clip-vit-base-patch32_mbart-large-50
Pretrained CLIP-Vision-mBART50 pre-trained on subset of translated Conceptual-12M image-text pairs using a seq2seq model training objective. 2.5M cleaned...
Pretrained CLIP-Vision-mBART50 pre-trained on subset of translated Conceptual-12M image-text pairs using a seq2seq model training objective. 2.5M cleaned...