diff --git "a/pytorch_model.bin.index.json" "b/pytorch_model.bin.index.json"
new file mode 100644--- /dev/null
+++ "b/pytorch_model.bin.index.json"
@@ -0,0 +1,3256 @@
+{
+  "metadata": {
+    "total_size": 29343704390
+  },
+  "weight_map": {
+    "grounding_dino.backbone.swintransformer.layers.0.blocks.0.attn.proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.0.blocks.0.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.0.blocks.0.attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.0.blocks.0.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.0.blocks.0.attn.relative_position_bias_table": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.0.blocks.0.attn.relative_position_index": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.0.blocks.0.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.0.blocks.0.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.0.blocks.0.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.0.blocks.0.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.0.blocks.0.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.0.blocks.0.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.0.blocks.0.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.0.blocks.0.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.0.blocks.1.attn.proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.0.blocks.1.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.0.blocks.1.attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.0.blocks.1.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.0.blocks.1.attn.relative_position_bias_table": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.0.blocks.1.attn.relative_position_index": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.0.blocks.1.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.0.blocks.1.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.0.blocks.1.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.0.blocks.1.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.0.blocks.1.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.0.blocks.1.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.0.blocks.1.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.0.blocks.1.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.0.downsample.norm.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.0.downsample.norm.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.0.downsample.reduction.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.1.blocks.0.attn.proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.1.blocks.0.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.1.blocks.0.attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.1.blocks.0.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.1.blocks.0.attn.relative_position_bias_table": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.1.blocks.0.attn.relative_position_index": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.1.blocks.0.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.1.blocks.0.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.1.blocks.0.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.1.blocks.0.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.1.blocks.0.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.1.blocks.0.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.1.blocks.0.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.1.blocks.0.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.1.blocks.1.attn.proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.1.blocks.1.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.1.blocks.1.attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.1.blocks.1.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.1.blocks.1.attn.relative_position_bias_table": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.1.blocks.1.attn.relative_position_index": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.1.blocks.1.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.1.blocks.1.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.1.blocks.1.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.1.blocks.1.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.1.blocks.1.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.1.blocks.1.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.1.blocks.1.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.1.blocks.1.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.1.downsample.norm.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.1.downsample.norm.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.1.downsample.reduction.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.0.attn.proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.0.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.0.attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.0.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.0.attn.relative_position_bias_table": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.0.attn.relative_position_index": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.0.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.0.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.0.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.0.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.0.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.0.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.0.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.0.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.1.attn.proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.1.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.1.attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.1.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.1.attn.relative_position_bias_table": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.1.attn.relative_position_index": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.1.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.1.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.1.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.1.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.1.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.1.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.1.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.1.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.2.attn.proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.2.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.2.attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.2.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.2.attn.relative_position_bias_table": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.2.attn.relative_position_index": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.2.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.2.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.2.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.2.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.2.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.2.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.2.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.2.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.3.attn.proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.3.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.3.attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.3.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.3.attn.relative_position_bias_table": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.3.attn.relative_position_index": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.3.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.3.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.3.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.3.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.3.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.3.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.3.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.3.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.4.attn.proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.4.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.4.attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.4.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.4.attn.relative_position_bias_table": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.4.attn.relative_position_index": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.4.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.4.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.4.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.4.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.4.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.4.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.4.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.4.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.5.attn.proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.5.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.5.attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.5.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.5.attn.relative_position_bias_table": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.5.attn.relative_position_index": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.5.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.5.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.5.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.5.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.5.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.5.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.5.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.blocks.5.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.downsample.norm.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.downsample.norm.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.2.downsample.reduction.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.3.blocks.0.attn.proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.3.blocks.0.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.3.blocks.0.attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.3.blocks.0.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.3.blocks.0.attn.relative_position_bias_table": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.3.blocks.0.attn.relative_position_index": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.3.blocks.0.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.3.blocks.0.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.3.blocks.0.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.3.blocks.0.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.3.blocks.0.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.3.blocks.0.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.3.blocks.0.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.3.blocks.0.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.3.blocks.1.attn.proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.3.blocks.1.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.3.blocks.1.attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.3.blocks.1.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.3.blocks.1.attn.relative_position_bias_table": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.3.blocks.1.attn.relative_position_index": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.3.blocks.1.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.3.blocks.1.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.3.blocks.1.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.3.blocks.1.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.3.blocks.1.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.3.blocks.1.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.3.blocks.1.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.layers.3.blocks.1.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.norm3.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.norm3.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.patch_embed.norm.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.patch_embed.norm.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.patch_embed.proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.backbone.swintransformer.patch_embed.proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bbox_embed.0.layers.0.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bbox_embed.0.layers.0.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bbox_embed.0.layers.1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bbox_embed.0.layers.1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bbox_embed.0.layers.2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bbox_embed.0.layers.2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bbox_embed.1.layers.0.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bbox_embed.1.layers.0.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bbox_embed.1.layers.1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bbox_embed.1.layers.1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bbox_embed.1.layers.2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bbox_embed.1.layers.2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bbox_embed.2.layers.0.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bbox_embed.2.layers.0.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bbox_embed.2.layers.1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bbox_embed.2.layers.1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bbox_embed.2.layers.2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bbox_embed.2.layers.2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bbox_embed.3.layers.0.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bbox_embed.3.layers.0.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bbox_embed.3.layers.1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bbox_embed.3.layers.1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bbox_embed.3.layers.2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bbox_embed.3.layers.2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bbox_embed.4.layers.0.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bbox_embed.4.layers.0.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bbox_embed.4.layers.1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bbox_embed.4.layers.1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bbox_embed.4.layers.2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bbox_embed.4.layers.2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bbox_embed.5.layers.0.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bbox_embed.5.layers.0.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bbox_embed.5.layers.1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bbox_embed.5.layers.1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bbox_embed.5.layers.2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bbox_embed.5.layers.2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.embeddings.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.embeddings.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.embeddings.position_embeddings.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.embeddings.token_type_embeddings.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.embeddings.word_embeddings.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.0.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.0.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.0.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.0.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.0.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.0.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.0.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.0.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.0.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.0.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.0.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.0.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.0.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.0.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.0.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.0.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.1.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.1.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.1.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.1.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.1.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.1.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.1.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.1.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.1.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.1.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.1.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.1.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.1.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.1.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.1.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.1.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.10.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.10.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.10.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.10.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.10.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.10.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.10.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.10.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.10.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.10.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.10.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.10.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.10.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.10.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.10.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.10.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.11.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.11.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.11.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.11.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.11.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.11.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.11.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.11.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.11.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.11.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.11.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.11.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.11.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.11.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.11.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.11.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.2.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.2.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.2.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.2.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.2.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.2.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.2.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.2.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.2.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.2.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.2.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.2.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.2.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.2.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.2.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.2.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.3.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.3.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.3.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.3.