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 +1,4749 @@
+{
+  "metadata": {
+    "total_size": 18745625996
+  },
+  "weight_map": {
+    "emb_embeddings_det.weight": "pytorch_model-00002-of-00002.bin",
+    "emb_embeddings_edit.weight": "pytorch_model-00002-of-00002.bin",
+    "emb_embeddings_gen.weight": "pytorch_model-00002-of-00002.bin",
+    "emb_embeddings_pose.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.bbox_embed.0.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.bbox_embed.0.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.bbox_embed.0.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.bbox_embed.0.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.bbox_embed.0.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.bbox_embed.0.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.bbox_embed.1.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.bbox_embed.1.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.bbox_embed.1.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.bbox_embed.1.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.bbox_embed.1.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.bbox_embed.1.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.bbox_embed.2.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.bbox_embed.2.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.bbox_embed.2.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.bbox_embed.2.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.bbox_embed.2.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.bbox_embed.2.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.bbox_embed.3.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.bbox_embed.3.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.bbox_embed.3.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.bbox_embed.3.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.bbox_embed.3.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.bbox_embed.3.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.bbox_embed.4.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.bbox_embed.4.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.bbox_embed.4.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.bbox_embed.4.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.bbox_embed.4.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.bbox_embed.4.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.bbox_embed.5.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.bbox_embed.5.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.bbox_embed.5.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.bbox_embed.5.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.bbox_embed.5.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.bbox_embed.5.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.mask_embed.0.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.mask_embed.0.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.mask_embed.0.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.mask_embed.0.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.mask_embed.0.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.mask_embed.0.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.mask_embed.1.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.mask_embed.1.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.mask_embed.1.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.mask_embed.1.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.mask_embed.1.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.mask_embed.1.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.mask_embed.2.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.mask_embed.2.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.mask_embed.2.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.mask_embed.2.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.mask_embed.2.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.mask_embed.2.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.mask_embed.3.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.mask_embed.3.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.mask_embed.3.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.mask_embed.3.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.mask_embed.3.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.mask_embed.3.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.mask_embed.4.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.mask_embed.4.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.mask_embed.4.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.mask_embed.4.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.mask_embed.4.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.mask_embed.4.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.mask_embed.5.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.mask_embed.5.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.mask_embed.5.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.mask_embed.5.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.mask_embed.5.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.mask_embed.5.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.embeddings.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.embeddings.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.embeddings.patch_embeddings.projection.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.embeddings.patch_embeddings.projection.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.0.blocks.0.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.0.blocks.0.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.0.blocks.0.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.0.blocks.0.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.0.blocks.0.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.0.blocks.0.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.0.blocks.0.attention.self.relative_position_bias_table": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.0.blocks.0.attention.self.relative_position_index": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.0.blocks.0.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.0.blocks.0.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.0.blocks.0.intermediate.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.0.blocks.0.intermediate.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.0.blocks.0.layernorm_after.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.0.blocks.0.layernorm_after.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.0.blocks.0.layernorm_before.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.0.blocks.0.layernorm_before.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.0.blocks.0.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.0.blocks.0.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.0.blocks.1.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.0.blocks.1.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.0.blocks.1.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.0.blocks.1.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.0.blocks.1.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.0.blocks.1.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.0.blocks.1.attention.self.relative_position_bias_table": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.0.blocks.1.attention.self.relative_position_index": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.0.blocks.1.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.0.blocks.1.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.0.blocks.1.intermediate.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.0.blocks.1.intermediate.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.0.blocks.1.layernorm_after.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.0.blocks.1.layernorm_after.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.0.blocks.1.layernorm_before.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.0.blocks.1.layernorm_before.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.0.blocks.1.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.0.blocks.1.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.0.downsample.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.0.downsample.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.0.downsample.reduction.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.1.blocks.0.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.1.blocks.0.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.1.blocks.0.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.1.blocks.0.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.1.blocks.0.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.1.blocks.0.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.1.blocks.0.attention.self.relative_position_bias_table": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.1.blocks.0.attention.self.relative_position_index": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.1.blocks.0.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.1.blocks.0.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.1.blocks.0.intermediate.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.1.blocks.0.intermediate.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.1.blocks.0.layernorm_after.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.1.blocks.0.layernorm_after.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.1.blocks.0.layernorm_before.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.1.blocks.0.layernorm_before.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.1.blocks.0.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.1.blocks.0.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.1.blocks.1.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.1.blocks.1.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.1.blocks.1.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.1.blocks.1.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.1.blocks.1.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.1.blocks.1.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.1.blocks.1.attention.self.relative_position_bias_table": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.1.blocks.1.attention.self.relative_position_index": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.1.blocks.1.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.1.blocks.1.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.1.blocks.1.intermediate.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.1.blocks.1.intermediate.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.1.blocks.1.layernorm_after.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.1.blocks.1.layernorm_after.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.1.blocks.1.layernorm_before.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.1.blocks.1.layernorm_before.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.1.blocks.1.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.1.blocks.1.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.1.downsample.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.1.downsample.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.1.downsample.reduction.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.0.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.0.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.0.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.0.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.0.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.0.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.0.attention.self.relative_position_bias_table": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.0.attention.self.relative_position_index": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.0.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.0.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.0.intermediate.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.0.intermediate.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.0.layernorm_after.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.0.layernorm_after.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.0.layernorm_before.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.0.layernorm_before.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.0.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.0.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.1.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.1.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.1.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.1.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.1.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.1.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.1.attention.self.relative_position_bias_table": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.1.attention.self.relative_position_index": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.1.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.1.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.1.intermediate.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.1.intermediate.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.1.layernorm_after.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.1.layernorm_after.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.1.layernorm_before.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.1.layernorm_before.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.1.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.1.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.2.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.2.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.2.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.2.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.2.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.2.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.2.attention.self.relative_position_bias_table": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.2.attention.self.relative_position_index": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.2.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.2.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.2.intermediate.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.2.intermediate.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.2.layernorm_after.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.2.layernorm_after.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.2.layernorm_before.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.2.layernorm_before.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.2.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.2.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.3.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.3.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.3.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.3.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.3.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.3.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.3.attention.self.relative_position_bias_table": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.3.attention.self.relative_position_index": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.3.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.3.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.3.intermediate.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.3.intermediate.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.3.layernorm_after.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.3.layernorm_after.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.3.layernorm_before.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.3.layernorm_before.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.3.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.3.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.4.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.4.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.4.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.4.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.4.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.4.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.4.attention.self.relative_position_bias_table": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.4.attention.self.relative_position_index": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.4.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.4.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.4.intermediate.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.4.intermediate.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.4.layernorm_after.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.4.layernorm_after.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.4.layernorm_before.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.4.layernorm_before.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.4.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.4.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.5.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.5.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.5.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.5.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.5.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.5.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.5.attention.self.relative_position_bias_table": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.5.attention.self.relative_position_index": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.5.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.5.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.5.intermediate.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.5.intermediate.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.5.layernorm_after.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.5.layernorm_after.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.5.layernorm_before.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.5.layernorm_before.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.5.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.blocks.5.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.downsample.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.downsample.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.2.downsample.reduction.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.3.blocks.0.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.3.blocks.0.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.3.blocks.0.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.3.blocks.0.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.3.blocks.0.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.3.blocks.0.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.3.blocks.0.attention.self.relative_position_bias_table": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.3.blocks.0.attention.self.relative_position_index": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.3.blocks.0.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.3.blocks.0.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.3.blocks.0.intermediate.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.3.blocks.0.intermediate.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.3.blocks.0.layernorm_after.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.3.blocks.0.layernorm_after.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.3.blocks.0.layernorm_before.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.3.blocks.0.layernorm_before.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.3.blocks.0.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.3.blocks.0.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.3.blocks.1.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.3.blocks.1.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.3.blocks.1.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.3.blocks.1.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.3.blocks.1.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.3.blocks.1.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.3.blocks.1.attention.self.relative_position_bias_table": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.3.blocks.1.attention.self.relative_position_index": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.3.blocks.1.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.3.blocks.1.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.3.blocks.1.intermediate.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.3.blocks.1.intermediate.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.3.blocks.1.layernorm_after.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.3.blocks.1.layernorm_after.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.3.blocks.1.layernorm_before.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.3.blocks.1.layernorm_before.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.3.blocks.1.output.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.encoder.layers.3.blocks.1.output.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.hidden_states_norms.stage1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.hidden_states_norms.stage1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.hidden_states_norms.stage2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.hidden_states_norms.stage2.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.hidden_states_norms.stage3.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.hidden_states_norms.stage3.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.hidden_states_norms.stage4.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.backbone.conv_encoder.model.hidden_states_norms.stage4.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.bbox_embed.0.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.bbox_embed.0.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.bbox_embed.0.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.bbox_embed.0.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.bbox_embed.0.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.bbox_embed.0.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.bbox_embed.1.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.bbox_embed.1.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.bbox_embed.1.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.bbox_embed.1.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.bbox_embed.1.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.bbox_embed.1.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.bbox_embed.2.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.bbox_embed.2.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.bbox_embed.2.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.bbox_embed.2.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.bbox_embed.2.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.bbox_embed.2.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.bbox_embed.3.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.bbox_embed.3.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.bbox_embed.3.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.bbox_embed.3.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.bbox_embed.3.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.bbox_embed.3.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.bbox_embed.4.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.bbox_embed.4.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.bbox_embed.4.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.bbox_embed.4.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.bbox_embed.4.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.bbox_embed.4.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.bbox_embed.5.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.bbox_embed.5.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.bbox_embed.5.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.bbox_embed.5.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.bbox_embed.5.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.bbox_embed.5.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.0.encoder_attn.attention_weights.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.0.encoder_attn.attention_weights.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.0.encoder_attn.output_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.0.encoder_attn.output_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.0.encoder_attn.sampling_offsets.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.0.encoder_attn.sampling_offsets.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.0.encoder_attn.value_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.0.encoder_attn.value_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.0.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.0.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.0.encoder_attn_text.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.0.encoder_attn_text.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.0.encoder_attn_text.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.0.encoder_attn_text.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.0.encoder_attn_text_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.0.encoder_attn_text_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.0.