| from transformers import PretrainedConfig |
| import torch |
|
|
|
|
| class ImpressoConfig(PretrainedConfig): |
| model_type = "stacked_bert" |
|
|
| def __init__( |
| self, |
| vocab_size=30522, |
| hidden_size=768, |
| num_hidden_layers=12, |
| num_attention_heads=12, |
| intermediate_size=3072, |
| hidden_act="gelu", |
| hidden_dropout_prob=0.1, |
| attention_probs_dropout_prob=0.1, |
| max_position_embeddings=512, |
| type_vocab_size=2, |
| initializer_range=0.02, |
| layer_norm_eps=1e-12, |
| pad_token_id=0, |
| position_embedding_type="absolute", |
| use_cache=True, |
| classifier_dropout=None, |
| pretrained_config=None, |
| values_override=None, |
| label_map=None, |
| **kwargs, |
| ): |
| super().__init__(pad_token_id=pad_token_id, **kwargs) |
|
|
| self.vocab_size = vocab_size |
| self.hidden_size = hidden_size |
| self.num_hidden_layers = num_hidden_layers |
| self.num_attention_heads = num_attention_heads |
| self.hidden_act = hidden_act |
| self.intermediate_size = intermediate_size |
| self.hidden_dropout_prob = hidden_dropout_prob |
| self.attention_probs_dropout_prob = attention_probs_dropout_prob |
| self.max_position_embeddings = max_position_embeddings |
| self.type_vocab_size = type_vocab_size |
| self.initializer_range = initializer_range |
| self.layer_norm_eps = layer_norm_eps |
| self.position_embedding_type = position_embedding_type |
| self.use_cache = use_cache |
| self.classifier_dropout = classifier_dropout |
| self.pretrained_config = pretrained_config |
| self.label_map = label_map |
|
|
| self.values_override = values_override or {} |
| self.outputs = { |
| "logits": {"shape": [None, None, self.hidden_size], "dtype": "float32"} |
| } |
|
|
|
|
| |
| ImpressoConfig.register_for_auto_class() |
|
|
