Что думаешь? Оцени!
Smaller models seem to be more complex. The encoding, reasoning, and decoding functions are more entangled, spread across the entire stack. I never found a single area of duplication that generalised across tasks, although clearly it was possible to boost one ‘talent’ at the expense of another. But as models get larger, the functional anatomy becomes more separated. The bigger models have more ‘space’ to develop generalised ‘thinking’ circuits, which may be why my method worked so dramatically on a 72B model. There’s a critical mass of parameters below which the ‘reasoning cortex’ hasn’t fully differentiated from the rest of the brain.。使用 WeChat 網頁版对此有专业解读
。关于这个话题，谷歌提供了深入分析
Дан прогноз по ключевой ставке в России14:48
«Распутица добралась до фронта». ВСУ начали охоту на российских военнослужащих, которые сбивают их поставки дронами. Что известно?20:57。关于这个话题，移动版官网提供了深入分析