About me
Hailey Schoelkopf is a Research Scientist at EleutherAI, a non-profit research lab focused on enabling open science on large-scale AI models. Her research has focused on building reproducible infrastructure for empowering open science on large-scale models, with core interests in language model evaluation and systems optimizations in model pretraining. She is currently a maintainer of the LM Evaluation Harness library for standardized evaluations, and has previously worked on other projects across the LM development cycle such as pretraining Pythia, the first fully-transparent language models.