Toggle navigation sidebar
Toggle in-page Table of Contents
Yet Another (JAX) Transformer
Yet Another (JAX) Transformer
1️⃣ Introduction to The Transformer Architecture
2️⃣ Implementing the Core Components
Attention Mechanism in the Transformer
The Multi-Headed Attention
Turning Tokens into Vectors: Embeddings and Positional Encoding
3️⃣ Transformer Encoder and Word-level Language Modeling
Combining all together: the Transformer Encoder
🚀 Training your First Language Model
Fine-Tuning for Sentiment Classification
4️⃣ Transformer and Neural Machine Translation
The Transformer Decoder
Preparation for the MT task
Training a Neural Machine Translation Model 🇬🇧 -> 🇮🇹
Quantitative Evaluation with BLEU
(
Bonus
) All the glitter is not gold: Gender Bias in Machine Translation
Assessing Representational Harm using WinoMT
repository
open issue
Index
