| { | |
| "architectures": [ | |
| "CLIPVisionModel" | |
| ], | |
| "attention_dropout": 0.0, | |
| "hidden_act": "quick_gelu", | |
| "hidden_size": 1024, | |
| "image_size": 336, | |
| "initializer_factor": 1.0, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4096, | |
| "layer_norm_eps": 1e-05, | |
| "model_type": "clip_vision_model", | |
| "num_attention_heads": 16, | |
| "num_channels": 3, | |
| "num_hidden_layers": 24, | |
| "patch_size": 14, | |
| "projection_dim": 768, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.39.3", | |
| "vocab_size": 32000 | |
| } | |