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.0.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.0.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.0.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.0.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.0.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.0.self_attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.0.self_attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.0.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.0.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.1.encoder_attn.attention_weights.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.1.encoder_attn.attention_weights.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.1.encoder_attn.output_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.1.encoder_attn.output_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.1.encoder_attn.sampling_offsets.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.1.encoder_attn.sampling_offsets.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.1.encoder_attn.value_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.1.encoder_attn.value_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.1.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.1.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.1.encoder_attn_text.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.1.encoder_attn_text.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.1.encoder_attn_text.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.1.encoder_attn_text.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.1.encoder_attn_text_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.1.encoder_attn_text_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.1.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.1.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.1.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.1.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.1.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.1.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.1.self_attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.1.self_attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.1.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.1.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.2.encoder_attn.attention_weights.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.2.encoder_attn.attention_weights.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.2.encoder_attn.output_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.2.encoder_attn.output_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.2.encoder_attn.sampling_offsets.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.2.encoder_attn.sampling_offsets.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.2.encoder_attn.value_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.2.encoder_attn.value_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.2.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.2.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.2.encoder_attn_text.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.2.encoder_attn_text.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.2.encoder_attn_text.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.2.encoder_attn_text.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.2.encoder_attn_text_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.2.encoder_attn_text_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.2.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.2.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.2.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.2.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.2.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.2.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.2.self_attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.2.self_attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.2.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.2.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.3.encoder_attn.attention_weights.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.3.encoder_attn.attention_weights.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.3.encoder_attn.output_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.3.encoder_attn.output_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.3.encoder_attn.sampling_offsets.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.3.encoder_attn.sampling_offsets.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.3.encoder_attn.value_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.3.encoder_attn.value_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.3.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.3.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.3.encoder_attn_text.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.3.encoder_attn_text.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.3.encoder_attn_text.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.3.encoder_attn_text.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.3.encoder_attn_text_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.3.encoder_attn_text_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.3.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.3.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.3.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.3.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.3.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.3.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.3.self_attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.3.self_attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.3.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.3.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.4.encoder_attn.attention_weights.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.4.encoder_attn.attention_weights.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.4.encoder_attn.output_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.4.encoder_attn.output_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.4.encoder_attn.sampling_offsets.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.4.encoder_attn.sampling_offsets.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.4.encoder_attn.value_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.4.encoder_attn.value_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.4.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.4.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.4.encoder_attn_text.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.4.encoder_attn_text.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.4.encoder_attn_text.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.4.encoder_attn_text.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.4.encoder_attn_text_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.4.encoder_attn_text_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.4.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.4.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.4.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.4.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.4.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.4.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.4.self_attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.4.self_attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.4.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.4.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.5.encoder_attn.attention_weights.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.5.encoder_attn.attention_weights.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.5.encoder_attn.output_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.5.encoder_attn.output_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.5.encoder_attn.sampling_offsets.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.5.encoder_attn.sampling_offsets.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.5.encoder_attn.value_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.5.encoder_attn.value_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.5.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.5.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.5.encoder_attn_text.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.5.encoder_attn_text.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.5.encoder_attn_text.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.5.encoder_attn_text.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.5.encoder_attn_text_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.5.encoder_attn_text_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.5.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.5.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.5.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.5.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.5.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.5.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.5.self_attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.5.self_attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.5.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.layers.5.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.reference_points_head.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.reference_points_head.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.reference_points_head.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.decoder.reference_points_head.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.enc_output.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.enc_output.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.enc_output_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.enc_output_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.deformable_layer.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.deformable_layer.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.deformable_layer.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.deformable_layer.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.deformable_layer.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.deformable_layer.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.deformable_layer.self_attn.attention_weights.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.deformable_layer.self_attn.attention_weights.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.deformable_layer.self_attn.output_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.deformable_layer.self_attn.output_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.deformable_layer.self_attn.sampling_offsets.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.deformable_layer.self_attn.sampling_offsets.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.deformable_layer.self_attn.value_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.deformable_layer.self_attn.value_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.deformable_layer.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.deformable_layer.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.fusion_layer.attn.out_text_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.fusion_layer.attn.out_text_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.fusion_layer.attn.out_vision_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.fusion_layer.attn.out_vision_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.fusion_layer.attn.text_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.fusion_layer.attn.text_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.fusion_layer.attn.values_text_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.fusion_layer.attn.values_text_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.fusion_layer.attn.values_vision_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.fusion_layer.attn.values_vision_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.fusion_layer.attn.vision_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.fusion_layer.attn.vision_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.fusion_layer.layer_norm_text.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.fusion_layer.layer_norm_text.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.fusion_layer.layer_norm_vision.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.fusion_layer.layer_norm_vision.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.fusion_layer.text_param": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.fusion_layer.vision_param": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.text_enhancer_layer.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.text_enhancer_layer.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.text_enhancer_layer.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.text_enhancer_layer.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.text_enhancer_layer.layer_norm_after.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.text_enhancer_layer.layer_norm_after.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.text_enhancer_layer.layer_norm_before.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.text_enhancer_layer.layer_norm_before.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.text_enhancer_layer.self_attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.text_enhancer_layer.self_attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.text_enhancer_layer.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.0.text_enhancer_layer.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.deformable_layer.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.deformable_layer.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.deformable_layer.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.deformable_layer.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.deformable_layer.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.deformable_layer.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.deformable_layer.self_attn.attention_weights.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.deformable_layer.self_attn.attention_weights.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.deformable_layer.self_attn.output_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.deformable_layer.self_attn.output_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.deformable_layer.self_attn.sampling_offsets.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.deformable_layer.self_attn.sampling_offsets.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.deformable_layer.self_attn.value_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.deformable_layer.self_attn.value_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.deformable_layer.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.deformable_layer.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.fusion_layer.attn.out_text_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.fusion_layer.attn.out_text_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.fusion_layer.attn.out_vision_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.fusion_layer.attn.out_vision_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.fusion_layer.attn.text_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.fusion_layer.attn.text_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.fusion_layer.attn.values_text_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.fusion_layer.attn.values_text_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.fusion_layer.attn.values_vision_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.fusion_layer.attn.values_vision_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.fusion_layer.attn.vision_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.fusion_layer.attn.vision_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.fusion_layer.layer_norm_text.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.fusion_layer.layer_norm_text.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.fusion_layer.layer_norm_vision.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.fusion_layer.layer_norm_vision.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.fusion_layer.text_param": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.fusion_layer.vision_param": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.text_enhancer_layer.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.text_enhancer_layer.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.text_enhancer_layer.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.text_enhancer_layer.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.text_enhancer_layer.layer_norm_after.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.text_enhancer_layer.layer_norm_after.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.text_enhancer_layer.layer_norm_before.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.text_enhancer_layer.layer_norm_before.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.text_enhancer_layer.self_attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.text_enhancer_layer.self_attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.text_enhancer_layer.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.1.text_enhancer_layer.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.deformable_layer.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.deformable_layer.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.deformable_layer.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.deformable_layer.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.deformable_layer.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.deformable_layer.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.deformable_layer.self_attn.attention_weights.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.deformable_layer.self_attn.attention_weights.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.deformable_layer.self_attn.output_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.deformable_layer.self_attn.output_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.deformable_layer.self_attn.sampling_offsets.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.deformable_layer.self_attn.sampling_offsets.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.deformable_layer.self_attn.value_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.deformable_layer.self_attn.value_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.deformable_layer.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.deformable_layer.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.fusion_layer.attn.out_text_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.fusion_layer.attn.out_text_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.fusion_layer.attn.out_vision_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.fusion_layer.attn.out_vision_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.fusion_layer.attn.text_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.fusion_layer.attn.text_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.fusion_layer.attn.values_text_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.fusion_layer.attn.values_text_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.fusion_layer.attn.values_vision_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.fusion_layer.attn.values_vision_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.fusion_layer.attn.vision_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.fusion_layer.attn.vision_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.fusion_layer.layer_norm_text.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.fusion_layer.layer_norm_text.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.fusion_layer.layer_norm_vision.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.fusion_layer.layer_norm_vision.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.fusion_layer.text_param": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.fusion_layer.vision_param": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.text_enhancer_layer.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.text_enhancer_layer.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.text_enhancer_layer.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.text_enhancer_layer.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.text_enhancer_layer.layer_norm_after.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.text_enhancer_layer.layer_norm_after.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.text_enhancer_layer.layer_norm_before.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.text_enhancer_layer.layer_norm_before.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.text_enhancer_layer.self_attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.text_enhancer_layer.self_attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.text_enhancer_layer.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.2.text_enhancer_layer.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.deformable_layer.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.deformable_layer.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.deformable_layer.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.deformable_layer.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.deformable_layer.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.deformable_layer.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.deformable_layer.self_attn.attention_weights.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.deformable_layer.self_attn.attention_weights.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.deformable_layer.self_attn.output_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.deformable_layer.self_attn.output_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.deformable_layer.self_attn.sampling_offsets.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.deformable_layer.self_attn.sampling_offsets.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.deformable_layer.self_attn.value_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.deformable_layer.self_attn.value_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.deformable_layer.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.deformable_layer.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.fusion_layer.attn.out_text_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.fusion_layer.attn.out_text_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.fusion_layer.attn.out_vision_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.fusion_layer.attn.out_vision_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.fusion_layer.attn.text_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.fusion_layer.attn.text_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.fusion_layer.attn.values_text_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.fusion_layer.attn.values_text_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.fusion_layer.attn.values_vision_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.fusion_layer.attn.values_vision_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.fusion_layer.attn.vision_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.fusion_layer.attn.vision_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.fusion_layer.layer_norm_text.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.fusion_layer.layer_norm_text.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.fusion_layer.layer_norm_vision.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.fusion_layer.layer_norm_vision.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.fusion_layer.text_param": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.fusion_layer.vision_param": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.text_enhancer_layer.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.text_enhancer_layer.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.text_enhancer_layer.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.text_enhancer_layer.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.text_enhancer_layer.layer_norm_after.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.text_enhancer_layer.layer_norm_after.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.text_enhancer_layer.layer_norm_before.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.text_enhancer_layer.layer_norm_before.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.text_enhancer_layer.self_attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.text_enhancer_layer.self_attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.text_enhancer_layer.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.3.text_enhancer_layer.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.deformable_layer.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.deformable_layer.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.deformable_layer.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.deformable_layer.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.deformable_layer.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.deformable_layer.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.deformable_layer.self_attn.attention_weights.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.deformable_layer.self_attn.attention_weights.