| from transformers import PretrainedConfig | |
| class ThetaConfig(PretrainedConfig): | |
| model_type = "theta" | |
| def __init__( | |
| self, | |
| vocab_size=32000, | |
| hidden_size=4096, | |
| intermediate_size=11008, | |
| num_hidden_layers=32, | |
| num_attention_heads=32, | |
| hidden_act="silu", | |
| max_position_embeddings=2048, | |
| initializer_range=0.02, | |
| rms_norm_eps=1e-5, | |
| use_cache=True, | |
| **kwargs, | |
| ): | |
| super().__init__(**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.hidden_act = hidden_act | |
| self.max_position_embeddings = max_position_embeddings | |
| self.initializer_range = initializer_range | |
| self.rms_norm_eps = rms_norm_eps | |
| self.use_cache = use_cache | |