Extreme Compression of Large Language Models via Additive Quantization.
Vage EgiazarianAndrei PanferovDenis KuznedelevElias FrantarArtem BabenkoDan AlistarhPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- document retrieval
- n gram
- probabilistic model
- query expansion
- speech recognition
- context sensitive
- compression ratio
- image compression
- retrieval model
- test collection
- statistical language models
- smoothing methods
- language modelling
- compression scheme
- language models for information retrieval
- document length
- information retrieval
- query terms
- ad hoc information retrieval
- vector space model
- relevance model
- language model for information retrieval
- translation model
- passage retrieval
- pseudo relevance feedback
- web documents
- bayesian networks
- feature selection