Running on CPU Upgrade Featured 2.74k The Smol Training Playbook π 2.74k The secrets to building world-class LLMs
OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM Paper β’ 2510.15870 β’ Published Oct 17 β’ 89
Running 121 Berkeley Function Calling Leaderboard π 121 Display Berkeley Function-Calling Leaderboard
How Do Large Language Models Acquire Factual Knowledge During Pretraining? Paper β’ 2406.11813 β’ Published Jun 17, 2024 β’ 31