BlockPruner: Fine-grained Pruning for Large Language Models.
Longguang ZhongFanqi WanRuijun ChenXiaojun QuanLiangzhi LiPublished in: CoRR (2024)
Keyphrases
- fine grained
- language model
- language modeling
- coarse grained
- n gram
- probabilistic model
- document retrieval
- language modelling
- information retrieval
- access control
- speech recognition
- retrieval model
- query expansion
- test collection
- vector space model
- statistical language models
- context sensitive
- smoothing methods
- language models for information retrieval
- document ranking
- relevance model
- pseudo relevance feedback
- query terms
- user behavior