IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact.
Ruikang LiuHaoli BaiHaokun LinYuening LiHan GaoZhengzhuo XuLu HouJun YaoChun YuanPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- n gram
- document retrieval
- speech recognition
- information retrieval
- retrieval model
- probabilistic model
- query expansion
- language modelling
- mixture model
- test collection
- ad hoc information retrieval
- statistical language models
- language model for information retrieval
- context sensitive
- smoothing methods
- vector space model
- relevance model
- query terms
- word clouds
- pseudo relevance feedback
- document ranking
- pseudo feedback
- machine learning