| """Configuration for boilerplate detection model""" | |
| from transformers import PretrainedConfig | |
| class BoilerplateConfig(PretrainedConfig): | |
| model_type = "boilerplate" | |
| def __init__( | |
| self, | |
| base_model_name="sentence-transformers/all-mpnet-base-v2", | |
| num_labels=2, | |
| hidden_size=768, | |
| classifier_dims=[16, 8], | |
| dropout=0.05, | |
| **kwargs | |
| ): | |
| super().__init__(num_labels=num_labels, **kwargs) | |
| self.base_model_name = base_model_name | |
| self.hidden_size = hidden_size | |
| self.classifier_dims = classifier_dims | |
| self.dropout = dropout | |
| self.id2label = {0: "NOT_BOILERPLATE", 1: "BOILERPLATE"} | |
| self.label2id = {"NOT_BOILERPLATE": 0, "BOILERPLATE": 1} |