thnhan

> Hi, after downloading your latest model "uniref_embeddings", I found that the dimensionality of the protein word vector is not 100 dimensions, it is greater than 900 dimensions, so. Has...

> I’m using a pre-trained model `esm3-sm-open-v1` to extract residue embeddings via [link](https://github.com/evolutionaryscale/esm/issues/2#issuecomment-2189701682). However, the precision of my model is unexpectedly low. For reference, here’s a small snippet of the...