| """AQ model configuration. |
| |
| AQ (Academic Quotient) — Zyora Labs' proprietary, from-scratch decoder |
| architecture: RMSNorm, rotary position embeddings, grouped-query attention, |
| SwiGLU feed-forward, tied embeddings. |
| """ |
|
|
| from transformers import PretrainedConfig |
|
|
|
|
| class AQConfig(PretrainedConfig): |
| model_type = "aq" |
|
|
| def __init__( |
| self, |
| vocab_size: int = 32000, |
| hidden_size: int = 1536, |
| intermediate_size: int = 4096, |
| num_hidden_layers: int = 48, |
| num_attention_heads: int = 24, |
| num_key_value_heads: int = 8, |
| head_dim: int = 64, |
| max_position_embeddings: int = 2048, |
| rope_theta: float = 10000.0, |
| rms_norm_eps: float = 1e-5, |
| tie_word_embeddings: bool = True, |
| bos_token_id: int = 0, |
| eos_token_id: int = 0, |
| pad_token_id: int = 0, |
| **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.num_key_value_heads = num_key_value_heads |
| self.head_dim = head_dim |
| 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, |
| bos_token_id=bos_token_id, |
| eos_token_id=eos_token_id, |
| pad_token_id=pad_token_id, |
| **kwargs, |
| ) |
|
|
