OpenFold is trainable in full precision or `bfloat16` with or without DeepSpeed,
and we've trained it from scratch, matching the performance of the original.
We've publicly released model weights and our training data — some 400,000
MSAs — under a permissive license. Model weights are available from
scripts in this repository while the MSAs are hosted by the
MSAs and PDB70 template hit files — under a permissive license. Model weights
are available via scripts in this repository while the MSAs are hosted by the
[Registry of Open Data on AWS (RODA)](registry.opendata.aws/openfold).
Try out running inference for yourself with our [Colab notebook](https://colab.research.google.com/github/aqlaboratory/openfold/blob/main/notebooks/OpenFold.ipynb).
