{
    "metadata": {
        "total_size": 1037715168
    },
    "weight_map": {
        "detector_model.detr_decoder.box_head.layer1.bias": "model.safetensors",
        "detector_model.detr_decoder.box_head.layer1.biases": "model.safetensors",
        "detector_model.detr_decoder.box_head.layer1.scales": "model.safetensors",
        "detector_model.detr_decoder.box_head.layer1.weight": "model.safetensors",
        "detector_model.detr_decoder.box_head.layer2.bias": "model.safetensors",
        "detector_model.detr_decoder.box_head.layer2.biases": "model.safetensors",
        "detector_model.detr_decoder.box_head.layer2.scales": "model.safetensors",
        "detector_model.detr_decoder.box_head.layer2.weight": "model.safetensors",
        "detector_model.detr_decoder.box_head.layer3.bias": "model.safetensors",
        "detector_model.detr_decoder.box_head.layer3.weight": "model.safetensors",
        "detector_model.detr_decoder.box_rpb_embed_x.layer1.bias": "model.safetensors",
        "detector_model.detr_decoder.box_rpb_embed_x.layer1.weight": "model.safetensors",
        "detector_model.detr_decoder.box_rpb_embed_x.layer2.bias": "model.safetensors",
        "detector_model.detr_decoder.box_rpb_embed_x.layer2.weight": "model.safetensors",
        "detector_model.detr_decoder.box_rpb_embed_y.layer1.bias": "model.safetensors",
        "detector_model.detr_decoder.box_rpb_embed_y.layer1.weight": "model.safetensors",
        "detector_model.detr_decoder.box_rpb_embed_y.layer2.bias": "model.safetensors",
        "detector_model.detr_decoder.box_rpb_embed_y.layer2.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.0.mlp.fc1.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.0.mlp.fc1.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.0.mlp.fc1.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.0.mlp.fc1.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.0.mlp.fc2.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.0.mlp.fc2.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.0.mlp.fc2.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.0.mlp.fc2.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.0.mlp_layer_norm.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.0.mlp_layer_norm.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.0.self_attn.k_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.0.self_attn.k_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.0.self_attn.k_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.0.self_attn.k_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.0.self_attn.o_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.0.self_attn.o_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.0.self_attn.o_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.0.self_attn.o_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.0.self_attn.q_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.0.self_attn.q_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.0.self_attn.q_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.0.self_attn.q_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.0.self_attn.v_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.0.self_attn.v_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.0.self_attn.v_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.0.self_attn.v_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.0.self_attn_layer_norm.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.0.self_attn_layer_norm.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.0.text_cross_attn.k_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.0.text_cross_attn.k_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.0.text_cross_attn.k_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.0.text_cross_attn.k_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.0.text_cross_attn.o_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.0.text_cross_attn.o_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.0.text_cross_attn.o_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.0.text_cross_attn.o_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.0.text_cross_attn.q_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.0.text_cross_attn.q_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.0.text_cross_attn.q_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.0.text_cross_attn.q_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.0.text_cross_attn.v_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.0.text_cross_attn.v_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.0.text_cross_attn.v_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.0.text_cross_attn.v_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.0.text_cross_attn_layer_norm.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.0.text_cross_attn_layer_norm.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.0.vision_cross_attn.k_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.0.vision_cross_attn.k_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.0.vision_cross_attn.k_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.0.vision_cross_attn.k_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.0.vision_cross_attn.o_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.0.vision_cross_attn.o_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.0.vision_cross_attn.o_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.0.vision_cross_attn.o_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.0.vision_cross_attn.q_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.0.vision_cross_attn.q_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.0.vision_cross_attn.q_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.0.vision_cross_attn.q_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.0.vision_cross_attn.v_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.0.vision_cross_attn.v_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.0.vision_cross_attn.v_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.0.vision_cross_attn.v_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.0.vision_cross_attn_layer_norm.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.0.vision_cross_attn_layer_norm.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.1.mlp.fc1.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.1.mlp.fc1.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.1.mlp.fc1.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.1.mlp.fc1.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.1.mlp.fc2.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.1.mlp.fc2.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.1.mlp.fc2.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.1.mlp.fc2.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.1.mlp_layer_norm.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.1.mlp_layer_norm.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.1.self_attn.k_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.1.self_attn.k_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.1.self_attn.k_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.1.self_attn.k_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.1.self_attn.o_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.1.self_attn.o_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.1.self_attn.o_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.1.self_attn.o_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.1.self_attn.q_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.1.self_attn.q_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.1.self_attn.q_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.1.self_attn.q_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.1.self_attn.v_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.1.self_attn.v_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.1.self_attn.v_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.1.self_attn.v_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.1.self_attn_layer_norm.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.1.self_attn_layer_norm.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.1.text_cross_attn.k_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.1.text_cross_attn.k_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.1.text_cross_attn.k_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.1.text_cross_attn.k_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.1.text_cross_attn.o_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.1.text_cross_attn.o_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.1.text_cross_attn.o_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.1.text_cross_attn.o_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.1.text_cross_attn.q_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.1.text_cross_attn.q_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.1.text_cross_attn.q_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.1.text_cross_attn.q_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.1.text_cross_attn.v_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.1.text_cross_attn.v_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.1.text_cross_attn.v_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.1.text_cross_attn.v_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.1.text_cross_attn_layer_norm.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.1.text_cross_attn_layer_norm.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.1.vision_cross_attn.k_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.1.vision_cross_attn.k_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.1.vision_cross_attn.k_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.1.vision_cross_attn.k_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.1.vision_cross_attn.o_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.1.vision_cross_attn.o_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.1.vision_cross_attn.o_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.1.vision_cross_attn.o_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.1.vision_cross_attn.q_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.1.vision_cross_attn.q_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.1.vision_cross_attn.q_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.1.vision_cross_attn.q_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.1.vision_cross_attn.v_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.1.vision_cross_attn.v_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.1.vision_cross_attn.v_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.1.vision_cross_attn.v_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.1.vision_cross_attn_layer_norm.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.1.vision_cross_attn_layer_norm.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.2.mlp.fc1.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.2.mlp.fc1.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.2.mlp.fc1.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.2.mlp.fc1.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.2.mlp.fc2.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.2.mlp.fc2.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.2.mlp.fc2.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.2.mlp.fc2.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.2.mlp_layer_norm.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.2.mlp_layer_norm.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.2.self_attn.k_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.2.self_attn.k_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.2.self_attn.k_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.2.self_attn.k_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.2.self_attn.o_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.2.self_attn.o_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.2.self_attn.o_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.2.self_attn.o_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.2.self_attn.q_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.2.self_attn.q_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.2.self_attn.q_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.2.self_attn.q_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.2.self_attn.v_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.2.self_attn.v_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.2.self_attn.v_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.2.self_attn.v_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.2.self_attn_layer_norm.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.2.self_attn_layer_norm.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.2.text_cross_attn.k_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.2.text_cross_attn.k_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.2.text_cross_attn.k_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.2.text_cross_attn.k_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.2.text_cross_attn.o_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.2.text_cross_attn.o_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.2.text_cross_attn.o_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.2.text_cross_attn.o_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.2.text_cross_attn.q_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.2.text_cross_attn.q_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.2.text_cross_attn.q_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.2.text_cross_attn.q_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.2.text_cross_attn.v_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.2.text_cross_attn.v_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.2.text_cross_attn.v_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.2.text_cross_attn.v_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.2.text_cross_attn_layer_norm.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.2.text_cross_attn_layer_norm.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.2.vision_cross_attn.k_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.2.vision_cross_attn.k_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.2.vision_cross_attn.k_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.2.vision_cross_attn.k_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.2.vision_cross_attn.o_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.2.vision_cross_attn.o_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.2.vision_cross_attn.o_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.2.vision_cross_attn.o_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.2.vision_cross_attn.q_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.2.vision_cross_attn.q_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.2.vision_cross_attn.q_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.2.vision_cross_attn.q_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.2.vision_cross_attn.v_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.2.vision_cross_attn.v_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.2.vision_cross_attn.v_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.2.vision_cross_attn.v_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.2.vision_cross_attn_layer_norm.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.2.vision_cross_attn_layer_norm.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.3.mlp.fc1.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.3.mlp.fc1.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.3.mlp.fc1.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.3.mlp.fc1.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.3.mlp.fc2.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.3.mlp.fc2.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.3.mlp.fc2.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.3.mlp.fc2.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.3.mlp_layer_norm.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.3.mlp_layer_norm.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.3.self_attn.k_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.3.self_attn.k_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.3.self_attn.k_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.3.self_attn.k_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.3.self_attn.o_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.3.self_attn.o_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.3.self_attn.o_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.3.self_attn.o_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.3.self_attn.q_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.3.self_attn.q_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.3.self_attn.q_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.3.self_attn.q_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.3.self_attn.v_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.3.self_attn.v_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.3.self_attn.v_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.3.self_attn.v_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.3.self_attn_layer_norm.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.3.self_attn_layer_norm.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.3.text_cross_attn.k_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.3.text_cross_attn.k_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.3.text_cross_attn.k_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.3.text_cross_attn.k_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.3.text_cross_attn.o_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.3.text_cross_attn.o_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.3.text_cross_attn.o_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.3.text_cross_attn.o_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.3.text_cross_attn.q_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.3.text_cross_attn.q_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.3.text_cross_attn.q_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.3.text_cross_attn.q_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.3.text_cross_attn.v_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.3.text_cross_attn.v_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.3.text_cross_attn.v_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.3.text_cross_attn.v_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.3.text_cross_attn_layer_norm.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.3.text_cross_attn_layer_norm.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.3.vision_cross_attn.k_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.3.vision_cross_attn.k_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.3.vision_cross_attn.k_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.3.vision_cross_attn.k_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.3.vision_cross_attn.o_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.3.vision_cross_attn.o_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.3.vision_cross_attn.o_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.3.vision_cross_attn.o_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.3.vision_cross_attn.q_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.3.vision_cross_attn.q_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.3.vision_cross_attn.q_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.3.vision_cross_attn.q_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.3.vision_cross_attn.v_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.3.vision_cross_attn.v_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.3.vision_cross_attn.v_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.3.vision_cross_attn.v_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.3.vision_cross_attn_layer_norm.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.3.vision_cross_attn_layer_norm.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.4.mlp.fc1.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.4.mlp.fc1.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.4.mlp.fc1.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.4.mlp.fc1.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.4.mlp.fc2.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.4.mlp.fc2.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.4.mlp.fc2.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.4.mlp.fc2.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.4.mlp_layer_norm.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.4.mlp_layer_norm.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.4.self_attn.k_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.4.self_attn.k_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.4.self_attn.k_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.4.self_attn.k_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.4.self_attn.o_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.4.self_attn.o_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.4.self_attn.o_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.4.self_attn.o_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.4.self_attn.q_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.4.self_attn.q_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.4.self_attn.q_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.4.self_attn.q_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.4.self_attn.v_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.4.self_attn.v_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.4.self_attn.v_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.4.self_attn.v_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.4.self_attn_layer_norm.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.4.self_attn_layer_norm.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.4.text_cross_attn.k_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.4.text_cross_attn.k_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.4.text_cross_attn.k_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.4.text_cross_attn.k_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.4.text_cross_attn.o_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.4.text_cross_attn.o_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.4.text_cross_attn.o_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.4.text_cross_attn.o_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.4.text_cross_attn.q_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.4.text_cross_attn.q_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.4.text_cross_attn.q_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.4.text_cross_attn.q_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.4.text_cross_attn.v_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.4.text_cross_attn.v_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.4.text_cross_attn.v_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.4.text_cross_attn.v_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.4.text_cross_attn_layer_norm.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.4.text_cross_attn_layer_norm.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.4.vision_cross_attn.k_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.4.vision_cross_attn.k_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.4.vision_cross_attn.k_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.4.vision_cross_attn.k_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.4.vision_cross_attn.o_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.4.vision_cross_attn.o_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.4.vision_cross_attn.o_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.4.vision_cross_attn.o_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.4.vision_cross_attn.q_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.4.vision_cross_attn.q_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.4.vision_cross_attn.q_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.4.vision_cross_attn.q_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.4.vision_cross_attn.v_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.4.vision_cross_attn.v_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.4.vision_cross_attn.v_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.4.vision_cross_attn.v_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.4.vision_cross_attn_layer_norm.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.4.vision_cross_attn_layer_norm.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.5.mlp.fc1.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.5.mlp.fc1.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.5.mlp.fc1.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.5.mlp.fc1.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.5.mlp.fc2.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.5.mlp.fc2.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.5.mlp.fc2.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.5.mlp.fc2.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.5.mlp_layer_norm.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.5.mlp_layer_norm.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.5.self_attn.k_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.5.self_attn.k_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.5.self_attn.k_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.5.self_attn.k_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.5.self_attn.o_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.5.self_attn.o_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.5.self_attn.o_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.5.self_attn.o_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.5.self_attn.q_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.5.self_attn.q_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.5.self_attn.q_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.5.self_attn.q_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.5.self_attn.v_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.5.self_attn.v_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.5.self_attn.v_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.5.self_attn.v_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.5.self_attn_layer_norm.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.5.self_attn_layer_norm.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.5.text_cross_attn.k_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.5.text_cross_attn.k_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.5.text_cross_attn.k_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.5.text_cross_attn.k_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.5.text_cross_attn.o_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.5.text_cross_attn.o_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.5.text_cross_attn.o_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.5.text_cross_attn.o_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.5.text_cross_attn.q_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.5.text_cross_attn.q_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.5.text_cross_attn.q_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.5.text_cross_attn.q_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.5.text_cross_attn.v_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.5.text_cross_attn.v_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.5.text_cross_attn.v_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.5.text_cross_attn.v_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.5.text_cross_attn_layer_norm.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.5.text_cross_attn_layer_norm.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.5.vision_cross_attn.k_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.5.vision_cross_attn.k_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.5.vision_cross_attn.k_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.5.vision_cross_attn.k_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.5.vision_cross_attn.o_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.5.vision_cross_attn.o_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.5.vision_cross_attn.o_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.5.vision_cross_attn.o_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.5.vision_cross_attn.q_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.5.vision_cross_attn.q_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.5.vision_cross_attn.q_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.5.vision_cross_attn.q_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.5.vision_cross_attn.v_proj.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.5.vision_cross_attn.v_proj.biases": "model.safetensors",
