examples/complete-v1.2.okt

# okto_version: "1.2"
PROJECT "CompleteV12Example"
DESCRIPTION "Complete example demonstrating all v1.2 features"

ENV {
  accelerator: "gpu"
  min_memory: "16GB"
  precision: "fp16"
  backend: "oktoseek"
  install_missing: true
}

DATASET {
  train: "examples/datasets/demo_train.jsonl"
  validation: "examples/datasets/demo_train.jsonl"
  format: "jsonl"
  type: "chat"
  language: "en"
}

MODEL {
  name: "complete-v12-model"
  base: "google/flan-t5-base"
  device: "cuda"
  
  ADAPTER {
    type: "lora"
    path: "./adapters/my-adapter"
    rank: 16
    alpha: 32
  }
}

TRAIN {
  epochs: 10
  batch_size: 32
  learning_rate: 0.0001
  optimizer: "adamw"
  scheduler: "cosine"
  device: "cuda"
  checkpoint_steps: 100
}

METRICS {
  accuracy
  loss
  perplexity
  f1
  confidence
}

MONITOR {
  metrics: [
    "loss",
    "val_loss",
    "accuracy",
    "gpu_usage",
    "ram_usage",
    "throughput",
    "latency",
    "confidence"
  ]
  
  notify_if {
    loss > 2.0
    gpu_usage > 90%
    temperature > 85
    hallucination_score > 0.5
  }
  
  log_to: "logs/training.log"
}

BEHAVIOR {
  mode: "chat"
  personality: "assistant"
  verbosity: "medium"
  language: "en"
  avoid: ["politics", "violence", "hate"]
  fallback: "How can I help you?"
  prompt_style: "User: {input}\nAssistant:"
}

STABILITY {
  stop_if_nan: true
  stop_if_diverges: true
  min_improvement: 0.001
}

EXPLORER {
  try {
    lr: [0.0003, 0.0001]
    batch_size: [16, 32]
  }
  max_tests: 4
  pick_best_by: "val_loss"
}

CONTROL {
  on_epoch_end {
    SAVE model
    LOG "Epoch completed"
    
    IF loss > 2.0 {
      SET LR = 0.00005
      LOG "High loss detected"
      
      WHEN gpu_usage > 90% {
        SET batch_size = 16
        LOG "Reducing batch size due to GPU pressure"
      }
    }
    
    IF val_loss > 2.5 {
      STOP_TRAINING
    }
    
    IF accuracy > 0.9 {
      SAVE "best_model"
      LOG "High accuracy reached"
    }
  }
  
  validate_every: 200
  
  WHEN gpu_memory < 12GB {
    SET batch_size = 16
  }
  
  EVERY 500 steps {
    SAVE checkpoint
  }
}

INFERENCE {
  mode: "chat"
  format: "User: {input}\nAssistant:"
  exit_command: "/exit"
  
  params {
    temperature: 0.7
    max_length: 120
    top_p: 0.9
    beams: 2
    do_sample: true
  }
  
  CONTROL {
    IF confidence < 0.3 { RETRY }
    IF hallucination_score > 0.5 { REPLACE WITH "I'm not certain about that." }
  }
}

GUARD {
  prevent {
    hallucination
    toxicity
    bias
    data_leak
    unsafe_code
  }
  
  detect_using: ["classifier", "regex", "embedding"]
  
  on_violation {
    REPLACE
    with_message: "Sorry, this request is not allowed."
  }
}

SECURITY {
  input_validation {
    max_length: 500
    disallow_patterns: [
      "<script>",
      "DROP TABLE",
      "rm -rf"
    ]
  }
  
  output_validation {
    prevent_data_leak: true
    mask_personal_info: true
  }
  
  rate_limit {
    max_requests_per_minute: 60
  }
  
  encryption {
    algorithm: "AES-256"
  }
}

EXPORT {
  format: ["okm", "onnx", "gguf"]
  path: "export/"
}

DEPLOY {
  target: "api"
  host: "0.0.0.0"
  endpoint: "/chatbot"
  requires_auth: true
  port: 9000
  max_concurrent_requests: 100
  protocol: "http"
  format: "onnx"
}