| from transformers.configuration_utils import PretrainedConfig | |
| class Phi3Config(PretrainedConfig): | |
| model_type = "phi3" | |
| def __init__(self, | |
| vocab_size=32064, | |
| hidden_size=3072, | |
| num_hidden_layers=32, | |
| num_attention_heads=32, | |
| intermediate_size=8192, | |
| max_position_embeddings=4096, | |
| **kwargs): | |
| super().__init__(**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.intermediate_size = intermediate_size | |
| self.max_position_embeddings = max_position_embeddings | |