        "detector_model.detr_decoder.layers.5.vision_cross_attn.v_proj.scales": "model.safetensors",
        "detector_model.detr_decoder.layers.5.vision_cross_attn.v_proj.weight": "model.safetensors",
        "detector_model.detr_decoder.layers.5.vision_cross_attn_layer_norm.bias": "model.safetensors",
        "detector_model.detr_decoder.layers.5.vision_cross_attn_layer_norm.weight": "model.safetensors",
        "detector_model.detr_decoder.output_layer_norm.bias": "model.safetensors",
        "detector_model.detr_decoder.output_layer_norm.weight": "model.safetensors",
        "detector_model.detr_decoder.presence_head.layer1.bias": "model.safetensors",
        "detector_model.detr_decoder.presence_head.layer1.biases": "model.safetensors",
        "detector_model.detr_decoder.presence_head.layer1.scales": "model.safetensors",
        "detector_model.detr_decoder.presence_head.layer1.weight": "model.safetensors",
        "detector_model.detr_decoder.presence_head.layer2.bias": "model.safetensors",
        "detector_model.detr_decoder.presence_head.layer2.biases": "model.safetensors",
        "detector_model.detr_decoder.presence_head.layer2.scales": "model.safetensors",
        "detector_model.detr_decoder.presence_head.layer2.weight": "model.safetensors",
        "detector_model.detr_decoder.presence_head.layer3.bias": "model.safetensors",
        "detector_model.detr_decoder.presence_head.layer3.weight": "model.safetensors",
        "detector_model.detr_decoder.presence_layer_norm.bias": "model.safetensors",
        "detector_model.detr_decoder.presence_layer_norm.weight": "model.safetensors",
        "detector_model.detr_decoder.presence_token.weight": "model.safetensors",
        "detector_model.detr_decoder.query_embed.weight": "model.safetensors",
        "detector_model.detr_decoder.ref_point_head.layer1.bias": "model.safetensors",
        "detector_model.detr_decoder.ref_point_head.layer1.biases": "model.safetensors",
        "detector_model.detr_decoder.ref_point_head.layer1.scales": "model.safetensors",
        "detector_model.detr_decoder.ref_point_head.layer1.weight": "model.safetensors",
        "detector_model.detr_decoder.ref_point_head.layer2.bias": "model.safetensors",
        "detector_model.detr_decoder.ref_point_head.layer2.biases": "model.safetensors",
        "detector_model.detr_decoder.ref_point_head.layer2.scales": "model.safetensors",
        "detector_model.detr_decoder.ref_point_head.layer2.weight": "model.safetensors",
        "detector_model.detr_decoder.reference_points.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.0.cross_attn.k_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.0.cross_attn.k_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.0.cross_attn.k_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.0.cross_attn.k_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.0.cross_attn.o_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.0.cross_attn.o_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.0.cross_attn.o_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.0.cross_attn.o_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.0.cross_attn.q_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.0.cross_attn.q_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.0.cross_attn.q_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.0.cross_attn.q_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.0.cross_attn.v_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.0.cross_attn.v_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.0.cross_attn.v_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.0.cross_attn.v_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.0.layer_norm1.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.0.layer_norm1.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.0.layer_norm2.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.0.layer_norm2.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.0.layer_norm3.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.0.layer_norm3.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.0.mlp.fc1.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.0.mlp.fc1.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.0.mlp.fc1.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.0.mlp.fc1.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.0.mlp.fc2.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.0.mlp.fc2.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.0.mlp.fc2.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.0.mlp.fc2.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.0.self_attn.k_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.0.self_attn.k_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.0.self_attn.k_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.0.self_attn.k_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.0.self_attn.o_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.0.self_attn.o_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.0.self_attn.o_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.0.self_attn.o_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.0.self_attn.q_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.0.self_attn.q_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.0.self_attn.q_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.0.self_attn.q_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.0.self_attn.v_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.0.self_attn.v_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.0.self_attn.v_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.0.self_attn.v_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.1.cross_attn.k_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.1.cross_attn.k_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.1.cross_attn.k_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.1.cross_attn.k_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.1.cross_attn.o_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.1.cross_attn.o_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.1.cross_attn.o_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.1.cross_attn.o_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.1.cross_attn.q_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.1.cross_attn.q_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.1.cross_attn.q_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.1.cross_attn.q_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.1.cross_attn.v_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.1.cross_attn.v_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.1.cross_attn.v_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.1.cross_attn.v_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.1.layer_norm1.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.1.layer_norm1.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.1.layer_norm2.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.1.layer_norm2.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.1.layer_norm3.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.1.layer_norm3.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.1.mlp.fc1.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.1.mlp.fc1.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.1.mlp.fc1.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.1.mlp.fc1.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.1.mlp.fc2.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.1.mlp.fc2.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.1.mlp.fc2.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.1.mlp.fc2.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.1.self_attn.k_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.1.self_attn.k_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.1.self_attn.k_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.1.self_attn.k_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.1.self_attn.o_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.1.self_attn.o_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.1.self_attn.o_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.1.self_attn.o_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.1.self_attn.q_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.1.self_attn.q_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.1.self_attn.q_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.1.self_attn.q_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.1.self_attn.v_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.1.self_attn.v_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.1.self_attn.v_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.1.self_attn.v_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.2.cross_attn.k_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.2.cross_attn.k_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.2.cross_attn.k_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.2.cross_attn.k_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.2.cross_attn.o_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.2.cross_attn.o_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.2.cross_attn.o_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.2.cross_attn.o_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.2.cross_attn.q_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.2.cross_attn.q_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.2.cross_attn.q_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.2.cross_attn.q_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.2.cross_attn.v_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.2.cross_attn.v_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.2.cross_attn.v_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.2.cross_attn.v_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.2.layer_norm1.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.2.layer_norm1.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.2.layer_norm2.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.2.layer_norm2.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.2.layer_norm3.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.2.layer_norm3.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.2.mlp.fc1.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.2.mlp.fc1.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.2.mlp.fc1.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.2.mlp.fc1.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.2.mlp.fc2.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.2.mlp.fc2.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.2.mlp.fc2.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.2.mlp.fc2.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.2.self_attn.k_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.2.self_attn.k_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.2.self_attn.k_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.2.self_attn.k_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.2.self_attn.o_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.2.self_attn.o_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.2.self_attn.o_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.2.self_attn.o_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.2.self_attn.q_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.2.self_attn.q_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.2.self_attn.q_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.2.self_attn.q_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.2.self_attn.v_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.2.self_attn.v_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.2.self_attn.v_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.2.self_attn.v_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.3.cross_attn.k_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.3.cross_attn.k_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.3.cross_attn.k_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.3.cross_attn.k_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.3.cross_attn.o_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.3.cross_attn.o_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.3.cross_attn.o_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.3.cross_attn.o_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.3.cross_attn.q_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.3.cross_attn.q_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.3.cross_attn.q_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.3.cross_attn.q_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.3.cross_attn.v_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.3.cross_attn.v_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.3.cross_attn.v_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.3.cross_attn.v_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.3.layer_norm1.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.3.layer_norm1.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.3.layer_norm2.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.3.layer_norm2.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.3.layer_norm3.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.3.layer_norm3.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.3.mlp.fc1.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.3.mlp.fc1.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.3.mlp.fc1.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.3.mlp.fc1.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.3.mlp.fc2.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.3.mlp.fc2.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.3.mlp.fc2.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.3.mlp.fc2.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.3.self_attn.k_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.3.self_attn.k_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.3.self_attn.k_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.3.self_attn.k_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.3.self_attn.o_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.3.self_attn.o_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.3.self_attn.o_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.3.self_attn.o_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.3.self_attn.q_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.3.self_attn.q_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.3.self_attn.q_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.3.self_attn.q_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.3.self_attn.v_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.3.self_attn.v_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.3.self_attn.v_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.3.self_attn.v_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.4.cross_attn.k_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.4.cross_attn.k_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.4.cross_attn.k_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.4.cross_attn.k_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.4.cross_attn.o_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.4.cross_attn.o_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.4.cross_attn.o_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.4.cross_attn.o_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.4.cross_attn.q_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.4.cross_attn.q_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.4.cross_attn.q_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.4.cross_attn.q_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.4.cross_attn.v_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.4.cross_attn.v_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.4.cross_attn.v_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.4.cross_attn.v_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.4.layer_norm1.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.4.layer_norm1.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.4.layer_norm2.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.4.layer_norm2.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.4.layer_norm3.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.4.layer_norm3.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.4.mlp.fc1.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.4.mlp.fc1.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.4.mlp.fc1.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.4.mlp.fc1.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.4.mlp.fc2.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.4.mlp.fc2.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.4.mlp.fc2.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.4.mlp.fc2.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.4.self_attn.k_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.4.self_attn.k_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.4.self_attn.k_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.4.self_attn.k_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.4.self_attn.o_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.4.self_attn.o_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.4.self_attn.o_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.4.self_attn.o_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.4.self_attn.q_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.4.self_attn.q_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.4.self_attn.q_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.4.self_attn.q_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.4.self_attn.v_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.4.self_attn.v_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.4.self_attn.v_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.4.self_attn.v_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.5.cross_attn.k_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.5.cross_attn.k_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.5.cross_attn.k_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.5.cross_attn.k_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.5.cross_attn.o_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.5.cross_attn.o_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.5.cross_attn.o_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.5.cross_attn.o_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.5.cross_attn.q_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.5.cross_attn.q_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.5.cross_attn.q_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.5.cross_attn.q_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.5.cross_attn.v_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.5.cross_attn.v_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.5.cross_attn.v_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.5.cross_attn.v_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.5.layer_norm1.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.5.layer_norm1.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.5.layer_norm2.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.5.layer_norm2.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.5.layer_norm3.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.5.layer_norm3.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.5.mlp.fc1.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.5.mlp.fc1.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.5.mlp.fc1.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.5.mlp.fc1.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.5.mlp.fc2.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.5.mlp.fc2.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.5.mlp.fc2.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.5.mlp.fc2.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.5.self_attn.k_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.5.self_attn.k_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.5.self_attn.k_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.5.self_attn.k_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.5.self_attn.o_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.5.self_attn.o_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.5.self_attn.o_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.5.self_attn.o_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.5.self_attn.q_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.5.self_attn.q_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.5.self_attn.q_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.5.self_attn.q_proj.weight": "model.safetensors",
        "detector_model.detr_encoder.layers.5.self_attn.v_proj.bias": "model.safetensors",
        "detector_model.detr_encoder.layers.5.self_attn.v_proj.biases": "model.safetensors",
        "detector_model.detr_encoder.layers.5.self_attn.v_proj.scales": "model.safetensors",
        "detector_model.detr_encoder.layers.5.self_attn.v_proj.weight": "model.safetensors",
        "detector_model.dot_product_scoring.query_proj.bias": "model.safetensors",
        "detector_model.dot_product_scoring.query_proj.biases": "model.safetensors",
        "detector_model.dot_product_scoring.query_proj.scales": "model.safetensors",
        "detector_model.dot_product_scoring.query_proj.weight": "model.safetensors",
        "detector_model.dot_product_scoring.text_mlp.layer1.bias": "model.safetensors",
        "detector_model.dot_product_scoring.text_mlp.layer1.biases": "model.safetensors",
        "detector_model.dot_product_scoring.text_mlp.layer1.scales": "model.safetensors",
        "detector_model.dot_product_scoring.text_mlp.layer1.weight": "model.safetensors",
        "detector_model.dot_product_scoring.text_mlp.layer2.bias": "model.safetensors",
        "detector_model.dot_product_scoring.text_mlp.layer2.biases": "model.safetensors",
        "detector_model.dot_product_scoring.text_mlp.layer2.scales": "model.safetensors",
        "detector_model.dot_product_scoring.text_mlp.layer2.weight": "model.safetensors",
        "detector_model.dot_product_scoring.text_mlp_out_norm.bias": "model.safetensors",
        "detector_model.dot_product_scoring.text_mlp_out_norm.weight": "model.safetensors",
        "detector_model.dot_product_scoring.text_proj.bias": "model.safetensors",
        "detector_model.dot_product_scoring.text_proj.biases": "model.safetensors",
        "detector_model.dot_product_scoring.text_proj.scales": "model.safetensors",
        "detector_model.dot_product_scoring.text_proj.weight": "model.safetensors",
        "detector_model.geometry_encoder.boxes_direct_project.bias": "model.safetensors",
        "detector_model.geometry_encoder.boxes_direct_project.weight": "model.safetensors",
        "detector_model.geometry_encoder.boxes_pool_project.bias": "model.safetensors",
        "detector_model.geometry_encoder.boxes_pool_project.weight": "model.safetensors",
        "detector_model.geometry_encoder.boxes_pos_enc_project.bias": "model.safetensors",
        "detector_model.geometry_encoder.boxes_pos_enc_project.weight": "model.safetensors",
        "detector_model.geometry_encoder.cls_embed.weight": "model.safetensors",
        "detector_model.geometry_encoder.final_proj.bias": "model.safetensors",
        "detector_model.geometry_encoder.final_proj.biases": "model.safetensors",
        "detector_model.geometry_encoder.final_proj.scales": "model.safetensors",
        "detector_model.geometry_encoder.final_proj.weight": "model.safetensors",