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.3.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.3.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.3.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.3.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.3.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.3.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.3.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.3.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.3.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.3.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.3.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.3.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.4.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.4.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.4.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.4.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.4.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.4.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.4.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.4.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.4.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.4.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.4.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.4.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.4.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.4.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.4.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.4.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.5.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.5.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.5.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.5.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.5.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.5.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.5.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.5.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.5.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.5.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.5.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.5.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.5.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.5.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.5.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.5.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.6.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.6.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.6.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.6.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.6.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.6.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.6.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.6.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.6.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.6.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.6.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.6.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.6.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.6.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.6.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.6.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.7.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.7.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.7.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.7.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.7.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.7.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.7.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.7.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.7.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.7.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.7.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.7.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.7.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.7.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.7.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.7.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.8.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.8.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.8.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.8.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.8.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.8.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.8.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.8.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.8.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.8.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.8.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.8.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.8.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.8.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.8.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.8.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.9.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.9.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.9.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.9.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.9.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.9.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.9.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.9.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.9.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.9.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.9.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.9.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.9.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.9.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.9.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.encoder.layer.9.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.pooler.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.bert.pooler.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.feat_map.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.feat_map.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.input_proj.0.0.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.input_proj.0.0.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.input_proj.0.1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.input_proj.0.1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.input_proj.1.0.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.input_proj.1.0.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.input_proj.1.1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.input_proj.1.1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.input_proj.2.0.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.input_proj.2.0.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.input_proj.2.1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.input_proj.2.1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.input_proj.3.0.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.input_proj.3.0.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.input_proj.3.1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.input_proj.3.1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.bbox_embed.0.layers.0.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.bbox_embed.0.layers.0.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.bbox_embed.0.layers.1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.bbox_embed.0.layers.1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.bbox_embed.0.layers.2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.bbox_embed.0.layers.2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.bbox_embed.1.layers.0.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.bbox_embed.1.layers.0.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.bbox_embed.1.layers.1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.bbox_embed.1.layers.1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.bbox_embed.1.layers.2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.bbox_embed.1.layers.2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.bbox_embed.2.layers.0.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.bbox_embed.2.layers.0.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.bbox_embed.2.layers.1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.bbox_embed.2.layers.1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.bbox_embed.2.layers.2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.bbox_embed.2.layers.2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.bbox_embed.3.layers.0.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.bbox_embed.3.layers.0.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.bbox_embed.3.layers.1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.bbox_embed.3.layers.1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.bbox_embed.3.layers.2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.bbox_embed.3.layers.2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.bbox_embed.4.layers.0.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.bbox_embed.4.layers.0.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.bbox_embed.4.layers.1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.bbox_embed.4.layers.1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.bbox_embed.4.layers.2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.bbox_embed.4.layers.2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.bbox_embed.5.layers.0.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.bbox_embed.5.layers.0.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.bbox_embed.5.layers.1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.bbox_embed.5.layers.1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.bbox_embed.5.layers.2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.bbox_embed.5.layers.2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.0.ca_text.in_proj_bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.0.ca_text.in_proj_weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.0.ca_text.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.0.ca_text.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.0.catext_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.0.catext_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.0.cross_attn.attention_weights.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.0.cross_attn.attention_weights.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.0.cross_attn.output_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.0.cross_attn.output_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.0.cross_attn.sampling_offsets.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.0.cross_attn.sampling_offsets.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.0.cross_attn.value_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.0.cross_attn.value_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.0.linear1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.0.linear1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.0.linear2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.0.linear2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.0.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.0.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.0.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.0.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.0.norm3.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.0.norm3.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.0.self_attn.in_proj_bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.0.self_attn.in_proj_weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.1.ca_text.in_proj_bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.1.ca_text.in_proj_weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.1.ca_text.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.1.ca_text.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.1.catext_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.1.catext_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.1.cross_attn.attention_weights.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.1.cross_attn.attention_weights.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.1.cross_attn.output_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.1.cross_attn.output_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.1.cross_attn.sampling_offsets.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.1.cross_attn.sampling_offsets.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.1.cross_attn.value_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.1.cross_attn.value_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.1.linear1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.1.linear1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.1.linear2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.1.linear2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.1.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.1.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.1.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.1.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.1.norm3.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.1.norm3.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.1.self_attn.in_proj_bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.1.self_attn.in_proj_weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.2.ca_text.in_proj_bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.2.ca_text.in_proj_weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.2.ca_text.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.2.ca_text.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.2.catext_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.2.catext_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.2.cross_attn.attention_weights.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.2.cross_attn.attention_weights.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.2.cross_attn.output_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.2.cross_attn.output_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.2.cross_attn.sampling_offsets.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.2.cross_attn.sampling_offsets.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.2.cross_attn.value_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.2.cross_attn.value_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.2.linear1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.2.linear1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.2.linear2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.2.linear2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.2.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.2.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.2.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.2.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.2.norm3.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.2.norm3.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.2.self_attn.in_proj_bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.2.self_attn.in_proj_weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.3.ca_text.in_proj_bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.3.ca_text.in_proj_weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.3.ca_text.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.3.ca_text.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.3.catext_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.3.catext_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.3.cross_attn.attention_weights.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.3.cross_attn.attention_weights.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.3.cross_attn.output_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.3.cross_attn.output_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.3.cross_attn.sampling_offsets.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.3.cross_attn.sampling_offsets.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.3.cross_attn.value_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.3.cross_attn.value_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.3.linear1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.3.linear1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.3.linear2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.3.linear2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.3.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.3.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.3.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.3.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.3.norm3.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.3.norm3.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.3.self_attn.in_proj_bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.3.self_attn.in_proj_weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.4.ca_text.in_proj_bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.4.ca_text.in_proj_weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.4.ca_text.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.4.ca_text.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.4.catext_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.4.catext_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.4.cross_attn.attention_weights.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.4.cross_attn.attention_weights.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.4.cross_attn.output_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.4.cross_attn.output_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.4.cross_attn.sampling_offsets.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.4.cross_attn.sampling_offsets.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.4.cross_attn.value_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.4.cross_attn.value_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.4.linear1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.4.linear1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.4.linear2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.4.linear2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.4.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.4.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.4.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.4.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.4.norm3.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.4.norm3.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.4.self_attn.in_proj_bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.4.self_attn.in_proj_weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.5.ca_text.in_proj_bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.5.ca_text.in_proj_weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.5.ca_text.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.5.ca_text.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.5.catext_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.5.catext_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.5.cross_attn.attention_weights.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.5.cross_attn.attention_weights.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.5.cross_attn.output_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.5.cross_attn.output_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.5.cross_attn.sampling_offsets.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.5.cross_attn.sampling_offsets.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.5.cross_attn.value_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.5.cross_attn.value_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.5.linear1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.5.linear1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.5.linear2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.5.linear2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.5.