Implement the "Attention Is All You Need" paper from scratch using PyTorch, focusing on building a sequence-to-sequence transformer architecture for translating text from English to Italian
Transformer-based Neural Machine Translation model for English to Italian, built with PyTorch and Hugging Face’s transformers. This project includes full training and inference capabilities, and is designed to demonstrate the implementation of the architecture as described in the ‘Attention is All You Need’ paper.
Texts, translation resources, dateset subsets and notebooks for translating TICO-19 (EN-IT) PubMed texts with NMT and LLMs. Original TICO 19 project available at: https://tico-19.github.io/
Transformer NMT from scratch for English→Italian — full encoder-decoder, word-level tokenizers (Whitespace + WordLevel) on opus_books, loss 6.17→2.28 over 20 epochs on P100
Add a description, image, and links to the english-italian topic page so that developers can more easily learn about it.
To associate your repository with the english-italian topic, visit your repo's landing page and select "manage topics."