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.deformable_layer.self_attn.output_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.deformable_layer.self_attn.output_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.deformable_layer.self_attn.sampling_offsets.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.deformable_layer.self_attn.sampling_offsets.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.deformable_layer.self_attn.value_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.deformable_layer.self_attn.value_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.deformable_layer.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.deformable_layer.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.fusion_layer.attn.out_text_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.fusion_layer.attn.out_text_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.fusion_layer.attn.out_vision_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.fusion_layer.attn.out_vision_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.fusion_layer.attn.text_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.fusion_layer.attn.text_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.fusion_layer.attn.values_text_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.fusion_layer.attn.values_text_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.fusion_layer.attn.values_vision_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.fusion_layer.attn.values_vision_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.fusion_layer.attn.vision_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.fusion_layer.attn.vision_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.fusion_layer.layer_norm_text.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.fusion_layer.layer_norm_text.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.fusion_layer.layer_norm_vision.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.fusion_layer.layer_norm_vision.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.fusion_layer.text_param": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.fusion_layer.vision_param": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.text_enhancer_layer.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.text_enhancer_layer.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.text_enhancer_layer.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.text_enhancer_layer.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.text_enhancer_layer.layer_norm_after.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.text_enhancer_layer.layer_norm_after.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.text_enhancer_layer.layer_norm_before.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.text_enhancer_layer.layer_norm_before.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.text_enhancer_layer.self_attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.text_enhancer_layer.self_attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.text_enhancer_layer.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.4.text_enhancer_layer.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.deformable_layer.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.deformable_layer.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.deformable_layer.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.deformable_layer.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.deformable_layer.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.deformable_layer.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.deformable_layer.self_attn.attention_weights.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.deformable_layer.self_attn.attention_weights.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.deformable_layer.self_attn.output_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.deformable_layer.self_attn.output_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.deformable_layer.self_attn.sampling_offsets.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.deformable_layer.self_attn.sampling_offsets.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.deformable_layer.self_attn.value_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.deformable_layer.self_attn.value_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.deformable_layer.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.deformable_layer.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.fusion_layer.attn.out_text_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.fusion_layer.attn.out_text_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.fusion_layer.attn.out_vision_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.fusion_layer.attn.out_vision_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.fusion_layer.attn.text_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.fusion_layer.attn.text_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.fusion_layer.attn.values_text_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.fusion_layer.attn.values_text_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.fusion_layer.attn.values_vision_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.fusion_layer.attn.values_vision_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.fusion_layer.attn.vision_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.fusion_layer.attn.vision_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.fusion_layer.layer_norm_text.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.fusion_layer.layer_norm_text.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.fusion_layer.layer_norm_vision.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.fusion_layer.layer_norm_vision.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.fusion_layer.text_param": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.fusion_layer.vision_param": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.text_enhancer_layer.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.text_enhancer_layer.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.text_enhancer_layer.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.text_enhancer_layer.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.text_enhancer_layer.layer_norm_after.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.text_enhancer_layer.layer_norm_after.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.text_enhancer_layer.layer_norm_before.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.text_enhancer_layer.layer_norm_before.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.text_enhancer_layer.self_attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.text_enhancer_layer.self_attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.text_enhancer_layer.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder.layers.5.text_enhancer_layer.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder_output_bbox_embed.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder_output_bbox_embed.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder_output_bbox_embed.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder_output_bbox_embed.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder_output_bbox_embed.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.encoder_output_bbox_embed.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.input_proj_vision.0.0.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.input_proj_vision.0.0.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.input_proj_vision.0.1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.input_proj_vision.0.1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.input_proj_vision.1.0.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.input_proj_vision.1.0.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.input_proj_vision.1.1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.input_proj_vision.1.1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.input_proj_vision.2.0.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.input_proj_vision.2.0.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.input_proj_vision.2.1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.input_proj_vision.2.1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.input_proj_vision.3.0.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.input_proj_vision.3.0.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.input_proj_vision.3.1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.input_proj_vision.3.1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.lateral_convs.0.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.lateral_convs.0.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.lateral_convs.0.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.level_embed": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.mask_embed.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.mask_embed.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.mask_embed.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.mask_embed.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.mask_embed.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.mask_embed.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.mask_features.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.mask_features.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.output_convs.0.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.output_convs.0.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.output_convs.0.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.model.query_position_embeddings.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.patch2query.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.patch2query.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.patch2query.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.patch2query.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "gdino.patch2query.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "gdino.patch2query.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.emb_proj.0.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.emb_proj.0.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.emb_proj.2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.emb_proj.2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.llm2sd_mapper.decoder.layers.0.linear1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.llm2sd_mapper.decoder.layers.0.linear1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.llm2sd_mapper.decoder.layers.0.linear2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.llm2sd_mapper.decoder.layers.0.linear2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.llm2sd_mapper.decoder.layers.0.multihead_attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.llm2sd_mapper.decoder.layers.0.multihead_attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.llm2sd_mapper.decoder.layers.0.multihead_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.llm2sd_mapper.decoder.layers.0.multihead_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.llm2sd_mapper.decoder.layers.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.llm2sd_mapper.decoder.layers.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.llm2sd_mapper.decoder.layers.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.llm2sd_mapper.decoder.layers.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.llm2sd_mapper.decoder.layers.0.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.llm2sd_mapper.decoder.layers.0.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.llm2sd_mapper.decoder.layers.0.self_attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.llm2sd_mapper.decoder.layers.0.self_attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.llm2sd_mapper.decoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.llm2sd_mapper.decoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.llm2sd_mapper.decoder.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.llm2sd_mapper.decoder.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.llm2sd_mapper.encoder.layers.0.linear1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.llm2sd_mapper.encoder.layers.0.linear1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.llm2sd_mapper.encoder.layers.0.linear2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.llm2sd_mapper.encoder.layers.0.linear2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.llm2sd_mapper.encoder.layers.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.llm2sd_mapper.encoder.layers.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.llm2sd_mapper.encoder.layers.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.llm2sd_mapper.encoder.layers.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.llm2sd_mapper.encoder.layers.0.self_attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.llm2sd_mapper.encoder.layers.0.self_attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.llm2sd_mapper.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.llm2sd_mapper.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.llm2sd_mapper.encoder.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.llm2sd_mapper.encoder.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.llm2sd_mapper_queries": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.embeddings.position_embedding.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.embeddings.token_embedding.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_text_encoder.text_model.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.conv_in.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.conv_in.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.conv_norm_out.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.conv_norm_out.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.conv_out.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.conv_out.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.0.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.0.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.0.proj_in.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.0.proj_in.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.0.proj_out.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.0.proj_out.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.attn1.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.attn1.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.attn1.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.attn1.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.attn1.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.attn2.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.attn2.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.attn2.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.attn2.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.attn2.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.ff.net.0.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.ff.net.0.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.ff.net.2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.ff.net.2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.1.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.1.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.1.proj_in.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.1.proj_in.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.1.proj_out.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.1.proj_out.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.attn1.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.attn1.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.attn1.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.attn1.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.attn1.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.attn2.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.attn2.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.attn2.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.attn2.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.attn2.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.ff.net.0.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.ff.net.0.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.ff.net.2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.ff.net.2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.downsamplers.0.conv.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.downsamplers.0.conv.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.resnets.0.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.resnets.0.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.resnets.0.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.resnets.0.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.resnets.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.resnets.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.resnets.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.resnets.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.resnets.0.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.resnets.0.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.resnets.1.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.resnets.1.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.resnets.1.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.resnets.1.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.resnets.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.resnets.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.resnets.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.resnets.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.resnets.1.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.0.resnets.1.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.0.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.0.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.0.proj_in.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.0.proj_in.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.0.proj_out.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.0.proj_out.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.attn1.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.attn1.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.attn1.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.attn1.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.attn1.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.attn2.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.attn2.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.attn2.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.attn2.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.attn2.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.ff.net.0.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.ff.net.0.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.ff.net.2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.ff.net.2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.1.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.1.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.1.proj_in.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.1.proj_in.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.1.proj_out.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.1.proj_out.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.attn1.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.attn1.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.attn1.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.attn1.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.attn1.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.attn2.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.attn2.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.attn2.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.attn2.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.attn2.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.ff.net.0.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.ff.net.0.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.ff.net.2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.ff.net.2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.downsamplers.0.conv.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.downsamplers.0.conv.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.resnets.0.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.resnets.0.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.resnets.0.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.resnets.0.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.resnets.0.conv_shortcut.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.resnets.0.conv_shortcut.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.resnets.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.resnets.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.resnets.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.resnets.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.resnets.0.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.resnets.0.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.resnets.1.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.resnets.1.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.resnets.1.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.resnets.1.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.resnets.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.resnets.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.resnets.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.resnets.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.resnets.1.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.1.resnets.1.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.0.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.0.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.0.proj_in.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.0.proj_in.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.0.proj_out.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.0.proj_out.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.attn1.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.attn1.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.attn1.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.attn1.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.attn1.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.attn2.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.attn2.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.attn2.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.attn2.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.attn2.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.ff.net.0.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.ff.net.0.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.ff.net.2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.ff.net.2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.1.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.1.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.1.proj_in.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.1.proj_in.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.1.proj_out.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.1.proj_out.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.attn1.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.attn1.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.attn1.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.attn1.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.attn1.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.attn2.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.attn2.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.attn2.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.attn2.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.attn2.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.ff.net.0.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.ff.net.0.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.ff.net.2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.ff.net.2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.downsamplers.0.conv.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.downsamplers.0.conv.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.resnets.0.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.resnets.0.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.resnets.0.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.resnets.0.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.resnets.0.conv_shortcut.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.resnets.0.conv_shortcut.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.resnets.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.resnets.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.resnets.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.resnets.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.resnets.0.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.resnets.0.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.resnets.1.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.resnets.1.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.resnets.1.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.resnets.1.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.resnets.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.resnets.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.resnets.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.resnets.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.resnets.1.