{ "metadata": { "total_size": 18389161416 }, "weight_map": { "emb_embeddings_det.weight": "model-00004-of-00004.safetensors", "emb_embeddings_edit.weight": "model-00004-of-00004.safetensors", "emb_embeddings_gen.weight": "model-00004-of-00004.safetensors", "emb_embeddings_pose.weight": "model-00004-of-00004.safetensors", "gdino.bbox_embed.0.layers.0.bias": "model-00004-of-00004.safetensors", "gdino.bbox_embed.0.layers.0.weight": "model-00004-of-00004.safetensors", "gdino.bbox_embed.0.layers.1.bias": "model-00004-of-00004.safetensors", "gdino.bbox_embed.0.layers.1.weight": "model-00004-of-00004.safetensors", "gdino.bbox_embed.0.layers.2.bias": "model-00004-of-00004.safetensors", "gdino.bbox_embed.0.layers.2.weight": "model-00004-of-00004.safetensors", "gdino.bbox_embed.1.layers.0.bias": "model-00004-of-00004.safetensors", "gdino.bbox_embed.1.layers.0.weight": "model-00004-of-00004.safetensors", "gdino.bbox_embed.1.layers.1.bias": "model-00004-of-00004.safetensors", "gdino.bbox_embed.1.layers.1.weight": "model-00004-of-00004.safetensors", "gdino.bbox_embed.1.layers.2.bias": "model-00004-of-00004.safetensors", "gdino.bbox_embed.1.layers.2.weight": "model-00004-of-00004.safetensors", "gdino.bbox_embed.2.layers.0.bias": "model-00004-of-00004.safetensors", "gdino.bbox_embed.2.layers.0.weight": "model-00004-of-00004.safetensors", "gdino.bbox_embed.2.layers.1.bias": "model-00004-of-00004.safetensors", "gdino.bbox_embed.2.layers.1.weight": "model-00004-of-00004.safetensors", "gdino.bbox_embed.2.layers.2.bias": "model-00004-of-00004.safetensors", "gdino.bbox_embed.2.layers.2.weight": "model-00004-of-00004.safetensors", "gdino.bbox_embed.3.layers.0.bias": "model-00004-of-00004.safetensors", "gdino.bbox_embed.3.layers.0.weight": "model-00004-of-00004.safetensors", "gdino.bbox_embed.3.layers.1.bias": "model-00004-of-00004.safetensors", "gdino.bbox_embed.3.layers.1.weight": "model-00004-of-00004.safetensors", "gdino.bbox_embed.3.layers.2.bias": "model-00004-of-00004.safetensors", "gdino.bbox_embed.3.layers.2.weight": "model-00004-of-00004.safetensors", "gdino.bbox_embed.4.layers.0.bias": "model-00004-of-00004.safetensors", "gdino.bbox_embed.4.layers.0.weight": "model-00004-of-00004.safetensors", "gdino.bbox_embed.4.layers.1.bias": "model-00004-of-00004.safetensors", "gdino.bbox_embed.4.layers.1.weight": "model-00004-of-00004.safetensors", "gdino.bbox_embed.4.layers.2.bias": "model-00004-of-00004.safetensors", "gdino.bbox_embed.4.layers.2.weight": "model-00004-of-00004.safetensors", "gdino.bbox_embed.5.layers.0.bias": "model-00004-of-00004.safetensors", "gdino.bbox_embed.5.layers.0.weight": "model-00004-of-00004.safetensors", "gdino.bbox_embed.5.layers.1.bias": "model-00004-of-00004.safetensors", "gdino.bbox_embed.5.layers.1.weight": "model-00004-of-00004.safetensors", "gdino.bbox_embed.5.layers.2.bias": "model-00004-of-00004.safetensors", "gdino.bbox_embed.5.layers.2.weight": "model-00004-of-00004.safetensors", "gdino.mask_embed.0.layers.0.bias": "model-00004-of-00004.safetensors", "gdino.mask_embed.0.layers.0.weight": "model-00004-of-00004.safetensors", "gdino.mask_embed.0.layers.1.bias": "model-00004-of-00004.safetensors", "gdino.mask_embed.0.layers.1.weight": "model-00004-of-00004.safetensors", "gdino.mask_embed.0.layers.2.bias": "model-00004-of-00004.safetensors", "gdino.mask_embed.0.layers.2.weight": "model-00004-of-00004.safetensors", "gdino.mask_embed.1.layers.0.bias": "model-00004-of-00004.safetensors", "gdino.mask_embed.1.layers.0.weight": "model-00004-of-00004.safetensors", "gdino.mask_embed.1.layers.1.bias": "model-00004-of-00004.safetensors", "gdino.mask_embed.1.layers.1.weight": "model-00004-of-00004.safetensors", "gdino.mask_embed.1.layers.2.bias": "model-00004-of-00004.safetensors", "gdino.mask_embed.1.layers.2.weight": "model-00004-of-00004.safetensors", "gdino.mask_embed.2.layers.0.bias": "model-00004-of-00004.safetensors", "gdino.mask_embed.2.layers.0.weight": "model-00004-of-00004.safetensors", "gdino.mask_embed.2.layers.1.bias": "model-00004-of-00004.safetensors", "gdino.mask_embed.2.layers.1.weight": "model-00004-of-00004.safetensors", "gdino.mask_embed.2.layers.2.bias": "model-00004-of-00004.safetensors", "gdino.mask_embed.2.layers.2.weight": "model-00004-of-00004.safetensors", "gdino.mask_embed.3.layers.0.bias": "model-00004-of-00004.safetensors", "gdino.mask_embed.3.layers.0.weight": "model-00004-of-00004.safetensors", "gdino.mask_embed.3.layers.1.bias": "model-00004-of-00004.safetensors", "gdino.mask_embed.3.layers.1.weight": "model-00004-of-00004.safetensors", "gdino.mask_embed.3.layers.2.bias": "model-00004-of-00004.safetensors", "gdino.mask_embed.3.layers.2.weight": "model-00004-of-00004.safetensors", "gdino.mask_embed.4.layers.0.bias": "model-00004-of-00004.safetensors", "gdino.mask_embed.4.layers.0.weight": "model-00004-of-00004.safetensors", "gdino.mask_embed.4.layers.1.bias": "model-00004-of-00004.safetensors", "gdino.mask_embed.4.layers.1.weight": "model-00004-of-00004.safetensors", "gdino.mask_embed.4.layers.2.bias": "model-00004-of-00004.safetensors", "gdino.mask_embed.4.layers.2.weight": "model-00004-of-00004.safetensors", "gdino.mask_embed.5.layers.0.bias": "model-00004-of-00004.safetensors", "gdino.mask_embed.5.layers.0.weight": "model-00004-of-00004.safetensors", "gdino.mask_embed.5.layers.1.bias": "model-00004-of-00004.safetensors", "gdino.mask_embed.5.layers.1.weight": "model-00004-of-00004.safetensors", "gdino.mask_embed.5.layers.2.bias": "model-00004-of-00004.safetensors", "gdino.mask_embed.5.layers.2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.0.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.0.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.0.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.0.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.0.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.0.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.0.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.0.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.0.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.0.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.0.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.0.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.0.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.0.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.0.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.0.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.0.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.0.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.0.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.0.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.0.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.0.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.0.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.0.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.0.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.0.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.1.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.1.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.1.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.1.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.1.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.1.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.1.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.1.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.1.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.1.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.1.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.1.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.1.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.1.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.1.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.1.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.1.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.1.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.1.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.1.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.1.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.1.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.1.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.1.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.1.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.1.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.2.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.2.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.2.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.2.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.2.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.2.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.2.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.2.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.2.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.2.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.2.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.2.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.2.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.2.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.2.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.2.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.2.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.2.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.2.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.2.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.2.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.2.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.2.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.2.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.2.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.2.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.3.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.3.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.3.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.3.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.3.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.3.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.3.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.3.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.3.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.3.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.3.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.3.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.3.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.3.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.3.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.3.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.3.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.3.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.3.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.3.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.3.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.3.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.3.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.3.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.3.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.3.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.4.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.4.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.4.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.4.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.4.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.4.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.4.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.4.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.4.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.4.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.4.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.4.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.4.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.4.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.4.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.4.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.4.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.4.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.4.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.4.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.4.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.4.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.4.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.4.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.4.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.4.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.5.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.5.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.5.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.5.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.5.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.5.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.5.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.5.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.5.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.5.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.5.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.5.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.5.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.5.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.5.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.5.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.5.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.5.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.5.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.5.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.5.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.5.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.5.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.5.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.5.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.blocks.5.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.downsample.conv.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.downsample.norm.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.downsample.norm.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.norm.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.0.norm.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.0.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.0.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.0.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.0.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.0.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.0.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.0.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.0.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.0.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.0.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.0.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.0.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.0.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.0.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.0.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.0.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.0.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.0.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.0.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.0.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.0.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.0.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.0.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.0.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.0.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.0.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.1.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.1.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.1.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.1.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.1.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.1.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.1.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.1.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.1.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.1.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.1.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.1.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.1.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.1.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.1.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.1.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.1.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.1.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.1.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.1.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.1.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.1.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.1.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.1.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.1.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.1.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.2.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.2.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.2.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.2.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.2.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.2.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.2.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.2.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.2.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.2.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.2.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.2.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.2.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.2.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.2.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.2.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.2.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.2.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.2.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.2.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.2.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.2.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.2.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.2.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.2.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.2.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.3.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.3.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.3.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.3.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.3.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.3.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.3.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.3.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.3.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.3.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.3.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.3.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.3.