        "detector_model.geometry_encoder.label_embed.weight": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.cross_attn.k_proj.bias": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.cross_attn.k_proj.biases": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.cross_attn.k_proj.scales": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.cross_attn.k_proj.weight": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.cross_attn.o_proj.bias": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.cross_attn.o_proj.biases": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.cross_attn.o_proj.scales": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.cross_attn.o_proj.weight": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.cross_attn.q_proj.bias": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.cross_attn.q_proj.biases": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.cross_attn.q_proj.scales": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.cross_attn.q_proj.weight": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.cross_attn.v_proj.bias": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.cross_attn.v_proj.biases": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.cross_attn.v_proj.scales": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.cross_attn.v_proj.weight": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.layer_norm1.bias": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.layer_norm1.weight": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.layer_norm2.bias": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.layer_norm2.weight": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.layer_norm3.bias": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.layer_norm3.weight": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.mlp.fc1.bias": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.mlp.fc1.biases": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.mlp.fc1.scales": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.mlp.fc1.weight": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.mlp.fc2.bias": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.mlp.fc2.biases": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.mlp.fc2.scales": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.mlp.fc2.weight": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.self_attn.k_proj.bias": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.self_attn.k_proj.biases": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.self_attn.k_proj.scales": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.self_attn.k_proj.weight": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.self_attn.o_proj.bias": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.self_attn.o_proj.biases": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.self_attn.o_proj.scales": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.self_attn.o_proj.weight": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.self_attn.q_proj.bias": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.self_attn.q_proj.biases": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.self_attn.q_proj.scales": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.self_attn.q_proj.weight": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.self_attn.v_proj.bias": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.self_attn.v_proj.biases": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.self_attn.v_proj.scales": "model.safetensors",
        "detector_model.geometry_encoder.layers.0.self_attn.v_proj.weight": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.cross_attn.k_proj.bias": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.cross_attn.k_proj.biases": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.cross_attn.k_proj.scales": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.cross_attn.k_proj.weight": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.cross_attn.o_proj.bias": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.cross_attn.o_proj.biases": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.cross_attn.o_proj.scales": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.cross_attn.o_proj.weight": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.cross_attn.q_proj.bias": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.cross_attn.q_proj.biases": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.cross_attn.q_proj.scales": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.cross_attn.q_proj.weight": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.cross_attn.v_proj.bias": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.cross_attn.v_proj.biases": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.cross_attn.v_proj.scales": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.cross_attn.v_proj.weight": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.layer_norm1.bias": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.layer_norm1.weight": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.layer_norm2.bias": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.layer_norm2.weight": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.layer_norm3.bias": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.layer_norm3.weight": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.mlp.fc1.bias": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.mlp.fc1.biases": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.mlp.fc1.scales": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.mlp.fc1.weight": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.mlp.fc2.bias": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.mlp.fc2.biases": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.mlp.fc2.scales": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.mlp.fc2.weight": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.self_attn.k_proj.bias": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.self_attn.k_proj.biases": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.self_attn.k_proj.scales": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.self_attn.k_proj.weight": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.self_attn.o_proj.bias": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.self_attn.o_proj.biases": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.self_attn.o_proj.scales": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.self_attn.o_proj.weight": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.self_attn.q_proj.bias": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.self_attn.q_proj.biases": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.self_attn.q_proj.scales": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.self_attn.q_proj.weight": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.self_attn.v_proj.bias": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.self_attn.v_proj.biases": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.self_attn.v_proj.scales": "model.safetensors",
        "detector_model.geometry_encoder.layers.1.self_attn.v_proj.weight": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.cross_attn.k_proj.bias": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.cross_attn.k_proj.biases": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.cross_attn.k_proj.scales": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.cross_attn.k_proj.weight": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.cross_attn.o_proj.bias": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.cross_attn.o_proj.biases": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.cross_attn.o_proj.scales": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.cross_attn.o_proj.weight": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.cross_attn.q_proj.bias": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.cross_attn.q_proj.biases": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.cross_attn.q_proj.scales": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.cross_attn.q_proj.weight": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.cross_attn.v_proj.bias": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.cross_attn.v_proj.biases": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.cross_attn.v_proj.scales": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.cross_attn.v_proj.weight": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.layer_norm1.bias": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.layer_norm1.weight": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.layer_norm2.bias": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.layer_norm2.weight": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.layer_norm3.bias": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.layer_norm3.weight": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.mlp.fc1.bias": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.mlp.fc1.biases": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.mlp.fc1.scales": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.mlp.fc1.weight": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.mlp.fc2.bias": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.mlp.fc2.biases": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.mlp.fc2.scales": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.mlp.fc2.weight": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.self_attn.k_proj.bias": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.self_attn.k_proj.biases": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.self_attn.k_proj.scales": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.self_attn.k_proj.weight": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.self_attn.o_proj.bias": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.self_attn.o_proj.biases": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.self_attn.o_proj.scales": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.self_attn.o_proj.weight": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.self_attn.q_proj.bias": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.self_attn.q_proj.biases": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.self_attn.q_proj.scales": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.self_attn.q_proj.weight": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.self_attn.v_proj.bias": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.self_attn.v_proj.biases": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.self_attn.v_proj.scales": "model.safetensors",
        "detector_model.geometry_encoder.layers.2.self_attn.v_proj.weight": "model.safetensors",
        "detector_model.geometry_encoder.output_layer_norm.bias": "model.safetensors",
        "detector_model.geometry_encoder.output_layer_norm.weight": "model.safetensors",
        "detector_model.geometry_encoder.prompt_layer_norm.bias": "model.safetensors",
        "detector_model.geometry_encoder.prompt_layer_norm.weight": "model.safetensors",
        "detector_model.geometry_encoder.vision_layer_norm.bias": "model.safetensors",
        "detector_model.geometry_encoder.vision_layer_norm.weight": "model.safetensors",
        "detector_model.mask_decoder.instance_projection.bias": "model.safetensors",
        "detector_model.mask_decoder.instance_projection.weight": "model.safetensors",
        "detector_model.mask_decoder.mask_embedder.layers.0.bias": "model.safetensors",
        "detector_model.mask_decoder.mask_embedder.layers.0.biases": "model.safetensors",
        "detector_model.mask_decoder.mask_embedder.layers.0.scales": "model.safetensors",
        "detector_model.mask_decoder.mask_embedder.layers.0.weight": "model.safetensors",
        "detector_model.mask_decoder.mask_embedder.layers.1.bias": "model.safetensors",
        "detector_model.mask_decoder.mask_embedder.layers.1.biases": "model.safetensors",
        "detector_model.mask_decoder.mask_embedder.layers.1.scales": "model.safetensors",
        "detector_model.mask_decoder.mask_embedder.layers.1.weight": "model.safetensors",
        "detector_model.mask_decoder.mask_embedder.layers.2.bias": "model.safetensors",
        "detector_model.mask_decoder.mask_embedder.layers.2.biases": "model.safetensors",
        "detector_model.mask_decoder.mask_embedder.layers.2.scales": "model.safetensors",
        "detector_model.mask_decoder.mask_embedder.layers.2.weight": "model.safetensors",
        "detector_model.mask_decoder.pixel_decoder.conv_layers.0.bias": "model.safetensors",
        "detector_model.mask_decoder.pixel_decoder.conv_layers.0.weight": "model.safetensors",
        "detector_model.mask_decoder.pixel_decoder.conv_layers.1.bias": "model.safetensors",
        "detector_model.mask_decoder.pixel_decoder.conv_layers.1.weight": "model.safetensors",
        "detector_model.mask_decoder.pixel_decoder.conv_layers.2.bias": "model.safetensors",
        "detector_model.mask_decoder.pixel_decoder.conv_layers.2.weight": "model.safetensors",
        "detector_model.mask_decoder.pixel_decoder.norms.0.bias": "model.safetensors",
        "detector_model.mask_decoder.pixel_decoder.norms.0.weight": "model.safetensors",
        "detector_model.mask_decoder.pixel_decoder.norms.1.bias": "model.safetensors",
        "detector_model.mask_decoder.pixel_decoder.norms.1.weight": "model.safetensors",
        "detector_model.mask_decoder.pixel_decoder.norms.2.bias": "model.safetensors",
        "detector_model.mask_decoder.pixel_decoder.norms.2.weight": "model.safetensors",
        "detector_model.mask_decoder.prompt_cross_attn.k_proj.bias": "model.safetensors",
        "detector_model.mask_decoder.prompt_cross_attn.k_proj.biases": "model.safetensors",
        "detector_model.mask_decoder.prompt_cross_attn.k_proj.scales": "model.safetensors",
        "detector_model.mask_decoder.prompt_cross_attn.k_proj.weight": "model.safetensors",
        "detector_model.mask_decoder.prompt_cross_attn.o_proj.bias": "model.safetensors",
        "detector_model.mask_decoder.prompt_cross_attn.o_proj.biases": "model.safetensors",
        "detector_model.mask_decoder.prompt_cross_attn.o_proj.scales": "model.safetensors",
        "detector_model.mask_decoder.prompt_cross_attn.o_proj.weight": "model.safetensors",
        "detector_model.mask_decoder.prompt_cross_attn.q_proj.bias": "model.safetensors",
        "detector_model.mask_decoder.prompt_cross_attn.q_proj.biases": "model.safetensors",
        "detector_model.mask_decoder.prompt_cross_attn.q_proj.scales": "model.safetensors",
        "detector_model.mask_decoder.prompt_cross_attn.q_proj.weight": "model.safetensors",
        "detector_model.mask_decoder.prompt_cross_attn.v_proj.bias": "model.safetensors",
        "detector_model.mask_decoder.prompt_cross_attn.v_proj.biases": "model.safetensors",
        "detector_model.mask_decoder.prompt_cross_attn.v_proj.scales": "model.safetensors",
        "detector_model.mask_decoder.prompt_cross_attn.v_proj.weight": "model.safetensors",
        "detector_model.mask_decoder.prompt_cross_attn_norm.bias": "model.safetensors",
        "detector_model.mask_decoder.prompt_cross_attn_norm.weight": "model.safetensors",
        "detector_model.mask_decoder.semantic_projection.bias": "model.safetensors",
        "detector_model.mask_decoder.semantic_projection.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.embeddings.position_embedding.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.embeddings.token_embedding.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.embeddings.token_embedding.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.embeddings.token_embedding.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.0.layer_norm1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.0.layer_norm1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.0.layer_norm2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.0.layer_norm2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.0.mlp.fc1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.0.mlp.fc1.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.0.mlp.fc1.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.0.mlp.fc1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.0.mlp.fc2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.0.mlp.fc2.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.0.mlp.fc2.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.0.mlp.fc2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.0.self_attn.k_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.0.self_attn.k_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.0.self_attn.k_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.0.self_attn.k_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.0.self_attn.out_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.0.self_attn.out_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.0.self_attn.out_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.0.self_attn.out_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.0.self_attn.q_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.0.self_attn.q_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.0.self_attn.q_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.0.self_attn.q_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.0.self_attn.v_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.0.self_attn.v_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.0.self_attn.v_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.0.self_attn.v_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.1.layer_norm1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.1.layer_norm1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.1.layer_norm2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.1.layer_norm2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.1.mlp.fc1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.1.mlp.fc1.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.1.mlp.fc1.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.1.mlp.fc1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.1.mlp.fc2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.1.mlp.fc2.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.1.mlp.fc2.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.1.mlp.fc2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.1.self_attn.k_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.1.self_attn.k_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.1.self_attn.k_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.1.self_attn.k_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.1.self_attn.out_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.1.self_attn.out_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.1.self_attn.out_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.1.self_attn.out_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.1.self_attn.q_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.1.self_attn.q_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.1.self_attn.q_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.1.self_attn.q_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.1.self_attn.v_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.1.self_attn.v_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.1.self_attn.v_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.1.self_attn.v_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.10.layer_norm1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.10.layer_norm1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.10.layer_norm2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.10.layer_norm2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.10.mlp.fc1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.10.mlp.fc1.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.10.mlp.fc1.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.10.mlp.fc1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.10.mlp.fc2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.10.mlp.fc2.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.10.mlp.fc2.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.10.mlp.fc2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.10.self_attn.k_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.10.self_attn.k_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.10.self_attn.k_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.10.self_attn.k_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.10.self_attn.out_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.10.self_attn.out_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.10.self_attn.out_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.10.self_attn.out_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.10.self_attn.q_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.10.self_attn.q_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.10.self_attn.q_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.10.self_attn.q_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.10.self_attn.v_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.10.self_attn.v_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.10.self_attn.v_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.10.self_attn.v_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.11.layer_norm1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.11.layer_norm1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.11.layer_norm2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.11.layer_norm2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.11.mlp.fc1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.11.mlp.fc1.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.11.mlp.fc1.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.11.mlp.fc1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.11.mlp.fc2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.11.mlp.fc2.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.11.mlp.fc2.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.11.mlp.fc2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.11.self_attn.k_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.11.self_attn.k_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.11.self_attn.k_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.11.self_attn.k_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.11.self_attn.out_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.11.self_attn.out_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.11.self_attn.out_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.11.self_attn.out_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.11.self_attn.q_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.11.self_attn.q_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.11.self_attn.q_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.11.self_attn.q_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.11.self_attn.v_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.11.self_attn.v_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.11.self_attn.v_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.11.self_attn.v_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.12.layer_norm1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.12.layer_norm1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.12.layer_norm2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.12.layer_norm2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.12.mlp.fc1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.12.mlp.fc1.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.12.mlp.fc1.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.12.mlp.fc1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.12.mlp.fc2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.12.mlp.fc2.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.12.mlp.fc2.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.12.mlp.fc2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.12.self_attn.k_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.12.self_attn.k_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.12.self_attn.k_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.12.self_attn.k_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.12.self_attn.out_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.12.self_attn.out_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.12.self_attn.out_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.12.self_attn.out_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.12.self_attn.q_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.12.self_attn.q_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.12.self_attn.q_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.12.self_attn.q_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.12.self_attn.v_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.12.self_attn.v_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.12.self_attn.v_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.12.self_attn.v_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.13.layer_norm1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.13.layer_norm1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.13.layer_norm2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.13.layer_norm2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.13.mlp.fc1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.13.mlp.fc1.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.13.mlp.fc1.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.13.mlp.fc1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.13.mlp.fc2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.13.mlp.fc2.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.13.mlp.fc2.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.13.mlp.fc2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.13.self_attn.k_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.13.self_attn.k_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.13.self_attn.k_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.13.self_attn.k_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.13.self_attn.out_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.13.self_attn.out_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.13.self_attn.out_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.13.self_attn.out_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.13.self_attn.q_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.13.self_attn.q_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.13.self_attn.q_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.13.self_attn.q_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.13.self_attn.v_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.13.self_attn.v_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.13.self_attn.v_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.13.self_attn.v_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.14.layer_norm1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.14.layer_norm1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.14.layer_norm2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.14.layer_norm2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.14.mlp.fc1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.14.mlp.fc1.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.14.mlp.fc1.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.14.mlp.fc1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.14.mlp.fc2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.14.mlp.fc2.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.14.mlp.fc2.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.14.mlp.fc2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.14.self_attn.k_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.14.self_attn.k_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.14.self_attn.k_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.14.self_attn.k_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.14.self_attn.out_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.14.self_attn.out_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.14.self_attn.out_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.14.self_attn.out_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.14.self_attn.q_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.14.self_attn.q_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.14.self_attn.q_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.14.self_attn.q_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.14.self_attn.v_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.14.self_attn.v_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.14.self_attn.v_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.14.self_attn.v_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.15.layer_norm1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.15.layer_norm1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.15.layer_norm2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.15.layer_norm2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.15.mlp.fc1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.15.mlp.fc1.