CompactifAI: Extreme Compression of Large Language Models using Quantum-Inspired Tensor Networks.
Andrei TomutSaeed S. JahromiSukhbinder SinghFaysal IshtiaqCésar MuñozPrabdeep Singh BajajAli ElboradyGianni Del BimboMehrazin AlizadehDavid MonteroPablo Martin-RamiroMuhammad IbrahimOussama Tahiri-AlaouiJohn MalcolmSamuel MugelRoman OrusPublished in: CoRR (2024)
Keyphrases
- language model
- quantum inspired
- language modeling
- binary gravitational search algorithm
- n gram
- document retrieval
- language modelling
- speech recognition
- information retrieval
- probabilistic model
- quantum computing
- retrieval model
- test collection
- context sensitive
- document ranking
- query expansion
- statistical language models
- network structure
- language models for information retrieval
- vector space model
- smoothing methods
- translation model
- relevance model
- pseudo relevance feedback
- mutation operator
- immune clonal
- evolutionary algorithm
- database systems