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.3.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.3.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.3.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.3.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.3.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.3.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.3.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.3.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.3.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.3.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.3.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.3.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.3.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.4.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.4.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.4.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.4.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.4.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.4.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.4.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.4.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.4.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.4.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.4.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.4.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.4.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.4.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.4.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.4.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.4.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.4.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.4.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.4.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.4.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.4.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.4.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.4.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.4.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.4.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.5.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.5.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.5.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.5.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.5.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.5.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.5.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.5.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.5.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.5.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.5.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.5.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.5.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.5.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.5.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.5.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.5.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.5.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.5.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.5.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.5.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.5.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.5.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.5.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.5.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.blocks.5.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.downsample.conv.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.downsample.norm.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.downsample.norm.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.norm.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.1.norm.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.0.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.0.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.0.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.0.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.0.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.0.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.0.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.0.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.0.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.0.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.0.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.0.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.0.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.0.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.0.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.0.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.0.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.0.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.0.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.0.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.0.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.0.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.0.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.0.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.0.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.0.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.1.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.1.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.1.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.1.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.1.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.1.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.1.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.1.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.1.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.1.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.1.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.1.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.1.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.1.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.1.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.1.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.1.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.1.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.1.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.1.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.1.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.1.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.1.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.1.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.1.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.1.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.10.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.10.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.10.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.10.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.10.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.10.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.10.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.10.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.10.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.10.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.10.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.10.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.10.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.10.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.10.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.10.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.10.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.10.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.10.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.10.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.10.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.10.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.10.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.10.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.10.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.10.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.11.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.11.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.11.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.11.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.11.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.11.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.11.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.11.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.11.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.11.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.11.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.11.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.11.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.11.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.11.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.11.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.11.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.11.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.11.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.11.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.11.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.11.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.11.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.11.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.11.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.11.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.12.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.12.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.12.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.12.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.12.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.12.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.12.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.12.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.12.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.12.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.12.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.12.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.12.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.12.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.12.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.12.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.12.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.12.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.12.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.12.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.12.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.12.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.12.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.12.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.12.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.12.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.13.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.13.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.13.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.13.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.13.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.13.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.13.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.13.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.13.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.13.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.13.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.13.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.13.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.13.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.13.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.13.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.13.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.13.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.13.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.13.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.13.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.13.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.13.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.13.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.13.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.13.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.14.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.14.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.14.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.14.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.14.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.14.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.14.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.14.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.14.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.14.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.14.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.14.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.14.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.14.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.14.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.14.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.14.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.14.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.14.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.14.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.14.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.14.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.14.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.14.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.14.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.14.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.15.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.15.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.15.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.15.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.15.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.15.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.15.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.15.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.15.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.15.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.15.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.15.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.15.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.15.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.15.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.15.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.15.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.15.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.15.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.15.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.15.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.15.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.15.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.15.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.15.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.15.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.16.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.16.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.16.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.16.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.16.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.16.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.16.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.16.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.16.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.16.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.16.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.16.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.16.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.16.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.16.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.16.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.16.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.16.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.16.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.16.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.16.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.16.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.16.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.16.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.16.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.16.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.17.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.17.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.17.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.17.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.17.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.17.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.17.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.17.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.17.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.17.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.17.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.17.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.17.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.17.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.17.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.17.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.17.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.17.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.17.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.17.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.17.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.17.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.17.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.17.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.17.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.17.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.18.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.18.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.18.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.18.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.18.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.18.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.18.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.18.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.18.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.18.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.18.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.18.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.18.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.18.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.18.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.18.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.18.