config.json

{
  "_class_name": "VisionLanguageActionModel",
  "architectures": [
    "VisionLanguageActionModel"
  ],
  "model_type": "vla-model",
  "hidden_size": 768,
  "num_tasks": 6,
  "vision_config": {
    "model_type": "vit",
    "image_size": 224,
    "patch_size": 14,
    "hidden_size": 1024,
    "num_hidden_layers": 24,
    "num_attention_heads": 16,
    "intermediate_size": 4096,
    "projection_dim": 768
  },
  "caption_config": {
    "model_type": "bert",
    "vocab_size": 30522,
    "hidden_size": 1024,
    "num_hidden_layers": 24,
    "num_attention_heads": 16,
    "intermediate_size": 4096,
    "projection_dim": 768
  },
  "context_config": {
    "model_type": "gpt2",
    "vocab_size": 50257,
    "n_positions": 1024,
    "n_embd": 1024,
    "n_layer": 24,
    "n_head": 16,
    "projection_dim": 768
  },
  "spatial_config": {
    "input_dim": 10,
    "output_dim": 768
  },
  "temporal_config": {
    "input_dim": 1280,
    "output_dim": 768
  },
  "fusion_config": {
    "input_dim": 3840,
    "output_dim": 768
  },
  "reasoning_config": {
    "d_model": 768,
    "nhead": 12,
    "num_layers": 8
  },
  "action_head_config": {
    "num_actions": 8
  },
  "explanation_head_config": {
    "vocab_size": 30522
  }
}