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.2.resnets.1.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.3.resnets.0.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.3.resnets.0.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.3.resnets.0.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.3.resnets.0.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.3.resnets.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.3.resnets.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.3.resnets.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.3.resnets.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.3.resnets.0.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.3.resnets.0.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.3.resnets.1.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.3.resnets.1.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.3.resnets.1.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.3.resnets.1.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.3.resnets.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.3.resnets.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.3.resnets.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.3.resnets.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.3.resnets.1.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.down_blocks.3.resnets.1.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.attentions.0.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.attentions.0.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.attentions.0.proj_in.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.attentions.0.proj_in.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.attentions.0.proj_out.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.attentions.0.proj_out.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.attentions.0.transformer_blocks.0.attn1.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.attentions.0.transformer_blocks.0.attn1.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.attentions.0.transformer_blocks.0.attn1.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.attentions.0.transformer_blocks.0.attn1.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.attentions.0.transformer_blocks.0.attn1.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.attentions.0.transformer_blocks.0.attn2.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.attentions.0.transformer_blocks.0.attn2.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.attentions.0.transformer_blocks.0.attn2.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.attentions.0.transformer_blocks.0.attn2.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.attentions.0.transformer_blocks.0.attn2.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.attentions.0.transformer_blocks.0.ff.net.0.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.attentions.0.transformer_blocks.0.ff.net.0.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.attentions.0.transformer_blocks.0.ff.net.2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.attentions.0.transformer_blocks.0.ff.net.2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.attentions.0.transformer_blocks.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.attentions.0.transformer_blocks.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.attentions.0.transformer_blocks.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.attentions.0.transformer_blocks.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.attentions.0.transformer_blocks.0.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.attentions.0.transformer_blocks.0.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.resnets.0.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.resnets.0.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.resnets.0.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.resnets.0.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.resnets.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.resnets.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.resnets.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.resnets.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.resnets.0.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.resnets.0.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.resnets.1.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.resnets.1.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.resnets.1.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.resnets.1.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.resnets.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.resnets.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.resnets.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.resnets.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.resnets.1.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.mid_block.resnets.1.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.time_embedding.linear_1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.time_embedding.linear_1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.time_embedding.linear_2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.time_embedding.linear_2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.0.resnets.0.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.0.resnets.0.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.0.resnets.0.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.0.resnets.0.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.0.resnets.0.conv_shortcut.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.0.resnets.0.conv_shortcut.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.0.resnets.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.0.resnets.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.0.resnets.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.0.resnets.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.0.resnets.0.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.0.resnets.0.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.0.resnets.1.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.0.resnets.1.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.0.resnets.1.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.0.resnets.1.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.0.resnets.1.conv_shortcut.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.0.resnets.1.conv_shortcut.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.0.resnets.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.0.resnets.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.0.resnets.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.0.resnets.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.0.resnets.1.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.0.resnets.1.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.0.resnets.2.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.0.resnets.2.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.0.resnets.2.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.0.resnets.2.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.0.resnets.2.conv_shortcut.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.0.resnets.2.conv_shortcut.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.0.resnets.2.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.0.resnets.2.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.0.resnets.2.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.0.resnets.2.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.0.resnets.2.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.0.resnets.2.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.0.upsamplers.0.conv.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.0.upsamplers.0.conv.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.0.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.0.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.0.proj_in.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.0.proj_in.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.0.proj_out.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.0.proj_out.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.attn1.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.attn1.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.attn1.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.attn1.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.attn1.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.attn2.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.attn2.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.attn2.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.attn2.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.attn2.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.ff.net.0.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.ff.net.0.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.ff.net.2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.ff.net.2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.1.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.1.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.1.proj_in.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.1.proj_in.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.1.proj_out.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.1.proj_out.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.attn1.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.attn1.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.attn1.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.attn1.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.attn1.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.attn2.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.attn2.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.attn2.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.attn2.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.attn2.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.ff.net.0.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.ff.net.0.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.ff.net.2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.ff.net.2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.2.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.2.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.2.proj_in.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.2.proj_in.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.2.proj_out.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.2.proj_out.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.attn1.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.attn1.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.attn1.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.attn1.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.attn1.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.attn2.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.attn2.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.attn2.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.attn2.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.attn2.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.ff.net.0.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.ff.net.0.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.ff.net.2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.ff.net.2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.resnets.0.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.resnets.0.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.resnets.0.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.resnets.0.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.resnets.0.conv_shortcut.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.resnets.0.conv_shortcut.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.resnets.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.resnets.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.resnets.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.resnets.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.resnets.0.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.resnets.0.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.resnets.1.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.resnets.1.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.resnets.1.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.resnets.1.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.resnets.1.conv_shortcut.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.resnets.1.conv_shortcut.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.resnets.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.resnets.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.resnets.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.resnets.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.resnets.1.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.resnets.1.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.resnets.2.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.resnets.2.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.resnets.2.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.resnets.2.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.resnets.2.conv_shortcut.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.resnets.2.conv_shortcut.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.resnets.2.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.resnets.2.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.resnets.2.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.resnets.2.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.resnets.2.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.resnets.2.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.upsamplers.0.conv.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.1.upsamplers.0.conv.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.0.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.0.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.0.proj_in.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.0.proj_in.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.0.proj_out.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.0.proj_out.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.attn1.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.attn1.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.attn1.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.attn1.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.attn1.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.attn2.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.attn2.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.attn2.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.attn2.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.attn2.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.ff.net.0.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.ff.net.0.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.ff.net.2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.ff.net.2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.1.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.1.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.1.proj_in.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.1.proj_in.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.1.proj_out.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.1.proj_out.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.attn1.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.attn1.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.attn1.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.attn1.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.attn1.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.attn2.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.attn2.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.attn2.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.attn2.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.attn2.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.ff.net.0.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.ff.net.0.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.ff.net.2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.ff.net.2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.2.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.2.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.2.proj_in.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.2.proj_in.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.2.proj_out.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.2.proj_out.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.attn1.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.attn1.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.attn1.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.attn1.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.attn1.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.attn2.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.attn2.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.attn2.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.attn2.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.attn2.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.ff.net.0.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.ff.net.0.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.ff.net.2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.ff.net.2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.resnets.0.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.resnets.0.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.resnets.0.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.resnets.0.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.resnets.0.conv_shortcut.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.resnets.0.conv_shortcut.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.resnets.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.resnets.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.resnets.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.resnets.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.resnets.0.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.resnets.0.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.resnets.1.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.resnets.1.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.resnets.1.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.resnets.1.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.resnets.1.conv_shortcut.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.resnets.1.conv_shortcut.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.resnets.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.resnets.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.resnets.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.resnets.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.resnets.1.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.resnets.1.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.resnets.2.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.resnets.2.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.resnets.2.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.resnets.2.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.resnets.2.conv_shortcut.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.resnets.2.conv_shortcut.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.resnets.2.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.resnets.2.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.resnets.2.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.resnets.2.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.resnets.2.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.resnets.2.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.upsamplers.0.conv.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.2.upsamplers.0.conv.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.0.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.0.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.0.proj_in.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.0.proj_in.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.0.proj_out.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.0.proj_out.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.attn1.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.attn1.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.attn1.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.attn1.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.attn1.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.attn2.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.attn2.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.attn2.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.attn2.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.attn2.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.ff.net.0.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.ff.net.0.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.ff.net.2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.ff.net.2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.1.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.1.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.1.proj_in.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.1.proj_in.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.1.proj_out.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.1.proj_out.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.attn1.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.attn1.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.attn1.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.attn1.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.attn1.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.attn2.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.attn2.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.attn2.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.attn2.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.attn2.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.ff.net.0.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.ff.net.0.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.ff.net.2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.ff.net.2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.2.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.2.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.2.proj_in.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.2.proj_in.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.2.proj_out.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.2.proj_out.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.attn1.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.attn1.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.attn1.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.attn1.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.attn1.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.attn2.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.attn2.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.attn2.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.attn2.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.attn2.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.ff.net.0.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.ff.net.0.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.ff.net.2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.ff.net.2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.resnets.0.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.resnets.0.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.resnets.0.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.resnets.0.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.resnets.0.conv_shortcut.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.resnets.0.conv_shortcut.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.resnets.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.resnets.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.resnets.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.resnets.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.resnets.0.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.resnets.0.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.resnets.1.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.resnets.1.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.resnets.1.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.resnets.1.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.resnets.1.conv_shortcut.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.resnets.1.conv_shortcut.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.resnets.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.resnets.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.resnets.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.resnets.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.resnets.1.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.resnets.1.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.resnets.2.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.resnets.2.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.resnets.2.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.resnets.2.