| from transformers import PretrainedConfig | |
| class G0NanoConfig(PretrainedConfig): | |
| model_type = "g0nano" | |
| def __init__( | |
| self, | |
| vocab_size=16384, | |
| hidden_size=640, | |
| num_hidden_layers=12, | |
| num_attention_heads=10, | |
| num_key_value_heads=2, | |
| head_dim=64, | |
| intermediate_size=1728, | |
| max_position_embeddings=1024, | |
| rope_theta=10000.0, | |
| rms_norm_eps=1e-5, | |
| tie_word_embeddings=True, | |
| **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.num_key_value_heads = num_key_value_heads | |
| self.head_dim = head_dim | |
| self.intermediate_size = intermediate_size | |
| self.max_position_embeddings = max_position_embeddings | |
| self.rope_theta = rope_theta | |
| self.rms_norm_eps = rms_norm_eps | |
| super().__init__(tie_word_embeddings=tie_word_embeddings, **kwargs) | |