Mahdi Pourmirzaei
Mahdi Pourmirzaei
Is there any limitation for inferencing with higher resolution?? If the answer is no, does the model perform well on higher resolution such as 1024×1024 or more for in-painting?
Are there any experiments regarding the speed of efficientformer on gpu devices?
Would you please add `gradient_checkpointing_enable()` feature for ESM models? These models currently are the best available pre-trained protein language models for researchers. Many thanks.
# 🌟 New adapter setup ## Model description ESM represents a family of pre-trained models dedicated to protein studies, originating from Meta. The ESM-V2 models, in particular, stand out as...
Hello, I have a few questions which might be very basic to others. 1. Can we convert the 3Di tokens produced by foldseek into the actual 3D structure format like...
Hello I want to install TE using pip: `pip install git+https://github.com/NVIDIA/TransformerEngine.git@stable` But I got the following error during installation: ``` Collecting git+https://github.com/NVIDIA/TransformerEngine.git@stable Cloning https://github.com/NVIDIA/TransformerEngine.git (to revision stable) to /tmp/pip-req-build-c6l34itl Running...
Hello, I was looking into the huggingface tokenizer of BARTSmile and I could not find the mask token ( key) in the vocabulary. What was the mask token name during...
Hello, Thanks for your amazing repository. Do you have any plans to complete these two? ` refactor into full so3 -> so2 linear layer, as proposed in eSCN paper` `add...
Hello Thank you for this useful repository. My question is how much customizable foldcomp compression procedure? I want to exclude all bytes related to amino acid types and side chain...
Hi, Thanks to your amazing team for open-sourcing the ESM series. It's been a huge help to the research community! Could you please validate the correctness of the backbone coordinate...