MINI-LLM: Memory-Efficient Structured Pruning for Large Language Models.
Hongrong ChengMiao ZhangJaven Qinfeng ShiPublished in: CoRR (2024)
Keyphrases
- language model
- memory efficient
- language modeling
- n gram
- probabilistic model
- speech recognition
- retrieval model
- information retrieval
- document retrieval
- test collection
- context sensitive
- iterative deepening
- query expansion
- statistical language models
- document ranking
- structured data
- language modelling
- smoothing methods
- pseudo relevance feedback
- search space
- language models for information retrieval
- vector space model
- query terms
- structured queries
- ad hoc information retrieval
- term dependencies
- cross lingual
- okapi bm
- translation model
- query specific
- word error rate
- statistical language modeling
- naive bayes