aboutexo04

Multi Head Attention 부터 Original Transformer 모델, BERT, Encoder-Decoder 기반의 MarianMT 번역 모델까지 코드로 직접 구현하며 Transformer에 대해 속속들이 배우게 됩니다. 

권 철민

구현하며 배우는 Transformer

이론과 실습 한 번에

이론 실습 모두

transformer

바닥부터구현

From Multi Head Attention to the Original Transformer model, BERT, and Encoder-Decoder based MarianMT translation model, you'll learn Transformer inside and out by implementing them directly with code.

dooleyz3525

입문

초급

중급이상

Deep Learning(DL)

파이토치

PyTorch

encoder-decoder

bert

Learning Transformer Through Implementation

Course Introduction and Practice Environment Setup

Prerequisite Knowledge for Transformers - Understanding NLP Fundamentals and RNNs

Transformer Overview and Multi Head Self Attention Implementation

Implementing Transformer Encoder

Transformer Decoder Implementation

Handling Hugging Face Datasets

Handling Hugging Face Tokenizer and DataCollator

BERT Model Implementation, Training, and Inference

Implementing Encoder-Decoder Translation Model MarianMT

Implementation of MarianMT Model Training and Inference

Vision Transformer(ViT) Implementation