A clean PyTorch implementation of the original Transformer model + A German -> English translation example
-
Updated
Jan 24, 2022 - Python
A clean PyTorch implementation of the original Transformer model + A German -> English translation example
Cross-lingual Visual Pre-training for Multimodal Machine Translation
The Transformer model implemented from scratch using PyTorch. The model uses weight sharing between the embedding layers and the pre-softmax linear layer. Training on the Multi30k machine translation task is shown.
Neural Machine Tranlation using Local Attention
[KDD 2024] Improving the Consistency in Cross-Lingual Cross-Modal Retrieval with 1-to-K Contrastive Learning
Full training pipeline of attention model for machine translation task with PyTorch
English-To-German Neural Machine Translation Using Transformer
[SGU] 841448 - NLP (2025-2026 / HK1)
Original transformer model from scratch
A basic seq2seq transformers model trained and validated on the Multi30k dataset.
A from-scratch PyTorch implementation of the Transformer architecture from "Attention Is All You Need," trained for English-to-German translation on Multi30k.
To associate your repository with the multi30k topic, visit your repo's landing page and select "manage topics."