{ "vision_backbone": "repvit", "language_backbone": "tinyllm", "vision_model": "repvit_m0_9", "vision_pretrained": true, "freeze_vision": true, "num_visual_tokens": 8, "vision_output_dim": 384, "image_size": 224, "language_hidden_size": 384, "language_num_layers": 6, "language_num_heads": 6, "language_vocab_size": 50262, "language_max_length": 1024, "freeze_language_base": true, "unfreeze_last_layer": true, "use_pretrained_language": true, "pretrained_language_model": "tinyllm/30M-0.4", "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_token": "<|image|>" }, "dropout": 0.1, "initializer_range": 0.02, "vocab_size": 50262 }