Amelie
Amelie
It would probably be a good idea to update this filter to the [AlphaFold-Multimer LIS Score](https://github.com/flyark/AFM-LIS) instead of the pAE filtering. It looks like this is significantly better based on...
Same!!! @sai-advaith please share!!! Or @LifeWorks do you have it?
@LifeWorks and @sai-advaith if either of you have the datasets and checkpoints, please let me know. I think @sai-advaith has a very useful repo, but it's unclear to me at...
Thanks so much @sai-advaith and @LifeWorks! I really appreciate the help getting the weights (and the excellent repo for getting the single and pair representations from EvoFormer)! I'd like the...
I wish I had them @pujaltes. If you get them, please let me know. I still don't have them.
Thanks for the tip @eskin22 really appreciate this! I will give this a try shortly and see how it goes and report back if there are any issues.
Thanks @kosonocky any chance you've had any luck with ProteinDT (the other CLIP based model by @chao1224) as well?
Would you be willing to provide your settings?
Thanks for the response! I'm still getting deterministic output. Any ideas why? Also, your first example above returns a warning: ``` UserWarning: `do_sample` is set to `False`. However, `temperature` is...
I am still getting deterministic behavior from the model. I've tried your recommendations, as well as top-k sampling, top-p sampling, temperature sampling, and a couple of others, and the model...