| { | |
| "_name_or_path": "openai/clip-vit-large-patch14", | |
| "architectures": [ | |
| "CLIPForImageClassification" | |
| ], | |
| "id2label": { | |
| "0": "0", | |
| "1": "1", | |
| "2": "2", | |
| "3": "3", | |
| "4": "4", | |
| "5": "5", | |
| "6": "6", | |
| "7": "7", | |
| "8": "8", | |
| "9": "9" | |
| }, | |
| "initializer_factor": 1.0, | |
| "label2id": { | |
| "0": 0, | |
| "1": 1, | |
| "2": 2, | |
| "3": 3, | |
| "4": 4, | |
| "5": 5, | |
| "6": 6, | |
| "7": 7, | |
| "8": 8, | |
| "9": 9 | |
| }, | |
| "logit_scale_init_value": 2.6592, | |
| "model_type": "clip", | |
| "problem_type": "single_label_classification", | |
| "projection_dim": 768, | |
| "text_config": { | |
| "dropout": 0.0, | |
| "hidden_size": 768, | |
| "intermediate_size": 3072, | |
| "model_type": "clip_text_model", | |
| "num_attention_heads": 12, | |
| "projection_dim": 768 | |
| }, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.44.2", | |
| "vision_config": { | |
| "dropout": 0.0, | |
| "hidden_size": 1024, | |
| "intermediate_size": 4096, | |
| "model_type": "clip_vision_model", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 24, | |
| "patch_size": 14, | |
| "projection_dim": 768 | |
| } | |
| } | |