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.resnets.2.conv_shortcut.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.resnets.2.conv_shortcut.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.resnets.2.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.resnets.2.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.resnets.2.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.resnets.2.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.resnets.2.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_unet.up_blocks.3.resnets.2.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.conv_in.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.conv_in.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.conv_norm_out.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.conv_norm_out.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.conv_out.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.conv_out.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.mid_block.attentions.0.group_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.mid_block.attentions.0.group_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.mid_block.attentions.0.to_k.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.mid_block.attentions.0.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.mid_block.attentions.0.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.mid_block.attentions.0.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.mid_block.attentions.0.to_q.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.mid_block.attentions.0.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.mid_block.attentions.0.to_v.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.mid_block.attentions.0.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.mid_block.resnets.0.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.mid_block.resnets.0.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.mid_block.resnets.0.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.mid_block.resnets.0.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.mid_block.resnets.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.mid_block.resnets.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.mid_block.resnets.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.mid_block.resnets.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.mid_block.resnets.1.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.mid_block.resnets.1.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.mid_block.resnets.1.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.mid_block.resnets.1.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.mid_block.resnets.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.mid_block.resnets.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.mid_block.resnets.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.mid_block.resnets.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.0.resnets.0.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.0.resnets.0.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.0.resnets.0.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.0.resnets.0.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.0.resnets.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.0.resnets.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.0.resnets.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.0.resnets.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.0.resnets.1.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.0.resnets.1.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.0.resnets.1.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.0.resnets.1.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.0.resnets.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.0.resnets.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.0.resnets.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.0.resnets.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.0.resnets.2.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.0.resnets.2.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.0.resnets.2.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.0.resnets.2.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.0.resnets.2.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.0.resnets.2.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.0.resnets.2.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.0.resnets.2.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.0.upsamplers.0.conv.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.0.upsamplers.0.conv.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.1.resnets.0.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.1.resnets.0.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.1.resnets.0.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.1.resnets.0.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.1.resnets.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.1.resnets.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.1.resnets.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.1.resnets.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.1.resnets.1.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.1.resnets.1.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.1.resnets.1.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.1.resnets.1.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.1.resnets.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.1.resnets.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.1.resnets.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.1.resnets.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.1.resnets.2.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.1.resnets.2.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.1.resnets.2.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.1.resnets.2.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.1.resnets.2.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.1.resnets.2.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.1.resnets.2.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.1.resnets.2.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.1.upsamplers.0.conv.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.1.upsamplers.0.conv.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.2.resnets.0.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.2.resnets.0.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.2.resnets.0.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.2.resnets.0.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.2.resnets.0.conv_shortcut.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.2.resnets.0.conv_shortcut.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.2.resnets.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.2.resnets.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.2.resnets.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.2.resnets.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.2.resnets.1.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.2.resnets.1.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.2.resnets.1.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.2.resnets.1.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.2.resnets.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.2.resnets.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.2.resnets.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.2.resnets.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.2.resnets.2.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.2.resnets.2.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.2.resnets.2.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.2.resnets.2.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.2.resnets.2.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.2.resnets.2.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.2.resnets.2.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.2.resnets.2.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.2.upsamplers.0.conv.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.2.upsamplers.0.conv.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.3.resnets.0.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.3.resnets.0.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.3.resnets.0.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.3.resnets.0.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.3.resnets.0.conv_shortcut.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.3.resnets.0.conv_shortcut.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.3.resnets.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.3.resnets.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.3.resnets.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.3.resnets.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.3.resnets.1.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.3.resnets.1.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.3.resnets.1.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.3.resnets.1.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.3.resnets.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.3.resnets.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.3.resnets.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.3.resnets.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.3.resnets.2.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.3.resnets.2.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.3.resnets.2.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.3.resnets.2.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.3.resnets.2.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.3.resnets.2.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.3.resnets.2.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.decoder.up_blocks.3.resnets.2.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.conv_in.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.conv_in.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.conv_norm_out.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.conv_norm_out.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.conv_out.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.conv_out.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.0.downsamplers.0.conv.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.0.downsamplers.0.conv.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.0.resnets.0.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.0.resnets.0.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.0.resnets.0.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.0.resnets.0.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.0.resnets.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.0.resnets.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.0.resnets.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.0.resnets.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.0.resnets.1.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.0.resnets.1.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.0.resnets.1.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.0.resnets.1.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.0.resnets.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.0.resnets.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.0.resnets.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.0.resnets.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.1.downsamplers.0.conv.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.1.downsamplers.0.conv.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.1.resnets.0.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.1.resnets.0.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.1.resnets.0.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.1.resnets.0.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.1.resnets.0.conv_shortcut.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.1.resnets.0.conv_shortcut.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.1.resnets.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.1.resnets.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.1.resnets.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.1.resnets.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.1.resnets.1.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.1.resnets.1.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.1.resnets.1.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.1.resnets.1.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.1.resnets.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.1.resnets.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.1.resnets.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.1.resnets.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.2.downsamplers.0.conv.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.2.downsamplers.0.conv.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.2.resnets.0.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.2.resnets.0.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.2.resnets.0.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.2.resnets.0.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.2.resnets.0.conv_shortcut.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.2.resnets.0.conv_shortcut.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.2.resnets.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.2.resnets.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.2.resnets.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.2.resnets.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.2.resnets.1.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.2.resnets.1.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.2.resnets.1.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.2.resnets.1.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.2.resnets.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.2.resnets.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.2.resnets.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.2.resnets.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.3.resnets.0.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.3.resnets.0.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.3.resnets.0.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.3.resnets.0.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.3.resnets.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.3.resnets.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.3.resnets.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.3.resnets.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.3.resnets.1.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.3.resnets.1.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.3.resnets.1.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.3.resnets.1.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.3.resnets.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.3.resnets.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.3.resnets.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.down_blocks.3.resnets.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.mid_block.attentions.0.group_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.mid_block.attentions.0.group_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.mid_block.attentions.0.to_k.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.mid_block.attentions.0.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.mid_block.attentions.0.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.mid_block.attentions.0.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.mid_block.attentions.0.to_q.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.mid_block.attentions.0.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.mid_block.attentions.0.to_v.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.mid_block.attentions.0.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.mid_block.resnets.0.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.mid_block.resnets.0.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.mid_block.resnets.0.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.mid_block.resnets.0.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.mid_block.resnets.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.mid_block.resnets.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.mid_block.resnets.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.mid_block.resnets.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.mid_block.resnets.1.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.mid_block.resnets.1.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.mid_block.resnets.1.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.mid_block.resnets.1.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.mid_block.resnets.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.mid_block.resnets.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.mid_block.resnets.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.encoder.mid_block.resnets.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.post_quant_conv.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.post_quant_conv.weight": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.quant_conv.bias": "pytorch_model-00002-of-00002.bin",
+    "ip2p.sd_vae.quant_conv.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.lm_head.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "llm.model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "llm.model.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "region_encoder.mask_embedding.0.bias": "pytorch_model-00002-of-00002.bin",
+    "region_encoder.mask_embedding.0.weight": "pytorch_model-00002-of-00002.bin",
+    "region_encoder.mask_embedding.1.bias": "pytorch_model-00002-of-00002.bin",
+    "region_encoder.mask_embedding.1.weight": "pytorch_model-00002-of-00002.bin",
+    "region_encoder.mask_embedding.3.bias": "pytorch_model-00002-of-00002.bin",
+    "region_encoder.mask_embedding.3.weight": "pytorch_model-00002-of-00002.bin",
+    "region_encoder.mask_embedding.4.bias": "pytorch_model-00002-of-00002.bin",
+    "region_encoder.mask_embedding.4.weight": "pytorch_model-00002-of-00002.bin",
+    "region_encoder.mask_embedding.6.bias": "pytorch_model-00002-of-00002.bin",
+    "region_encoder.mask_embedding.6.weight": "pytorch_model-00002-of-00002.bin",
+    "region_encoder.up_dim.bias": "pytorch_model-00002-of-00002.bin",
+    "region_encoder.up_dim.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.emb_proj.0.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.emb_proj.0.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.emb_proj.2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.emb_proj.2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.llm2sd_mapper.decoder.layers.0.linear1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.llm2sd_mapper.decoder.layers.0.linear1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.llm2sd_mapper.decoder.layers.0.linear2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.llm2sd_mapper.decoder.layers.0.linear2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.llm2sd_mapper.decoder.layers.0.multihead_attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "sd.llm2sd_mapper.decoder.layers.0.multihead_attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "sd.llm2sd_mapper.decoder.layers.0.multihead_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.llm2sd_mapper.decoder.layers.0.multihead_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.llm2sd_mapper.decoder.layers.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.llm2sd_mapper.decoder.layers.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.llm2sd_mapper.decoder.layers.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.llm2sd_mapper.decoder.layers.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.llm2sd_mapper.decoder.layers.0.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.llm2sd_mapper.decoder.layers.0.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.llm2sd_mapper.decoder.layers.0.self_attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "sd.llm2sd_mapper.decoder.layers.0.self_attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "sd.llm2sd_mapper.decoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.llm2sd_mapper.decoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.llm2sd_mapper.decoder.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.llm2sd_mapper.decoder.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.llm2sd_mapper.encoder.layers.0.linear1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.llm2sd_mapper.encoder.layers.0.linear1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.llm2sd_mapper.encoder.layers.0.linear2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.llm2sd_mapper.encoder.layers.0.linear2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.llm2sd_mapper.encoder.layers.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.llm2sd_mapper.encoder.layers.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.llm2sd_mapper.encoder.layers.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.llm2sd_mapper.encoder.layers.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.llm2sd_mapper.encoder.layers.0.self_attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "sd.llm2sd_mapper.encoder.layers.0.self_attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "sd.llm2sd_mapper.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.llm2sd_mapper.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.llm2sd_mapper.encoder.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.llm2sd_mapper.encoder.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.llm2sd_mapper_queries": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.embeddings.position_embedding.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.embeddings.token_embedding.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_text_encoder.text_model.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.conv_in.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.conv_in.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.conv_norm_out.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.conv_norm_out.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.conv_out.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.conv_out.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.0.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.0.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.0.proj_in.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.0.proj_in.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.0.proj_out.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.0.proj_out.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.attn1.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.attn1.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.attn1.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.attn1.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.attn1.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.attn2.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.attn2.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.attn2.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.attn2.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.attn2.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.ff.net.0.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.ff.net.0.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.ff.net.2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.ff.net.2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.0.transformer_blocks.0.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.1.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.1.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.1.proj_in.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.1.proj_in.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.1.proj_out.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.1.proj_out.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.attn1.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.attn1.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.attn1.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.attn1.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.attn1.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.attn2.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.attn2.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.attn2.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.attn2.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.attn2.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.ff.net.0.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.ff.net.0.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.ff.net.2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.ff.net.2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.attentions.1.transformer_blocks.0.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.downsamplers.0.conv.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.downsamplers.0.conv.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.resnets.0.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.resnets.0.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.resnets.0.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.resnets.0.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.resnets.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.resnets.