config.json

{
  "vision_backbone": "dinov2_small",
  "language_backbone": "smollm_135m",
  "vision_model": "facebook/dinov2-small",
  "vision_pretrained": true,
  "freeze_vision": true,
  "num_visual_tokens": 258,
  "vision_output_dim": 384,
  "image_size": 224,
  "language_hidden_size": 576,
  "language_num_layers": 30,
  "language_num_heads": 9,
  "language_vocab_size": 49161,
  "language_max_length": 1024,
  "freeze_language_base": true,
  "unfreeze_last_layer": true,
  "use_pretrained_language": true,
  "pretrained_language_model": "HuggingFaceTB/SmolLM-135M",
  "fusion_bottleneck_dim": 48,
  "fusion_dropout": 0.1,
  "use_qk_norm": true,
  "reasoning_enabled": true,
  "reasoning_hidden_dim": 192,
  "reasoning_num_layers": 2,
  "reasoning_num_heads": 4,
  "num_reasoning_steps": 4,
  "max_plan_steps": 5,
  "num_robots": 5,
  "robot_names": [
    "Drone",
    "Humanoid",
    "Wheeled",
    "Legged",
    "Underwater"
  ],
  "special_tokens": {
    "reasoning_start": "<|reasoning_start|>",
    "reasoning_end": "<|reasoning_end|>",
    "robot_selection": "<|robot_selection|>",
    "action_plan": "<|action_plan|>",
    "image_start": "<image>",
    "image_end": "</image>",
    "question_start": "<question>",
    "question_end": "</question>",
    "answer_start": "<answer>"
  },
  "dropout": 0.1,
  "initializer_range": 0.02,
  "use_va_refiner": false,
  "va_p_threshold": 0.7,
  "va_layer_indices": [
    10,
    15,
    20,
    25,
    28
  ],
  "vocab_size": 49161
}