代码
class Solution {public int findNthDigit(int n) {int base 1;//位数int weight 9;//权重while(n>(long)base*weight){//300n-base*weight;base;weight*10;}//n111 base3 weight900;n--;int res (int)Math.pow(10,base-1)n/base;int index n%base;return String…
论文速读|Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Models 论文信息: 简介: 本文讨论的背景是大型语言模型(LLMs)的自我对齐问题。传统的LLMs对齐方法依赖于昂贵的训练和人类偏好注释&am…