GitHubRepoluoshu_kitLuoshuKit: making neural activations addressable and computable.mechanistic-interpretabilitypytorchstructured-computation2Python8 mo agoluolearningShare or keepTake it
lm resiliencyGitHubRepolm-resiliencyClosed-loop fault localization and checkpoint recovery for LLM Pre-trainingcheckpoint-recoveryfailure-localizationresiliency190PythonBSD-3-Clause5 d agoLMResiliencyShare or keepTake it