mt5-M2M-comparison
OpenNMT-Tutorial
Our great sponsors
| mt5-M2M-comparison | OpenNMT-Tutorial | |
|---|---|---|
| 1 | 3 | |
| 13 | 137 | |
| - | - | |
| 3.8 | 4.6 | |
| almost 3 years ago | 13 days ago | |
| Jupyter Notebook | Jupyter Notebook | |
| - | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
mt5-M2M-comparison
-
[D] Comparing M2M to mT5 in low resource translation (10k dataset Yoruba - English)
I found no clear comparison nor a clear guide on how to fine tune both of the models on the translation task, so I decided to write it myself. (code: https://github.com/maroxtn/mt5-M2M-comparison)
OpenNMT-Tutorial
What are some alternatives?
fastT5 - ⚡ boost inference speed of T5 models by 5x & reduce the model size by 3x.
CTranslate2 - Fast inference engine for Transformer models
keytotext - Keywords to Sentences
sentencepiece - Unsupervised text tokenizer for Neural Network-based text generation.
100DaysOfML - 100 Days Of Machine Learning. New Content in every 1-2 day and projects every week. The massive 100DaysOfML in building
NeMo - A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
fake-news - Building a fake news detector from initial ideation to model deployment
pytorch-seq2seq - Tutorials on implementing a few sequence-to-sequence (seq2seq) models with PyTorch and TorchText.
question_generation - Neural question generation using transformers