| """ GPT1 model configuration """ | |
| from transformers.configuration_utils import PretrainedConfig | |
| class GPT1Config(PretrainedConfig): | |
| model_type = "gpt1" | |
| def __init__( | |
| self, | |
| vocab_size=40478, | |
| hidden_size=768, | |
| intermediate_size=3072, | |
| num_hidden_layers=12, | |
| num_attention_heads=12, | |
| resid_pdrop=0.1, | |
| embd_pdrop=0.1, | |
| attention_dropout=0.1, | |
| hidden_act="gelu", | |
| max_position_embeddings=512, | |
| initializer_range=0.02, | |
| layer_norm_eps=1e-5, | |
| tie_word_embeddings=True, | |
| **kwargs | |
| ): | |
| self.vocab_size = vocab_size | |
| self.hidden_size = hidden_size | |
| self.intermediate_size = intermediate_size | |
| self.num_hidden_layers = num_hidden_layers | |
| self.num_attention_heads = num_attention_heads | |
| self.resid_pdrop = resid_pdrop | |
| self.embd_pdrop = embd_pdrop | |
| self.attention_dropout = attention_dropout | |
| self.hidden_act = hidden_act | |
| self.max_position_embeddings = max_position_embeddings | |
| self.initializer_range = initializer_range | |
| self.layer_norm_eps = layer_norm_eps | |
| super().__init__( | |
| tie_word_embeddings=tie_word_embeddings, | |
| **kwargs, | |
| ) | |