eDKM: An Efficient and Accurate Train-time Weight Clustering for Large Language Models.
Minsik ChoKeivan Alizadeh-VahidQichen FuSaurabh AdyaCarlo C. Del MundoMohammad RastegariDevang NaikPeter ZatloukalPublished in: CoRR (2023)
Keyphrases
- language model
- language modeling
- document retrieval
- language modelling
- n gram
- clustering algorithm
- probabilistic model
- statistical language models
- retrieval model
- speech recognition
- query expansion
- mixture model
- test collection
- language model for information retrieval
- smoothing methods
- context sensitive
- information retrieval
- data clustering
- clustering method
- query terms
- hierarchical clustering
- document clustering
- retrieval effectiveness
- language models for information retrieval
- ad hoc information retrieval
- spectral clustering
- web search
- translation model
- k means
- document ranking
- query specific
- machine learning
- keywords
- information extraction
- document level
- passage retrieval
- relevance model
- vector space model
- text classification