44% on ARC-AGI-1 in 67 cents
发生了什么
I trained a small transformer from scratch in 1.5hrs on a 5090 Beats many LLMs, and scores the same as TRM/HRM
摘要按规则整理自下方来源原文
I trained a small transformer from scratch in 1.5hrs on a 5090 Beats many LLMs, and scores the same as TRM/HRM
摘要按规则整理自下方来源原文