AdaZeta: Adaptive Zeroth-Order Tensor-Train Adaption for Memory-Efficient Large Language Models Fine-Tuning.
Yifan YangKai ZhenErshad BanijamalAthanasios MouchtarisZheng ZhangPublished in: CoRR (2024)
Keyphrases
- language model
- memory efficient
- fine tuning
- language modeling
- n gram
- probabilistic model
- document retrieval
- speech recognition
- fine tune
- language modelling
- information retrieval
- viable alternative
- statistical language models
- retrieval model
- test collection
- context sensitive
- order tensor
- query expansion
- smoothing methods
- ad hoc information retrieval
- vector space model
- okapi bm
- document ranking
- language model for information retrieval
- fine tuned
- relevance model
- cross lingual
- language models for information retrieval
- retrieval effectiveness
- query terms