Pavel Yakovlev

I have the same issue on my MacBook Pro 14 M1 Max. Torch version is `1.14.0.dev20221017`. ``` % python main.py ~/Downloads/rcsb_pdb_1FSD.fasta ~/Downloads/1FSD_output INFO:root:Loading weights from /Users/pavel/.cache/omegafold_ckpt/model.pt INFO:root:Constructing OmegaFold INFO:root:Reading /Users/pavel/Downloads/rcsb_pdb_1FSD.fasta...

Thank you for the hint. I use `SoftSPI` with MISO=37 and everything works fine at the same time with a display.

And when will it done? Or how can I change an example myself?

I have the same issue. BTW, if I use open-source pymol from Homebrew, there is no such problem. I've met it only on `conda-forge` version.

I have the same problem on my MacBook Pro (M1 Pro) even with a fresh environment: Python 3.9 ```bash % conda create -n abnumber -c bioconda python=3.9 abnumber Collecting package...

Thank! I've [fixed](https://github.com/RosettaCommons/RFdiffusion/issues/13#issuecomment-1535972773) the package for Windows environment.

I have the same issue on windows PC. It would be great to fix it, as WSL2 reduces CUDA perfomance.

I've found a solution. Open `rfdiffusion/inference/model_runners.py` and find the line `308`. Change this: ``` seq_orig = self.target_feats['seq'] ``` to this: ``` seq_orig = self.target_feats['seq'].long() ```

And how can `WNil` and `WCons` be written for this encoding? I've tried to use such sort of encoding: ``` WList = λ(a : *) → ∀(WList : * →...