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.15.mlp.fc1.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.15.mlp.fc1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.15.mlp.fc2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.15.mlp.fc2.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.15.mlp.fc2.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.15.mlp.fc2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.15.self_attn.k_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.15.self_attn.k_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.15.self_attn.k_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.15.self_attn.k_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.15.self_attn.out_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.15.self_attn.out_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.15.self_attn.out_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.15.self_attn.out_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.15.self_attn.q_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.15.self_attn.q_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.15.self_attn.q_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.15.self_attn.q_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.15.self_attn.v_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.15.self_attn.v_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.15.self_attn.v_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.15.self_attn.v_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.16.layer_norm1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.16.layer_norm1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.16.layer_norm2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.16.layer_norm2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.16.mlp.fc1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.16.mlp.fc1.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.16.mlp.fc1.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.16.mlp.fc1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.16.mlp.fc2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.16.mlp.fc2.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.16.mlp.fc2.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.16.mlp.fc2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.16.self_attn.k_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.16.self_attn.k_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.16.self_attn.k_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.16.self_attn.k_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.16.self_attn.out_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.16.self_attn.out_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.16.self_attn.out_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.16.self_attn.out_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.16.self_attn.q_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.16.self_attn.q_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.16.self_attn.q_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.16.self_attn.q_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.16.self_attn.v_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.16.self_attn.v_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.16.self_attn.v_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.16.self_attn.v_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.17.layer_norm1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.17.layer_norm1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.17.layer_norm2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.17.layer_norm2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.17.mlp.fc1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.17.mlp.fc1.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.17.mlp.fc1.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.17.mlp.fc1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.17.mlp.fc2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.17.mlp.fc2.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.17.mlp.fc2.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.17.mlp.fc2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.17.self_attn.k_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.17.self_attn.k_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.17.self_attn.k_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.17.self_attn.k_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.17.self_attn.out_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.17.self_attn.out_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.17.self_attn.out_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.17.self_attn.out_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.17.self_attn.q_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.17.self_attn.q_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.17.self_attn.q_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.17.self_attn.q_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.17.self_attn.v_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.17.self_attn.v_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.17.self_attn.v_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.17.self_attn.v_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.18.layer_norm1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.18.layer_norm1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.18.layer_norm2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.18.layer_norm2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.18.mlp.fc1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.18.mlp.fc1.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.18.mlp.fc1.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.18.mlp.fc1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.18.mlp.fc2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.18.mlp.fc2.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.18.mlp.fc2.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.18.mlp.fc2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.18.self_attn.k_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.18.self_attn.k_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.18.self_attn.k_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.18.self_attn.k_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.18.self_attn.out_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.18.self_attn.out_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.18.self_attn.out_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.18.self_attn.out_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.18.self_attn.q_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.18.self_attn.q_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.18.self_attn.q_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.18.self_attn.q_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.18.self_attn.v_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.18.self_attn.v_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.18.self_attn.v_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.18.self_attn.v_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.19.layer_norm1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.19.layer_norm1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.19.layer_norm2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.19.layer_norm2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.19.mlp.fc1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.19.mlp.fc1.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.19.mlp.fc1.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.19.mlp.fc1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.19.mlp.fc2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.19.mlp.fc2.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.19.mlp.fc2.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.19.mlp.fc2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.19.self_attn.k_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.19.self_attn.k_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.19.self_attn.k_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.19.self_attn.k_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.19.self_attn.out_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.19.self_attn.out_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.19.self_attn.out_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.19.self_attn.out_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.19.self_attn.q_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.19.self_attn.q_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.19.self_attn.q_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.19.self_attn.q_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.19.self_attn.v_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.19.self_attn.v_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.19.self_attn.v_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.19.self_attn.v_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.2.layer_norm1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.2.layer_norm1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.2.layer_norm2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.2.layer_norm2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.2.mlp.fc1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.2.mlp.fc1.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.2.mlp.fc1.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.2.mlp.fc1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.2.mlp.fc2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.2.mlp.fc2.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.2.mlp.fc2.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.2.mlp.fc2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.2.self_attn.k_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.2.self_attn.k_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.2.self_attn.k_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.2.self_attn.k_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.2.self_attn.out_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.2.self_attn.out_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.2.self_attn.out_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.2.self_attn.out_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.2.self_attn.q_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.2.self_attn.q_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.2.self_attn.q_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.2.self_attn.q_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.2.self_attn.v_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.2.self_attn.v_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.2.self_attn.v_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.2.self_attn.v_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.20.layer_norm1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.20.layer_norm1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.20.layer_norm2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.20.layer_norm2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.20.mlp.fc1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.20.mlp.fc1.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.20.mlp.fc1.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.20.mlp.fc1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.20.mlp.fc2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.20.mlp.fc2.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.20.mlp.fc2.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.20.mlp.fc2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.20.self_attn.k_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.20.self_attn.k_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.20.self_attn.k_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.20.self_attn.k_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.20.self_attn.out_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.20.self_attn.out_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.20.self_attn.out_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.20.self_attn.out_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.20.self_attn.q_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.20.self_attn.q_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.20.self_attn.q_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.20.self_attn.q_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.20.self_attn.v_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.20.self_attn.v_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.20.self_attn.v_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.20.self_attn.v_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.21.layer_norm1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.21.layer_norm1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.21.layer_norm2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.21.layer_norm2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.21.mlp.fc1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.21.mlp.fc1.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.21.mlp.fc1.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.21.mlp.fc1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.21.mlp.fc2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.21.mlp.fc2.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.21.mlp.fc2.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.21.mlp.fc2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.21.self_attn.k_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.21.self_attn.k_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.21.self_attn.k_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.21.self_attn.k_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.21.self_attn.out_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.21.self_attn.out_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.21.self_attn.out_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.21.self_attn.out_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.21.self_attn.q_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.21.self_attn.q_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.21.self_attn.q_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.21.self_attn.q_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.21.self_attn.v_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.21.self_attn.v_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.21.self_attn.v_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.21.self_attn.v_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.22.layer_norm1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.22.layer_norm1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.22.layer_norm2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.22.layer_norm2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.22.mlp.fc1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.22.mlp.fc1.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.22.mlp.fc1.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.22.mlp.fc1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.22.mlp.fc2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.22.mlp.fc2.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.22.mlp.fc2.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.22.mlp.fc2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.22.self_attn.k_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.22.self_attn.k_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.22.self_attn.k_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.22.self_attn.k_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.22.self_attn.out_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.22.self_attn.out_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.22.self_attn.out_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.22.self_attn.out_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.22.self_attn.q_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.22.self_attn.q_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.22.self_attn.q_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.22.self_attn.q_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.22.self_attn.v_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.22.self_attn.v_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.22.self_attn.v_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.22.self_attn.v_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.23.layer_norm1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.23.layer_norm1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.23.layer_norm2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.23.layer_norm2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.23.mlp.fc1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.23.mlp.fc1.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.23.mlp.fc1.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.23.mlp.fc1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.23.mlp.fc2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.23.mlp.fc2.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.23.mlp.fc2.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.23.mlp.fc2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.23.self_attn.k_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.23.self_attn.k_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.23.self_attn.k_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.23.self_attn.k_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.23.self_attn.out_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.23.self_attn.out_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.23.self_attn.out_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.23.self_attn.out_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.23.self_attn.q_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.23.self_attn.q_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.23.self_attn.q_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.23.self_attn.q_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.23.self_attn.v_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.23.self_attn.v_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.23.self_attn.v_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.23.self_attn.v_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.3.layer_norm1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.3.layer_norm1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.3.layer_norm2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.3.layer_norm2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.3.mlp.fc1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.3.mlp.fc1.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.3.mlp.fc1.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.3.mlp.fc1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.3.mlp.fc2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.3.mlp.fc2.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.3.mlp.fc2.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.3.mlp.fc2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.3.self_attn.k_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.3.self_attn.k_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.3.self_attn.k_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.3.self_attn.k_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.3.self_attn.out_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.3.self_attn.out_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.3.self_attn.out_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.3.self_attn.out_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.3.self_attn.q_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.3.self_attn.q_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.3.self_attn.q_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.3.self_attn.q_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.3.self_attn.v_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.3.self_attn.v_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.3.self_attn.v_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.3.self_attn.v_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.4.layer_norm1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.4.layer_norm1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.4.layer_norm2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.4.layer_norm2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.4.mlp.fc1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.4.mlp.fc1.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.4.mlp.fc1.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.4.mlp.fc1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.4.mlp.fc2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.4.mlp.fc2.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.4.mlp.fc2.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.4.mlp.fc2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.4.self_attn.k_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.4.self_attn.k_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.4.self_attn.k_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.4.self_attn.k_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.4.self_attn.out_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.4.self_attn.out_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.4.self_attn.out_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.4.self_attn.out_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.4.self_attn.q_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.4.self_attn.q_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.4.self_attn.q_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.4.self_attn.q_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.4.self_attn.v_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.4.self_attn.v_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.4.self_attn.v_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.4.self_attn.v_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.5.layer_norm1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.5.layer_norm1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.5.layer_norm2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.5.layer_norm2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.5.mlp.fc1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.5.mlp.fc1.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.5.mlp.fc1.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.5.mlp.fc1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.5.mlp.fc2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.5.mlp.fc2.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.5.mlp.fc2.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.5.mlp.fc2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.5.self_attn.k_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.5.self_attn.k_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.5.self_attn.k_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.5.self_attn.k_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.5.self_attn.out_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.5.self_attn.out_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.5.self_attn.out_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.5.self_attn.out_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.5.self_attn.q_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.5.self_attn.q_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.5.self_attn.q_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.5.self_attn.q_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.5.self_attn.v_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.5.self_attn.v_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.5.self_attn.v_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.5.self_attn.v_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.6.layer_norm1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.6.layer_norm1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.6.layer_norm2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.6.layer_norm2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.6.mlp.fc1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.6.mlp.fc1.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.6.mlp.fc1.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.6.mlp.fc1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.6.mlp.fc2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.6.mlp.fc2.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.6.mlp.fc2.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.6.mlp.fc2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.6.self_attn.k_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.6.self_attn.k_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.6.self_attn.k_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.6.self_attn.k_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.6.self_attn.out_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.6.self_attn.out_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.6.self_attn.out_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.6.self_attn.out_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.6.self_attn.q_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.6.self_attn.q_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.6.self_attn.q_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.6.self_attn.q_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.6.self_attn.v_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.6.self_attn.v_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.6.self_attn.v_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.6.self_attn.v_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.7.layer_norm1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.7.layer_norm1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.7.layer_norm2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.7.layer_norm2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.7.mlp.fc1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.7.mlp.fc1.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.7.mlp.fc1.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.7.mlp.fc1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.7.mlp.fc2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.7.mlp.fc2.