no code implementations • 8 May 2024 • Luke Merrick, Danmei Xu, Gaurav Nuti, Daniel Campos
This report describes the training dataset creation and recipe behind the family of \texttt{arctic-embed} text embedding models (a set of five models ranging from 22 to 334 million parameters with weights open-sourced under an Apache-2 license).
no code implementations • 1 Oct 2019 • Luke Merrick
Given a model $f$ that predicts a target $y$ from a vector of input features $\pmb{x} = x_1, x_2, \ldots, x_M$, we seek to measure the importance of each feature with respect to the model's ability to make a good prediction.
1 code implementation • 17 Sep 2019 • Luke Merrick, Ankur Taly
While existing papers focus on the axiomatic motivation of Shapley values, and efficient techniques for computing them, they offer little justification for the game formulations used, and do not address the uncertainty implicit in their methods' outputs.