Rare find

Language Model Training. Learn how to build and train AI models that understand language.

github.com/nickchen121/Pre-training-language-model
by @nickchen121

Vaya's read on this project

Problem, audience, market, and the verdict — sign in to see it.

Updates

July 2022
  • Add files via upload
  • Delete 19 Transformer 解码器的两个为什么（为什么做掩码、为什么用编码器-解码器注意力）.md
  • Delete 18 Transformer 的动态流程演示.md
  • Delete 17 Transformer 的解码器（Decoders）——我要生成一个又一个单词.md
  • Delete 16 Transformer 的编码器（Encodes）——我在做更优秀的词向量.md
  • Delete 15 Transformer 框架概述.md
  • Delete 14 Positional Encoding （为什么 Self-Attention 需要位置编码）.md
  • Delete 13 Multi-Head Self-Attention（从空间角度解释为什么做多头）.md
  • Delete 12 Masked Self-Attention（掩码自注意力机制）.md
  • Delete 11 Self-Attention相比较 RNN和LSTM的优缺点.md
  • Delete 10 Self-Attention（自注意力机制）.md
  • Delete 09 什么是注意力机制（Attention ）.md
  • Delete 08 ELMo模型（双向LSTM模型解决词向量多义问题）.md
  • Delete 07 预训练语言模型的下游任务改造简介（如何使用词向量）.md
  • Delete 06 Word2Vec模型（第一个专门做词向量的模型，CBOW和Skip-gram）.md
  • Delete 05 神经网络语言模型（独热编码+词向量的起源）.md
  • Delete 04 统计语言模型（n元语言模型）.md
  • Delete 03 什么是预训练（Transformer 前奏）.md
  • Update 18 Transformer 的动态流程演示.md
  • Add files via upload