Dissecting the Runtime Performance of the Training, Fine-tuning, and Inference of Large Language Models.
Longteng ZhangXiang LiuZeyu LiXinglin PanPeijie DongRuibo FanRui GuoXin WangQiong LuoShaohuai ShiXiaowen ChuPublished in: CoRR (2023)
Keyphrases
- language model
- fine tuning
- language modeling
- fine tuned
- document retrieval
- probabilistic model
- language modelling
- n gram
- viable alternative
- speech recognition
- mixture model
- information retrieval
- statistical language models
- retrieval model
- test collection
- context sensitive
- query expansion
- language models for information retrieval
- ad hoc information retrieval
- vector space model
- pseudo relevance feedback
- relevance model
- word error rate
- smoothing methods
- passage retrieval
- query terms
- machine learning
- relevant documents
- okapi bm
- decision trees
- bayesian networks
- term dependencies
- training set
- query specific
- document ranking
- knn