pseudo relevance feedback
- uniform quantization
- vector space model
- statistical language modeling
- cross lingual
- language modeling approaches
- knn