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
Hi, I would like to ask, in Swift fine-tuning, for a multimodal model, when --sft_type is set to full, does it mean that the parameters of all modules will be unfrozen, including the visual encoder?
The text was updated successfully, but these errors were encountered:
Hi, I would like to ask, in Swift fine-tuning, for a multimodal model, when --sft_type is set to full, does it mean that the parameters of all modules will be unfrozen, including the visual encoder?
Hi, I would like to ask, in Swift fine-tuning, for a multimodal model, when --sft_type is set to full, does it mean that the parameters of all modules will be unfrozen, including the visual encoder?
The text was updated successfully, but these errors were encountered: