| custom_config = { | |
| "_class_name": "CLIPModel", | |
| "_diffusers_version": "1.0.0", # You can adjust the version | |
| "_name_or_path": "custom-clip-model", | |
| "temperature": 1.0, | |
| "image_embedding": 2048, | |
| "text_embedding": 768, | |
| "image_encoder": { | |
| "_class_name": "ImageEncoder", | |
| "model_name": "resnet50", | |
| "pretrained": True, | |
| "trainable": True | |
| }, | |
| "text_encoder": { | |
| "_class_name": "TextEncoder", | |
| "model_name": "distilbert-base-multilingual-cased", | |
| "pretrained": True, | |
| "trainable": True | |
| }, | |
| "image_projection": { | |
| "_class_name": "ProjectionHead", | |
| "embedding_dim": 2048, | |
| "projection_dim": 256, | |
| "dropout": 0.1 | |
| }, | |
| "text_projection": { | |
| "_class_name": "ProjectionHead", | |
| "embedding_dim": 768, | |
| "projection_dim": 256, | |
| "dropout": 0.1 | |
| } | |
| } | |
| # Adjust the class names and versions accordingly | |