I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Models.
Xing HuYuan ChengDawei YangZhihang YuanJiangyong YuChen XuSifan ZhouPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- n gram
- probabilistic model
- information retrieval
- document retrieval
- statistical language models
- language modelling
- retrieval model
- test collection
- context sensitive
- speech recognition
- relevance model
- smoothing methods
- mixture model
- vector space model
- query expansion
- significant bit
- ad hoc information retrieval
- language model for information retrieval
- word error rate
- translation model
- text retrieval
- bayesian networks