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
First of all, I want to thank everyone involved in such a great project! It is getting better with every release :)
I am wondering what would be the best sentence transformer for 4GB GPU - is there a significant quality difference betwen hkunlp/instructor-large and hkunlp/instructor-xl? The latter is too big for my 4 GB GPU and I understand that it cannot be partially offloaded to GPU VRAM as gguf models can
Is there enough of a quality difference between the two? I am using it mostly to infer from my old notes and if so, what transformer would you guys suggest besides hkunlp/instructor-large that is smaller than hkunlp/instructor-xl which uses > 5GB VRAM
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
First of all, I want to thank everyone involved in such a great project! It is getting better with every release :)
I am wondering what would be the best sentence transformer for 4GB GPU - is there a significant quality difference betwen hkunlp/instructor-large and hkunlp/instructor-xl? The latter is too big for my 4 GB GPU and I understand that it cannot be partially offloaded to GPU VRAM as gguf models can
Is there enough of a quality difference between the two? I am using it mostly to infer from my old notes and if so, what transformer would you guys suggest besides hkunlp/instructor-large that is smaller than hkunlp/instructor-xl which uses > 5GB VRAM
thank you in advance for any suggestions
Beta Was this translation helpful? Give feedback.
All reactions