| { | |
| "architectures": [ | |
| "KEEPModel" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "modeling_keep.KEEPConfig", | |
| "AutoModel": "modeling_keep.KEEPModel" | |
| }, | |
| "model_type": "keep", | |
| "projection_dim": 768, | |
| "text_config": { | |
| "attention_probs_dropout_prob": 0.1, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 512, | |
| "model_type": "bert", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "type_vocab_size": 2, | |
| "vocab_size": 30522 | |
| }, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.46.3", | |
| "vision_config": { | |
| "attn_drop_rate": 0.0, | |
| "drop_rate": 0.0, | |
| "dynamic_img_size": true, | |
| "hidden_size": 1024, | |
| "img_size": 224, | |
| "init_values": 1e-05, | |
| "mlp_ratio": 4.0, | |
| "model_type": "vit", | |
| "num_classes": 0, | |
| "num_heads": 16, | |
| "num_layers": 24, | |
| "patch_size": 16, | |
| "qkv_bias": true | |
| } | |
| } | |