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.7.mlp.fc2.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.7.mlp.fc2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.7.self_attn.k_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.7.self_attn.k_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.7.self_attn.k_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.7.self_attn.k_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.7.self_attn.out_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.7.self_attn.out_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.7.self_attn.out_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.7.self_attn.out_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.7.self_attn.q_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.7.self_attn.q_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.7.self_attn.q_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.7.self_attn.q_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.7.self_attn.v_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.7.self_attn.v_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.7.self_attn.v_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.7.self_attn.v_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.8.layer_norm1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.8.layer_norm1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.8.layer_norm2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.8.layer_norm2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.8.mlp.fc1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.8.mlp.fc1.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.8.mlp.fc1.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.8.mlp.fc1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.8.mlp.fc2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.8.mlp.fc2.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.8.mlp.fc2.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.8.mlp.fc2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.8.self_attn.k_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.8.self_attn.k_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.8.self_attn.k_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.8.self_attn.k_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.8.self_attn.out_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.8.self_attn.out_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.8.self_attn.out_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.8.self_attn.out_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.8.self_attn.q_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.8.self_attn.q_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.8.self_attn.q_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.8.self_attn.q_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.8.self_attn.v_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.8.self_attn.v_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.8.self_attn.v_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.8.self_attn.v_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.9.layer_norm1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.9.layer_norm1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.9.layer_norm2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.9.layer_norm2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.9.mlp.fc1.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.9.mlp.fc1.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.9.mlp.fc1.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.9.mlp.fc1.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.9.mlp.fc2.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.9.mlp.fc2.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.9.mlp.fc2.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.9.mlp.fc2.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.9.self_attn.k_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.9.self_attn.k_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.9.self_attn.k_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.9.self_attn.k_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.9.self_attn.out_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.9.self_attn.out_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.9.self_attn.out_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.9.self_attn.out_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.9.self_attn.q_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.9.self_attn.q_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.9.self_attn.q_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.9.self_attn.q_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.9.self_attn.v_proj.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.9.self_attn.v_proj.biases": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.9.self_attn.v_proj.scales": "model.safetensors",
        "detector_model.text_encoder.text_model.encoder.layers.9.self_attn.v_proj.weight": "model.safetensors",
        "detector_model.text_encoder.text_model.final_layer_norm.bias": "model.safetensors",
        "detector_model.text_encoder.text_model.final_layer_norm.weight": "model.safetensors",
        "detector_model.text_encoder.text_projection.biases": "model.safetensors",
        "detector_model.text_encoder.text_projection.scales": "model.safetensors",
        "detector_model.text_encoder.text_projection.weight": "model.safetensors",
        "detector_model.text_projection.bias": "model.safetensors",
        "detector_model.text_projection.biases": "model.safetensors",
        "detector_model.text_projection.scales": "model.safetensors",
        "detector_model.text_projection.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.embeddings.patch_embeddings.projection.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.embeddings.position_embeddings": "model.safetensors",
        "detector_model.vision_encoder.backbone.layer_norm.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layer_norm.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.0.attention.k_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.0.attention.k_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.0.attention.k_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.0.attention.k_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.0.attention.o_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.0.attention.o_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.0.attention.o_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.0.attention.o_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.0.attention.q_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.0.attention.q_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.0.attention.q_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.0.attention.q_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.0.attention.v_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.0.attention.v_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.0.attention.v_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.0.attention.v_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.0.layer_norm1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.0.layer_norm1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.0.layer_norm2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.0.layer_norm2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.0.mlp.fc1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.0.mlp.fc1.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.0.mlp.fc1.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.0.mlp.fc1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.0.mlp.fc2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.0.mlp.fc2.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.0.mlp.fc2.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.0.mlp.fc2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.1.attention.k_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.1.attention.k_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.1.attention.k_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.1.attention.k_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.1.attention.o_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.1.attention.o_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.1.attention.o_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.1.attention.o_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.1.attention.q_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.1.attention.q_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.1.attention.q_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.1.attention.q_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.1.attention.v_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.1.attention.v_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.1.attention.v_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.1.attention.v_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.1.layer_norm1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.1.layer_norm1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.1.layer_norm2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.1.layer_norm2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.1.mlp.fc1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.1.mlp.fc1.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.1.mlp.fc1.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.1.mlp.fc1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.1.mlp.fc2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.1.mlp.fc2.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.1.mlp.fc2.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.1.mlp.fc2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.10.attention.k_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.10.attention.k_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.10.attention.k_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.10.attention.k_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.10.attention.o_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.10.attention.o_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.10.attention.o_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.10.attention.o_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.10.attention.q_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.10.attention.q_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.10.attention.q_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.10.attention.q_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.10.attention.v_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.10.attention.v_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.10.attention.v_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.10.attention.v_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.10.layer_norm1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.10.layer_norm1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.10.layer_norm2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.10.layer_norm2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.10.mlp.fc1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.10.mlp.fc1.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.10.mlp.fc1.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.10.mlp.fc1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.10.mlp.fc2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.10.mlp.fc2.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.10.mlp.fc2.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.10.mlp.fc2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.11.attention.k_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.11.attention.k_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.11.attention.k_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.11.attention.k_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.11.attention.o_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.11.attention.o_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.11.attention.o_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.11.attention.o_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.11.attention.q_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.11.attention.q_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.11.attention.q_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.11.attention.q_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.11.attention.v_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.11.attention.v_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.11.attention.v_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.11.attention.v_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.11.layer_norm1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.11.layer_norm1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.11.layer_norm2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.11.layer_norm2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.11.mlp.fc1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.11.mlp.fc1.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.11.mlp.fc1.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.11.mlp.fc1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.11.mlp.fc2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.11.mlp.fc2.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.11.mlp.fc2.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.11.mlp.fc2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.12.attention.k_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.12.attention.k_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.12.attention.k_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.12.attention.k_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.12.attention.o_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.12.attention.o_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.12.attention.o_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.12.attention.o_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.12.attention.q_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.12.attention.q_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.12.attention.q_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.12.attention.q_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.12.attention.v_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.12.attention.v_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.12.attention.v_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.12.attention.v_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.12.layer_norm1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.12.layer_norm1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.12.layer_norm2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.12.layer_norm2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.12.mlp.fc1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.12.mlp.fc1.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.12.mlp.fc1.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.12.mlp.fc1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.12.mlp.fc2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.12.mlp.fc2.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.12.mlp.fc2.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.12.mlp.fc2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.13.attention.k_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.13.attention.k_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.13.attention.k_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.13.attention.k_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.13.attention.o_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.13.attention.o_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.13.attention.o_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.13.attention.o_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.13.attention.q_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.13.attention.q_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.13.attention.q_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.13.attention.q_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.13.attention.v_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.13.attention.v_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.13.attention.v_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.13.attention.v_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.13.layer_norm1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.13.layer_norm1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.13.layer_norm2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.13.layer_norm2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.13.mlp.fc1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.13.mlp.fc1.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.13.mlp.fc1.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.13.mlp.fc1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.13.mlp.fc2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.13.mlp.fc2.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.13.mlp.fc2.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.13.mlp.fc2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.14.attention.k_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.14.attention.k_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.14.attention.k_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.14.attention.k_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.14.attention.o_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.14.attention.o_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.14.attention.o_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.14.attention.o_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.14.attention.q_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.14.attention.q_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.14.attention.q_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.14.attention.q_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.14.attention.v_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.14.attention.v_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.14.attention.v_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.14.attention.v_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.14.layer_norm1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.14.layer_norm1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.14.layer_norm2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.14.layer_norm2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.14.mlp.fc1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.14.mlp.fc1.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.14.mlp.fc1.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.14.mlp.fc1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.14.mlp.fc2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.14.mlp.fc2.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.14.mlp.fc2.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.14.mlp.fc2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.15.attention.k_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.15.attention.k_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.15.attention.k_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.15.attention.k_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.15.attention.o_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.15.attention.o_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.15.attention.o_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.15.attention.o_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.15.attention.q_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.15.attention.q_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.15.attention.q_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.15.attention.q_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.15.attention.v_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.15.attention.v_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.15.attention.v_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.15.attention.v_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.15.layer_norm1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.15.layer_norm1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.15.layer_norm2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.15.layer_norm2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.15.mlp.fc1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.15.mlp.fc1.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.15.mlp.fc1.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.15.mlp.fc1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.15.mlp.fc2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.15.mlp.fc2.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.15.mlp.fc2.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.15.mlp.fc2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.16.attention.k_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.16.attention.k_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.16.attention.k_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.16.attention.k_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.16.attention.o_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.16.attention.o_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.16.attention.o_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.16.attention.o_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.16.attention.q_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.16.attention.q_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.16.attention.q_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.16.attention.q_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.16.attention.v_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.16.attention.v_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.16.attention.v_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.16.attention.v_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.16.layer_norm1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.16.layer_norm1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.16.layer_norm2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.16.layer_norm2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.16.mlp.fc1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.16.mlp.fc1.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.16.mlp.fc1.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.16.mlp.fc1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.16.mlp.fc2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.16.mlp.fc2.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.16.mlp.fc2.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.16.mlp.fc2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.17.attention.k_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.17.attention.k_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.17.attention.k_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.17.attention.k_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.17.attention.o_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.17.attention.o_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.17.attention.o_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.17.attention.o_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.17.attention.q_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.17.attention.q_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.17.attention.q_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.17.attention.q_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.17.attention.v_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.17.attention.v_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.17.attention.v_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.17.attention.v_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.17.layer_norm1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.17.layer_norm1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.17.layer_norm2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.17.layer_norm2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.17.mlp.fc1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.17.mlp.fc1.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.17.mlp.fc1.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.17.mlp.fc1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.17.mlp.fc2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.17.mlp.fc2.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.17.mlp.fc2.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.17.mlp.fc2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.18.attention.k_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.18.attention.k_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.18.attention.k_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.18.attention.k_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.18.attention.o_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.18.attention.o_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.18.attention.o_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.18.attention.o_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.18.attention.q_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.18.attention.q_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.18.attention.q_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.18.attention.q_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.18.attention.v_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.18.attention.v_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.18.attention.v_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.18.attention.v_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.18.layer_norm1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.18.layer_norm1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.18.layer_norm2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.18.layer_norm2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.18.mlp.fc1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.18.mlp.fc1.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.18.mlp.fc1.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.18.mlp.fc1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.18.mlp.fc2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.18.mlp.fc2.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.18.mlp.fc2.