| { | |
| "architectures": [ | |
| "CLIPModel" | |
| ], | |
| "model_type": "clip", | |
| "projection_dim": 512, | |
| "text_config": { | |
| "architectures": [ | |
| "CLIPTextModel" | |
| ], | |
| "attention_dropout": 0.0, | |
| "dropout": 0.0, | |
| "hidden_act": "quick_gelu", | |
| "hidden_size": 512, | |
| "initializer_factor": 1.0, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 2048, | |
| "layer_norm_eps": 1e-05, | |
| "max_position_embeddings": 77, | |
| "model_type": "clip_text_model", | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 0, | |
| "vocab_size": 49408 | |
| }, | |
| "vision_config": { | |
| "architectures": [ | |
| "CLIPVisionModel" | |
| ], | |
| "attention_dropout": 0.0, | |
| "dropout": 0.0, | |
| "hidden_act": "quick_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": 12, | |
| "num_channels": 3, | |
| "num_hidden_layers": 12, | |
| "patch_size": 32 | |
| } | |
| } |