GPT-3(Language Models are Few-Shot Learners)论文阅读

还行! 目前共计 48 篇日志。 继续努力。

2023

06-19

GPT-3(Language Models are Few-Shot Learners)论文阅读

06-18

GPT-1(Improving Language Understanding by Generative Pre-Training)论文阅读

06-16

GPT-2(Language Models are Unsupervised Multitask Learners)论文阅读

06-15

CLIP(Contrastive Language–Image Pre-training)论文阅读

06-14

ViT(Vision Transformer)论文阅读

06-12

pytorch分布式训练使用Dataloader/WebDataset进行数据并行加载

06-08

Rotary Position Embeddings论文阅读

06-07

RMSNorm论文阅读

06-07

SwiGLU论文阅读

06-06

LLaMA(Large Language Model Meta AI)论文阅读