BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation.
Peng XuWenqi ShaoMengzhao ChenShitao TangKaipeng ZhangPeng GaoFengwei AnYu QiaoPing LuoPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- document retrieval
- n gram
- probabilistic model
- speech recognition
- information retrieval
- language modelling
- test collection
- query expansion
- language model for information retrieval
- language models for information retrieval
- statistical language models
- retrieval model
- document length
- context sensitive
- query terms
- web pages
- translation model
- smoothing methods
- information retrieval systems
- feature selection