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.resnets.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.resnets.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.resnets.0.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.resnets.0.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.resnets.1.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.resnets.1.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.resnets.1.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.resnets.1.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.resnets.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.resnets.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.resnets.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.resnets.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.resnets.1.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.0.resnets.1.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.0.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.0.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.0.proj_in.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.0.proj_in.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.0.proj_out.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.0.proj_out.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.attn1.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.attn1.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.attn1.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.attn1.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.attn1.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.attn2.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.attn2.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.attn2.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.attn2.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.attn2.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.ff.net.0.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.ff.net.0.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.ff.net.2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.ff.net.2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.0.transformer_blocks.0.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.1.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.1.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.1.proj_in.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.1.proj_in.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.1.proj_out.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.1.proj_out.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.attn1.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.attn1.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.attn1.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.attn1.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.attn1.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.attn2.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.attn2.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.attn2.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.attn2.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.attn2.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.ff.net.0.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.ff.net.0.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.ff.net.2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.ff.net.2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.attentions.1.transformer_blocks.0.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.downsamplers.0.conv.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.downsamplers.0.conv.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.resnets.0.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.resnets.0.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.resnets.0.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.resnets.0.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.resnets.0.conv_shortcut.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.resnets.0.conv_shortcut.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.resnets.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.resnets.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.resnets.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.resnets.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.resnets.0.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.resnets.0.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.resnets.1.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.resnets.1.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.resnets.1.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.resnets.1.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.resnets.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.resnets.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.resnets.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.resnets.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.resnets.1.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.1.resnets.1.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.0.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.0.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.0.proj_in.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.0.proj_in.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.0.proj_out.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.0.proj_out.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.attn1.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.attn1.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.attn1.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.attn1.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.attn1.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.attn2.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.attn2.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.attn2.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.attn2.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.attn2.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.ff.net.0.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.ff.net.0.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.ff.net.2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.ff.net.2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.0.transformer_blocks.0.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.1.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.1.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.1.proj_in.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.1.proj_in.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.1.proj_out.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.1.proj_out.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.attn1.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.attn1.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.attn1.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.attn1.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.attn1.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.attn2.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.attn2.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.attn2.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.attn2.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.attn2.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.ff.net.0.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.ff.net.0.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.ff.net.2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.ff.net.2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.attentions.1.transformer_blocks.0.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.downsamplers.0.conv.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.downsamplers.0.conv.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.resnets.0.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.resnets.0.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.resnets.0.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.resnets.0.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.resnets.0.conv_shortcut.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.resnets.0.conv_shortcut.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.resnets.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.resnets.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.resnets.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.resnets.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.resnets.0.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.resnets.0.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.resnets.1.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.resnets.1.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.resnets.1.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.resnets.1.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.resnets.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.resnets.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.resnets.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.resnets.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.resnets.1.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.2.resnets.1.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.3.resnets.0.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.3.resnets.0.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.3.resnets.0.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.3.resnets.0.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.3.resnets.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.3.resnets.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.3.resnets.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.3.resnets.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.3.resnets.0.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.3.resnets.0.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.3.resnets.1.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.3.resnets.1.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.3.resnets.1.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.3.resnets.1.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.3.resnets.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.3.resnets.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.3.resnets.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.3.resnets.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.3.resnets.1.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.down_blocks.3.resnets.1.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.attentions.0.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.attentions.0.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.attentions.0.proj_in.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.attentions.0.proj_in.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.attentions.0.proj_out.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.attentions.0.proj_out.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.attentions.0.transformer_blocks.0.attn1.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.attentions.0.transformer_blocks.0.attn1.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.attentions.0.transformer_blocks.0.attn1.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.attentions.0.transformer_blocks.0.attn1.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.attentions.0.transformer_blocks.0.attn1.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.attentions.0.transformer_blocks.0.attn2.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.attentions.0.transformer_blocks.0.attn2.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.attentions.0.transformer_blocks.0.attn2.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.attentions.0.transformer_blocks.0.attn2.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.attentions.0.transformer_blocks.0.attn2.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.attentions.0.transformer_blocks.0.ff.net.0.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.attentions.0.transformer_blocks.0.ff.net.0.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.attentions.0.transformer_blocks.0.ff.net.2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.attentions.0.transformer_blocks.0.ff.net.2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.attentions.0.transformer_blocks.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.attentions.0.transformer_blocks.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.attentions.0.transformer_blocks.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.attentions.0.transformer_blocks.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.attentions.0.transformer_blocks.0.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.attentions.0.transformer_blocks.0.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.resnets.0.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.resnets.0.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.resnets.0.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.resnets.0.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.resnets.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.resnets.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.resnets.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.resnets.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.resnets.0.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.resnets.0.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.resnets.1.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.resnets.1.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.resnets.1.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.resnets.1.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.resnets.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.resnets.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.resnets.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.resnets.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.resnets.1.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.mid_block.resnets.1.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.time_embedding.linear_1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.time_embedding.linear_1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.time_embedding.linear_2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.time_embedding.linear_2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.0.resnets.0.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.0.resnets.0.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.0.resnets.0.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.0.resnets.0.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.0.resnets.0.conv_shortcut.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.0.resnets.0.conv_shortcut.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.0.resnets.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.0.resnets.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.0.resnets.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.0.resnets.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.0.resnets.0.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.0.resnets.0.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.0.resnets.1.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.0.resnets.1.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.0.resnets.1.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.0.resnets.1.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.0.resnets.1.conv_shortcut.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.0.resnets.1.conv_shortcut.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.0.resnets.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.0.resnets.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.0.resnets.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.0.resnets.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.0.resnets.1.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.0.resnets.1.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.0.resnets.2.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.0.resnets.2.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.0.resnets.2.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.0.resnets.2.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.0.resnets.2.conv_shortcut.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.0.resnets.2.conv_shortcut.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.0.resnets.2.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.0.resnets.2.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.0.resnets.2.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.0.resnets.2.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.0.resnets.2.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.0.resnets.2.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.0.upsamplers.0.conv.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.0.upsamplers.0.conv.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.0.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.0.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.0.proj_in.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.0.proj_in.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.0.proj_out.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.0.proj_out.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.attn1.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.attn1.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.attn1.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.attn1.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.attn1.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.attn2.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.attn2.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.attn2.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.attn2.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.attn2.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.ff.net.0.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.ff.net.0.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.ff.net.2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.ff.net.2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.0.transformer_blocks.0.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.1.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.1.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.1.proj_in.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.1.proj_in.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.1.proj_out.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.1.proj_out.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.attn1.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.attn1.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.attn1.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.attn1.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.attn1.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.attn2.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.attn2.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.attn2.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.attn2.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.attn2.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.ff.net.0.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.ff.net.0.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.ff.net.2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.ff.net.2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.1.transformer_blocks.0.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.2.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.2.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.2.proj_in.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.2.proj_in.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.2.proj_out.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.2.proj_out.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.attn1.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.attn1.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.attn1.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.attn1.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.attn1.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.attn2.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.attn2.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.attn2.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.attn2.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.attn2.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.ff.net.0.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.ff.net.0.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.ff.net.2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.ff.net.2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.attentions.2.transformer_blocks.0.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.resnets.0.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.resnets.0.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.resnets.0.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.resnets.0.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.resnets.0.conv_shortcut.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.resnets.0.conv_shortcut.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.resnets.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.resnets.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.resnets.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.resnets.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.resnets.0.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.resnets.0.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.resnets.1.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.resnets.1.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.resnets.1.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.resnets.1.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.resnets.1.conv_shortcut.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.resnets.1.conv_shortcut.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.resnets.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.resnets.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.resnets.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.resnets.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.resnets.1.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.resnets.1.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.resnets.2.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.resnets.2.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.resnets.2.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.resnets.2.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.resnets.2.conv_shortcut.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.resnets.2.conv_shortcut.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.resnets.2.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.resnets.2.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.resnets.2.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.resnets.2.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.resnets.2.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.resnets.2.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.upsamplers.0.conv.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.1.upsamplers.0.conv.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.0.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.0.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.0.proj_in.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.0.proj_in.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.0.proj_out.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.0.proj_out.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.attn1.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.attn1.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.attn1.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.attn1.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.attn1.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.attn2.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.attn2.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.attn2.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.attn2.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.attn2.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.ff.net.0.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.ff.net.0.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.ff.net.2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.ff.net.2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.0.transformer_blocks.0.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.1.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.1.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.1.proj_in.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.1.proj_in.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.1.proj_out.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.1.proj_out.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.attn1.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.attn1.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.attn1.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.attn1.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.attn1.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.attn2.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.attn2.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.attn2.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.attn2.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.attn2.