T5 Base Swedish

🚀 Google's T5 - A Unified Text-to-Text Transformer

Google's T5 is a pre - trained model that explores transfer learning in natural language processing by converting every language problem into a text - to - text format, achieving state - of - the - art results on multiple benchmarks.

🚀 Quick Start

This README provides an overview of Google's T5 model, including its pre - training dataset, related research paper, and some associated model series and specific model links.

✨ Features

• Transfer Learning: Utilizes transfer learning, pre - training on a data - rich task and then fine - tuning on downstream tasks.
• Unified Framework: Converts every language problem into a text - to - text format.
• State - of - the - art Results: Achieves excellent performance on many benchmarks such as summarization, question answering, and text classification.

📚 Documentation

Model Information

• Model Link: Google's T5
• Pretraining Dataset: C4
• Paper: Exploring the Limits of Transfer Learning with a Unified Text - to - Text Transformer
• Authors: Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, Peter J. Liu

Abstract

Transfer learning, where a model is first pre - trained on a data - rich task before being fine - tuned on a downstream task, has emerged as a powerful technique in natural language processing (NLP). The effectiveness of transfer learning has given rise to a diversity of approaches, methodology, and practice. In this paper, we explore the landscape of transfer learning techniques for NLP by introducing a unified framework that converts every language problem into a text - to - text format. Our systematic study compares pre - training objectives, architectures, unlabeled datasets, transfer approaches, and other factors on dozens of language understanding tasks. By combining the insights from our exploration with scale and our new “Colossal Clean Crawled Corpus”, we achieve state - of - the - art results on many benchmarks covering summarization, question answering, text classification, and more. To facilitate future work on transfer learning for NLP, we release our dataset, pre - trained models, and code.

Model Image

Model Series

This model is part of a series of models training on TPU with Flax Jax during Huggingface Flax/Jax challenge.

Specific Models

Gpt models

• Swedish Gpt: https://huggingface.co/birgermoell/swedish - gpt/
• Swedish gpt wiki: https://huggingface.co/flax - community/swe - gpt - wiki
• Nordic gpt wiki: https://huggingface.co/flax - community/nordic - gpt - wiki
• Dansk gpt wiki: https://huggingface.co/flax - community/dansk - gpt - wiki
• Norsk gpt wiki: https://huggingface.co/flax - community/norsk - gpt - wiki

Roberta models

• Nordic Roberta Wiki: https://huggingface.co/flax - community/nordic - roberta - wiki
• Swe Roberta Wiki Oscar: https://huggingface.co/flax - community/swe - roberta - wiki - oscar
• Roberta Swedish Scandi: https://huggingface.co/birgermoell/roberta - swedish - scandi
• Roberta Swedish: https://huggingface.co/birgermoell/roberta - swedish

Swedish T5 model

• Swedish T5 model: https://huggingface.co/birgermoell/t5 - base - swedish

📄 License

This project is licensed under the [apache - 2.0](https://www.apache.org/licenses/LICENSE - 2.0) license.