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.18.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.18.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.18.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.18.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.18.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.18.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.18.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.18.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.18.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.19.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.19.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.19.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.19.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.19.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.19.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.19.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.19.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.19.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.19.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.19.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.19.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.19.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.19.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.19.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.19.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.19.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.19.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.19.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.19.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.19.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.19.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.19.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.19.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.19.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.19.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.2.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.2.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.2.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.2.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.2.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.2.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.2.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.2.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.2.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.2.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.2.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.2.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.2.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.2.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.2.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.2.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.2.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.2.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.2.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.2.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.2.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.2.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.2.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.2.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.2.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.2.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.20.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.20.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.20.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.20.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.20.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.20.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.20.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.20.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.20.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.20.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.20.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.20.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.20.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.20.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.20.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.20.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.20.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.20.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.20.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.20.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.20.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.20.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.20.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.20.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.20.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.20.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.21.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.21.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.21.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.21.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.21.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.21.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.21.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.21.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.21.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.21.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.21.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.21.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.21.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.21.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.21.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.21.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.21.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.21.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.21.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.21.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.21.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.21.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.21.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.21.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.21.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.21.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.22.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.22.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.22.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.22.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.22.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.22.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.22.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.22.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.22.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.22.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.22.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.22.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.22.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.22.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.22.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.22.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.22.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.22.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.22.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.22.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.22.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.22.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.22.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.22.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.22.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.22.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.23.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.23.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.23.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.23.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.23.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.23.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.23.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.23.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.23.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.23.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.23.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.23.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.23.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.23.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.23.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.23.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.23.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.23.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.23.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.23.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.23.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.23.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.23.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.23.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.23.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.23.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.24.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.24.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.24.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.24.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.24.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.24.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.24.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.24.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.24.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.24.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.24.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.24.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.24.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.24.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.24.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.24.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.24.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.24.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.24.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.24.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.24.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.24.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.24.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.24.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.24.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.24.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.25.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.25.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.25.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.25.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.25.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.25.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.25.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.25.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.25.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.25.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.25.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.25.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.25.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.25.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.25.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.25.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.25.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.25.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.25.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.25.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.25.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.25.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.25.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.25.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.25.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.25.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.26.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.26.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.26.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.26.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.26.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.26.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.26.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.26.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.26.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.26.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.26.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.26.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.26.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.26.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.26.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.26.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.26.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.26.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.26.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.26.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.26.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.26.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.26.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.26.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.26.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.26.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.27.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.27.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.27.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.27.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.27.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.27.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.27.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.27.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.27.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.27.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.27.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.27.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.27.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.27.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.27.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.27.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.27.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.27.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.27.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.27.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.27.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.27.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.27.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.27.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.27.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.27.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.28.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.28.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.28.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.28.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.28.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.28.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.28.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.28.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.28.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.28.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.28.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.28.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.28.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.28.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.28.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.28.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.28.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.28.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.28.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.28.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.28.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.28.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.28.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.28.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.28.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.28.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.29.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.29.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.29.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.29.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.29.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.29.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.29.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.29.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.29.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.29.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.29.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.29.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.29.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.29.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.29.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.29.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.29.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.29.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.29.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.29.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.29.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.29.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.29.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.29.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.29.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.29.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.3.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.3.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.3.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.3.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.3.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.3.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.3.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.3.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.3.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.3.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.3.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.3.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.3.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.3.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.3.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.3.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.3.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.3.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.3.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.3.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.3.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.3.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.3.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.3.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.3.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.3.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.30.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.30.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.30.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.30.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.30.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.30.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.30.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.30.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.30.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.30.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.30.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.30.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.30.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.30.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.30.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.30.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.30.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.30.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.30.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.30.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.30.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.30.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.30.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.30.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.30.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.30.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.31.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.31.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.31.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.31.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.31.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.31.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.31.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.31.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.31.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.31.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.31.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.31.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.31.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.31.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.31.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.31.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.31.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.31.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.31.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.31.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.31.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.31.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.31.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.31.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.31.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.31.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.4.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.4.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.4.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.4.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.4.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.4.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.4.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.4.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.4.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.4.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.4.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.4.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.4.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.4.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.4.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.4.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.4.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.4.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.4.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.4.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.4.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.4.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.4.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.4.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.4.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.4.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.5.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.5.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.5.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.5.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.5.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.5.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.5.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.5.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.5.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.5.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.5.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.5.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.5.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.5.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.5.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.5.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.5.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.5.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.5.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.5.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.5.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.5.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.5.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.5.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.5.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.5.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.6.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.6.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.6.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.6.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.6.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.6.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.6.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.6.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.6.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.6.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.6.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.6.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.6.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.6.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.6.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.6.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.6.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.6.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.6.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.6.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.6.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.6.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.6.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.6.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.6.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.6.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.7.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.7.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.7.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.7.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.7.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.7.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.7.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.7.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.7.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.7.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.7.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.7.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.7.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.7.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.7.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.7.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.7.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.7.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.7.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.7.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.7.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.7.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.7.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.7.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.7.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.7.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.8.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.8.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.8.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.8.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.8.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.8.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.8.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.8.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.8.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.8.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.8.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.8.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.8.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.8.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.8.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.8.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.8.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.8.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.8.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.8.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.8.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.8.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.8.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.8.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.8.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.8.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.9.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.9.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.9.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.9.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.9.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.9.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.9.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.9.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.9.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.9.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.9.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.9.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.9.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.9.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.9.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.9.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.9.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.9.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.9.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.9.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.9.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.9.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.9.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.9.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.9.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.blocks.9.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.downsample.conv.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.downsample.norm.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.downsample.norm.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.norm.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.norm.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.post_norms.0.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.post_norms.0.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.post_norms.1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.post_norms.1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.post_norms.2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.post_norms.2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.post_norms.3.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.post_norms.3.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.post_norms.4.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.2.post_norms.4.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.0.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.0.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.0.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.0.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.0.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.0.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.0.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.0.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.0.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.0.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.0.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.0.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.0.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.0.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.0.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.0.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.0.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.0.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.0.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.0.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.0.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.0.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.0.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.0.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.0.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.0.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.1.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.1.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.1.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.1.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.1.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.1.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.1.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.1.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.1.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.1.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.1.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.1.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.1.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.1.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.1.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.1.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.1.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.1.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.1.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.1.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.1.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.1.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.1.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.1.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.1.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.1.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.2.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.2.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.2.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.2.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.2.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.2.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.2.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.2.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.2.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.2.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.2.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.2.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.2.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.2.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.2.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.2.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.2.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.2.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.2.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.2.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.2.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.2.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.2.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.2.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.2.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.2.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.3.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.3.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.3.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.3.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.3.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.3.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.3.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.3.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.3.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.3.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.3.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.3.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.3.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.3.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.3.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.3.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.3.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.3.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.3.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.3.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.3.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.3.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.3.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.3.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.3.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.3.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.4.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.4.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.4.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.4.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.4.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.4.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.4.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.4.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.4.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.4.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.4.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.4.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.4.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.4.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.4.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.4.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.4.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.4.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.4.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.4.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.4.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.4.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.4.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.4.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.4.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.4.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.5.dcn.center_feature_scale_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.5.dcn.center_feature_scale_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.5.dcn.dw_conv.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.5.dcn.dw_conv.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.5.dcn.dw_conv.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.5.dcn.dw_conv.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.5.dcn.input_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.5.dcn.input_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.5.dcn.mask.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.5.dcn.mask.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.5.dcn.offset.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.5.dcn.offset.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.5.dcn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.5.dcn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.5.mlp.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.5.mlp.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.5.mlp.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.5.mlp.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.5.norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.5.norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.5.norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.5.norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.5.res_post_norm1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.5.res_post_norm1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.5.res_post_norm2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.blocks.5.res_post_norm2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.norm.0.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.levels.3.norm.0.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.patch_embed.conv1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.patch_embed.conv1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.patch_embed.conv2.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.patch_embed.conv2.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.patch_embed.norm1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.patch_embed.norm1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.patch_embed.norm2.1.bias": "model-00004-of-00004.safetensors", "gdino.model.backbone.conv_encoder.model.patch_embed.norm2.1.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.bbox_embed.0.layers.0.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.bbox_embed.0.layers.0.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.bbox_embed.0.layers.1.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.bbox_embed.0.layers.1.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.bbox_embed.0.layers.2.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.bbox_embed.0.layers.2.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.bbox_embed.1.layers.0.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.bbox_embed.1.layers.0.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.bbox_embed.1.layers.1.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.bbox_embed.1.layers.1.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.bbox_embed.1.layers.2.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.bbox_embed.1.layers.2.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.bbox_embed.2.layers.0.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.bbox_embed.2.layers.0.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.bbox_embed.2.layers.1.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.bbox_embed.2.layers.1.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.bbox_embed.2.layers.2.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.bbox_embed.2.layers.2.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.bbox_embed.3.layers.0.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.bbox_embed.3.layers.0.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.bbox_embed.3.layers.1.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.bbox_embed.3.layers.1.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.bbox_embed.3.layers.2.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.bbox_embed.3.layers.2.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.bbox_embed.4.layers.0.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.bbox_embed.4.layers.0.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.bbox_embed.4.layers.1.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.bbox_embed.4.layers.1.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.bbox_embed.4.layers.2.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.bbox_embed.4.layers.2.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.bbox_embed.5.layers.0.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.bbox_embed.5.layers.0.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.bbox_embed.5.layers.1.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.bbox_embed.5.layers.1.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.bbox_embed.5.layers.2.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.bbox_embed.5.layers.2.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layer_norm.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layer_norm.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.0.encoder_attn.attention_weights.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.0.encoder_attn.attention_weights.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.0.encoder_attn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.0.encoder_attn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.0.encoder_attn.sampling_offsets.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.0.encoder_attn.sampling_offsets.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.0.encoder_attn.value_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.0.encoder_attn.value_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.0.encoder_attn_layer_norm.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.0.encoder_attn_layer_norm.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.0.encoder_attn_text.in_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.0.encoder_attn_text.in_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.0.encoder_attn_text.out_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.0.encoder_attn_text.out_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.0.encoder_attn_text_layer_norm.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.0.encoder_attn_text_layer_norm.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.0.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.0.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.0.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.0.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.0.final_layer_norm.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.0.final_layer_norm.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.0.self_attn.in_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.0.self_attn.in_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.0.self_attn.out_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.0.self_attn.out_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.0.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.0.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.1.encoder_attn.attention_weights.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.1.encoder_attn.attention_weights.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.1.encoder_attn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.1.encoder_attn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.1.encoder_attn.sampling_offsets.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.1.encoder_attn.sampling_offsets.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.1.encoder_attn.value_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.1.encoder_attn.value_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.1.encoder_attn_layer_norm.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.1.encoder_attn_layer_norm.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.1.encoder_attn_text.in_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.1.encoder_attn_text.in_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.1.encoder_attn_text.out_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.1.encoder_attn_text.out_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.1.encoder_attn_text_layer_norm.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.1.encoder_attn_text_layer_norm.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.1.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.1.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.1.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.1.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.1.final_layer_norm.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.1.final_layer_norm.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.1.self_attn.in_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.1.self_attn.in_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.1.self_attn.out_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.1.self_attn.out_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.1.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.1.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.2.encoder_attn.attention_weights.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.2.encoder_attn.attention_weights.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.2.encoder_attn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.2.encoder_attn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.2.encoder_attn.sampling_offsets.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.2.encoder_attn.sampling_offsets.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.2.encoder_attn.value_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.2.encoder_attn.value_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.2.encoder_attn_layer_norm.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.2.encoder_attn_layer_norm.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.2.encoder_attn_text.in_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.2.encoder_attn_text.in_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.2.encoder_attn_text.out_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.2.encoder_attn_text.out_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.2.encoder_attn_text_layer_norm.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.2.encoder_attn_text_layer_norm.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.2.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.2.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.2.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.2.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.2.final_layer_norm.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.2.final_layer_norm.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.2.self_attn.in_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.2.self_attn.in_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.2.self_attn.out_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.2.self_attn.out_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.2.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.2.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.3.encoder_attn.attention_weights.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.3.encoder_attn.attention_weights.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.3.encoder_attn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.3.encoder_attn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.3.encoder_attn.sampling_offsets.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.3.encoder_attn.sampling_offsets.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.3.encoder_attn.value_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.3.encoder_attn.value_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.3.encoder_attn_layer_norm.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.3.encoder_attn_layer_norm.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.3.encoder_attn_text.in_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.3.encoder_attn_text.in_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.3.encoder_attn_text.out_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.3.encoder_attn_text.out_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.3.encoder_attn_text_layer_norm.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.3.encoder_attn_text_layer_norm.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.3.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.3.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.3.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.3.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.3.final_layer_norm.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.3.final_layer_norm.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.3.self_attn.in_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.3.self_attn.in_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.3.self_attn.out_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.3.self_attn.out_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.3.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.3.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.4.encoder_attn.attention_weights.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.4.encoder_attn.attention_weights.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.4.encoder_attn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.4.encoder_attn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.4.encoder_attn.sampling_offsets.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.4.encoder_attn.sampling_offsets.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.4.encoder_attn.value_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.4.encoder_attn.value_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.4.encoder_attn_layer_norm.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.4.encoder_attn_layer_norm.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.4.encoder_attn_text.in_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.4.encoder_attn_text.in_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.4.encoder_attn_text.out_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.4.encoder_attn_text.out_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.4.encoder_attn_text_layer_norm.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.4.encoder_attn_text_layer_norm.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.4.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.4.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.4.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.4.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.4.final_layer_norm.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.4.final_layer_norm.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.4.self_attn.in_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.4.self_attn.in_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.4.self_attn.out_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.4.self_attn.out_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.4.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.4.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.5.encoder_attn.attention_weights.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.5.encoder_attn.attention_weights.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.5.encoder_attn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.5.encoder_attn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.5.encoder_attn.sampling_offsets.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.5.encoder_attn.sampling_offsets.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.5.encoder_attn.value_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.5.encoder_attn.value_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.5.encoder_attn_layer_norm.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.5.encoder_attn_layer_norm.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.5.encoder_attn_text.in_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.5.encoder_attn_text.in_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.5.encoder_attn_text.out_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.5.encoder_attn_text.out_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.5.encoder_attn_text_layer_norm.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.5.encoder_attn_text_layer_norm.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.5.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.5.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.5.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.5.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.5.final_layer_norm.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.5.final_layer_norm.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.5.self_attn.in_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.5.self_attn.in_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.5.self_attn.out_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.5.self_attn.out_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.5.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.layers.5.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.reference_points_head.layers.0.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.reference_points_head.layers.0.weight": "model-00004-of-00004.safetensors", "gdino.model.decoder.reference_points_head.layers.1.bias": "model-00004-of-00004.safetensors", "gdino.model.decoder.reference_points_head.layers.1.weight": "model-00004-of-00004.safetensors", "gdino.model.enc_output.bias": "model-00004-of-00004.safetensors", "gdino.model.enc_output.weight": "model-00004-of-00004.safetensors", "gdino.model.enc_output_norm.bias": "model-00004-of-00004.safetensors", "gdino.model.enc_output_norm.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.deformable_layer.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.deformable_layer.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.deformable_layer.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.deformable_layer.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.deformable_layer.final_layer_norm.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.deformable_layer.final_layer_norm.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.deformable_layer.self_attn.attention_weights.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.deformable_layer.self_attn.attention_weights.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.deformable_layer.self_attn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.deformable_layer.self_attn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.deformable_layer.self_attn.sampling_offsets.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.deformable_layer.self_attn.sampling_offsets.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.deformable_layer.self_attn.value_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.deformable_layer.self_attn.value_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.deformable_layer.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.deformable_layer.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.fusion_layer.attn.out_text_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.fusion_layer.attn.out_text_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.fusion_layer.attn.out_vision_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.fusion_layer.attn.out_vision_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.fusion_layer.attn.text_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.fusion_layer.attn.text_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.fusion_layer.attn.values_text_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.fusion_layer.attn.values_text_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.fusion_layer.attn.values_vision_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.fusion_layer.attn.values_vision_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.fusion_layer.attn.vision_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.fusion_layer.attn.vision_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.fusion_layer.layer_norm_text.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.fusion_layer.layer_norm_text.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.fusion_layer.layer_norm_vision.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.fusion_layer.layer_norm_vision.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.fusion_layer.text_param": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.fusion_layer.vision_param": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.text_enhancer_layer.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.text_enhancer_layer.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.text_enhancer_layer.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.text_enhancer_layer.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.text_enhancer_layer.layer_norm_after.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.text_enhancer_layer.layer_norm_after.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.text_enhancer_layer.layer_norm_before.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.text_enhancer_layer.layer_norm_before.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.text_enhancer_layer.self_attn.in_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.text_enhancer_layer.self_attn.in_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.text_enhancer_layer.self_attn.out_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.0.text_enhancer_layer.self_attn.out_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.deformable_layer.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.deformable_layer.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.deformable_layer.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.deformable_layer.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.deformable_layer.final_layer_norm.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.deformable_layer.final_layer_norm.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.deformable_layer.self_attn.attention_weights.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.deformable_layer.self_attn.attention_weights.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.deformable_layer.self_attn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.deformable_layer.self_attn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.deformable_layer.self_attn.sampling_offsets.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.deformable_layer.self_attn.sampling_offsets.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.deformable_layer.self_attn.value_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.deformable_layer.self_attn.value_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.deformable_layer.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.deformable_layer.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.fusion_layer.attn.out_text_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.fusion_layer.attn.out_text_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.fusion_layer.attn.out_vision_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.fusion_layer.attn.out_vision_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.fusion_layer.attn.text_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.fusion_layer.attn.text_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.fusion_layer.attn.values_text_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.fusion_layer.attn.values_text_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.fusion_layer.attn.values_vision_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.fusion_layer.attn.values_vision_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.fusion_layer.attn.vision_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.fusion_layer.attn.vision_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.fusion_layer.layer_norm_text.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.fusion_layer.layer_norm_text.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.fusion_layer.layer_norm_vision.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.fusion_layer.layer_norm_vision.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.fusion_layer.text_param": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.fusion_layer.vision_param": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.text_enhancer_layer.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.text_enhancer_layer.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.text_enhancer_layer.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.text_enhancer_layer.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.text_enhancer_layer.layer_norm_after.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.text_enhancer_layer.layer_norm_after.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.text_enhancer_layer.layer_norm_before.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.text_enhancer_layer.layer_norm_before.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.text_enhancer_layer.self_attn.in_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.text_enhancer_layer.self_attn.in_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.text_enhancer_layer.self_attn.out_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.1.text_enhancer_layer.self_attn.out_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.deformable_layer.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.deformable_layer.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.deformable_layer.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.deformable_layer.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.deformable_layer.final_layer_norm.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.deformable_layer.final_layer_norm.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.deformable_layer.self_attn.attention_weights.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.deformable_layer.self_attn.attention_weights.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.deformable_layer.self_attn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.deformable_layer.self_attn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.deformable_layer.self_attn.sampling_offsets.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.deformable_layer.self_attn.sampling_offsets.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.deformable_layer.self_attn.value_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.deformable_layer.self_attn.value_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.deformable_layer.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.deformable_layer.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.fusion_layer.attn.out_text_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.fusion_layer.attn.out_text_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.fusion_layer.attn.out_vision_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.fusion_layer.attn.out_vision_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.fusion_layer.attn.text_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.fusion_layer.attn.text_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.fusion_layer.attn.values_text_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.fusion_layer.attn.values_text_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.fusion_layer.attn.values_vision_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.fusion_layer.attn.values_vision_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.fusion_layer.attn.vision_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.fusion_layer.attn.vision_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.fusion_layer.layer_norm_text.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.fusion_layer.layer_norm_text.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.fusion_layer.layer_norm_vision.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.fusion_layer.layer_norm_vision.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.fusion_layer.text_param": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.fusion_layer.vision_param": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.text_enhancer_layer.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.text_enhancer_layer.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.text_enhancer_layer.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.text_enhancer_layer.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.text_enhancer_layer.layer_norm_after.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.text_enhancer_layer.layer_norm_after.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.text_enhancer_layer.layer_norm_before.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.text_enhancer_layer.layer_norm_before.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.text_enhancer_layer.self_attn.in_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.text_enhancer_layer.self_attn.in_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.text_enhancer_layer.self_attn.out_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.2.text_enhancer_layer.self_attn.out_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.deformable_layer.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.deformable_layer.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.deformable_layer.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.deformable_layer.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.deformable_layer.final_layer_norm.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.deformable_layer.final_layer_norm.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.deformable_layer.self_attn.attention_weights.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.deformable_layer.self_attn.attention_weights.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.deformable_layer.self_attn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.deformable_layer.self_attn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.deformable_layer.self_attn.sampling_offsets.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.deformable_layer.self_attn.sampling_offsets.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.deformable_layer.self_attn.value_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.deformable_layer.self_attn.value_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.deformable_layer.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.deformable_layer.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.fusion_layer.attn.out_text_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.fusion_layer.attn.out_text_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.fusion_layer.attn.out_vision_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.fusion_layer.attn.out_vision_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.fusion_layer.attn.text_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.fusion_layer.attn.text_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.fusion_layer.attn.values_text_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.fusion_layer.attn.values_text_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.fusion_layer.attn.values_vision_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.fusion_layer.attn.values_vision_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.fusion_layer.attn.vision_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.fusion_layer.attn.vision_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.fusion_layer.layer_norm_text.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.fusion_layer.layer_norm_text.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.fusion_layer.layer_norm_vision.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.fusion_layer.layer_norm_vision.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.fusion_layer.text_param": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.fusion_layer.vision_param": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.text_enhancer_layer.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.text_enhancer_layer.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.text_enhancer_layer.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.text_enhancer_layer.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.text_enhancer_layer.layer_norm_after.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.text_enhancer_layer.layer_norm_after.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.text_enhancer_layer.layer_norm_before.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.text_enhancer_layer.layer_norm_before.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.text_enhancer_layer.self_attn.in_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.text_enhancer_layer.self_attn.in_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.text_enhancer_layer.self_attn.out_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.3.text_enhancer_layer.self_attn.out_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.deformable_layer.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.deformable_layer.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.deformable_layer.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.deformable_layer.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.deformable_layer.final_layer_norm.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.deformable_layer.final_layer_norm.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.deformable_layer.self_attn.attention_weights.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.deformable_layer.self_attn.attention_weights.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.deformable_layer.self_attn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.deformable_layer.self_attn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.deformable_layer.self_attn.sampling_offsets.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.deformable_layer.self_attn.sampling_offsets.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.deformable_layer.self_attn.value_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.deformable_layer.self_attn.value_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.deformable_layer.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.deformable_layer.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.fusion_layer.attn.out_text_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.fusion_layer.attn.out_text_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.fusion_layer.attn.out_vision_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.fusion_layer.attn.out_vision_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.fusion_layer.attn.text_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.fusion_layer.attn.text_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.fusion_layer.attn.values_text_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.fusion_layer.attn.values_text_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.fusion_layer.attn.values_vision_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.fusion_layer.attn.values_vision_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.fusion_layer.attn.vision_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.fusion_layer.attn.vision_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.fusion_layer.layer_norm_text.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.fusion_layer.layer_norm_text.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.fusion_layer.layer_norm_vision.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.fusion_layer.layer_norm_vision.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.fusion_layer.text_param": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.fusion_layer.vision_param": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.text_enhancer_layer.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.text_enhancer_layer.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.text_enhancer_layer.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.text_enhancer_layer.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.text_enhancer_layer.layer_norm_after.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.text_enhancer_layer.layer_norm_after.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.text_enhancer_layer.layer_norm_before.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.text_enhancer_layer.layer_norm_before.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.text_enhancer_layer.self_attn.in_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.text_enhancer_layer.self_attn.in_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.text_enhancer_layer.self_attn.out_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.4.text_enhancer_layer.self_attn.out_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.deformable_layer.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.deformable_layer.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.deformable_layer.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.deformable_layer.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.deformable_layer.final_layer_norm.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.deformable_layer.final_layer_norm.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.deformable_layer.self_attn.attention_weights.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.deformable_layer.self_attn.attention_weights.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.deformable_layer.self_attn.output_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.deformable_layer.self_attn.output_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.deformable_layer.self_attn.sampling_offsets.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.deformable_layer.self_attn.sampling_offsets.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.deformable_layer.self_attn.value_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.deformable_layer.self_attn.value_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.deformable_layer.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.deformable_layer.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.fusion_layer.attn.out_text_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.fusion_layer.attn.out_text_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.fusion_layer.attn.out_vision_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.fusion_layer.attn.out_vision_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.fusion_layer.attn.text_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.fusion_layer.attn.text_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.fusion_layer.attn.values_text_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.fusion_layer.attn.values_text_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.fusion_layer.attn.values_vision_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.fusion_layer.attn.values_vision_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.fusion_layer.attn.vision_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.fusion_layer.attn.vision_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.fusion_layer.layer_norm_text.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.fusion_layer.layer_norm_text.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.fusion_layer.layer_norm_vision.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.fusion_layer.layer_norm_vision.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.fusion_layer.text_param": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.fusion_layer.vision_param": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.text_enhancer_layer.fc1.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.text_enhancer_layer.fc1.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.text_enhancer_layer.fc2.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.text_enhancer_layer.fc2.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.text_enhancer_layer.layer_norm_after.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.text_enhancer_layer.layer_norm_after.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.text_enhancer_layer.layer_norm_before.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.text_enhancer_layer.layer_norm_before.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.text_enhancer_layer.self_attn.in_proj_bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.text_enhancer_layer.self_attn.in_proj_weight": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.text_enhancer_layer.self_attn.out_proj.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder.layers.5.text_enhancer_layer.self_attn.out_proj.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder_output_bbox_embed.layers.0.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder_output_bbox_embed.layers.0.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder_output_bbox_embed.layers.1.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder_output_bbox_embed.layers.1.weight": "model-00004-of-00004.safetensors", "gdino.model.encoder_output_bbox_embed.layers.2.bias": "model-00004-of-00004.safetensors", "gdino.model.encoder_output_bbox_embed.layers.2.weight": "model-00004-of-00004.safetensors", "gdino.model.input_proj_vision.0.0.bias": "model-00004-of-00004.safetensors", "gdino.model.input_proj_vision.0.0.weight": "model-00004-of-00004.safetensors", "gdino.model.input_proj_vision.0.1.bias": "model-00004-of-00004.safetensors", "gdino.model.input_proj_vision.0.1.weight": "model-00004-of-00004.safetensors", "gdino.model.input_proj_vision.1.0.bias": "model-00004-of-00004.safetensors", "gdino.model.input_proj_vision.1.0.weight": "model-00004-of-00004.safetensors", "gdino.model.input_proj_vision.1.1.bias": "model-00004-of-00004.safetensors", "gdino.model.input_proj_vision.1.1.weight": "model-00004-of-00004.safetensors", "gdino.model.input_proj_vision.2.0.bias": "model-00004-of-00004.safetensors", "gdino.model.input_proj_vision.2.0.weight": "model-00004-of-00004.safetensors", "gdino.model.input_proj_vision.2.1.bias": "model-00004-of-00004.safetensors", "gdino.model.input_proj_vision.2.1.weight": "model-00004-of-00004.safetensors", "gdino.model.input_proj_vision.3.0.bias": "model-00004-of-00004.safetensors", "gdino.model.input_proj_vision.3.0.weight": "model-00004-of-00004.safetensors", "gdino.model.input_proj_vision.3.1.bias": "model-00004-of-00004.safetensors", "gdino.model.input_proj_vision.3.1.weight": "model-00004-of-00004.safetensors", "gdino.model.lateral_convs.0.norm.bias": "model-00004-of-00004.safetensors", "gdino.model.lateral_convs.0.norm.weight": "model-00004-of-00004.safetensors", "gdino.model.lateral_convs.0.weight": "model-00004-of-00004.safetensors", "gdino.model.level_embed": "model-00004-of-00004.safetensors", "gdino.model.mask_embed.layers.0.bias": "model-00004-of-00004.safetensors", "gdino.model.mask_embed.layers.0.weight": "model-00004-of-00004.safetensors", "gdino.model.mask_embed.layers.1.bias": "model-00004-of-00004.safetensors", "gdino.model.mask_embed.layers.1.weight": "model-00004-of-00004.safetensors", "gdino.model.mask_embed.layers.2.bias": "model-00004-of-00004.safetensors", "gdino.model.mask_embed.layers.2.weight": "model-00004-of-00004.safetensors", "gdino.model.mask_features.bias": "model-00004-of-00004.safetensors", "gdino.model.mask_features.weight": "model-00004-of-00004.safetensors", "gdino.model.output_convs.0.norm.bias": "model-00004-of-00004.safetensors", "gdino.model.output_convs.0.norm.weight": "model-00004-of-00004.safetensors", "gdino.model.output_convs.0.weight": "model-00004-of-00004.safetensors", "gdino.model.query_position_embeddings.weight": "model-00004-of-00004.safetensors", "gdino.patch2query.layers.0.bias": "model-00004-of-00004.safetensors", "gdino.patch2query.layers.0.weight": "model-00004-of-00004.safetensors", "gdino.patch2query.layers.1.bias": "model-00004-of-00004.safetensors", "gdino.patch2query.layers.1.weight": "model-00004-of-00004.safetensors", "gdino.patch2query.layers.2.bias": "model-00004-of-00004.safetensors", "gdino.patch2query.layers.2.weight": "model-00004-of-00004.safetensors", "llm.model.layers.0.attention.wo.weight": "model-00001-of-00004.safetensors", "llm.model.layers.0.attention.wqkv.weight": "model-00001-of-00004.safetensors", "llm.model.layers.0.attention_norm.weight": "model-00001-of-00004.safetensors", "llm.model.layers.0.feed_forward.w1.weight": "model-00001-of-00004.safetensors", "llm.model.layers.0.feed_forward.w2.weight": "model-00001-of-00004.safetensors", "llm.model.layers.0.feed_forward.w3.weight": "model-00001-of-00004.safetensors", "llm.model.layers.0.ffn_norm.weight": "model-00001-of-00004.safetensors", "llm.model.layers.1.attention.wo.weight": "model-00001-of-00004.safetensors", "llm.model.layers.1.attention.wqkv.weight": "model-00001-of-00004.safetensors", "llm.model.layers.1.attention_norm.weight": "model-00001-of-00004.safetensors", "llm.model.layers.1.feed_forward.w1.weight": "model-00001-of-00004.safetensors", "llm.model.layers.1.feed_forward.w2.weight": "model-00001-of-00004.safetensors", "llm.model.layers.1.feed_forward.w3.weight": "model-00001-of-00004.safetensors", "llm.model.layers.1.ffn_norm.weight": "model-00001-of-00004.safetensors", "llm.model.layers.10.attention.wo.weight": "model-00002-of-00004.safetensors", "llm.model.layers.10.attention.wqkv.weight": "model-00002-of-00004.safetensors", "llm.model.layers.10.attention_norm.weight": "model-00002-of-00004.safetensors", "llm.model.layers.10.feed_forward.w1.weight": "model-00002-of-00004.safetensors", "llm.model.layers.10.feed_forward.w2.weight": "model-00002-of-00004.safetensors", "llm.model.layers.10.feed_forward.w3.weight": "model-00002-of-00004.safetensors", "llm.model.layers.10.ffn_norm.weight": "model-00002-of-00004.safetensors", "llm.model.layers.11.attention.wo.weight": "model-00002-of-00004.safetensors", "llm.model.layers.11.attention.wqkv.weight": "model-00002-of-00004.safetensors", "llm.model.layers.11.attention_norm.weight": "model-00002-of-00004.safetensors", "llm.model.layers.11.feed_forward.w1.weight": "model-00002-of-00004.safetensors", "llm.model.layers.11.feed_forward.w2.weight": "model-00002-of-00004.safetensors", "llm.model.layers.11.feed_forward.w3.weight": "model-00002-of-00004.safetensors", "llm.model.layers.11.ffn_norm.weight": "model-00002-of-00004.safetensors", "llm.model.layers.12.attention.wo.weight": "model-00002-of-00004.safetensors", "llm.model.layers.12.attention.wqkv.weight": "model-00002-of-00004.safetensors", "llm.model.layers.12.attention_norm.weight": "model-00002-of-00004.safetensors", "llm.model.layers.12.feed_forward.w1.weight": "model-00002-of-00004.safetensors", "llm.model.layers.12.feed_forward.w2.weight": "model-00002-of-00004.safetensors", "llm.model.layers.12.feed_forward.w3.weight": "model-00002-of-00004.safetensors", "llm.model.layers.12.ffn_norm.weight": "model-00002-of-00004.safetensors", "llm.model.layers.13.attention.wo.weight": "model-00002-of-00004.safetensors", "llm.model.layers.13.attention.wqkv.weight": "model-00002-of-00004.safetensors", "llm.model.layers.13.attention_norm.weight": "model-00002-of-00004.safetensors", "llm.model.layers.13.feed_forward.w1.weight": "model-00002-of-00004.safetensors", "llm.model.layers.13.feed_forward.w2.weight": "model-00002-of-00004.safetensors", "llm.model.layers.13.feed_forward.w3.weight": "model-00002-of-00004.safetensors", "llm.model.layers.13.ffn_norm.weight": "model-00002-of-00004.safetensors", "llm.model.layers.14.attention.wo.weight": "model-00002-of-00004.safetensors", "llm.model.layers.14.attention.wqkv.weight": "model-00002-of-00004.safetensors", "llm.model.layers.14.attention_norm.weight": "model-00002-of-00004.safetensors", "llm.model.layers.14.feed_forward.w1.weight": "model-00002-of-00004.safetensors", "llm.model.layers.14.feed_forward.w2.weight": "model-00002-of-00004.safetensors", "llm.model.layers.14.feed_forward.w3.weight": "model-00002-of-00004.safetensors", "llm.model.layers.14.ffn_norm.weight": "model-00002-of-00004.safetensors", "llm.model.layers.15.attention.wo.weight": "model-00002-of-00004.safetensors", "llm.model.layers.15.attention.wqkv.weight": "model-00002-of-00004.safetensors", "llm.model.layers.15.attention_norm.weight": "model-00002-of-00004.safetensors", "llm.model.layers.15.feed_forward.w1.weight": "model-00002-of-00004.safetensors", "llm.model.layers.15.feed_forward.w2.weight": "model-00002-of-00004.safetensors", "llm.model.layers.15.feed_forward.w3.weight": "model-00002-of-00004.safetensors", "llm.model.layers.15.ffn_norm.weight": "model-00002-of-00004.safetensors", "llm.model.layers.16.attention.wo.weight": "model-00002-of-00004.safetensors", "llm.model.layers.16.attention.wqkv.weight": "model-00002-of-00004.safetensors", "llm.model.layers.16.attention_norm.weight": "model-00002-of-00004.safetensors", "llm.model.layers.16.feed_forward.w1.weight": "model-00002-of-00004.safetensors", "llm.model.layers.16.feed_forward.w2.weight": "model-00002-of-00004.safetensors", "llm.model.layers.16.feed_forward.w3.weight": "model-00002-of-00004.safetensors", "llm.model.layers.16.ffn_norm.weight": "model-00002-of-00004.safetensors", "llm.model.layers.17.attention.wo.weight": "model-00002-of-00004.safetensors", "llm.model.layers.17.attention.wqkv.weight": "model-00002-of-00004.safetensors", "llm.model.layers.17.attention_norm.weight": "model-00002-of-00004.safetensors", "llm.model.layers.17.feed_forward.w1.weight": "model-00002-of-00004.safetensors", "llm.model.layers.17.feed_forward.w2.weight": "model-00002-of-00004.safetensors", "llm.model.layers.17.feed_forward.w3.weight": "model-00002-of-00004.safetensors", "llm.model.layers.17.ffn_norm.weight": "model-00002-of-00004.safetensors", "llm.model.layers.18.attention.wo.weight": "model-00002-of-00004.safetensors", "llm.model.layers.18.attention.wqkv.weight": "model-00002-of-00004.safetensors", "llm.model.layers.18.attention_norm.weight": "model-00002-of-00004.safetensors", "llm.model.layers.18.feed_forward.w1.weight": "model-00002-of-00004.safetensors", "llm.model.layers.18.feed_forward.w2.weight": "model-00002-of-00004.safetensors", "llm.model.layers.18.feed_forward.w3.weight": "model-00002-of-00004.safetensors", "llm.model.layers.18.ffn_norm.weight": "model-00002-of-00004.safetensors", "llm.model.layers.19.attention.wo.weight": "model-00002-of-00004.safetensors", "llm.model.layers.19.attention.wqkv.weight": "model-00002-of-00004.safetensors", "llm.model.layers.19.attention_norm.weight": "model-00003-of-00004.safetensors", "llm.model.layers.19.feed_forward.w1.weight": "model-00002-of-00004.safetensors", "llm.model.layers.19.feed_forward.w2.weight": "model-00003-of-00004.safetensors", "llm.model.layers.19.feed_forward.w3.weight": "model-00003-of-00004.safetensors", "llm.model.layers.19.ffn_norm.weight": "model-00003-of-00004.safetensors", "llm.model.layers.2.attention.wo.weight": "model-00001-of-00004.safetensors", "llm.model.layers.2.attention.wqkv.weight": "model-00001-of-00004.safetensors", "llm.model.layers.2.attention_norm.weight": "model-00001-of-00004.safetensors", "llm.model.layers.2.feed_forward.w1.weight": "model-00001-of-00004.safetensors", "llm.model.layers.2.feed_forward.w2.weight": "model-00001-of-00004.safetensors", "llm.model.layers.2.feed_forward.w3.weight": "model-00001-of-00004.safetensors", "llm.model.layers.2.ffn_norm.weight": "model-00001-of-00004.safetensors", "llm.model.layers.20.attention.wo.weight": "model-00003-of-00004.safetensors", "llm.model.layers.20.attention.wqkv.weight": "model-00003-of-00004.safetensors", "llm.model.layers.20.attention_norm.weight": "model-00003-of-00004.safetensors", "llm.model.layers.20.feed_forward.w1.weight": "model-00003-of-00004.safetensors", "llm.model.layers.20.feed_forward.w2.weight": "model-00003-of-00004.safetensors", "llm.model.layers.20.feed_forward.w3.weight": "model-00003-of-00004.safetensors", "llm.model.layers.20.ffn_norm.weight": "model-00003-of-00004.safetensors", "llm.model.layers.21.attention.wo.weight": "model-00003-of-00004.safetensors", "llm.model.layers.21.attention.wqkv.weight": "model-00003-of-00004.safetensors", "llm.model.layers.21.attention_norm.weight": "model-00003-of-00004.safetensors", "llm.model.layers.21.feed_forward.w1.weight": "model-00003-of-00004.safetensors", "llm.model.layers.21.feed_forward.w2.weight": "model-00003-of-00004.safetensors", "llm.model.layers.21.feed_forward.w3.weight": "model-00003-of-00004.safetensors", "llm.model.layers.21.ffn_norm.weight": "model-00003-of-00004.safetensors", "llm.model.layers.22.attention.wo.weight": "model-00003-of-00004.safetensors", "llm.model.layers.22.attention.wqkv.weight": "model-00003-of-00004.safetensors", "llm.model.layers.22.attention_norm.weight": "model-00003-of-00004.safetensors", "llm.model.layers.22.feed_forward.w1.weight": "model-00003-of-00004.safetensors", "llm.model.layers.22.feed_forward.w2.weight": "model-00003-of-00004.safetensors", "llm.model.layers.22.feed_forward.w3.weight": "model-00003-of-00004.safetensors", "llm.model.layers.22.ffn_norm.weight": "model-00003-of-00004.safetensors", "llm.model.layers.23.attention.wo.weight": "model-00003-of-00004.safetensors", "llm.model.layers.23.attention.wqkv.weight": "model-00003-of-00004.safetensors", "llm.model.layers.23.attention_norm.weight": "model-00003-of-00004.safetensors", "llm.model.layers.23.feed_forward.w1.weight": "model-00003-of-00004.safetensors", "llm.model.layers.23.feed_forward.w2.weight": "model-00003-of-00004.safetensors", "llm.model.layers.23.feed_forward.w3.weight": "model-00003-of-00004.safetensors", "llm.model.layers.23.ffn_norm.weight": "model-00003-of-00004.safetensors", "llm.model.layers.24.attention.wo.weight": "model-00003-of-00004.safetensors", "llm.model.layers.24.attention.wqkv.weight": "model-00003-of-00004.safetensors", "llm.model.layers.24.attention_norm.weight": "model-00003-of-00004.safetensors", "llm.model.layers.24.feed_forward.w1.weight": "model-00003-of-00004.safetensors", "llm.model.layers.24.feed_forward.w2.weight": "model-00003-of-00004.safetensors", "llm.model.layers.24.feed_forward.w3.weight": "model-00003-of-00004.safetensors", "llm.model.layers.24.ffn_norm.weight": "model-00003-of-00004.safetensors", "llm.model.layers.25.attention.wo.weight": "model-00003-of-00004.safetensors", "llm.model.layers.25.attention.wqkv.weight": "model-00003-of-00004.safetensors", "llm.model.layers.25.attention_norm.weight": "model-00003-of-00004.safetensors", "llm.model.layers.25.feed_forward.w1.weight": "model-00003-of-00004.safetensors", "llm.model.layers.25.feed_forward.w2.weight": "model-00003-of-00004.safetensors", "llm.model.layers.25.feed_forward.w3.weight": "model-00003-of-00004.safetensors", "llm.model.layers.25.ffn_norm.weight": "model-00003-of-00004.safetensors", "llm.model.layers.26.attention.wo.weight": "model-00003-of-00004.safetensors", "llm.model.layers.26.attention.wqkv.weight": "model-00003-of-00004.safetensors", "llm.model.layers.26.attention_norm.weight": "model-00003-of-00004.safetensors", "llm.model.layers.26.feed_forward.w1.weight": "model-00003-of-00004.safetensors", "llm.model.layers.26.feed_forward.w2.weight": "model-00003-of-00004.safetensors", "llm.model.layers.26.feed_forward.w3.weight": "model-00003-of-00004.safetensors", "llm.model.layers.26.ffn_norm.weight": "model-00003-of-00004.safetensors", "llm.model.layers.27.attention.wo.weight": "model-00003-of-00004.safetensors", "llm.model.layers.27.attention.wqkv.weight": "model-00003-of-00004.safetensors", "llm.model.layers.27.attention_norm.weight": "model-00003-of-00004.safetensors", "llm.model.layers.27.feed_forward.w1.weight": "model-00003-of-00004.safetensors", "llm.model.layers.27.feed_forward.w2.weight": "model-00003-of-00004.safetensors", "llm.model.layers.27.feed_forward.w3.weight": "model-00003-of-00004.safetensors", "llm.model.layers.27.ffn_norm.weight": "model-00003-of-00004.safetensors", "llm.model.layers.28.attention.wo.weight": "model-00003-of-00004.safetensors", "llm.model.layers.28.attention.wqkv.weight": "model-00003-of-00004.safetensors", "llm.model.layers.28.attention_norm.weight": "model-00003-of-00004.safetensors", "llm.model.layers.28.feed_forward.w1.weight": "model-00003-of-00004.safetensors", "llm.model.layers.28.feed_forward.w2.weight": "model-00003-of-00004.safetensors", "llm.model.layers.28.feed_forward.w3.weight": "model-00003-of-00004.safetensors", "llm.model.layers.28.ffn_norm.weight": "model-00003-of-00004.safetensors", "llm.model.layers.29.attention.wo.weight": "model-00003-of-00004.safetensors", "llm.model.layers.29.attention.wqkv.weight": "model-00003-of-00004.safetensors", "llm.model.layers.29.attention_norm.weight": "model-00003-of-00004.safetensors", "llm.model.layers.29.feed_forward.w1.weight": "model-00003-of-00004.safetensors", "llm.model.layers.29.feed_forward.w2.weight": "model-00003-of-00004.safetensors", "llm.model.layers.29.feed_forward.w3.weight": "model-00003-of-00004.safetensors", "llm.model.layers.29.ffn_norm.weight": "model-00003-of-00004.safetensors", "llm.model.layers.3.attention.wo.weight": "model-00001-of-00004.safetensors", "llm.model.layers.3.attention.wqkv.weight": "model-00001-of-00004.safetensors", "llm.model.layers.3.attention_norm.weight": "model-00001-of-00004.safetensors", "llm.model.layers.3.feed_forward.w1.weight": "model-00001-of-00004.safetensors", "llm.model.layers.3.feed_forward.w2.weight": "model-00001-of-00004.safetensors", "llm.model.layers.3.feed_forward.w3.weight": "model-00001-of-00004.safetensors", "llm.model.layers.3.ffn_norm.weight": "model-00001-of-00004.safetensors", "llm.model.layers.30.attention.wo.weight": "model-00003-of-00004.safetensors", "llm.model.layers.30.attention.wqkv.weight": "model-00003-of-00004.safetensors", "llm.model.layers.30.attention_norm.weight": "model-00004-of-00004.safetensors", "llm.model.layers.30.feed_forward.w1.weight": "model-00003-of-00004.safetensors", "llm.model.layers.30.feed_forward.w2.weight": "model-00004-of-00004.safetensors", "llm.model.layers.30.feed_forward.w3.weight": "model-00003-of-00004.safetensors", "llm.model.layers.30.ffn_norm.weight": "model-00004-of-00004.safetensors", "llm.model.layers.31.attention.wo.weight": "model-00004-of-00004.safetensors", "llm.model.layers.31.attention.wqkv.weight": "model-00004-of-00004.safetensors", "llm.model.layers.31.attention_norm.weight": "model-00004-of-00004.safetensors", "llm.model.layers.31.feed_forward.w1.weight