Ata uhi

NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals

I tiakina i:
I whakaputaina i:arXiv.org (Dec 8, 2024), p. n/a
Kaituhi matua: Fiotto-Kaufman, Jaden
Ētahi atu kaituhi: Loftus, Alexander R, Todd, Eric, Brinkmann, Jannik, Pal, Koyena, Troitskii, Dmitrii, Ripa, Michael, Belfki, Adam, Rager, Can, Juang, Caden, Mueller, Aaron, Marks, Samuel, Arnab Sen Sharma, Lucchetti, Francesca, Prakash, Nikhil, Brodley, Carla, Guha, Arjun, Bell, Jonathan, Wallace, Byron C, Bau, David
I whakaputaina:
Cornell University Library, arXiv.org
Ngā marau:
Application programming interface
Python
Source code
Neural networks
Urunga tuihono:Citation/Abstract
Full text outside of ProQuest
Ngā Tūtohu: Tāpirihia he Tūtohu
Kāore He Tūtohu, Me noho koe te mea tuatahi ki te tūtohu i tēnei pūkete!
Whakarāpopotonga:We introduce NNsight and NDIF, technologies that work in tandem to enable scientific study of very large neural networks. NNsight is an open-source system that extends PyTorch to introduce deferred remote execution. NDIF is a scalable inference service that executes NNsight requests, allowing users to share GPU resources and pretrained models. These technologies are enabled by the intervention graph, an architecture developed to decouple experiment design from model runtime. Together, this framework provides transparent and efficient access to the internals of deep neural networks such as very large language models (LLMs) without imposing the cost or complexity of hosting customized models individually. We conduct a quantitative survey of the machine learning literature that reveals a growing gap in the study of the internals of large-scale AI. We demonstrate the design and use of our framework to address this gap by enabling a range of research methods on huge models. Finally, we conduct benchmarks to compare performance with previous approaches. Code documentation, and materials are available at https://nnsight.net/.
ISSN:2331-8422
Puna:Engineering Database