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.ff.net.0.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.ff.net.0.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.ff.net.2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.ff.net.2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.1.transformer_blocks.0.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.2.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.2.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.2.proj_in.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.2.proj_in.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.2.proj_out.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.2.proj_out.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.attn1.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.attn1.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.attn1.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.attn1.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.attn1.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.attn2.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.attn2.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.attn2.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.attn2.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.attn2.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.ff.net.0.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.ff.net.0.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.ff.net.2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.ff.net.2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.attentions.2.transformer_blocks.0.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.resnets.0.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.resnets.0.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.resnets.0.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.resnets.0.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.resnets.0.conv_shortcut.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.resnets.0.conv_shortcut.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.resnets.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.resnets.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.resnets.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.resnets.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.resnets.0.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.resnets.0.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.resnets.1.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.resnets.1.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.resnets.1.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.resnets.1.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.resnets.1.conv_shortcut.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.resnets.1.conv_shortcut.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.resnets.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.resnets.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.resnets.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.resnets.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.resnets.1.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.resnets.1.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.resnets.2.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.resnets.2.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.resnets.2.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.resnets.2.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.resnets.2.conv_shortcut.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.resnets.2.conv_shortcut.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.resnets.2.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.resnets.2.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.resnets.2.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.resnets.2.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.resnets.2.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.resnets.2.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.upsamplers.0.conv.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.2.upsamplers.0.conv.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.0.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.0.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.0.proj_in.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.0.proj_in.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.0.proj_out.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.0.proj_out.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.attn1.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.attn1.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.attn1.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.attn1.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.attn1.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.attn2.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.attn2.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.attn2.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.attn2.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.attn2.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.ff.net.0.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.ff.net.0.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.ff.net.2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.ff.net.2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.0.transformer_blocks.0.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.1.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.1.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.1.proj_in.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.1.proj_in.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.1.proj_out.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.1.proj_out.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.attn1.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.attn1.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.attn1.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.attn1.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.attn1.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.attn2.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.attn2.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.attn2.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.attn2.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.attn2.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.ff.net.0.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.ff.net.0.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.ff.net.2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.ff.net.2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.1.transformer_blocks.0.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.2.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.2.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.2.proj_in.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.2.proj_in.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.2.proj_out.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.2.proj_out.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.attn1.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.attn1.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.attn1.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.attn1.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.attn1.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.attn2.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.attn2.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.attn2.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.attn2.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.attn2.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.ff.net.0.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.ff.net.0.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.ff.net.2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.ff.net.2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.attentions.2.transformer_blocks.0.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.resnets.0.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.resnets.0.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.resnets.0.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.resnets.0.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.resnets.0.conv_shortcut.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.resnets.0.conv_shortcut.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.resnets.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.resnets.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.resnets.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.resnets.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.resnets.0.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.resnets.0.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.resnets.1.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.resnets.1.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.resnets.1.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.resnets.1.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.resnets.1.conv_shortcut.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.resnets.1.conv_shortcut.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.resnets.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.resnets.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.resnets.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.resnets.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.resnets.1.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.resnets.1.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.resnets.2.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.resnets.2.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.resnets.2.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.resnets.2.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.resnets.2.conv_shortcut.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.resnets.2.conv_shortcut.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.resnets.2.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.resnets.2.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.resnets.2.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.resnets.2.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.resnets.2.time_emb_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_unet.up_blocks.3.resnets.2.time_emb_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.conv_in.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.conv_in.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.conv_norm_out.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.conv_norm_out.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.conv_out.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.conv_out.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.mid_block.attentions.0.group_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.mid_block.attentions.0.group_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.mid_block.attentions.0.to_k.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.mid_block.attentions.0.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.mid_block.attentions.0.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.mid_block.attentions.0.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.mid_block.attentions.0.to_q.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.mid_block.attentions.0.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.mid_block.attentions.0.to_v.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.mid_block.attentions.0.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.mid_block.resnets.0.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.mid_block.resnets.0.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.mid_block.resnets.0.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.mid_block.resnets.0.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.mid_block.resnets.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.mid_block.resnets.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.mid_block.resnets.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.mid_block.resnets.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.mid_block.resnets.1.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.mid_block.resnets.1.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.mid_block.resnets.1.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.mid_block.resnets.1.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.mid_block.resnets.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.mid_block.resnets.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.mid_block.resnets.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.mid_block.resnets.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.0.resnets.0.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.0.resnets.0.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.0.resnets.0.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.0.resnets.0.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.0.resnets.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.0.resnets.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.0.resnets.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.0.resnets.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.0.resnets.1.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.0.resnets.1.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.0.resnets.1.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.0.resnets.1.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.0.resnets.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.0.resnets.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.0.resnets.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.0.resnets.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.0.resnets.2.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.0.resnets.2.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.0.resnets.2.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.0.resnets.2.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.0.resnets.2.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.0.resnets.2.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.0.resnets.2.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.0.resnets.2.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.0.upsamplers.0.conv.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.0.upsamplers.0.conv.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.1.resnets.0.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.1.resnets.0.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.1.resnets.0.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.1.resnets.0.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.1.resnets.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.1.resnets.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.1.resnets.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.1.resnets.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.1.resnets.1.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.1.resnets.1.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.1.resnets.1.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.1.resnets.1.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.1.resnets.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.1.resnets.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.1.resnets.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.1.resnets.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.1.resnets.2.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.1.resnets.2.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.1.resnets.2.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.1.resnets.2.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.1.resnets.2.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.1.resnets.2.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.1.resnets.2.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.1.resnets.2.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.1.upsamplers.0.conv.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.1.upsamplers.0.conv.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.2.resnets.0.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.2.resnets.0.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.2.resnets.0.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.2.resnets.0.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.2.resnets.0.conv_shortcut.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.2.resnets.0.conv_shortcut.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.2.resnets.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.2.resnets.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.2.resnets.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.2.resnets.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.2.resnets.1.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.2.resnets.1.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.2.resnets.1.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.2.resnets.1.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.2.resnets.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.2.resnets.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.2.resnets.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.2.resnets.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.2.resnets.2.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.2.resnets.2.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.2.resnets.2.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.2.resnets.2.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.2.resnets.2.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.2.resnets.2.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.2.resnets.2.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.2.resnets.2.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.2.upsamplers.0.conv.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.2.upsamplers.0.conv.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.3.resnets.0.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.3.resnets.0.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.3.resnets.0.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.3.resnets.0.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.3.resnets.0.conv_shortcut.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.3.resnets.0.conv_shortcut.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.3.resnets.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.3.resnets.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.3.resnets.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.3.resnets.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.3.resnets.1.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.3.resnets.1.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.3.resnets.1.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.3.resnets.1.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.3.resnets.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.3.resnets.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.3.resnets.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.3.resnets.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.3.resnets.2.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.3.resnets.2.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.3.resnets.2.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.3.resnets.2.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.3.resnets.2.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.3.resnets.2.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.3.resnets.2.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.decoder.up_blocks.3.resnets.2.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.conv_in.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.conv_in.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.conv_norm_out.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.conv_norm_out.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.conv_out.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.conv_out.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.0.downsamplers.0.conv.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.0.downsamplers.0.conv.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.0.resnets.0.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.0.resnets.0.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.0.resnets.0.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.0.resnets.0.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.0.resnets.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.0.resnets.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.0.resnets.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.0.resnets.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.0.resnets.1.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.0.resnets.1.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.0.resnets.1.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.0.resnets.1.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.0.resnets.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.0.resnets.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.0.resnets.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.0.resnets.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.1.downsamplers.0.conv.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.1.downsamplers.0.conv.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.1.resnets.0.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.1.resnets.0.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.1.resnets.0.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.1.resnets.0.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.1.resnets.0.conv_shortcut.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.1.resnets.0.conv_shortcut.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.1.resnets.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.1.resnets.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.1.resnets.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.1.resnets.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.1.resnets.1.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.1.resnets.1.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.1.resnets.1.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.1.resnets.1.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.1.resnets.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.1.resnets.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.1.resnets.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.1.resnets.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.2.downsamplers.0.conv.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.2.downsamplers.0.conv.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.2.resnets.0.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.2.resnets.0.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.2.resnets.0.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.2.resnets.0.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.2.resnets.0.conv_shortcut.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.2.resnets.0.conv_shortcut.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.2.resnets.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.2.resnets.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.2.resnets.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.2.resnets.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.2.resnets.1.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.2.resnets.1.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.2.resnets.1.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.2.resnets.1.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.2.resnets.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.2.resnets.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.2.resnets.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.2.resnets.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.3.resnets.0.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.3.resnets.0.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.3.resnets.0.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.3.resnets.0.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.3.resnets.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.3.resnets.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.3.resnets.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.3.resnets.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.3.resnets.1.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.3.resnets.1.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.3.resnets.1.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.3.resnets.1.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.3.resnets.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.3.resnets.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.3.resnets.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.down_blocks.3.resnets.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.mid_block.attentions.0.group_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.mid_block.attentions.0.group_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.mid_block.attentions.0.to_k.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.mid_block.attentions.0.to_k.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.mid_block.attentions.0.to_out.0.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.mid_block.attentions.0.to_out.0.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.mid_block.attentions.0.to_q.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.mid_block.attentions.0.to_q.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.mid_block.attentions.0.to_v.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.mid_block.attentions.0.to_v.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.mid_block.resnets.0.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.mid_block.resnets.0.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.mid_block.resnets.0.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.mid_block.resnets.0.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.mid_block.resnets.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.mid_block.resnets.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.mid_block.resnets.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.mid_block.resnets.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.mid_block.resnets.1.conv1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.mid_block.resnets.1.conv1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.mid_block.resnets.1.conv2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.mid_block.resnets.1.conv2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.mid_block.resnets.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.mid_block.resnets.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.mid_block.resnets.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.encoder.mid_block.resnets.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.post_quant_conv.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.post_quant_conv.weight": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.quant_conv.bias": "pytorch_model-00002-of-00002.bin",