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.5.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.5.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.5.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.5.norm3.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.5.norm3.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.5.self_attn.in_proj_bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.5.self_attn.in_proj_weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.norm.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.norm.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.ref_point_head.layers.0.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.ref_point_head.layers.0.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.ref_point_head.layers.1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.decoder.ref_point_head.layers.1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.enc_out_bbox_embed.layers.0.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.enc_out_bbox_embed.layers.0.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.enc_out_bbox_embed.layers.1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.enc_out_bbox_embed.layers.1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.enc_out_bbox_embed.layers.2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.enc_out_bbox_embed.layers.2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.enc_output.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.enc_output.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.enc_output_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.enc_output_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.0.attn.l_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.0.attn.l_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.0.attn.out_l_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.0.attn.out_l_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.0.attn.out_v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.0.attn.out_v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.0.attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.0.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.0.attn.values_l_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.0.attn.values_l_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.0.attn.values_v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.0.attn.values_v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.0.layer_norm_l.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.0.layer_norm_l.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.0.layer_norm_v.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.0.layer_norm_v.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.0.temp_l": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.0.temp_v": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.1.attn.l_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.1.attn.l_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.1.attn.out_l_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.1.attn.out_l_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.1.attn.out_v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.1.attn.out_v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.1.attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.1.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.1.attn.values_l_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.1.attn.values_l_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.1.attn.values_v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.1.attn.values_v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.1.layer_norm_l.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.1.layer_norm_l.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.1.layer_norm_v.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.1.layer_norm_v.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.1.temp_l": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.1.temp_v": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.2.attn.l_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.2.attn.l_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.2.attn.out_l_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.2.attn.out_l_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.2.attn.out_v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.2.attn.out_v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.2.attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.2.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.2.attn.values_l_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.2.attn.values_l_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.2.attn.values_v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.2.attn.values_v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.2.layer_norm_l.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.2.layer_norm_l.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.2.layer_norm_v.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.2.layer_norm_v.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.2.temp_l": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.2.temp_v": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.3.attn.l_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.3.attn.l_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.3.attn.out_l_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.3.attn.out_l_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.3.attn.out_v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.3.attn.out_v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.3.attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.3.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.3.attn.values_l_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.3.attn.values_l_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.3.attn.values_v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.3.attn.values_v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.3.layer_norm_l.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.3.layer_norm_l.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.3.layer_norm_v.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.3.layer_norm_v.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.3.temp_l": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.3.temp_v": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.4.attn.l_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.4.attn.l_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.4.attn.out_l_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.4.attn.out_l_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.4.attn.out_v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.4.attn.out_v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.4.attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.4.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.4.attn.values_l_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.4.attn.values_l_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.4.attn.values_v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.4.attn.values_v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.4.layer_norm_l.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.4.layer_norm_l.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.4.layer_norm_v.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.4.layer_norm_v.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.4.temp_l": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.4.temp_v": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.5.attn.l_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.5.attn.l_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.5.attn.out_l_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.5.attn.out_l_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.5.attn.out_v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.5.attn.out_v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.5.attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.5.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.5.attn.values_l_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.5.attn.values_l_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.5.attn.values_v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.5.attn.values_v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.5.layer_norm_l.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.5.layer_norm_l.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.5.layer_norm_v.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.5.layer_norm_v.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.5.temp_l": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.fusion_layers.5.temp_v": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.0.linear1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.0.linear1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.0.linear2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.0.linear2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.0.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.0.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.0.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.0.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.0.self_attn.attention_weights.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.0.self_attn.attention_weights.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.0.self_attn.output_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.0.self_attn.output_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.0.self_attn.sampling_offsets.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.0.self_attn.sampling_offsets.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.0.self_attn.value_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.0.self_attn.value_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.1.linear1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.1.linear1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.1.linear2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.1.linear2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.1.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.1.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.1.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.1.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.1.self_attn.attention_weights.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.1.self_attn.attention_weights.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.1.self_attn.output_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.1.self_attn.output_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.1.self_attn.sampling_offsets.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.1.self_attn.sampling_offsets.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.1.self_attn.value_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.1.self_attn.value_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.2.linear1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.2.linear1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.2.linear2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.2.linear2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.2.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.2.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.2.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.2.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.2.self_attn.attention_weights.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.2.self_attn.attention_weights.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.2.self_attn.output_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.2.self_attn.output_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.2.self_attn.sampling_offsets.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.2.self_attn.sampling_offsets.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.2.self_attn.value_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.2.self_attn.value_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.3.linear1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.3.linear1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.3.linear2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.3.linear2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.3.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.3.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.3.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.3.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.3.self_attn.attention_weights.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.3.self_attn.attention_weights.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.3.self_attn.output_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.3.self_attn.output_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.3.self_attn.sampling_offsets.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.3.self_attn.sampling_offsets.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.3.self_attn.value_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.3.self_attn.value_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.4.linear1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.4.linear1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.4.linear2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.4.linear2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.4.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.4.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.4.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.4.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.4.self_attn.attention_weights.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.4.self_attn.attention_weights.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.4.self_attn.output_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.4.self_attn.output_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.4.self_attn.sampling_offsets.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.4.self_attn.sampling_offsets.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.4.self_attn.value_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.4.self_attn.value_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.5.linear1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.5.linear1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.5.linear2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.5.linear2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.5.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.5.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.5.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.5.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.5.self_attn.attention_weights.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.5.self_attn.attention_weights.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.5.self_attn.output_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.5.self_attn.output_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.5.self_attn.sampling_offsets.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.5.self_attn.sampling_offsets.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.5.self_attn.value_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.layers.5.self_attn.value_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.0.linear1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.0.linear1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.0.linear2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.0.linear2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.0.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.0.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.0.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.0.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.0.self_attn.in_proj_bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.0.self_attn.in_proj_weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.0.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.0.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.1.linear1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.1.linear1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.1.linear2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.1.linear2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.1.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.1.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.1.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.1.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.1.self_attn.in_proj_bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.1.self_attn.in_proj_weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.1.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.1.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.2.linear1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.2.linear1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.2.linear2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.2.linear2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.2.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.2.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.2.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.2.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.2.self_attn.in_proj_bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.2.self_attn.in_proj_weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.2.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.2.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.3.linear1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.3.linear1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.3.linear2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.3.linear2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.3.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.3.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.3.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.3.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.3.self_attn.in_proj_bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.3.self_attn.in_proj_weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.3.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.3.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.4.linear1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.4.linear1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.4.linear2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.4.linear2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.4.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.4.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.4.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.4.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.4.self_attn.in_proj_bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.4.self_attn.in_proj_weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.4.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.4.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.5.linear1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.5.linear1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.5.linear2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.5.linear2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.5.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.5.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.5.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.5.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.5.self_attn.in_proj_bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.5.self_attn.in_proj_weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.5.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.encoder.text_layers.5.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.level_embed": "pytorch_model-00001-of-00003.bin",
