Divergent Token Metrics: Measuring degradation to prune away LLM components – and optimize quantization Björn Deiseroth author Max Meuer author Nikolas Gritsch author Constantin Eichenberg author Patrick Schramowski author Matthias Aßenmacher author Kristian Kersting author 2024-06 text Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) Kevin Duh editor Helena Gomez editor Steven Bethard editor Association for Computational Linguistics Mexico City, Mexico conference publication deiseroth-etal-2024-divergent 10.18653/v1/2024.naacl-long.377 https://aclanthology.org/2024.naacl-long.377/ 2024-06 6764 6783