ares/config.py

from dataclasses import dataclass, asdict

@dataclass
class AresConfig:
    vocab_size: int = 16_000
    max_seq_len: int = 2048
    dim: int = 512
    n_layers: int = 12
    n_heads: int = 8
    n_kv_heads: int = 2
    ffn_multiplier: float = 2.67
    rope_theta: float = 10000.0
    rms_norm_eps: float = 1e-5
    dropout: float = 0.0
    tie_embeddings: bool = True
    def to_dict(self): return asdict(self)