How to use facebook/PE-Core-G14-448 with PerceptionEncoder:
# Use PE-Core models as CLIP models import core.vision_encoder.pe as pe model = pe.CLIP.from_config("facebook/PE-Core-G14-448", pretrained=True)
# Use any PE model as a vision encoder import core.vision_encoder.pe as pe model = pe.VisionTransformer.from_config("facebook/PE-Core-G14-448", pretrained=True)
· Sign up or log in to comment
