| """Hugging Face configuration for Vortex Alpha.""" | |
| from __future__ import annotations | |
| from transformers import PretrainedConfig | |
| class VortexConfig(PretrainedConfig): | |
| model_type = "vortex" | |
| def __init__( | |
| self, | |
| vocab_size: int = 8192, | |
| hidden_size: int = 1024, | |
| num_hidden_layers: int = 12, | |
| num_attention_heads: int = 16, | |
| num_key_value_heads: int = 4, | |
| head_dim: int = 64, | |
| intermediate_size: int = 3664, | |
| hidden_act: str = "silu", | |
| max_position_embeddings: int = 4096, | |
| rope_theta: float = 100000.0, | |
| rms_norm_eps: float = 1e-5, | |
| attention_bias: bool = False, | |
| tie_word_embeddings: bool = True, | |
| use_cache: bool = False, | |
| **kwargs, | |
| ) -> None: | |
| super().__init__( | |
| tie_word_embeddings=tie_word_embeddings, | |
| **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.hidden_act = hidden_act | |
| self.max_position_embeddings = max_position_embeddings | |
| self.rope_theta = rope_theta | |
| self.rms_norm_eps = rms_norm_eps | |
| self.attention_bias = attention_bias | |
| self.tie_word_embeddings = tie_word_embeddings | |
| self.use_cache = use_cache | |