configuration_unicosys.py

"""Unicosys Hypergraph Knowledge Model — Configuration."""

from transformers import PretrainedConfig


class UnicosysConfig(PretrainedConfig):
    """HuggingFace-compatible config for the Unicosys knowledge model."""

    model_type = "unicosys_hypergraph"

    def __init__(
        self,
        # Graph structure
        num_node_types: int = 8,
        num_edge_types: int = 15,
        num_subsystems: int = 6,
        max_nodes: int = 250000,
        # Embedding dimensions
        node_embed_dim: int = 128,
        text_embed_dim: int = 256,
        hidden_dim: int = 256,
        # Transformer text encoder
        text_vocab_size: int = 32000,
        text_max_length: int = 128,
        text_num_heads: int = 4,
        text_num_layers: int = 2,
        # Graph attention
        gat_num_heads: int = 4,
        gat_num_layers: int = 2,
        gat_dropout: float = 0.1,
        # Training
        negative_sample_ratio: int = 5,
        margin: float = 1.0,
        # Metadata
        case_number: str = "2025-137857",
        num_entities: int = 0,
        num_evidence: int = 0,
        num_cross_links: int = 0,
        node_type_vocab: dict = None,
        edge_type_vocab: dict = None,
        subsystem_vocab: dict = None,
        **kwargs,
    ):
        super().__init__(**kwargs)
        self.num_node_types = num_node_types
        self.num_edge_types = num_edge_types
        self.num_subsystems = num_subsystems
        self.max_nodes = max_nodes
        self.node_embed_dim = node_embed_dim
        self.text_embed_dim = text_embed_dim
        self.hidden_dim = hidden_dim
        self.text_vocab_size = text_vocab_size
        self.text_max_length = text_max_length
        self.text_num_heads = text_num_heads
        self.text_num_layers = text_num_layers
        self.gat_num_heads = gat_num_heads
        self.gat_num_layers = gat_num_layers
        self.gat_dropout = gat_dropout
        self.negative_sample_ratio = negative_sample_ratio
        self.margin = margin
        self.case_number = case_number
        self.num_entities = num_entities
        self.num_evidence = num_evidence
        self.num_cross_links = num_cross_links
        self.node_type_vocab = node_type_vocab or {}
        self.edge_type_vocab = edge_type_vocab or {}
        self.subsystem_vocab = subsystem_vocab or {}