How to use bdsqlsz/image_encoder with Transformers:
# Load model directly from transformers import AutoTokenizer, CLIPVisionModelWithProjection tokenizer = AutoTokenizer.from_pretrained("bdsqlsz/image_encoder") model = CLIPVisionModelWithProjection.from_pretrained("bdsqlsz/image_encoder")
# Load model directly from transformers import AutoTokenizer, CLIPVisionModelWithProjection tokenizer = AutoTokenizer.from_pretrained("bdsqlsz/image_encoder") model = CLIPVisionModelWithProjection.from_pretrained("bdsqlsz/image_encoder")