Generative Lecture 4: Autoregressive Models (AR)
The note introduces autoregressive models, covering their training, evaluation, decoding strategies, RNN and Transformer implementations, and computational complexity.
TAG
#transformer
共有 3 篇文章提到了这个关键词。
带有transformer标签的文章列表
20260908
月亮
CS336 Assignment 1：BPE Tokenizer 实现与优化
以 CS336 Assignment 1 为基础，从零实现 byte-level BPE Tokenizer，并通过增量更新、优先队列与多进程预分词优化训练性能