摘要: 文章目录 1. Self-attention2. Multi-head Self-attention3. Positional Encoding4. Transformer4.1 Encoder4.2 Decoder4.2.1 Autoregressive4.2.2 Non-autoregressi 阅读全文
posted @ 2024-01-10 10:19 mango1698 阅读(36) 评论(0) 推荐(0) 编辑