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
In the paper, there is an 8 million weight model trained on the SPICE dataset. This model apparently took 7 days to train on an A100, so it's not that cheap to recreate.
I have looked through the paper and discussions and I don't see the weights available anywhere (nor anyone requesting them)?
I imagine many use-cases would start with a pre-trained SPICE model.
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
-
In the paper, there is an 8 million weight model trained on the SPICE dataset. This model apparently took 7 days to train on an A100, so it's not that cheap to recreate.
I have looked through the paper and discussions and I don't see the weights available anywhere (nor anyone requesting them)?
I imagine many use-cases would start with a pre-trained SPICE model.
Fantastic work -- thanks!
Beta Was this translation helpful? Give feedback.
All reactions