| { | |
| "architectures": [ | |
| "CvtForImageClassification" | |
| ], | |
| "attention_drop_rate": [ | |
| 0.0, | |
| 0.0, | |
| 0.0 | |
| ], | |
| "cls_token": [ | |
| false, | |
| false, | |
| true | |
| ], | |
| "depth": [ | |
| 1, | |
| 2, | |
| 10 | |
| ], | |
| "drop_path_rate": [ | |
| 0.0, | |
| 0.0, | |
| 0.1 | |
| ], | |
| "drop_rate": [ | |
| 0.0, | |
| 0.0, | |
| 0.0 | |
| ], | |
| "dtype": "float32", | |
| "embed_dim": [ | |
| 16, | |
| 32, | |
| 48 | |
| ], | |
| "image_size": 64, | |
| "initializer_range": 0.02, | |
| "kernel_qkv": [ | |
| 3, | |
| 3, | |
| 3 | |
| ], | |
| "layer_norm_eps": 1e-12, | |
| "mlp_ratio": [ | |
| 4.0, | |
| 4.0, | |
| 4.0 | |
| ], | |
| "model_type": "cvt", | |
| "num_channels": 3, | |
| "num_heads": [ | |
| 1, | |
| 2, | |
| 3 | |
| ], | |
| "padding_kv": [ | |
| 1, | |
| 1, | |
| 1 | |
| ], | |
| "padding_q": [ | |
| 1, | |
| 1, | |
| 1 | |
| ], | |
| "patch_padding": [ | |
| 2, | |
| 1, | |
| 1 | |
| ], | |
| "patch_sizes": [ | |
| 7, | |
| 3, | |
| 3 | |
| ], | |
| "patch_stride": [ | |
| 4, | |
| 2, | |
| 2 | |
| ], | |
| "qkv_bias": [ | |
| true, | |
| true, | |
| true | |
| ], | |
| "qkv_projection_method": [ | |
| "dw_bn", | |
| "dw_bn", | |
| "dw_bn" | |
| ], | |
| "stride_kv": [ | |
| 2, | |
| 2, | |
| 2 | |
| ], | |
| "stride_q": [ | |
| 1, | |
| 1, | |
| 1 | |
| ], | |
| "transformers_version": "5.16.0.dev0" | |
| } | |