| { | |
| "_name_or_path": "./image_encoder", | |
| "architectures": [ | |
| "CLIPVisionModelWithProjection" | |
| ], | |
| "attention_dropout": 0.0, | |
| "dropout": 0.0, | |
| "hidden_act": "gelu", | |
| "hidden_size": 768, | |
| "image_size": 224, | |
| "initializer_factor": 1.0, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "layer_norm_eps": 1e-05, | |
| "model_type": "clip_vision_model", | |
| "num_attention_heads": 8, | |
| "num_channels": 3, | |
| "num_hidden_layers": 12, | |
| "patch_size": 16, | |
| "projection_dim": 512, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.28.0.dev0" | |
| } |