QuIP: 2-Bit Quantization of Large Language Models With Guarantees.
Jerry CheeYaohui CaiVolodymyr KuleshovChristopher De SaPublished in: NeurIPS (2023)
Keyphrases
- language model
- uniform quantization
- language modeling
- n gram
- probabilistic model
- document retrieval
- retrieval model
- speech recognition
- statistical language models
- language modelling
- query expansion
- test collection
- smoothing methods
- context sensitive
- information retrieval
- document ranking
- language models for information retrieval
- relevance model
- okapi bm
- spoken term detection
- word error rate
- vector space model
- query terms
- ad hoc information retrieval
- statistical language modeling
- language model for information retrieval
- document length
- term dependencies
- translation model