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.18.mlp.fc2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.19.attention.k_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.19.attention.k_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.19.attention.k_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.19.attention.k_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.19.attention.o_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.19.attention.o_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.19.attention.o_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.19.attention.o_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.19.attention.q_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.19.attention.q_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.19.attention.q_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.19.attention.q_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.19.attention.v_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.19.attention.v_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.19.attention.v_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.19.attention.v_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.19.layer_norm1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.19.layer_norm1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.19.layer_norm2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.19.layer_norm2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.19.mlp.fc1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.19.mlp.fc1.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.19.mlp.fc1.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.19.mlp.fc1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.19.mlp.fc2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.19.mlp.fc2.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.19.mlp.fc2.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.19.mlp.fc2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.2.attention.k_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.2.attention.k_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.2.attention.k_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.2.attention.k_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.2.attention.o_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.2.attention.o_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.2.attention.o_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.2.attention.o_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.2.attention.q_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.2.attention.q_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.2.attention.q_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.2.attention.q_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.2.attention.v_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.2.attention.v_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.2.attention.v_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.2.attention.v_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.2.layer_norm1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.2.layer_norm1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.2.layer_norm2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.2.layer_norm2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.2.mlp.fc1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.2.mlp.fc1.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.2.mlp.fc1.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.2.mlp.fc1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.2.mlp.fc2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.2.mlp.fc2.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.2.mlp.fc2.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.2.mlp.fc2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.20.attention.k_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.20.attention.k_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.20.attention.k_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.20.attention.k_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.20.attention.o_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.20.attention.o_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.20.attention.o_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.20.attention.o_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.20.attention.q_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.20.attention.q_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.20.attention.q_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.20.attention.q_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.20.attention.v_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.20.attention.v_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.20.attention.v_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.20.attention.v_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.20.layer_norm1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.20.layer_norm1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.20.layer_norm2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.20.layer_norm2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.20.mlp.fc1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.20.mlp.fc1.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.20.mlp.fc1.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.20.mlp.fc1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.20.mlp.fc2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.20.mlp.fc2.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.20.mlp.fc2.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.20.mlp.fc2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.21.attention.k_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.21.attention.k_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.21.attention.k_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.21.attention.k_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.21.attention.o_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.21.attention.o_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.21.attention.o_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.21.attention.o_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.21.attention.q_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.21.attention.q_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.21.attention.q_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.21.attention.q_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.21.attention.v_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.21.attention.v_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.21.attention.v_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.21.attention.v_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.21.layer_norm1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.21.layer_norm1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.21.layer_norm2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.21.layer_norm2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.21.mlp.fc1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.21.mlp.fc1.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.21.mlp.fc1.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.21.mlp.fc1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.21.mlp.fc2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.21.mlp.fc2.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.21.mlp.fc2.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.21.mlp.fc2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.22.attention.k_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.22.attention.k_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.22.attention.k_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.22.attention.k_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.22.attention.o_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.22.attention.o_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.22.attention.o_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.22.attention.o_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.22.attention.q_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.22.attention.q_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.22.attention.q_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.22.attention.q_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.22.attention.v_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.22.attention.v_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.22.attention.v_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.22.attention.v_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.22.layer_norm1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.22.layer_norm1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.22.layer_norm2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.22.layer_norm2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.22.mlp.fc1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.22.mlp.fc1.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.22.mlp.fc1.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.22.mlp.fc1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.22.mlp.fc2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.22.mlp.fc2.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.22.mlp.fc2.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.22.mlp.fc2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.23.attention.k_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.23.attention.k_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.23.attention.k_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.23.attention.k_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.23.attention.o_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.23.attention.o_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.23.attention.o_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.23.attention.o_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.23.attention.q_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.23.attention.q_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.23.attention.q_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.23.attention.q_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.23.attention.v_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.23.attention.v_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.23.attention.v_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.23.attention.v_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.23.layer_norm1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.23.layer_norm1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.23.layer_norm2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.23.layer_norm2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.23.mlp.fc1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.23.mlp.fc1.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.23.mlp.fc1.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.23.mlp.fc1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.23.mlp.fc2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.23.mlp.fc2.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.23.mlp.fc2.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.23.mlp.fc2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.24.attention.k_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.24.attention.k_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.24.attention.k_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.24.attention.k_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.24.attention.o_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.24.attention.o_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.24.attention.o_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.24.attention.o_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.24.attention.q_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.24.attention.q_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.24.attention.q_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.24.attention.q_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.24.attention.v_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.24.attention.v_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.24.attention.v_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.24.attention.v_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.24.layer_norm1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.24.layer_norm1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.24.layer_norm2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.24.layer_norm2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.24.mlp.fc1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.24.mlp.fc1.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.24.mlp.fc1.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.24.mlp.fc1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.24.mlp.fc2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.24.mlp.fc2.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.24.mlp.fc2.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.24.mlp.fc2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.25.attention.k_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.25.attention.k_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.25.attention.k_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.25.attention.k_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.25.attention.o_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.25.attention.o_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.25.attention.o_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.25.attention.o_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.25.attention.q_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.25.attention.q_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.25.attention.q_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.25.attention.q_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.25.attention.v_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.25.attention.v_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.25.attention.v_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.25.attention.v_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.25.layer_norm1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.25.layer_norm1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.25.layer_norm2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.25.layer_norm2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.25.mlp.fc1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.25.mlp.fc1.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.25.mlp.fc1.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.25.mlp.fc1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.25.mlp.fc2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.25.mlp.fc2.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.25.mlp.fc2.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.25.mlp.fc2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.26.attention.k_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.26.attention.k_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.26.attention.k_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.26.attention.k_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.26.attention.o_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.26.attention.o_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.26.attention.o_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.26.attention.o_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.26.attention.q_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.26.attention.q_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.26.attention.q_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.26.attention.q_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.26.attention.v_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.26.attention.v_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.26.attention.v_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.26.attention.v_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.26.layer_norm1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.26.layer_norm1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.26.layer_norm2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.26.layer_norm2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.26.mlp.fc1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.26.mlp.fc1.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.26.mlp.fc1.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.26.mlp.fc1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.26.mlp.fc2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.26.mlp.fc2.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.26.mlp.fc2.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.26.mlp.fc2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.27.attention.k_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.27.attention.k_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.27.attention.k_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.27.attention.k_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.27.attention.o_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.27.attention.o_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.27.attention.o_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.27.attention.o_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.27.attention.q_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.27.attention.q_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.27.attention.q_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.27.attention.q_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.27.attention.v_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.27.attention.v_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.27.attention.v_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.27.attention.v_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.27.layer_norm1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.27.layer_norm1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.27.layer_norm2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.27.layer_norm2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.27.mlp.fc1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.27.mlp.fc1.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.27.mlp.fc1.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.27.mlp.fc1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.27.mlp.fc2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.27.mlp.fc2.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.27.mlp.fc2.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.27.mlp.fc2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.28.attention.k_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.28.attention.k_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.28.attention.k_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.28.attention.k_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.28.attention.o_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.28.attention.o_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.28.attention.o_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.28.attention.o_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.28.attention.q_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.28.attention.q_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.28.attention.q_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.28.attention.q_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.28.attention.v_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.28.attention.v_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.28.attention.v_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.28.attention.v_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.28.layer_norm1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.28.layer_norm1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.28.layer_norm2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.28.layer_norm2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.28.mlp.fc1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.28.mlp.fc1.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.28.mlp.fc1.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.28.mlp.fc1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.28.mlp.fc2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.28.mlp.fc2.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.28.mlp.fc2.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.28.mlp.fc2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.29.attention.k_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.29.attention.k_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.29.attention.k_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.29.attention.k_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.29.attention.o_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.29.attention.o_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.29.attention.o_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.29.attention.o_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.29.attention.q_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.29.attention.q_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.29.attention.q_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.29.attention.q_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.29.attention.v_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.29.attention.v_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.29.attention.v_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.29.attention.v_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.29.layer_norm1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.29.layer_norm1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.29.layer_norm2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.29.layer_norm2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.29.mlp.fc1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.29.mlp.fc1.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.29.mlp.fc1.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.29.mlp.fc1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.29.mlp.fc2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.29.mlp.fc2.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.29.mlp.fc2.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.29.mlp.fc2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.3.attention.k_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.3.attention.k_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.3.attention.k_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.3.attention.k_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.3.attention.o_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.3.attention.o_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.3.attention.o_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.3.attention.o_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.3.attention.q_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.3.attention.q_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.3.attention.q_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.3.attention.q_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.3.attention.v_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.3.attention.v_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.3.attention.v_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.3.attention.v_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.3.layer_norm1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.3.layer_norm1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.3.layer_norm2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.3.layer_norm2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.3.mlp.fc1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.3.mlp.fc1.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.3.mlp.fc1.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.3.mlp.fc1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.3.mlp.fc2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.3.mlp.fc2.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.3.mlp.fc2.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.3.mlp.fc2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.30.attention.k_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.30.attention.k_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.30.attention.k_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.30.attention.k_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.30.attention.o_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.30.attention.o_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.30.attention.o_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.30.attention.o_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.30.attention.q_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.30.attention.q_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.30.attention.q_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.30.attention.q_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.30.attention.v_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.30.attention.v_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.30.attention.v_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.30.attention.v_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.30.layer_norm1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.30.layer_norm1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.30.layer_norm2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.30.layer_norm2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.30.mlp.fc1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.30.mlp.fc1.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.30.mlp.fc1.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.30.mlp.fc1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.30.mlp.fc2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.30.mlp.fc2.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.30.mlp.fc2.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.30.mlp.fc2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.31.attention.k_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.31.attention.k_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.31.attention.k_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.31.attention.k_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.31.attention.o_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.31.attention.o_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.31.attention.o_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.31.attention.o_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.31.attention.q_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.31.attention.q_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.31.attention.q_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.31.attention.q_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.31.attention.v_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.31.attention.v_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.31.attention.v_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.31.attention.v_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.31.layer_norm1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.31.layer_norm1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.31.layer_norm2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.31.layer_norm2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.31.mlp.fc1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.31.mlp.fc1.