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
Hello, I am confused about the parameter number of CogVLM. According to README, its a 10B vision + 7B text. But according to the paper, visual encoder is a EVA2-CLIP-E model (4.4B). Did you add vision expert module's parameter number to vision account?
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
-
Hello, I am confused about the parameter number of CogVLM. According to README, its a 10B vision + 7B text. But according to the paper, visual encoder is a EVA2-CLIP-E model (4.4B). Did you add vision expert module's parameter number to vision account?
Beta Was this translation helpful? Give feedback.
All reactions