{
  "model_type": "foveated_vlm",
  "architectures": [
    "FoveatedVLM"
  ],
  "llm_name": "HuggingFaceTB/SmolLM2-135M-Instruct",
  "dino_name": "facebook/dinov2-small",
  "llm_dim": 576,
  "dino_dim": 384,
  "query_dim": 384,
  "visual_scale": 0.14,
  "lambda_coarse": 0.0,
  "deep_query": true,
  "total_params": 185622528,
  "training_stages": [
    "Stage 1: Visual Alignment (OpenVid + WebVid + text retention)",
    "Stage 2: Vision-Language SFT (Cauldron + video + text retention)",
    "Stage 3: DPO (RLAIF-V preference pairs)"
  ]
}