The LLM Surgeon

arXiv:2312.17244v2 Announce Type: replace
Abstract: State-of-the-art language models are becoming increasingly large in an effort to achieve the highest performance on large corpora of available textual data. However, the sheer size of the Transformer architectures makes it difficult to deploy models within computational, environmental or device-specific constraints. We explore data-driven compression of existing pretrained models as an alternative to training smaller models from scratch. To do so, we scale Kronecker-factored curvature approximations of the target loss landscape to large language …

abstract architectures art arxiv compression computational constraints cs.cl cs.lg data data-driven deploy environmental explore however language language models llm performance pretrained models state textual transformer type