+    "grounding_dino.transformer.tgt_embed.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.lm_head.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.32.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.32.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.33.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.33.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.33.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.34.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.34.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.34.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.34.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.34.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.34.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.34.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.35.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.35.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.35.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.35.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.35.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.35.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.35.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.36.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.36.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.36.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.36.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.36.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.36.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.36.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.36.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.37.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.37.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.37.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.37.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.37.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.37.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.37.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.37.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.37.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.38.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.38.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.38.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.38.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.38.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.38.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.38.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.38.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.39.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.39.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.39.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.39.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.39.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.39.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.39.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.39.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.39.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.model.norm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_projection.bias": "pytorch_model-00001-of-00003.bin",
+    "language_projection.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.embeddings.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.embeddings.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.embeddings.position_embeddings.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.embeddings.position_ids": "pytorch_model-00001-of-00003.bin",
+    "qformer.embeddings.word_embeddings.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.attention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.attention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.attention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.attention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.attention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.attention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.crossattention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.crossattention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.crossattention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.crossattention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.crossattention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.crossattention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.detection_crossattention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.detection_crossattention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.detection_crossattention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.detection_crossattention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.detection_crossattention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.detection_crossattention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.detection_crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.detection_crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.detection_crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.detection_crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.intermediate_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.intermediate_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.output_query.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.output_query.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.output_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.output_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.attention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.attention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.attention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.attention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.attention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.attention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.intermediate_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.intermediate_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.output_query.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.output_query.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.output_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.output_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.attention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.attention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.attention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.attention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.attention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.attention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.crossattention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.crossattention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.crossattention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.crossattention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.crossattention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.crossattention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.detection_crossattention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.detection_crossattention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.detection_crossattention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.detection_crossattention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.detection_crossattention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.detection_crossattention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.detection_crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.detection_crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.detection_crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.detection_crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.intermediate_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.intermediate_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.output_query.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.output_query.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.output_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.output_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.attention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.attention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.attention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.attention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.attention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.attention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.intermediate_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.intermediate_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.output_query.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.output_query.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.output_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.output_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.attention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.attention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.attention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.attention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.attention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.attention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.crossattention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.crossattention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.crossattention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.crossattention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.crossattention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.crossattention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.detection_crossattention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.detection_crossattention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.detection_crossattention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.detection_crossattention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.detection_crossattention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.detection_crossattention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.detection_crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.detection_crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.detection_crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.detection_crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.intermediate_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.intermediate_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.output_query.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.output_query.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.output_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.output_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.attention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.attention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.attention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.attention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.attention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.attention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.intermediate_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.intermediate_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.output_query.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.output_query.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.output_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.output_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.attention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.attention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.attention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.attention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.attention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.attention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.crossattention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.crossattention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.crossattention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.crossattention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.crossattention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.crossattention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.detection_crossattention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.detection_crossattention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.detection_crossattention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.detection_crossattention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.detection_crossattention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.detection_crossattention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.detection_crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.detection_crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.detection_crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.detection_crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.intermediate_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.intermediate_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.output_query.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.output_query.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.output_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.output_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.attention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.attention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.attention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.attention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.attention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.attention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.intermediate_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.intermediate_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.output_query.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.output_query.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.output_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.output_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.attention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.attention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.attention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.attention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.attention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.attention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.crossattention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.crossattention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.crossattention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.crossattention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.crossattention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.crossattention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.detection_crossattention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.detection_crossattention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.detection_crossattention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.detection_crossattention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.detection_crossattention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.detection_crossattention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.detection_crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.detection_crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.detection_crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.detection_crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.intermediate_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.intermediate_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.output_query.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.output_query.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.output_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.output_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.attention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.attention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.attention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.attention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.attention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.attention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.intermediate_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.intermediate_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.output_query.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.output_query.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.output_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.output_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.attention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.attention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.attention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.attention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.attention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.attention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.crossattention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.crossattention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.crossattention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.crossattention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.crossattention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.crossattention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.detection_crossattention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.detection_crossattention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.detection_crossattention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.detection_crossattention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.detection_crossattention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.detection_crossattention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.detection_crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.detection_crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.detection_crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.detection_crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.intermediate_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.intermediate_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.output_query.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.output_query.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.output_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.output_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.attention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.attention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.attention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.attention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.attention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.attention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.intermediate_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.intermediate_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.output_query.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.output_query.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.output_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.output_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "query_tokens": "pytorch_model-00001-of-00003.bin",
+    "ram.fc.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.fc.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.image_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.image_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.label_embed": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.embeddings.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.embeddings.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.embeddings.position_embeddings.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.embeddings.position_ids": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.embeddings.word_embeddings.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.0.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.0.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.0.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.0.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.0.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.0.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.0.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.0.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.0.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.0.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.0.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.0.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.0.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.0.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.0.crossattention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.0.crossattention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.0.crossattention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.0.crossattention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.0.crossattention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.0.crossattention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.0.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.0.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.0.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.0.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.0.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.0.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.1.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.1.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.1.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.1.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.1.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.1.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.1.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.1.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.1.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.1.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.1.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.1.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.1.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.1.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.1.crossattention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.1.crossattention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.1.crossattention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.1.crossattention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.1.crossattention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.1.crossattention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.1.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.1.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.1.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.1.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.1.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.1.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.10.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.10.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.10.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.10.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.10.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.10.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.10.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.10.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.10.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.10.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.10.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.10.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.10.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.10.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.10.crossattention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.10.crossattention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.10.crossattention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.10.crossattention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.10.crossattention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.10.crossattention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.10.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.10.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.10.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.10.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.10.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.10.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.11.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.11.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.11.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.11.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.11.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.11.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.11.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.11.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.11.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.11.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.11.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.11.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.11.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.11.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.11.crossattention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.11.crossattention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.11.crossattention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.11.crossattention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.11.crossattention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.11.crossattention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.11.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.11.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.11.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.11.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.11.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.11.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.2.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.2.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.2.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.2.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.2.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.2.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.2.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.2.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.2.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.2.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.2.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.2.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.2.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.2.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.2.crossattention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.2.crossattention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.2.crossattention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.2.crossattention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.2.crossattention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.2.crossattention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.2.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.2.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.2.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.2.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.2.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.2.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.3.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.3.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.3.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.3.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.3.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.3.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.3.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.3.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.3.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.3.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.3.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.3.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.3.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.3.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.3.crossattention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.3.crossattention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.3.crossattention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.3.crossattention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.3.crossattention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.3.crossattention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.3.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.3.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.3.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.3.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.3.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.3.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.4.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.4.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.4.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.4.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.4.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.4.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.4.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.4.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.4.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.4.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.4.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.4.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.4.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.4.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.4.crossattention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.4.crossattention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.4.crossattention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.4.crossattention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.4.crossattention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.4.crossattention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.4.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.4.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.4.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.4.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.4.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.4.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.5.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.5.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.5.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.5.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.5.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.5.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.5.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.5.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.5.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.5.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.5.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.5.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.5.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.5.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.5.crossattention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.5.crossattention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.5.crossattention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.5.crossattention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.5.crossattention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.5.crossattention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.5.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.5.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.5.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.5.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.5.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.5.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.6.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.6.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.6.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.6.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.6.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.6.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.6.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.6.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.6.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.6.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.6.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.6.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.6.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.6.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.6.crossattention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.6.crossattention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.6.crossattention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.6.crossattention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.6.crossattention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.6.crossattention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.6.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.6.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.6.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.6.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.6.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.6.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.7.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.7.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.7.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.7.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.7.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.7.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.7.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.7.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.7.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.7.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.7.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.7.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.7.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.7.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.7.crossattention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.7.crossattention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.7.crossattention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.7.crossattention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.7.crossattention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.7.crossattention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.7.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.7.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.7.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.7.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.7.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.7.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.8.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.8.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.8.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.8.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.8.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.8.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.8.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.8.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.8.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.8.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.8.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.8.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.8.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.8.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.8.crossattention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.8.crossattention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.8.crossattention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.8.crossattention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.8.crossattention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.8.crossattention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.8.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.8.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.8.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.8.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.8.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.8.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.9.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.9.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.9.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.9.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.9.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.9.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.9.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.9.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.9.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.9.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.9.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.9.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.9.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.9.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.9.crossattention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.9.crossattention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.9.crossattention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.9.crossattention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.9.crossattention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.9.crossattention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.9.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.9.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.9.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.9.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.9.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tag_encoder.encoder.layer.9.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tagging_head.encoder.layer.0.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tagging_head.encoder.layer.0.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tagging_head.encoder.layer.0.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tagging_head.encoder.layer.0.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tagging_head.encoder.layer.0.crossattention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tagging_head.encoder.layer.0.crossattention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tagging_head.encoder.layer.0.crossattention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tagging_head.encoder.layer.0.crossattention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tagging_head.encoder.layer.0.crossattention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tagging_head.encoder.layer.0.crossattention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tagging_head.encoder.layer.0.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tagging_head.encoder.layer.0.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tagging_head.encoder.layer.0.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tagging_head.encoder.layer.0.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tagging_head.encoder.layer.0.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tagging_head.encoder.layer.0.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tagging_head.encoder.layer.1.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tagging_head.encoder.layer.1.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tagging_head.encoder.layer.1.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tagging_head.encoder.layer.1.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tagging_head.encoder.layer.1.crossattention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tagging_head.encoder.layer.1.crossattention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tagging_head.encoder.layer.1.crossattention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tagging_head.encoder.layer.1.crossattention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tagging_head.encoder.layer.1.crossattention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tagging_head.encoder.layer.1.crossattention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tagging_head.encoder.layer.1.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tagging_head.encoder.layer.1.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tagging_head.encoder.layer.1.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tagging_head.encoder.layer.1.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.tagging_head.encoder.layer.1.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.tagging_head.encoder.layer.1.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.embeddings.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.embeddings.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.embeddings.position_embeddings.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.embeddings.position_ids": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.embeddings.word_embeddings.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.0.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.0.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.0.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.0.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.0.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.0.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.0.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.0.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.0.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.0.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.0.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.0.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.0.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.0.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.0.crossattention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.0.crossattention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.0.crossattention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.0.crossattention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.0.crossattention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.0.crossattention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.0.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.0.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.0.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.0.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.0.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.0.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.1.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.1.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.1.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.1.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.1.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.1.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.1.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.1.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.1.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.1.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.1.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.1.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.1.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.1.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.1.crossattention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.1.crossattention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.1.crossattention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.1.crossattention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.1.crossattention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.1.crossattention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.1.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.1.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.1.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.1.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.1.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.1.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.10.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.10.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.10.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.10.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.10.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.10.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.10.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.10.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.10.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.10.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.10.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.10.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.10.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.10.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.10.crossattention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.10.crossattention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.10.crossattention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.10.crossattention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.10.crossattention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.10.crossattention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.10.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.10.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.10.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.10.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.10.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.10.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.11.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.11.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.11.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.11.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.11.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.11.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.11.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.11.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.11.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.11.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.11.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.11.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.11.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.11.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.11.crossattention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.11.crossattention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.11.crossattention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.11.crossattention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.11.crossattention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.11.crossattention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.11.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.11.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.11.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.11.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.11.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.11.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.2.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.2.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.2.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.2.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.2.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.2.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.2.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.2.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.2.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.2.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.2.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.2.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.2.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.2.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.2.crossattention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.2.crossattention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.2.crossattention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.2.crossattention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.2.crossattention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.2.crossattention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.2.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.2.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.2.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.2.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.2.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.2.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.3.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.3.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.3.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.3.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.3.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.3.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.3.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.3.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.3.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.3.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.3.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.3.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.3.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.3.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.3.crossattention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.3.crossattention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.3.crossattention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.3.crossattention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.3.crossattention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.3.crossattention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.3.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.3.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.3.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.3.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.3.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.3.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.4.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.4.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.4.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.4.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.4.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.4.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.4.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.4.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.4.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.4.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.4.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.4.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.4.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.4.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.4.crossattention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.4.crossattention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.4.crossattention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.4.crossattention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.4.crossattention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.4.crossattention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.4.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.4.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.4.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.4.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.4.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.4.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.5.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.5.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.5.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.5.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.5.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.5.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.5.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.5.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.5.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.5.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.5.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.5.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.5.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.5.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.5.crossattention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.5.crossattention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.5.crossattention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.5.crossattention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.5.crossattention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.5.crossattention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.5.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.5.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.5.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.5.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.5.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.5.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.6.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.6.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.6.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.6.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.6.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.6.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.6.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.6.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.6.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.6.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.6.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.6.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.6.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.6.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.6.crossattention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.6.crossattention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.6.crossattention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.6.crossattention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.6.crossattention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.6.crossattention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.6.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.6.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.6.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.6.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.6.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.6.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.7.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.7.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.7.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.7.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.7.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.7.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.7.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.7.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.7.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.7.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.7.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.7.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.7.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.7.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.7.crossattention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.7.crossattention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.7.crossattention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.7.crossattention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.7.crossattention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.7.crossattention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.7.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.7.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.7.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.7.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.7.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.7.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.8.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.8.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.8.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.8.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.8.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.8.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.8.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.8.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.8.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.8.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.8.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.8.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.8.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.8.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.8.crossattention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.8.crossattention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.8.crossattention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.8.crossattention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.8.crossattention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.8.crossattention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.8.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.8.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.8.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.8.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.8.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.8.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.9.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.9.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.9.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.9.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.9.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.9.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.9.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.9.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.9.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.9.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.9.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.9.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.9.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.9.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.9.crossattention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.9.crossattention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.9.crossattention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.9.crossattention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.9.crossattention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.9.crossattention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.9.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.9.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.9.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.9.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.9.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.bert.encoder.layer.9.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.cls.predictions.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.cls.predictions.decoder.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.cls.predictions.decoder.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.cls.predictions.transform.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.cls.predictions.transform.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.cls.predictions.transform.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.text_decoder.cls.predictions.transform.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.0.blocks.0.attn.proj.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.0.blocks.0.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.0.blocks.0.attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.0.blocks.0.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.0.blocks.0.attn.relative_position_bias_table": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.0.blocks.0.attn.relative_position_index": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.0.blocks.0.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.0.blocks.0.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.0.blocks.0.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.0.blocks.0.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.0.blocks.0.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.0.blocks.0.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.0.blocks.0.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.0.blocks.0.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.0.blocks.1.attn.proj.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.0.blocks.1.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.0.blocks.1.attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.0.blocks.1.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.0.blocks.1.attn.relative_position_bias_table": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.0.blocks.1.attn.relative_position_index": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.0.blocks.1.attn_mask": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.0.blocks.1.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.0.blocks.1.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.0.blocks.1.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.0.blocks.1.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.0.blocks.1.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.0.blocks.1.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.0.blocks.1.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.0.blocks.1.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.0.downsample.norm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.0.downsample.norm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.0.downsample.reduction.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.1.blocks.0.attn.proj.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.1.blocks.0.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.1.blocks.0.attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.1.blocks.0.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.1.blocks.0.attn.relative_position_bias_table": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.1.blocks.0.attn.relative_position_index": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.1.blocks.0.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.1.blocks.0.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.1.blocks.0.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.1.blocks.0.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.1.blocks.0.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.1.blocks.0.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.1.blocks.0.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.1.blocks.0.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.1.blocks.1.attn.proj.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.1.blocks.1.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.1.blocks.1.attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.1.blocks.1.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.1.blocks.1.attn.relative_position_bias_table": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.1.blocks.1.attn.relative_position_index": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.1.blocks.1.attn_mask": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.1.blocks.1.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.1.blocks.1.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.1.blocks.1.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.1.blocks.1.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.1.blocks.1.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.1.blocks.1.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.1.blocks.1.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.1.blocks.1.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.1.downsample.norm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.1.downsample.norm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.1.downsample.reduction.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.0.attn.proj.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.0.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.0.attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.0.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.0.attn.relative_position_bias_table": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.0.attn.relative_position_index": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.0.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.0.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.0.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.0.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.0.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.0.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.0.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.0.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.1.attn.proj.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.1.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.1.attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.1.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.1.attn.relative_position_bias_table": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.1.attn.relative_position_index": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.1.attn_mask": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.1.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.1.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.1.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.1.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.1.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.1.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.1.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.1.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.10.attn.proj.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.10.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.10.attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.10.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.10.attn.relative_position_bias_table": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.10.attn.relative_position_index": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.10.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.10.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.10.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.10.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.10.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.10.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.10.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.10.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.11.attn.proj.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.11.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.11.attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.11.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.11.attn.relative_position_bias_table": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.11.attn.relative_position_index": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.11.attn_mask": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.11.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.11.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.11.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.11.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.11.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.11.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.11.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.11.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.12.attn.proj.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.12.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.12.attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.12.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.12.attn.relative_position_bias_table": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.12.attn.relative_position_index": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.12.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.12.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.12.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.12.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.12.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.12.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.12.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.12.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.13.attn.proj.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.13.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.13.attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.13.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.13.attn.relative_position_bias_table": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.13.attn.relative_position_index": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.13.attn_mask": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.13.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.13.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.13.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.13.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.13.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.13.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.13.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.13.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.14.attn.proj.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.14.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.14.attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.14.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.14.attn.relative_position_bias_table": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.14.attn.relative_position_index": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.14.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.14.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.14.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.14.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.14.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.14.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.14.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.14.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.15.attn.proj.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.15.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.15.attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.15.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.15.attn.relative_position_bias_table": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.15.attn.relative_position_index": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.15.attn_mask": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.15.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.15.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.15.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.15.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.15.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.15.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.15.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.15.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.16.attn.proj.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.16.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.16.attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.16.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.16.attn.relative_position_bias_table": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.16.attn.relative_position_index": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.16.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.16.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.16.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.16.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.16.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.16.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.16.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.16.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.17.attn.proj.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.17.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.17.attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.17.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.17.attn.relative_position_bias_table": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.17.attn.relative_position_index": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.17.attn_mask": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.17.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.17.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.17.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.17.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.17.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.17.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.17.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.17.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.2.attn.proj.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.2.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.2.attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.2.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.2.attn.relative_position_bias_table": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.2.attn.relative_position_index": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.2.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.2.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.2.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.2.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.2.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.2.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.2.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.2.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.3.attn.proj.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.3.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.3.attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.3.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.3.attn.relative_position_bias_table": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.3.attn.relative_position_index": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.3.attn_mask": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.3.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.3.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.3.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.3.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.3.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.3.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.3.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.3.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.4.attn.proj.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.4.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.4.attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.4.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.4.attn.relative_position_bias_table": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.4.attn.relative_position_index": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.4.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.4.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.4.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.4.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.4.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.4.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.4.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.4.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.5.attn.proj.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.5.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.5.attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.5.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.5.attn.relative_position_bias_table": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.5.attn.relative_position_index": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.5.attn_mask": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.5.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.5.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.5.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.5.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.5.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.5.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.5.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.5.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.6.attn.proj.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.6.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.6.attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.6.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.6.attn.relative_position_bias_table": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.6.attn.relative_position_index": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.6.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.6.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.6.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.6.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.6.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.6.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.6.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.6.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.7.attn.proj.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.7.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.7.attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.7.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.7.attn.relative_position_bias_table": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.7.attn.relative_position_index": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.7.attn_mask": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.7.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.7.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.7.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.7.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.7.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.7.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.7.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.7.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.8.attn.proj.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.8.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.8.attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.8.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.8.attn.relative_position_bias_table": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.8.attn.relative_position_index": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.8.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.8.