BLOOM 训练背后的技术
Zero-Shot Information Extraction via Chatting with ChatGPT
ChatGPT 调研报告
Inverse scaling can become U-shaped
ChatGPT 标注指南来了!数据是关键
Large Language Models Are Human-Level Prompt Engineers
用于大型Transformer的8-bit矩阵乘法介绍
LoRA:Low-Rank Adaptation of Large Language Models
Reinforcement Learning from Human Feedback (RLHF)详解
多模态预训练模型综述
avatar
Weitang Liu
一个致力于记录技术的博客
Follow Me
公告
记录和分享一些学习和开源内容,若有任何问题可通过留言板或者微信公众号给我留言,谢谢!