You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I was wondering, using Ankh, have you generated the embeddings on uniref50 or another database and made it available somewhere by any chance ? It would be awesome and time saving ! Both in float16 or float64. (float16 would be easier to store, and I think it is as performant as float64 on downstream tasks ?)
Thanks
The text was updated successfully, but these errors were encountered:
We have not generated the embedding for uniref50. As you know, it would require a lot of computing and storage.
As our models are highly optimized, users could use them quickly to extract the embedding for their own use cases.
Could you please share your own use-case and what are the benefits for you to have access to the whole uniref50 embedding?
I have tagged our product owner @wafaaashraf to follow-up on this request.
Hi, thanks so much for your work !
I was wondering, using Ankh, have you generated the embeddings on uniref50 or another database and made it available somewhere by any chance ? It would be awesome and time saving ! Both in float16 or float64. (float16 would be easier to store, and I think it is as performant as float64 on downstream tasks ?)
Thanks
The text was updated successfully, but these errors were encountered: