config.json

{
  "architectures": ["CubiczanMoEForCausalLM"],
  "model_type": "cubiczan-moe",
  "auto_map": {
    "AutoModelForCausalLM": "modeling_cubiczan.CubiczanMoEForCausalLM",
    "AutoConfig": "configuration_cubiczan.CubiczanMoEConfig"
  },
  "torch_dtype": "bfloat16",
  "transformers_version": "4.46.0",

  "vocab_size": 151936,
  "hidden_size": 2048,
  "intermediate_size": 5504,
  "num_hidden_layers": 24,
  "num_attention_heads": 16,
  "num_key_value_heads": 4,
  "max_position_embeddings": 32768,
  "rms_norm_eps": 1e-6,
  "rope_theta": 1000000.0,
  "tie_word_embeddings": false,
  "use_cache": true,
  "bos_token_id": 151643,
  "eos_token_id": 151645,
  "pad_token_id": 151643,

  "moe_config": {
    "architecture": "mixture_of_experts",
    "total_parameters": "7.2B",
    "active_parameters_per_inference": "1.8B",
    "num_domain_experts": 20,
    "num_router_experts": 2,
    "expert_hidden_size": 240000000,
    "router_hidden_size": 60000000,
    "top_k_experts": 2,
    "expert_capacity_factor": 1.25,
    "router_type": "top2_softmax",
    "load_balancing_loss_weight": 0.01,
    "router_orthogonal_loss_weight": 0.005,
    "expert_dropout": 0.1
  },

  "expert_registry": {
    "E01": {"domain": "OKR Architecture", "framework": "Doerr Measure What Matters", "output_type": "objective_kr_cascade"},
    "E02": {"domain": "Competitive Strategy", "framework": "Lafley-Martin Playing to Win", "output_type": "strategy_cascade"},
    "E03": {"domain": "Market Creation", "framework": "Kim-Mauborgne Blue Ocean", "output_type": "errc_grid"},
    "E04": {"domain": "Strategy Kernel", "framework": "Rumelt Good Strategy Bad Strategy", "output_type": "diagnosis_policy_action"},
    "E05": {"domain": "Lean Validation", "framework": "Ries Lean Startup", "output_type": "build_measure_learn"},
    "E06": {"domain": "Probabilistic Forecasting", "framework": "Tetlock Superforecasting", "output_type": "probability_table"},
    "E07": {"domain": "Cognitive Debiasing", "framework": "Kahneman Thinking Fast and Slow", "output_type": "bias_audit_ryg"},
    "E08": {"domain": "Decision Audit", "framework": "Heath Decisive WRAP", "output_type": "wrap_audit"},
    "E09": {"domain": "Probabilistic Betting", "framework": "Duke Thinking in Bets", "output_type": "decision_outcome_separation"},
    "E10": {"domain": "Financial Risk", "framework": "5x5 Risk Assessment Matrix", "output_type": "risk_heat_map"},
    "E11": {"domain": "Investment Evaluation", "framework": "CFO Capital Allocation Rubric", "output_type": "weighted_rubric"},
    "E12": {"domain": "Bottleneck Optimization", "framework": "Goldratt The Goal", "output_type": "drum_buffer_rope"},
    "E13": {"domain": "Financial Narrative", "framework": "Stakeholder Storytelling", "output_type": "cnia_narrative"},
    "E14": {"domain": "Board Reporting", "framework": "Executive Report Generator", "output_type": "board_deck"},
    "E15": {"domain": "Design Thinking", "framework": "IDEO Stanford d.school", "output_type": "journey_empathy_map"},
    "E16": {"domain": "Agent Context Engineering", "framework": "Agentic Context Framework", "output_type": "context_spec"},
    "E17": {"domain": "Context Optimization", "framework": "Context Engineering Framework", "output_type": "prompt_design"},
    "E18": {"domain": "Multi-Agent Coordination", "framework": "Cognitive Mesh Protocol", "output_type": "mesh_topology"},
    "E19": {"domain": "Cross-Domain Bridging", "framework": "Bridge Framework", "output_type": "paradigm_translation"},
    "E20": {"domain": "First Principles", "framework": "MIT First-Principles Method", "output_type": "axiomatic_decomposition"}
  },

  "router_registry": {
    "R01": {"function": "framework_selector", "mechanism": "semantic_match_top2"},
    "R02": {"function": "composition_sequencer", "mechanism": "dependency_ordered_execution"}
  },

  "structured_output": {
    "constraint_validator_head_params": "156M",
    "framework_template_decoder_params": "220M",
    "protocol_state_machine": "TLP_v2.2.4",
    "enforced_output_types": [
      "scoring_table",
      "risk_matrix_5x5",
      "decision_tree_mece",
      "status_enum",
      "protocol_payload"
    ]
  },

  "backbone_config": {
    "embedding_params": "256M",
    "attention_layer_params": "1.2B",
    "layer_norm_params": "12M",
    "output_head_params": "256M",
    "total_backbone_params": "1.724B"
  }
}