# Delentia SLM — The Executor (slm-jitna-agentic) LoRA Configuration
# Purpose: Function Calling / Structured JSON Output
# Priority: #1 in 4-Pillar Architecture (unlocks Intent Memory Loop)
#
# The Executor MUST produce pure JSON with zero natural language contamination.
# It converts user intents into machine-executable tool-call payloads.

model:
  base_model: "Delentia/delentia-slm-jitna-v0.4"
  tokenizer: "Delentia/delentia-slm-jitna-v0.4"
  max_seq_length: 4096
  dtype: null
  load_in_4bit: true

lora:
  r: 32
  lora_alpha: 64                # α = 2r for optimal learning rate control
  lora_dropout: 0
  bias: "none"
  use_rslora: true
  target_modules:
    - "q_proj"
    - "k_proj"
    - "v_proj"
    - "o_proj"
    - "gate_proj"
    - "up_proj"
    - "down_proj"
  task_type: "CAUSAL_LM"

training:
  dataset_path: "datasets/processed/jitna_executor_pairs.parquet"
  dataset_split: "train"
  validation_split: 0.05
  max_samples: null

  per_device_train_batch_size: 1
  gradient_accumulation_steps: 8

  learning_rate: 3.0e-5         # Lower LR to force precise JSON structure learning
  lr_scheduler_type: "cosine"
  warmup_ratio: 0.05
  num_train_epochs: 5

  bf16: true
  fp16: false
  optim: "adamw_8bit"
  weight_decay: 0.01
  max_grad_norm: 0.3

  output_dir: "models/checkpoints/executor_agentic"
  save_strategy: "epoch"
  save_total_limit: 3
  logging_steps: 10

  evaluation_strategy: "epoch"
  load_best_model_at_end: true
  metric_for_best_model: "eval_loss"

chat_template: |
  <|system|>
  You are The Executor (slm-jitna-agentic) — a specialized LoRA adapter within the Delentia OS 1+4 Pillar Architecture. Your ONLY purpose is to convert user intents into machine-executable JSON payloads. You must NEVER produce natural language explanations. Output ONLY valid JSON — no markdown, no text, no comments. Your output must pass json.loads() without error.
  <|user|>
  {{ user_intent }}
  <|assistant|>

pillar_type: "executor"
adapter_name: "jitna_executor_v1"
adapter_save_path: "models/adapters/jitna_executor_v1"

mlflow:
  experiment_name: "delentia-slm-executor-agentic"
  tracking_uri: "https://delentia-delentia-agent-monitor.hf.space"
  log_model: true

target_metrics:
  json_validity: 0.99            # >= 99% valid JSON output
  tool_call_accuracy: 0.95       # >= 95% correct tool name + args
  fdia_avg: 0.90                 # avg F score >= 0.90
  hallucination_rate: 0.02       # <= 2% factual errors