| from transformers import PretrainedConfig | |
| class TunBertConfig(PretrainedConfig): | |
| model_type = "bert" | |
| def __init__(self, | |
| attention_probs_dropout_prob = 0.1, | |
| classifier_dropout = None, | |
| gradient_checkpointing = False, | |
| 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, | |
| pad_token_id = 0, | |
| position_embedding_type = "absolute", | |
| transformers_version = "4.35.2", | |
| type_vocab_size = 2, | |
| use_cache = True, | |
| vocab_size = 30522, | |
| **kwargs): | |
| self.attention_probs_dropout_prob = attention_probs_dropout_prob | |
| self.classifier_dropout = classifier_dropout | |
| self.gradient_checkpointing = gradient_checkpointing | |
| self.hidden_act = hidden_act | |
| self.hidden_dropout_prob = hidden_dropout_prob | |
| self.hidden_size = hidden_size | |
| self.initializer_range = initializer_range | |
| self.intermediate_size = intermediate_size | |
| self.layer_norm_eps = layer_norm_eps | |
| self.max_position_embeddings = max_position_embeddings | |
| self.model_type = model_type | |
| self.num_attention_heads = num_attention_heads | |
| self.num_hidden_layers = num_hidden_layers | |
| self.pad_token_id = pad_token_id | |
| self.position_embedding_type = position_embedding_type | |
| self.transformers_version = transformers_version | |
| self.type_vocab_size = type_vocab_size | |
| self.use_cache = use_cache | |
| self.vocab_size = vocab_size | |
| super().__init__(**kwargs) |