Naail Kashif-Khan

It looks like T1042 does indeed have a length of 73 residues, but from the PDB text you post @zhenyuhe00 the crystal structure only models residues 3-73. This would mean...

On DeepSpeed compatibility: this is actually an issue with OpenFold - see here [https://github.com/aqlaboratory/openfold/issues/276](https://github.com/aqlaboratory/openfold/issues/276). Replacing all occurrences of `deepspeed.utils.is_initialized()` with `deepspeed.comm.comm.is_initialized()` in `openfold/model/primitives.py` fixes the issue and allows you to...

I had a similar issue when trying to use Openfold as part of ESMFold, with DeepSpeed version `0.9.2` I get the error that `deepspeed.utils.is_initialized()` doesn't exist anymore. But replacing all...

Looks like you're trying to use `extract.py` with ESM-IF which isn't supported - `extract.py` is used for obtaining embeddings from the ESM language models. Also, I think the input file...

Looks like a bug, I've opened a PR to address this #488

You can get the PAE using this code snippet (adapted from the [ESMFold ColabFold notebook](https://colab.research.google.com/github/sokrypton/ColabFold/blob/main/ESMFold.ipynb#scrollTo=JM5ciSmeTZKO)): ``` with torch.no_grad(): output = model.infer(sequence) #Retrieve PAE values from the model outputs pae =...