T5 V1 1 Small

🚀 Google's T5 Version 1.1

Google's T5 Version 1.1 is an enhanced natural language processing model that offers significant improvements over the original T5, enabling more efficient and accurate text - to - text transformations.

🚀 Quick Start

This README provides detailed information about Google's T5 Version 1.1, including its improvements, pre - training details, and relevant research papers.

✨ Features

• Activation Function Upgrade: T5 Version 1.1 uses GEGLU activation in the feed - forward hidden layer instead of ReLU, as described in this paper.
• Dropout Adjustment: Dropout was turned off during pre - training to improve quality. It should be re - enabled during fine - tuning.
• Pre - training Strategy: The model was pre - trained only on C4 without mixing in downstream tasks.
• Parameter Sharing: There is no parameter sharing between the embedding and classifier layer.
• Model Naming and Shape: "xl" and "xxl" replace "3B" and "11B". The model shapes have a larger d_model and smaller num_heads and d_ff.

📚 Documentation

Version 1.1 Details

T5 Version 1.1 has several improvements compared to the original T5 model:

• GEGLU activation in the feed - forward hidden layer, rather than ReLU - see here.
• Dropout was turned off in pre - training (quality win). Dropout should be re - enabled during fine - tuning.
• Pre - trained on C4 only without mixing in the downstream tasks.
• No parameter sharing between the embedding and classifier layer.
• "xl" and "xxl" replace "3B" and "11B". The model shapes are a bit different - larger d_model and smaller num_heads and d_ff.

Note: T5 Version 1.1 was only pre - trained on C4 excluding any supervised training. Therefore, this model has to be fine - tuned before it is useable on a downstream task.

Pretraining Dataset

Pretraining Dataset: C4

Other Community Checkpoints

Other Community Checkpoints: [here](https://huggingface.co/models?search=t5 - v1_1)

Paper

Paper: Exploring the Limits of Transfer Learning with a Unified Text - to - Text Transformer

Authors

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.

📄 License

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