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.8.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.8.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.8.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.8.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.8.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.8.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.9.attn.proj.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.9.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.9.attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.9.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.9.attn.relative_position_bias_table": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.9.attn.relative_position_index": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.9.attn_mask": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.9.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.9.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.9.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.9.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.9.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.9.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.9.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.blocks.9.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.downsample.norm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.downsample.norm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.2.downsample.reduction.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.3.blocks.0.attn.proj.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.3.blocks.0.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.3.blocks.0.attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.3.blocks.0.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.3.blocks.0.attn.relative_position_bias_table": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.3.blocks.0.attn.relative_position_index": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.3.blocks.0.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.3.blocks.0.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.3.blocks.0.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.3.blocks.0.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.3.blocks.0.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.3.blocks.0.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.3.blocks.0.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.3.blocks.0.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.3.blocks.1.attn.proj.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.3.blocks.1.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.3.blocks.1.attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.3.blocks.1.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.3.blocks.1.attn.relative_position_bias_table": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.3.blocks.1.attn.relative_position_index": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.3.blocks.1.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.3.blocks.1.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.3.blocks.1.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.3.blocks.1.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.3.blocks.1.norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.3.blocks.1.norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.3.blocks.1.norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.layers.3.blocks.1.norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.norm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.norm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.patch_embed.norm.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.patch_embed.norm.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.patch_embed.proj.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.visual_encoder.patch_embed.proj.weight": "pytorch_model-00001-of-00003.bin",
+    "ram.wordvec_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "ram.wordvec_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.embeddings.class_embedding": "pytorch_model-00001-of-00003.bin",
+    "vision_model.embeddings.patch_embedding.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.embeddings.patch_embedding.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.embeddings.position_embedding": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.0.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.0.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.0.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.0.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.1.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.1.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.1.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.1.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.10.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.10.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.10.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.10.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.11.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.11.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.11.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.11.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.12.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.12.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.12.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.12.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.13.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.13.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.13.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.13.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.14.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.14.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.14.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.14.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.15.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.15.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.15.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.15.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.16.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.16.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.16.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.16.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.17.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.17.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.17.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.17.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.18.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.18.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.18.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.18.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.19.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.19.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.19.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.19.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.2.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.2.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.2.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.2.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.20.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.20.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.20.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.20.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.21.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.21.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.21.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.21.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.22.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.22.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.22.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.22.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.23.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.23.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.23.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.23.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.24.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.24.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.24.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.24.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.24.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.24.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.24.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.24.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.24.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.24.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.24.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.24.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.25.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.25.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.25.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.25.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.25.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.25.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.25.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.25.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.25.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.25.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.25.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.25.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.26.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.26.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.26.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.26.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.26.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.26.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.26.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.26.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.26.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.26.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.26.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.26.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.27.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.27.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.27.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.27.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.27.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.27.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.27.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.27.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.27.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.27.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.27.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.27.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.28.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.28.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.28.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.28.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.28.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.28.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.28.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.28.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.28.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.28.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.28.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.28.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.29.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.29.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.29.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.29.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.29.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.29.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.29.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.29.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.29.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.29.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.29.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.29.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.3.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.3.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.3.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.3.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.30.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.30.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.30.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.30.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.30.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.30.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.30.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.30.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.30.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.30.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.30.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.30.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.31.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.31.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.31.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.31.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.31.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.31.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.31.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.31.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.31.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.31.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.31.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.31.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.32.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.32.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.32.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.32.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.32.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.32.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.32.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.32.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.32.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.32.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.32.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.32.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.33.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.33.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.33.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.33.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.33.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.33.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.33.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.33.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.33.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.33.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.33.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.33.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.34.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.34.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.34.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.34.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.34.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.34.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.34.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.34.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.34.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.34.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.34.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.34.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.35.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.35.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.35.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.35.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.35.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.35.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.35.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.35.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.35.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.35.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.35.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.35.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.36.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.36.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.36.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.36.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.36.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.36.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.36.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.36.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.36.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.36.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.36.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.36.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.37.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.37.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.37.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.37.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.37.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.37.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.37.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.37.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.37.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.37.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.37.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.37.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.38.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.38.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.38.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.38.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.38.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.38.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.38.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.38.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.38.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.38.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.38.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.38.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.4.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.4.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.4.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.4.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.5.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.5.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.5.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.5.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.6.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.6.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.6.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.6.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.7.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.7.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.7.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.7.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.8.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.8.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.8.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.8.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.9.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.9.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.9.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.9.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.post_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.post_layernorm.weight": "pytorch_model-00001-of-00003.bin"
+  }
+}