This repository provides a notebook to continue the unsupervised pre-training of the ProtT5 model.
The original publication and repository can be found at:
- ProtTrans: Toward Understanding the Language of Life Through Self-Supervised Learning
- ProtTrans Repository
The EvoTuning notebook can be found here:
- PT5_EvoTuning.ipynb
- Colab version
To run the notebook locally you will need at least the following packages:
- Torch version: 1.13.1
- Cuda version: 11.7
- Numpy version: 1.22.3
- Pandas version: 1.5.3
- Transformers version: 4.47.1
- Datasets version: 2.9.0
- biopython
License
The source code in this repository is licensed under the MIT license, which you can find in the MIT-LICENSE.txt file.