attention_is_all_you_need and attention-is-all-you-need-paper

These are competitors—both are independent implementations of the same Transformer architecture from the seminal 2017 paper, so users would select one based on framework preference (Chainer vs. likely PyTorch/TensorFlow) rather than use them together.

Maintenance 0/25
Adoption 10/25
Maturity 16/25
Community 23/25
Maintenance 0/25
Adoption 10/25
Maturity 16/25
Community 22/25
Stars: 323
Forks: 66
Downloads:
Commits (30d): 0
Language: Jupyter Notebook
License: BSD-3-Clause
Stars: 243
Forks: 54
Downloads:
Commits (30d): 0
Language: Jupyter Notebook
License: MIT
Stale 6m No Package No Dependents
Stale 6m No Package No Dependents

About attention_is_all_you_need

soskek/attention_is_all_you_need

Transformer of "Attention Is All You Need" (Vaswani et al. 2017) by Chainer.

This project helps machine learning engineers or researchers implement the Transformer model for sequence-to-sequence tasks. You input pairs of text in different languages, and it generates a trained model capable of translating or transforming new text sequences. It's designed for those who need to experiment with or apply the Transformer architecture to problems like machine translation or text summarization.

natural-language-processing machine-translation sequence-modeling deep-learning-research

About attention-is-all-you-need-paper

brandokoch/attention-is-all-you-need-paper

Original transformer paper: Implementation of Vaswani, Ashish, et al. "Attention is all you need." Advances in neural information processing systems. 2017.

This project provides a clear, runnable implementation of the original Transformer neural network architecture. It allows machine learning researchers and students to input text data, train a model on it, and then use that model to translate text, for example, from English to German. This is ideal for those learning about or experimenting with foundational natural language processing models.

natural-language-processing machine-translation deep-learning-research neural-networks computational-linguistics

Scores updated daily from GitHub, PyPI, and npm data. How scores work