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.31.mlp.fc1.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.31.mlp.fc1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.31.mlp.fc2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.31.mlp.fc2.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.31.mlp.fc2.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.31.mlp.fc2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.4.attention.k_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.4.attention.k_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.4.attention.k_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.4.attention.k_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.4.attention.o_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.4.attention.o_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.4.attention.o_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.4.attention.o_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.4.attention.q_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.4.attention.q_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.4.attention.q_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.4.attention.q_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.4.attention.v_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.4.attention.v_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.4.attention.v_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.4.attention.v_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.4.layer_norm1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.4.layer_norm1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.4.layer_norm2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.4.layer_norm2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.4.mlp.fc1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.4.mlp.fc1.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.4.mlp.fc1.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.4.mlp.fc1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.4.mlp.fc2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.4.mlp.fc2.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.4.mlp.fc2.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.4.mlp.fc2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.5.attention.k_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.5.attention.k_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.5.attention.k_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.5.attention.k_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.5.attention.o_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.5.attention.o_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.5.attention.o_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.5.attention.o_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.5.attention.q_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.5.attention.q_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.5.attention.q_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.5.attention.q_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.5.attention.v_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.5.attention.v_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.5.attention.v_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.5.attention.v_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.5.layer_norm1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.5.layer_norm1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.5.layer_norm2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.5.layer_norm2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.5.mlp.fc1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.5.mlp.fc1.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.5.mlp.fc1.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.5.mlp.fc1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.5.mlp.fc2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.5.mlp.fc2.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.5.mlp.fc2.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.5.mlp.fc2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.6.attention.k_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.6.attention.k_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.6.attention.k_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.6.attention.k_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.6.attention.o_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.6.attention.o_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.6.attention.o_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.6.attention.o_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.6.attention.q_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.6.attention.q_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.6.attention.q_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.6.attention.q_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.6.attention.v_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.6.attention.v_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.6.attention.v_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.6.attention.v_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.6.layer_norm1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.6.layer_norm1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.6.layer_norm2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.6.layer_norm2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.6.mlp.fc1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.6.mlp.fc1.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.6.mlp.fc1.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.6.mlp.fc1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.6.mlp.fc2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.6.mlp.fc2.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.6.mlp.fc2.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.6.mlp.fc2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.7.attention.k_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.7.attention.k_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.7.attention.k_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.7.attention.k_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.7.attention.o_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.7.attention.o_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.7.attention.o_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.7.attention.o_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.7.attention.q_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.7.attention.q_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.7.attention.q_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.7.attention.q_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.7.attention.v_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.7.attention.v_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.7.attention.v_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.7.attention.v_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.7.layer_norm1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.7.layer_norm1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.7.layer_norm2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.7.layer_norm2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.7.mlp.fc1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.7.mlp.fc1.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.7.mlp.fc1.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.7.mlp.fc1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.7.mlp.fc2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.7.mlp.fc2.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.7.mlp.fc2.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.7.mlp.fc2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.8.attention.k_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.8.attention.k_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.8.attention.k_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.8.attention.k_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.8.attention.o_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.8.attention.o_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.8.attention.o_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.8.attention.o_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.8.attention.q_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.8.attention.q_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.8.attention.q_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.8.attention.q_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.8.attention.v_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.8.attention.v_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.8.attention.v_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.8.attention.v_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.8.layer_norm1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.8.layer_norm1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.8.layer_norm2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.8.layer_norm2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.8.mlp.fc1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.8.mlp.fc1.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.8.mlp.fc1.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.8.mlp.fc1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.8.mlp.fc2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.8.mlp.fc2.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.8.mlp.fc2.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.8.mlp.fc2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.9.attention.k_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.9.attention.k_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.9.attention.k_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.9.attention.k_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.9.attention.o_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.9.attention.o_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.9.attention.o_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.9.attention.o_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.9.attention.q_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.9.attention.q_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.9.attention.q_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.9.attention.q_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.9.attention.v_proj.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.9.attention.v_proj.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.9.attention.v_proj.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.9.attention.v_proj.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.9.layer_norm1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.9.layer_norm1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.9.layer_norm2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.9.layer_norm2.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.9.mlp.fc1.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.9.mlp.fc1.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.9.mlp.fc1.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.9.mlp.fc1.weight": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.9.mlp.fc2.bias": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.9.mlp.fc2.biases": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.9.mlp.fc2.scales": "model.safetensors",
        "detector_model.vision_encoder.backbone.layers.9.mlp.fc2.weight": "model.safetensors",
        "detector_model.vision_encoder.neck.fpn_layers.0.proj1.bias": "model.safetensors",
        "detector_model.vision_encoder.neck.fpn_layers.0.proj1.weight": "model.safetensors",
        "detector_model.vision_encoder.neck.fpn_layers.0.proj2.bias": "model.safetensors",
        "detector_model.vision_encoder.neck.fpn_layers.0.proj2.weight": "model.safetensors",
        "detector_model.vision_encoder.neck.fpn_layers.0.scale_layers.0.bias": "model.safetensors",
        "detector_model.vision_encoder.neck.fpn_layers.0.scale_layers.0.weight": "model.safetensors",
        "detector_model.vision_encoder.neck.fpn_layers.0.scale_layers.2.bias": "model.safetensors",
        "detector_model.vision_encoder.neck.fpn_layers.0.scale_layers.2.weight": "model.safetensors",
        "detector_model.vision_encoder.neck.fpn_layers.1.proj1.bias": "model.safetensors",
        "detector_model.vision_encoder.neck.fpn_layers.1.proj1.weight": "model.safetensors",
        "detector_model.vision_encoder.neck.fpn_layers.1.proj2.bias": "model.safetensors",
        "detector_model.vision_encoder.neck.fpn_layers.1.proj2.weight": "model.safetensors",
        "detector_model.vision_encoder.neck.fpn_layers.1.scale_layers.0.bias": "model.safetensors",
        "detector_model.vision_encoder.neck.fpn_layers.1.scale_layers.0.weight": "model.safetensors",
        "detector_model.vision_encoder.neck.fpn_layers.2.proj1.bias": "model.safetensors",
        "detector_model.vision_encoder.neck.fpn_layers.2.proj1.weight": "model.safetensors",
        "detector_model.vision_encoder.neck.fpn_layers.2.proj2.bias": "model.safetensors",
        "detector_model.vision_encoder.neck.fpn_layers.2.proj2.weight": "model.safetensors",
        "detector_model.vision_encoder.neck.fpn_layers.3.proj1.bias": "model.safetensors",
        "detector_model.vision_encoder.neck.fpn_layers.3.proj1.weight": "model.safetensors",
        "detector_model.vision_encoder.neck.fpn_layers.3.proj2.bias": "model.safetensors",
        "detector_model.vision_encoder.neck.fpn_layers.3.proj2.weight": "model.safetensors",
        "tracker_model.mask_decoder.conv_s0.bias": "model.safetensors",
        "tracker_model.mask_decoder.conv_s0.weight": "model.safetensors",
        "tracker_model.mask_decoder.conv_s1.bias": "model.safetensors",
        "tracker_model.mask_decoder.conv_s1.weight": "model.safetensors",
        "tracker_model.mask_decoder.iou_prediction_head.layers.0.bias": "model.safetensors",
        "tracker_model.mask_decoder.iou_prediction_head.layers.0.biases": "model.safetensors",
        "tracker_model.mask_decoder.iou_prediction_head.layers.0.scales": "model.safetensors",
        "tracker_model.mask_decoder.iou_prediction_head.layers.0.weight": "model.safetensors",
        "tracker_model.mask_decoder.iou_prediction_head.proj_in.bias": "model.safetensors",
        "tracker_model.mask_decoder.iou_prediction_head.proj_in.biases": "model.safetensors",
        "tracker_model.mask_decoder.iou_prediction_head.proj_in.scales": "model.safetensors",
        "tracker_model.mask_decoder.iou_prediction_head.proj_in.weight": "model.safetensors",
        "tracker_model.mask_decoder.iou_prediction_head.proj_out.bias": "model.safetensors",
        "tracker_model.mask_decoder.iou_prediction_head.proj_out.weight": "model.safetensors",
        "tracker_model.mask_decoder.iou_token.weight": "model.safetensors",
        "tracker_model.mask_decoder.mask_tokens.weight": "model.safetensors",
        "tracker_model.mask_decoder.obj_score_token.weight": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.0.layers.0.bias": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.0.layers.0.biases": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.0.layers.0.scales": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.0.layers.0.weight": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.0.proj_in.bias": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.0.proj_in.biases": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.0.proj_in.scales": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.0.proj_in.weight": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.0.proj_out.bias": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.0.proj_out.weight": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.1.layers.0.bias": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.1.layers.0.biases": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.1.layers.0.scales": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.1.layers.0.weight": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.1.proj_in.bias": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.1.proj_in.biases": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.1.proj_in.scales": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.1.proj_in.weight": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.1.proj_out.bias": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.1.proj_out.weight": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.2.layers.0.bias": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.2.layers.0.biases": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.2.layers.0.scales": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.2.layers.0.weight": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.2.proj_in.bias": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.2.proj_in.biases": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.2.proj_in.scales": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.2.proj_in.weight": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.2.proj_out.bias": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.2.proj_out.weight": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.3.layers.0.bias": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.3.layers.0.biases": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.3.layers.0.scales": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.3.layers.0.weight": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.3.proj_in.bias": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.3.proj_in.biases": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.3.proj_in.scales": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.3.proj_in.weight": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.3.proj_out.bias": "model.safetensors",
        "tracker_model.mask_decoder.output_hypernetworks_mlps.3.proj_out.weight": "model.safetensors",
        "tracker_model.mask_decoder.pred_obj_score_head.layers.0.bias": "model.safetensors",
        "tracker_model.mask_decoder.pred_obj_score_head.layers.0.biases": "model.safetensors",
        "tracker_model.mask_decoder.pred_obj_score_head.layers.0.scales": "model.safetensors",
        "tracker_model.mask_decoder.pred_obj_score_head.layers.0.weight": "model.safetensors",
        "tracker_model.mask_decoder.pred_obj_score_head.proj_in.bias": "model.safetensors",
        "tracker_model.mask_decoder.pred_obj_score_head.proj_in.biases": "model.safetensors",
        "tracker_model.mask_decoder.pred_obj_score_head.proj_in.scales": "model.safetensors",
        "tracker_model.mask_decoder.pred_obj_score_head.proj_in.weight": "model.safetensors",
        "tracker_model.mask_decoder.pred_obj_score_head.proj_out.bias": "model.safetensors",
        "tracker_model.mask_decoder.pred_obj_score_head.proj_out.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.final_attn_token_to_image.k_proj.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.final_attn_token_to_image.k_proj.biases": "model.safetensors",
        "tracker_model.mask_decoder.transformer.final_attn_token_to_image.k_proj.scales": "model.safetensors",
        "tracker_model.mask_decoder.transformer.final_attn_token_to_image.k_proj.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.final_attn_token_to_image.o_proj.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.final_attn_token_to_image.o_proj.biases": "model.safetensors",
        "tracker_model.mask_decoder.transformer.final_attn_token_to_image.o_proj.scales": "model.safetensors",
        "tracker_model.mask_decoder.transformer.final_attn_token_to_image.o_proj.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.final_attn_token_to_image.q_proj.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.final_attn_token_to_image.q_proj.biases": "model.safetensors",
        "tracker_model.mask_decoder.transformer.final_attn_token_to_image.q_proj.scales": "model.safetensors",
        "tracker_model.mask_decoder.transformer.final_attn_token_to_image.q_proj.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.final_attn_token_to_image.v_proj.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.final_attn_token_to_image.v_proj.biases": "model.safetensors",
        "tracker_model.mask_decoder.transformer.final_attn_token_to_image.v_proj.scales": "model.safetensors",
        "tracker_model.mask_decoder.transformer.final_attn_token_to_image.v_proj.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layer_norm_final_attn.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layer_norm_final_attn.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.cross_attn_image_to_token.k_proj.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.cross_attn_image_to_token.k_proj.biases": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.cross_attn_image_to_token.k_proj.scales": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.cross_attn_image_to_token.k_proj.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.cross_attn_image_to_token.o_proj.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.cross_attn_image_to_token.o_proj.biases": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.cross_attn_image_to_token.o_proj.scales": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.cross_attn_image_to_token.o_proj.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.cross_attn_image_to_token.q_proj.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.cross_attn_image_to_token.q_proj.biases": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.cross_attn_image_to_token.q_proj.scales": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.cross_attn_image_to_token.q_proj.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.cross_attn_image_to_token.v_proj.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.cross_attn_image_to_token.v_proj.biases": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.cross_attn_image_to_token.v_proj.scales": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.cross_attn_image_to_token.v_proj.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.cross_attn_token_to_image.k_proj.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.cross_attn_token_to_image.k_proj.biases": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.cross_attn_token_to_image.k_proj.scales": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.cross_attn_token_to_image.k_proj.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.cross_attn_token_to_image.o_proj.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.cross_attn_token_to_image.o_proj.biases": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.cross_attn_token_to_image.o_proj.scales": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.cross_attn_token_to_image.o_proj.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.cross_attn_token_to_image.q_proj.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.cross_attn_token_to_image.q_proj.biases": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.cross_attn_token_to_image.q_proj.scales": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.cross_attn_token_to_image.q_proj.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.cross_attn_token_to_image.v_proj.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.cross_attn_token_to_image.v_proj.biases": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.cross_attn_token_to_image.v_proj.scales": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.cross_attn_token_to_image.v_proj.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.layer_norm1.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.layer_norm1.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.layer_norm2.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.layer_norm2.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.layer_norm3.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.layer_norm3.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.layer_norm4.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.layer_norm4.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.mlp.proj_in.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.mlp.proj_in.biases": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.mlp.proj_in.scales": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.mlp.proj_in.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.mlp.proj_out.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.mlp.proj_out.biases": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.mlp.proj_out.scales": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.mlp.proj_out.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.self_attn.k_proj.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.self_attn.k_proj.biases": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.self_attn.k_proj.scales": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.self_attn.k_proj.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.self_attn.o_proj.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.self_attn.o_proj.biases": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.self_attn.o_proj.scales": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.self_attn.o_proj.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.self_attn.q_proj.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.self_attn.q_proj.biases": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.self_attn.q_proj.scales": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.self_attn.q_proj.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.self_attn.v_proj.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.self_attn.v_proj.biases": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.self_attn.v_proj.scales": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.0.self_attn.v_proj.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.cross_attn_image_to_token.k_proj.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.cross_attn_image_to_token.k_proj.biases": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.cross_attn_image_to_token.k_proj.scales": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.cross_attn_image_to_token.k_proj.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.cross_attn_image_to_token.o_proj.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.cross_attn_image_to_token.o_proj.biases": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.cross_attn_image_to_token.o_proj.scales": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.cross_attn_image_to_token.o_proj.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.cross_attn_image_to_token.q_proj.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.cross_attn_image_to_token.q_proj.biases": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.cross_attn_image_to_token.q_proj.scales": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.cross_attn_image_to_token.q_proj.