TY - GENERIC DO - 10.20944/preprints202407.1568.v1 UR - http://dx.doi.org/10.20944/preprints202407.1568.v1 TI - Sparsity Limit to Prune Large Language Models for on-Device AI Assistants: Llama-2 as an Example T2 - Preprints AU - Liu, Bo AU - Xu, Yuru PY - 2024 DA - 2024/07/19 PB - Preprints