Update llava/model/multimodal_encoder/builder.py

llava/model/multimodal_encoder/builder.py

@@ -1,6 +1,6 @@
 import os
-from .clip_encoder import CLIPVisionTower, FlorenceVisionTower
-
+from .clip_encoder import CLIPVisionTower
+from .florence_encoder import FlorenceVisionTower
 
 def build_vision_tower(vision_tower_cfg, **kwargs):
     vision_tower = getattr(vision_tower_cfg, 'mm_vision_tower', getattr(vision_tower_cfg, 'vision_tower', None))