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.cross_attn_image_to_token.v_proj.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.cross_attn_image_to_token.v_proj.biases": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.cross_attn_image_to_token.v_proj.scales": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.cross_attn_image_to_token.v_proj.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.cross_attn_token_to_image.k_proj.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.cross_attn_token_to_image.k_proj.biases": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.cross_attn_token_to_image.k_proj.scales": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.cross_attn_token_to_image.k_proj.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.cross_attn_token_to_image.o_proj.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.cross_attn_token_to_image.o_proj.biases": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.cross_attn_token_to_image.o_proj.scales": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.cross_attn_token_to_image.o_proj.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.cross_attn_token_to_image.q_proj.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.cross_attn_token_to_image.q_proj.biases": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.cross_attn_token_to_image.q_proj.scales": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.cross_attn_token_to_image.q_proj.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.cross_attn_token_to_image.v_proj.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.cross_attn_token_to_image.v_proj.biases": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.cross_attn_token_to_image.v_proj.scales": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.cross_attn_token_to_image.v_proj.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.layer_norm1.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.layer_norm1.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.layer_norm2.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.layer_norm2.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.layer_norm3.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.layer_norm3.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.layer_norm4.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.layer_norm4.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.mlp.proj_in.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.mlp.proj_in.biases": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.mlp.proj_in.scales": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.mlp.proj_in.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.mlp.proj_out.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.mlp.proj_out.biases": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.mlp.proj_out.scales": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.mlp.proj_out.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.self_attn.k_proj.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.self_attn.k_proj.biases": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.self_attn.k_proj.scales": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.self_attn.k_proj.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.self_attn.o_proj.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.self_attn.o_proj.biases": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.self_attn.o_proj.scales": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.self_attn.o_proj.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.self_attn.q_proj.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.self_attn.q_proj.biases": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.self_attn.q_proj.scales": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.self_attn.q_proj.weight": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.self_attn.v_proj.bias": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.self_attn.v_proj.biases": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.self_attn.v_proj.scales": "model.safetensors",
        "tracker_model.mask_decoder.transformer.layers.1.self_attn.v_proj.weight": "model.safetensors",
        "tracker_model.mask_decoder.upscale_conv1.bias": "model.safetensors",
        "tracker_model.mask_decoder.upscale_conv1.weight": "model.safetensors",
        "tracker_model.mask_decoder.upscale_conv2.bias": "model.safetensors",
        "tracker_model.mask_decoder.upscale_conv2.weight": "model.safetensors",
        "tracker_model.mask_decoder.upscale_layer_norm.bias": "model.safetensors",
        "tracker_model.mask_decoder.upscale_layer_norm.weight": "model.safetensors",
        "tracker_model.mask_downsample.bias": "model.safetensors",
        "tracker_model.mask_downsample.weight": "model.safetensors",
        "tracker_model.memory_attention.layer_norm.bias": "model.safetensors",
        "tracker_model.memory_attention.layer_norm.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.0.cross_attn_image.k_proj.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.0.cross_attn_image.k_proj.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.0.cross_attn_image.k_proj.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.0.cross_attn_image.k_proj.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.0.cross_attn_image.o_proj.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.0.cross_attn_image.o_proj.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.0.cross_attn_image.o_proj.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.0.cross_attn_image.o_proj.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.0.cross_attn_image.q_proj.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.0.cross_attn_image.q_proj.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.0.cross_attn_image.q_proj.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.0.cross_attn_image.q_proj.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.0.cross_attn_image.v_proj.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.0.cross_attn_image.v_proj.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.0.cross_attn_image.v_proj.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.0.cross_attn_image.v_proj.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.0.layer_norm1.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.0.layer_norm1.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.0.layer_norm2.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.0.layer_norm2.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.0.layer_norm3.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.0.layer_norm3.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.0.linear1.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.0.linear1.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.0.linear1.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.0.linear1.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.0.linear2.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.0.linear2.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.0.linear2.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.0.linear2.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.0.self_attn.k_proj.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.0.self_attn.k_proj.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.0.self_attn.k_proj.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.0.self_attn.k_proj.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.0.self_attn.o_proj.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.0.self_attn.o_proj.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.0.self_attn.o_proj.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.0.self_attn.o_proj.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.0.self_attn.q_proj.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.0.self_attn.q_proj.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.0.self_attn.q_proj.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.0.self_attn.q_proj.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.0.self_attn.v_proj.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.0.self_attn.v_proj.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.0.self_attn.v_proj.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.0.self_attn.v_proj.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.1.cross_attn_image.k_proj.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.1.cross_attn_image.k_proj.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.1.cross_attn_image.k_proj.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.1.cross_attn_image.k_proj.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.1.cross_attn_image.o_proj.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.1.cross_attn_image.o_proj.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.1.cross_attn_image.o_proj.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.1.cross_attn_image.o_proj.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.1.cross_attn_image.q_proj.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.1.cross_attn_image.q_proj.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.1.cross_attn_image.q_proj.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.1.cross_attn_image.q_proj.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.1.cross_attn_image.v_proj.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.1.cross_attn_image.v_proj.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.1.cross_attn_image.v_proj.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.1.cross_attn_image.v_proj.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.1.layer_norm1.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.1.layer_norm1.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.1.layer_norm2.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.1.layer_norm2.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.1.layer_norm3.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.1.layer_norm3.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.1.linear1.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.1.linear1.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.1.linear1.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.1.linear1.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.1.linear2.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.1.linear2.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.1.linear2.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.1.linear2.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.1.self_attn.k_proj.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.1.self_attn.k_proj.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.1.self_attn.k_proj.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.1.self_attn.k_proj.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.1.self_attn.o_proj.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.1.self_attn.o_proj.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.1.self_attn.o_proj.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.1.self_attn.o_proj.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.1.self_attn.q_proj.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.1.self_attn.q_proj.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.1.self_attn.q_proj.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.1.self_attn.q_proj.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.1.self_attn.v_proj.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.1.self_attn.v_proj.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.1.self_attn.v_proj.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.1.self_attn.v_proj.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.2.cross_attn_image.k_proj.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.2.cross_attn_image.k_proj.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.2.cross_attn_image.k_proj.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.2.cross_attn_image.k_proj.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.2.cross_attn_image.o_proj.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.2.cross_attn_image.o_proj.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.2.cross_attn_image.o_proj.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.2.cross_attn_image.o_proj.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.2.cross_attn_image.q_proj.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.2.cross_attn_image.q_proj.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.2.cross_attn_image.q_proj.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.2.cross_attn_image.q_proj.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.2.cross_attn_image.v_proj.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.2.cross_attn_image.v_proj.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.2.cross_attn_image.v_proj.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.2.cross_attn_image.v_proj.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.2.layer_norm1.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.2.layer_norm1.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.2.layer_norm2.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.2.layer_norm2.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.2.layer_norm3.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.2.layer_norm3.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.2.linear1.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.2.linear1.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.2.linear1.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.2.linear1.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.2.linear2.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.2.linear2.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.2.linear2.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.2.linear2.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.2.self_attn.k_proj.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.2.self_attn.k_proj.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.2.self_attn.k_proj.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.2.self_attn.k_proj.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.2.self_attn.o_proj.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.2.self_attn.o_proj.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.2.self_attn.o_proj.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.2.self_attn.o_proj.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.2.self_attn.q_proj.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.2.self_attn.q_proj.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.2.self_attn.q_proj.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.2.self_attn.q_proj.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.2.self_attn.v_proj.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.2.self_attn.v_proj.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.2.self_attn.v_proj.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.2.self_attn.v_proj.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.3.cross_attn_image.k_proj.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.3.cross_attn_image.k_proj.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.3.cross_attn_image.k_proj.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.3.cross_attn_image.k_proj.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.3.cross_attn_image.o_proj.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.3.cross_attn_image.o_proj.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.3.cross_attn_image.o_proj.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.3.cross_attn_image.o_proj.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.3.cross_attn_image.q_proj.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.3.cross_attn_image.q_proj.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.3.cross_attn_image.q_proj.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.3.cross_attn_image.q_proj.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.3.cross_attn_image.v_proj.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.3.cross_attn_image.v_proj.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.3.cross_attn_image.v_proj.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.3.cross_attn_image.v_proj.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.3.layer_norm1.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.3.layer_norm1.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.3.layer_norm2.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.3.layer_norm2.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.3.layer_norm3.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.3.layer_norm3.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.3.linear1.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.3.linear1.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.3.linear1.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.3.linear1.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.3.linear2.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.3.linear2.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.3.linear2.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.3.linear2.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.3.self_attn.k_proj.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.3.self_attn.k_proj.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.3.self_attn.k_proj.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.3.self_attn.k_proj.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.3.self_attn.o_proj.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.3.self_attn.o_proj.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.3.self_attn.o_proj.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.3.self_attn.o_proj.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.3.self_attn.q_proj.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.3.self_attn.q_proj.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.3.self_attn.q_proj.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.3.self_attn.q_proj.weight": "model.safetensors",
        "tracker_model.memory_attention.layers.3.self_attn.v_proj.bias": "model.safetensors",
        "tracker_model.memory_attention.layers.3.self_attn.v_proj.biases": "model.safetensors",
        "tracker_model.memory_attention.layers.3.self_attn.v_proj.scales": "model.safetensors",
        "tracker_model.memory_attention.layers.3.self_attn.v_proj.weight": "model.safetensors",
        "tracker_model.memory_encoder.feature_projection.bias": "model.safetensors",
        "tracker_model.memory_encoder.feature_projection.weight": "model.safetensors",
        "tracker_model.memory_encoder.mask_downsampler.final_conv.bias": "model.safetensors",
        "tracker_model.memory_encoder.mask_downsampler.final_conv.weight": "model.safetensors",
        "tracker_model.memory_encoder.mask_downsampler.layers.0.conv.bias": "model.safetensors",
        "tracker_model.memory_encoder.mask_downsampler.layers.0.conv.weight": "model.safetensors",
        "tracker_model.memory_encoder.mask_downsampler.layers.0.layer_norm.bias": "model.safetensors",
        "tracker_model.memory_encoder.mask_downsampler.layers.0.layer_norm.weight": "model.safetensors",
        "tracker_model.memory_encoder.mask_downsampler.layers.1.conv.bias": "model.safetensors",
        "tracker_model.memory_encoder.mask_downsampler.layers.1.conv.weight": "model.safetensors",
        "tracker_model.memory_encoder.mask_downsampler.layers.1.layer_norm.bias": "model.safetensors",
        "tracker_model.memory_encoder.mask_downsampler.layers.1.layer_norm.weight": "model.safetensors",
        "tracker_model.memory_encoder.mask_downsampler.layers.2.conv.bias": "model.safetensors",
        "tracker_model.memory_encoder.mask_downsampler.layers.2.conv.weight": "model.safetensors",
        "tracker_model.memory_encoder.mask_downsampler.layers.2.layer_norm.bias": "model.safetensors",
        "tracker_model.memory_encoder.mask_downsampler.layers.2.layer_norm.weight": "model.safetensors",
        "tracker_model.memory_encoder.mask_downsampler.layers.3.conv.bias": "model.safetensors",
        "tracker_model.memory_encoder.mask_downsampler.layers.3.conv.weight": "model.safetensors",
        "tracker_model.memory_encoder.mask_downsampler.layers.3.layer_norm.bias": "model.safetensors",
        "tracker_model.memory_encoder.mask_downsampler.layers.3.layer_norm.weight": "model.safetensors",
        "tracker_model.memory_encoder.memory_fuser.layers.0.depthwise_conv.bias": "model.safetensors",
        "tracker_model.memory_encoder.memory_fuser.layers.0.depthwise_conv.weight": "model.safetensors",
        "tracker_model.memory_encoder.memory_fuser.layers.0.layer_norm.bias": "model.safetensors",
        "tracker_model.memory_encoder.memory_fuser.layers.0.layer_norm.weight": "model.safetensors",
        "tracker_model.memory_encoder.memory_fuser.layers.0.pointwise_conv1.bias": "model.safetensors",
        "tracker_model.memory_encoder.memory_fuser.layers.0.pointwise_conv1.weight": "model.safetensors",
        "tracker_model.memory_encoder.memory_fuser.layers.0.pointwise_conv2.bias": "model.safetensors",
        "tracker_model.memory_encoder.memory_fuser.layers.0.pointwise_conv2.weight": "model.safetensors",
        "tracker_model.memory_encoder.memory_fuser.layers.0.scale": "model.safetensors",
        "tracker_model.memory_encoder.memory_fuser.layers.1.depthwise_conv.bias": "model.safetensors",
        "tracker_model.memory_encoder.memory_fuser.layers.1.depthwise_conv.weight": "model.safetensors",
        "tracker_model.memory_encoder.memory_fuser.layers.1.layer_norm.bias": "model.safetensors",
        "tracker_model.memory_encoder.memory_fuser.layers.1.layer_norm.weight": "model.safetensors",
        "tracker_model.memory_encoder.memory_fuser.layers.1.pointwise_conv1.bias": "model.safetensors",
        "tracker_model.memory_encoder.memory_fuser.layers.1.pointwise_conv1.weight": "model.safetensors",
        "tracker_model.memory_encoder.memory_fuser.layers.1.pointwise_conv2.bias": "model.safetensors",
        "tracker_model.memory_encoder.memory_fuser.layers.1.pointwise_conv2.weight": "model.safetensors",
        "tracker_model.memory_encoder.memory_fuser.layers.1.scale": "model.safetensors",
        "tracker_model.memory_encoder.projection.bias": "model.safetensors",
        "tracker_model.memory_encoder.projection.weight": "model.safetensors",
        "tracker_model.memory_temporal_positional_encoding": "model.safetensors",
        "tracker_model.no_memory_embedding": "model.safetensors",
        "tracker_model.no_memory_positional_encoding": "model.safetensors",
        "tracker_model.no_object_pointer": "model.safetensors",
        "tracker_model.object_pointer_proj.layers.0.bias": "model.safetensors",
        "tracker_model.object_pointer_proj.layers.0.biases": "model.safetensors",
        "tracker_model.object_pointer_proj.layers.0.scales": "model.safetensors",
        "tracker_model.object_pointer_proj.layers.0.weight": "model.safetensors",
        "tracker_model.object_pointer_proj.proj_in.bias": "model.safetensors",
        "tracker_model.object_pointer_proj.proj_in.biases": "model.safetensors",
        "tracker_model.object_pointer_proj.proj_in.scales": "model.safetensors",
        "tracker_model.object_pointer_proj.proj_in.weight": "model.safetensors",
        "tracker_model.object_pointer_proj.proj_out.bias": "model.safetensors",
        "tracker_model.object_pointer_proj.proj_out.biases": "model.safetensors",
        "tracker_model.object_pointer_proj.proj_out.scales": "model.safetensors",
        "tracker_model.object_pointer_proj.proj_out.weight": "model.safetensors",
        "tracker_model.occlusion_spatial_embedding_parameter": "model.safetensors",
        "tracker_model.prompt_encoder.mask_embed.conv1.bias": "model.safetensors",
        "tracker_model.prompt_encoder.mask_embed.conv1.weight": "model.safetensors",
        "tracker_model.prompt_encoder.mask_embed.conv2.bias": "model.safetensors",
        "tracker_model.prompt_encoder.mask_embed.conv2.weight": "model.safetensors",
        "tracker_model.prompt_encoder.mask_embed.conv3.bias": "model.safetensors",
        "tracker_model.prompt_encoder.mask_embed.conv3.weight": "model.safetensors",
        "tracker_model.prompt_encoder.mask_embed.layer_norm1.bias": "model.safetensors",
        "tracker_model.prompt_encoder.mask_embed.layer_norm1.weight": "model.safetensors",
        "tracker_model.prompt_encoder.mask_embed.layer_norm2.bias": "model.safetensors",
        "tracker_model.prompt_encoder.mask_embed.layer_norm2.weight": "model.safetensors",
        "tracker_model.prompt_encoder.no_mask_embed.weight": "model.safetensors",
        "tracker_model.prompt_encoder.not_a_point_embed.weight": "model.safetensors",
        "tracker_model.prompt_encoder.point_embed.weight": "model.safetensors",
        "tracker_model.prompt_encoder.shared_embedding.positional_embedding": "model.safetensors",
        "tracker_model.shared_image_embedding.positional_embedding": "model.safetensors",
        "tracker_model.temporal_positional_encoding_projection_layer.bias": "model.safetensors",
        "tracker_model.temporal_positional_encoding_projection_layer.biases": "model.safetensors",
        "tracker_model.temporal_positional_encoding_projection_layer.scales": "model.safetensors",
        "tracker_model.temporal_positional_encoding_projection_layer.weight": "model.safetensors",
        "tracker_neck.fpn_layers.0.proj1.bias": "model.safetensors",
        "tracker_neck.fpn_layers.0.proj1.weight": "model.safetensors",
        "tracker_neck.fpn_layers.0.proj2.bias": "model.safetensors",
        "tracker_neck.fpn_layers.0.proj2.weight": "model.safetensors",
        "tracker_neck.fpn_layers.0.scale_layers.0.bias": "model.safetensors",
        "tracker_neck.fpn_layers.0.scale_layers.0.weight": "model.safetensors",
        "tracker_neck.fpn_layers.0.scale_layers.2.bias": "model.safetensors",
        "tracker_neck.fpn_layers.0.scale_layers.2.weight": "model.safetensors",
        "tracker_neck.fpn_layers.1.proj1.bias": "model.safetensors",
        "tracker_neck.fpn_layers.1.proj1.weight": "model.safetensors",
        "tracker_neck.fpn_layers.1.proj2.bias": "model.safetensors",
        "tracker_neck.fpn_layers.1.proj2.weight": "model.safetensors",
        "tracker_neck.fpn_layers.1.scale_layers.0.bias": "model.safetensors",
        "tracker_neck.fpn_layers.1.scale_layers.0.weight": "model.safetensors",
        "tracker_neck.fpn_layers.2.proj1.bias": "model.safetensors",
        "tracker_neck.fpn_layers.2.proj1.weight": "model.safetensors",
        "tracker_neck.fpn_layers.2.proj2.bias": "model.safetensors",
        "tracker_neck.fpn_layers.2.proj2.weight": "model.safetensors",
        "tracker_neck.fpn_layers.3.proj1.bias": "model.safetensors",
        "tracker_neck.fpn_layers.3.proj1.weight": "model.safetensors",
        "tracker_neck.fpn_layers.3.proj2.bias": "model.safetensors",
        "tracker_neck.fpn_layers.3.proj2.weight": "model.safetensors"
    }
}