Multitask Text and Chemistry T5 Base Standard Open-Source Model - Solving Multidisciplinary Tasks in Chemistry and Natural Language

Multitask Text And Chemistry T5 Base Standard

Developed by GT4SD

A multi-domain, multitask language model designed to address a wide range of tasks in chemistry and natural language processing.

Large Language Model

Transformers

EnglishOpen Source License:MIT #Chemical Text Multitasking #Molecular Description Generation #Reaction Prediction

Downloads 150

Release Time : 5/19/2023

Model Overview

This model is based on the T5-base architecture and trained by aggregating datasets from multiple tasks, covering forward reaction prediction, retrosynthesis, molecular description, text-conditioned generation, and paragraph-to-action across multiple domains and tasks.

Model Features

Multi-domain Unified Representation

Capable of handling representation learning for both chemical molecules and natural language text.

Multitask Learning

Solves multiple tasks in chemistry and text domains with a single model.

Cross-modal Capabilities

Supports mutual conversion between chemical structures and text descriptions.

Model Capabilities

Chemical reaction prediction

Molecular description generation

Text-conditioned molecular generation

Chemical text conversion

Use Cases

Drug Discovery

Retrosynthetic Analysis

Predicts possible synthetic pathways for target molecules.

Chemical Education

Molecular Description Generation

Automatically generates text descriptions of chemical molecules.

Materials Research

Text-conditioned Molecular Generation

Generates molecular structures that meet requirements based on text descriptions.

🚀 Multitask Text and Chemistry T5

A multi - domain, multi - task language model designed to tackle a diverse array of tasks in both the chemical and natural language fields.

🚀 Quick Start

Multitask Text and Chemistry T5 is a multi - domain, multi - task language model. It can solve a wide range of tasks in both the chemical and natural language domains. It was published by Christofidellis et al..

✨ Features

Model Details

The Multitask Text and Chemistry T5 variant is trained using t5 - base as its pretrained base and the standard dataset.

Developers

Dimitrios Christofidellis*, Giorgio Giannone*, Jannis Born, Teodoro Laino, and Matteo Manica from IBM Research, and Ole Winther from Technical University of Denmark. (*equal contribution)

Distributors

The model is natively integrated into GT4SD.

Model Date

2023

Model Type

A Transformer - based language model trained on a multi - domain and multi - task dataset by aggregating available datasets for the tasks of Forward reaction prediction, Retrosynthesis, Molecular captioning, Text - conditional de novo generation, and Paragraph to actions.

Paper or Other Resources

For more information, refer to The Multitask Text and Chemistry T5 Christofidellis et al.(2023)

License

MIT

Contact

Open an issue on [GT4SD repository](https://github.com/GT4SD/gt4sd - core) to send questions or comments about the model.

📄 License

This project is licensed under the MIT License.

📚 Documentation

Information Table

Property	Details
Model Type	A Transformer - based language model that is trained on a multi - domain and a multi - task dataset by aggregating available datasets for the tasks of Forward reaction prediction, Retrosynthesis, Molecular captioning, Text - conditional de novo generation and Paragraph to actions.
Training Data	N.A.
Developers	Dimitrios Christofidellis, Giorgio Giannone, Jannis Born, Teodoro Laino and Matteo Manica from IBM Research and Ole Winther from Technical University of Denmark. (*equal contribution)
Distributors	Model natively integrated into GT4SD.
Model Date	2023
Paper	The Multitask Text and Chemistry T5 Christofidellis et al.(2023)
License	MIT
Contact	Open an issue on [GT4SD repository](https://github.com/GT4SD/gt4sd - core)

📚 Citation

@inproceedings{christofidellis2023unifying,
  title = 	 {Unifying Molecular and Textual Representations via Multi - task Language Modelling},
  author =       {Christofidellis, Dimitrios and Giannone, Giorgio and Born, Jannis and Winther, Ole and Laino, Teodoro and Manica, Matteo},
  booktitle = 	 {Proceedings of the 40th International Conference on Machine Learning},
  pages = 	 {6140--6157},
  year = 	 {2023},
  volume = 	 {202},
  series = 	 {Proceedings of Machine Learning Research},
  publisher =    {PMLR},
  pdf = 	 {https://proceedings.mlr.press/v202/christofidellis23a/christofidellis23a.pdf},
  url = 	 {https://proceedings.mlr.press/v202/christofidellis23a.html},
}

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご