config.json

{
  "architectures": [
    "VectorLLMWrapModel"
  ],
  "auto_map": {
    "AutoConfig": "configuration_vectorllm.VectorLLMConfig",
    "AutoImageProcessor": "image_processing_vectorllm.VectorLLMImageProcessor",
    "AutoModel": "modeling_vectorllm.VectorLLMWrapModel",
    "AutoModelForCausalLM": "modeling_vectorllm.VectorLLMWrapModel",
    "AutoProcessor": "processing_vectorllm.VectorLLMProcessor"
  },
  "dtype": "float32",
  "hidden_size": 1024,
  "llm_config": {
    "architectures": [
      "Qwen3ForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 151643,
    "dtype": "bfloat16",
    "eos_token_id": 151645,
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 1024,
    "initializer_range": 0.02,
    "intermediate_size": 3072,
    "layer_types": [
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention"
    ],
    "max_position_embeddings": 40960,
    "max_window_layers": 28,
    "model_type": "qwen3",
    "num_attention_heads": 16,
    "num_hidden_layers": 28,
    "num_key_value_heads": 8,
    "rms_norm_eps": 1e-06,
    "rope_scaling": null,
    "rope_theta": 1000000,
    "sliding_window": null,
    "tie_word_embeddings": true,
    "use_cache": true,
    "use_sliding_window": false,
    "vocab_size": 151926
  },
  "model_type": "vectorllm",
  "num_cls_register_tokens": 5,
  "output_attentions": false,
  "pixel_idx": 151669,
  "projector_config": {
    "bias": true,
    "depth": 2,
    "hidden_act": "gelu",
    "llm_hidden_size": 1024,
    "model_type": "projector",
    "visual_hidden_size": 1024
  },
  "regression_size": [
    128,
    128
  ],
  "text_config": {
    "architectures": [
      "Qwen3ForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 151643,
    "dtype": "bfloat16",
    "eos_token_id": 151645,
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 1024,
    "initializer_range": 0.02,
    "intermediate_size": 3072,
    "layer_types": [
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention"
    ],
    "max_position_embeddings": 40960,
    "max_window_layers": 28,
    "model_type": "qwen3",
    "num_attention_heads": 16,
    "num_hidden_layers": 28,
    "num_key_value_heads": 8,
    "rms_norm_eps": 1e-06,
    "rope_scaling": null,
    "rope_theta": 1000000,
    "sliding_window": null,
    "tie_word_embeddings": true,
    "use_cache": true,
    "use_sliding_window": false,
    "vocab_size": 151926
  },
  "tie_word_embeddings": false,
  "transformers_version": null,
  "vision_config": {
    "architectures": [
      "DINOv3ViTModel"
    ],
    "attention_dropout": 0.0,
    "drop_path_rate": 0.0,
    "dtype": "float32",
    "hidden_act": "gelu",
    "hidden_size": 1024,
    "image_size": 224,
    "initializer_range": 0.02,
    "intermediate_size": 4096,
    "key_bias": false,
    "layer_norm_eps": 1e-05,
    "layerscale_value": 1.0,
    "mlp_bias": true,
    "model_type": "dinov3_vit",
    "num_attention_heads": 16,
    "num_channels": 3,
    "num_hidden_layers": 24,
    "num_register_tokens": 4,
    "patch_size": 16,
    "pos_embed_jitter": null,
    "pos_embed_rescale": 2.0,
    "pos_embed_shift": null,
    "proj_bias": true,
    "query_bias": true,
    "rope_theta": 100.0,
    "use_flash_attn": true,
    "use_gated_mlp": false,
    "value_bias": true
  },
  "vision_hidden_size": 1024
}