": "model-00004-of-00004.safetensors", "llm.model.layers.31.feed_forward.w2.weight": "model-00004-of-00004.safetensors", "llm.model.layers.31.feed_forward.w3.weight": "model-00004-of-00004.safetensors", "llm.model.layers.31.ffn_norm.weight": "model-00004-of-00004.safetensors", "llm.model.layers.4.attention.wo.weight": "model-00001-of-00004.safetensors", "llm.model.layers.4.attention.wqkv.weight": "model-00001-of-00004.safetensors", "llm.model.layers.4.attention_norm.weight": "model-00001-of-00004.safetensors", "llm.model.layers.4.feed_forward.w1.weight": "model-00001-of-00004.safetensors", "llm.model.layers.4.feed_forward.w2.weight": "model-00001-of-00004.safetensors", "llm.model.layers.4.feed_forward.w3.weight": "model-00001-of-00004.safetensors", "llm.model.layers.4.ffn_norm.weight": "model-00001-of-00004.safetensors", "llm.model.layers.5.attention.wo.weight": "model-00001-of-00004.safetensors", "llm.model.layers.5.attention.wqkv.weight": "model-00001-of-00004.safetensors", "llm.model.layers.5.attention_norm.weight": "model-00001-of-00004.safetensors", "llm.model.layers.5.feed_forward.w1.weight": "model-00001-of-00004.safetensors", "llm.model.layers.5.feed_forward.w2.weight": "model-00001-of-00004.safetensors", "llm.model.layers.5.feed_forward.w3.weight": "model-00001-of-00004.safetensors", "llm.model.layers.5.ffn_norm.weight": "model-00001-of-00004.safetensors", "llm.model.layers.6.attention.wo.weight": "model-00001-of-00004.safetensors", "llm.model.layers.6.attention.wqkv.weight": "model-00001-of-00004.safetensors", "llm.model.layers.6.attention_norm.weight": "model-00001-of-00004.safetensors", "llm.model.layers.6.feed_forward.w1.weight": "model-00001-of-00004.safetensors", "llm.model.layers.6.feed_forward.w2.weight": "model-00001-of-00004.safetensors", "llm.model.layers.6.feed_forward.w3.weight": "model-00001-of-00004.safetensors", "llm.model.layers.6.ffn_norm.weight": "model-00001-of-00004.safetensors", "llm.model.layers.7.attention.wo.weight": "model-00001-of-00004.safetensors", "llm.model.layers.7.attention.wqkv.weight": "model-00001-of-00004.safetensors", "llm.model.layers.7.attention_norm.weight": "model-00001-of-00004.safetensors", "llm.model.layers.7.feed_forward.w1.weight": "model-00001-of-00004.safetensors", "llm.model.layers.7.feed_forward.w2.weight": "model-00001-of-00004.safetensors", "llm.model.layers.7.feed_forward.w3.weight": "model-00001-of-00004.safetensors", "llm.model.layers.7.ffn_norm.weight": "model-00001-of-00004.safetensors", "llm.model.layers.8.attention.wo.weight": "model-00001-of-00004.safetensors", "llm.model.layers.8.attention.wqkv.weight": "model-00001-of-00004.safetensors", "llm.model.layers.8.attention_norm.weight": "model-00002-of-00004.safetensors", "llm.model.layers.8.feed_forward.w1.weight": "model-00002-of-00004.safetensors", "llm.model.layers.8.feed_forward.w2.weight": "model-00002-of-00004.safetensors", "llm.model.layers.8.feed_forward.w3.weight": "model-00002-of-00004.safetensors", "llm.model.layers.8.ffn_norm.weight": "model-00002-of-00004.safetensors", "llm.model.layers.9.attention.wo.weight": "model-00002-of-00004.safetensors", "llm.model.layers.9.attention.wqkv.weight": "model-00002-of-00004.safetensors", "llm.model.layers.9.attention_norm.weight": "model-00002-of-00004.safetensors", "llm.model.layers.9.feed_forward.w1.weight": "model-00002-of-00004.safetensors", "llm.model.layers.9.feed_forward.w2.weight": "model-00002-of-00004.safetensors", "llm.model.layers.9.feed_forward.w3.weight": "model-00002-of-00004.safetensors", "llm.model.layers.9.ffn_norm.weight": "model-00002-of-00004.safetensors", "llm.model.norm.weight": "model-00004-of-00004.safetensors", "llm.model.tok_embeddings.weight": "model-00001-of-00004.safetensors", "llm.output.weight": "model-00004-of-00004.safetensors", "vis_encoder.embeddings.class_embedding": "model-00001-of-00004.safetensors", "vis_encoder.embeddings.patch_embedding.bias": "model-00001-of-00004.safetensors", "vis_encoder.embeddings.patch_embedding.weight": "model-00001-of-00004.safetensors", "vis_encoder.embeddings.position_embedding": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.0.attn.proj.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.0.attn.proj.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.0.attn.qkv.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.0.attn.qkv.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.0.ls1": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.0.ls2": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.0.norm1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.0.norm1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.0.norm2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.0.norm2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.1.attn.proj.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.1.attn.proj.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.1.attn.qkv.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.1.attn.qkv.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.1.ls1": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.1.ls2": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.1.norm1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.1.norm1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.1.norm2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.1.norm2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.10.attn.proj.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.10.attn.proj.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.10.attn.qkv.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.10.attn.qkv.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.10.ls1": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.10.ls2": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.10.norm1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.10.norm1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.10.norm2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.10.norm2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.11.attn.proj.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.11.attn.proj.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.11.attn.qkv.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.11.attn.qkv.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.11.ls1": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.11.ls2": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.11.norm1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.11.norm1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.11.norm2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.11.norm2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.12.attn.proj.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.12.attn.proj.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.12.attn.qkv.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.12.attn.qkv.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.12.ls1": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.12.ls2": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.12.norm1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.12.norm1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.12.norm2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.12.norm2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.13.attn.proj.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.13.attn.proj.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.13.attn.qkv.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.13.attn.qkv.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.13.ls1": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.13.ls2": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.13.norm1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.13.norm1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.13.norm2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.13.norm2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.14.attn.proj.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.14.attn.proj.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.14.attn.qkv.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.14.attn.qkv.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.14.ls1": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.14.ls2": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.14.norm1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.14.norm1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.14.norm2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.14.norm2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.15.attn.proj.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.15.attn.proj.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.15.attn.qkv.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.15.attn.qkv.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.15.ls1": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.15.ls2": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.15.norm1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.15.norm1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.15.norm2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.15.norm2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.16.attn.proj.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.16.attn.proj.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.16.attn.qkv.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.16.attn.qkv.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.16.ls1": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.16.ls2": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.16.norm1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.16.norm1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.16.norm2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.16.norm2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.17.attn.proj.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.17.attn.proj.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.17.attn.qkv.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.17.attn.qkv.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.17.ls1": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.17.ls2": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.17.norm1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.17.norm1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.17.norm2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.17.norm2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.18.attn.proj.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.18.attn.proj.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.18.attn.qkv.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.18.attn.qkv.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.18.ls1": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.18.ls2": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.18.norm1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.18.norm1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.18.norm2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.18.norm2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.19.attn.proj.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.19.attn.proj.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.19.attn.qkv.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.19.attn.qkv.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.19.ls1": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.19.ls2": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.19.norm1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.19.norm1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.19.norm2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.19.norm2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.2.attn.proj.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.2.attn.proj.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.2.attn.qkv.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.2.attn.qkv.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.2.ls1": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.2.ls2": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.2.norm1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.2.norm1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.2.norm2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.2.norm2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.20.attn.proj.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.20.attn.proj.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.20.attn.qkv.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.20.attn.qkv.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.20.ls1": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.20.ls2": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.20.norm1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.20.norm1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.20.norm2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.20.norm2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.21.attn.proj.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.21.attn.proj.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.21.attn.qkv.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.21.attn.qkv.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.21.ls1": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.21.ls2": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.21.norm1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.21.norm1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.21.norm2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.21.norm2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.22.attn.proj.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.22.attn.proj.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.22.attn.qkv.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.22.attn.qkv.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.22.ls1": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.22.ls2": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.22.norm1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.22.norm1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.22.norm2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.22.norm2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.23.attn.proj.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.23.attn.proj.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.23.attn.qkv.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.23.attn.qkv.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.23.ls1": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.23.ls2": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.23.norm1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.23.norm1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.23.norm2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.23.norm2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.3.attn.proj.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.3.attn.proj.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.3.attn.qkv.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.3.attn.qkv.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.3.ls1": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.3.ls2": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.3.norm1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.3.norm1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.3.norm2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.3.norm2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.4.attn.proj.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.4.attn.proj.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.4.attn.qkv.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.4.attn.qkv.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.4.ls1": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.4.ls2": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.4.norm1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.4.norm1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.4.norm2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.4.norm2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.5.attn.proj.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.5.attn.proj.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.5.attn.qkv.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.5.attn.qkv.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.5.ls1": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.5.ls2": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.5.norm1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.5.norm1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.5.norm2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.5.norm2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.6.attn.proj.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.6.attn.proj.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.6.attn.qkv.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.6.attn.qkv.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.6.ls1": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.6.ls2": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.6.norm1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.6.norm1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.6.norm2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.6.norm2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.7.attn.proj.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.7.attn.proj.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.7.attn.qkv.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.7.attn.qkv.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.7.ls1": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.7.ls2": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.7.norm1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.7.norm1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.7.norm2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.7.norm2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.8.attn.proj.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.8.attn.proj.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.8.attn.qkv.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.8.attn.qkv.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.8.ls1": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.8.ls2": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.8.norm1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.8.norm1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.8.norm2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.8.norm2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.9.attn.proj.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.9.attn.proj.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.9.attn.qkv.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.9.attn.qkv.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.9.ls1": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.9.ls2": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.9.norm1.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.9.norm1.weight": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.9.norm2.bias": "model-00001-of-00004.safetensors", "vis_encoder.encoder.layers.9.norm2.weight": "model-00001-of-00004.safetensors", "vl_bridge.0.bias": "model-00004-of-00004.safetensors", "vl_bridge.0.weight": "model-00004-of-00004.safetensors", "vl_bridge.1.bias": "model-00004-of-00004.safetensors", "vl_bridge.1.weight": "model-00004-of-00004.safetensors", "vl_bridge.3.bias": "model-00004-of-00004.safetensors", "vl_bridge.3.weight": "model-00004-of-00004.safetensors" } }