LoRAP: Transformer Sub-Layers Deserve Differentiated Structured Compression for Large Language Models.
Guangyan LiYongqiang TangWensheng ZhangPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- speech recognition
- document retrieval
- probabilistic model
- n gram
- query expansion
- retrieval model
- information retrieval
- language modelling
- statistical language models
- test collection
- context sensitive
- ad hoc information retrieval
- structured data
- word error rate
- language models for information retrieval
- feature selection
- smoothing methods
- document ranking
- vector space model
- query specific
- translation model
- retrieval effectiveness
- query terms
- statistical language modeling
- recommender systems