NNsight和NDIF：民主化存取基礎模型內部

NNsight and NDIF: Democratizing Access to Foundation Model Internals

July 18, 2024

作者: Jaden Fiotto-Kaufman, Alexander R Loftus, Eric Todd, Jannik Brinkmann, Caden Juang, Koyena Pal, Can Rager, Aaron Mueller, Samuel Marks, Arnab Sen Sharma, Francesca Lucchetti, Michael Ripa, Adam Belfki, Nikhil Prakash, Sumeet Multani, Carla Brodley, Arjun Guha, Jonathan Bell, Byron Wallace, David Bau

cs.AI

摘要

目前頂尖基礎模型的巨大規模限制了科學家們的可及性，因為在大型模型上進行定制實驗需要昂貴的硬體和複雜的工程，這對大多數研究人員來說是不切實際的。為了解決這些問題，我們引入了 NNsight，這是一個開源的 Python 套件，具有簡單靈活的 API，可以通過構建計算圖對任何 PyTorch 模型進行干預。我們還推出了 NDIF，這是一個協作研究平台，通過 NNsight API 為研究人員提供訪問基礎規模 LLMs 的途徑。代碼、文檔和教程可在 https://www.nnsight.net 上找到。

English

The enormous scale of state-of-the-art foundation models has limited their accessibility to scientists, because customized experiments at large model sizes require costly hardware and complex engineering that is impractical for most researchers. To alleviate these problems, we introduce NNsight, an open-source Python package with a simple, flexible API that can express interventions on any PyTorch model by building computation graphs. We also introduce NDIF, a collaborative research platform providing researchers access to foundation-scale LLMs via the NNsight API. Code, documentation, and tutorials are available at https://www.nnsight.net.