| from transformers import PretrainedConfig | |
| class AIXKCustomConfig(PretrainedConfig): | |
| model_type = "aixk_custom_arch" | |
| def __init__( | |
| self, | |
| vocab_size=250006, | |
| hidden_size=128, | |
| num_hidden_layers=3, | |
| num_attention_heads=4, | |
| intermediate_size=512, | |
| max_position_embeddings=512, | |
| eos_token_id=250004, | |
| **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 | |
| self.eos_token_id = eos_token_id |