| from transformers import PretrainedConfig | |
| class CSDConfig(PretrainedConfig): | |
| model_type = "CSDModel" | |
| def __init__( | |
| self, | |
| attention_dropout:float=0.0, | |
| dropout:float=0.0, | |
| hidden_act:str= "quick_gelu", | |
| hidden_size:int= 1024, | |
| image_size:int= 224, | |
| initializer_factor:float= 1.0, | |
| initializer_range:float=0.02, | |
| intermediate_size:int=4096, | |
| layer_norm_eps:float=1e-05, | |
| num_attention_heads:int=16, | |
| num_channels:int=3, | |
| num_hidden_layers:int=24, | |
| patch_size:int= 14, | |
| projection_dim:int=768, | |
| style_projection_dim:int=768, | |
| content_projection_dim:int=768, | |
| **kwargs, | |
| ): | |
| super().__init__(**kwargs) | |
| self.attention_dropout=attention_dropout | |
| self.dropout=dropout | |
| self.hidden_act=hidden_act | |
| self.hidden_size=hidden_size | |
| self.image_size=image_size | |
| self.initializer_factor=initializer_factor | |
| self.initializer_range=initializer_range | |
| self.intermediate_size=intermediate_size | |
| self.layer_norm_eps=layer_norm_eps | |
| self.num_attention_heads=num_attention_heads | |
| self.num_channels=num_channels | |
| self.num_hidden_layers=num_hidden_layers | |
| self.patch_size=patch_size | |
| self.projection_dim=projection_dim | |
| self.style_projection_dim=style_projection_dim | |
| self.content_projection_dim=content_projection_dim |