+    "sd.sd_vae.quant_conv.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.0.blocks.0.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.0.blocks.0.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.0.blocks.0.attn.qkv.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.0.blocks.0.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.0.blocks.0.attn.relative_position_bias_table": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.0.blocks.0.attn.relative_position_index": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.0.blocks.0.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.0.blocks.0.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.0.blocks.0.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.0.blocks.0.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.0.blocks.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.0.blocks.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.0.blocks.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.0.blocks.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.0.blocks.1.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.0.blocks.1.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.0.blocks.1.attn.qkv.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.0.blocks.1.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.0.blocks.1.attn.relative_position_bias_table": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.0.blocks.1.attn.relative_position_index": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.0.blocks.1.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.0.blocks.1.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.0.blocks.1.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.0.blocks.1.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.0.blocks.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.0.blocks.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.0.blocks.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.0.blocks.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.0.downsample.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.0.downsample.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.0.downsample.reduction.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.1.blocks.0.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.1.blocks.0.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.1.blocks.0.attn.qkv.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.1.blocks.0.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.1.blocks.0.attn.relative_position_bias_table": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.1.blocks.0.attn.relative_position_index": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.1.blocks.0.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.1.blocks.0.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.1.blocks.0.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.1.blocks.0.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.1.blocks.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.1.blocks.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.1.blocks.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.1.blocks.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.1.blocks.1.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.1.blocks.1.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.1.blocks.1.attn.qkv.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.1.blocks.1.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.1.blocks.1.attn.relative_position_bias_table": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.1.blocks.1.attn.relative_position_index": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.1.blocks.1.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.1.blocks.1.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.1.blocks.1.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.1.blocks.1.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.1.blocks.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.1.blocks.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.1.blocks.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.1.blocks.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.1.downsample.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.1.downsample.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.1.downsample.reduction.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.0.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.0.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.0.attn.qkv.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.0.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.0.attn.relative_position_bias_table": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.0.attn.relative_position_index": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.0.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.0.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.0.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.0.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.1.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.1.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.1.attn.qkv.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.1.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.1.attn.relative_position_bias_table": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.1.attn.relative_position_index": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.1.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.1.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.1.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.1.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.2.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.2.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.2.attn.qkv.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.2.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.2.attn.relative_position_bias_table": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.2.attn.relative_position_index": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.2.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.2.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.2.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.2.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.2.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.2.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.2.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.2.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.3.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.3.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.3.attn.qkv.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.3.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.3.attn.relative_position_bias_table": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.3.attn.relative_position_index": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.3.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.3.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.3.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.3.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.3.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.3.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.3.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.3.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.4.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.4.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.4.attn.qkv.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.4.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.4.attn.relative_position_bias_table": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.4.attn.relative_position_index": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.4.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.4.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.4.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.4.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.4.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.4.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.4.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.4.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.5.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.5.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.5.attn.qkv.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.5.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.5.attn.relative_position_bias_table": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.5.attn.relative_position_index": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.5.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.5.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.5.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.5.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.5.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.5.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.5.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.blocks.5.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.downsample.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.downsample.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.2.downsample.reduction.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.3.blocks.0.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.3.blocks.0.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.3.blocks.0.attn.qkv.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.3.blocks.0.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.3.blocks.0.attn.relative_position_bias_table": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.3.blocks.0.attn.relative_position_index": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.3.blocks.0.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.3.blocks.0.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.3.blocks.0.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.3.blocks.0.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.3.blocks.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.3.blocks.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.3.blocks.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.3.blocks.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.3.blocks.1.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.3.blocks.1.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.3.blocks.1.attn.qkv.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.3.blocks.1.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.3.blocks.1.attn.relative_position_bias_table": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.3.blocks.1.attn.relative_position_index": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.3.blocks.1.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.3.blocks.1.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.3.blocks.1.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.3.blocks.1.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.3.blocks.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.3.blocks.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.3.blocks.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.layers.3.blocks.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.patch_embed.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.patch_embed.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.patch_embed.proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.backbone.0.patch_embed.proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.bbox_embed.0.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.bbox_embed.0.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.bbox_embed.0.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.bbox_embed.0.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.bbox_embed.0.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.bbox_embed.0.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.bbox_embed.1.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.bbox_embed.1.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.bbox_embed.1.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.bbox_embed.1.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.bbox_embed.1.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.bbox_embed.1.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.bbox_embed.2.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.bbox_embed.2.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.bbox_embed.2.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.bbox_embed.2.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.bbox_embed.2.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.bbox_embed.2.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.bbox_embed.3.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.bbox_embed.3.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.bbox_embed.3.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.bbox_embed.3.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.bbox_embed.3.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.bbox_embed.3.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.bbox_embed.4.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.bbox_embed.4.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.bbox_embed.4.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.bbox_embed.4.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.bbox_embed.4.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.bbox_embed.4.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.bbox_embed.5.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.bbox_embed.5.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.bbox_embed.5.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.bbox_embed.5.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.bbox_embed.5.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.bbox_embed.5.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.input_proj.0.0.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.input_proj.0.0.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.input_proj.0.1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.input_proj.0.1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.input_proj.1.0.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.input_proj.1.0.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.input_proj.1.1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.input_proj.1.1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.input_proj.2.0.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.input_proj.2.0.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.input_proj.2.1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.input_proj.2.1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.input_proj.3.0.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.input_proj.3.0.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.input_proj.3.1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.input_proj.3.1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_embed.0.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_embed.0.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_embed.0.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_embed.0.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_embed.0.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_embed.0.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_embed.1.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_embed.1.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_embed.1.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_embed.1.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_embed.1.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_embed.1.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_embed.2.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_embed.2.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_embed.2.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_embed.2.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_embed.2.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_embed.2.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_embed.3.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_embed.3.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_embed.3.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_embed.3.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_embed.3.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_embed.3.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_embed.4.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_embed.4.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_embed.4.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_embed.4.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_embed.4.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_embed.4.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_hw_embed.0.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_hw_embed.0.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_hw_embed.0.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_hw_embed.0.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_hw_embed.0.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_hw_embed.0.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_hw_embed.1.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_hw_embed.1.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_hw_embed.1.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_hw_embed.1.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_hw_embed.1.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_hw_embed.1.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_hw_embed.2.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_hw_embed.2.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_hw_embed.2.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_hw_embed.2.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_hw_embed.2.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_hw_embed.2.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_hw_embed.3.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_hw_embed.3.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_hw_embed.3.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_hw_embed.3.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_hw_embed.3.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.pose_hw_embed.3.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.projection_kpt_llava.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.projection_kpt_llava.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.projection_kpt_llava.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.projection_kpt_llava.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.projection_kpt_llava.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.projection_kpt_llava.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.projection_llava.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.projection_llava.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.projection_llava.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.projection_llava.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.projection_llava.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.projection_llava.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.bbox_embed.0.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.bbox_embed.0.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.bbox_embed.0.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.bbox_embed.0.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.bbox_embed.0.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.bbox_embed.0.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.bbox_embed.1.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.bbox_embed.1.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.bbox_embed.1.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.bbox_embed.1.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.bbox_embed.1.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.bbox_embed.1.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.bbox_embed.2.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.bbox_embed.2.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.bbox_embed.2.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.bbox_embed.2.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.bbox_embed.2.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.bbox_embed.2.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.bbox_embed.3.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.bbox_embed.3.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.bbox_embed.3.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.bbox_embed.3.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.bbox_embed.3.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.bbox_embed.3.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.bbox_embed.4.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.bbox_embed.4.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.bbox_embed.4.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.bbox_embed.4.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.bbox_embed.4.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.bbox_embed.4.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.bbox_embed.5.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.bbox_embed.5.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.bbox_embed.5.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.bbox_embed.5.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.bbox_embed.5.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.bbox_embed.5.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.hw.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.hw_append.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.0.ca_text.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.0.ca_text.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.0.ca_text.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.0.ca_text.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.0.catext_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.0.catext_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.0.cross_attn.attention_weights.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.0.cross_attn.attention_weights.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.0.cross_attn.output_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.0.cross_attn.output_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.0.cross_attn.sampling_offsets.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.0.cross_attn.sampling_offsets.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.0.cross_attn.value_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.0.cross_attn.value_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.0.linear1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.0.linear1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.0.linear2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.0.linear2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.0.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.0.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.0.self_attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.0.self_attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.1.ca_text.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.1.ca_text.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.1.ca_text.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.1.ca_text.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.1.catext_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.1.catext_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.1.cross_attn.attention_weights.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.1.cross_attn.attention_weights.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.1.cross_attn.output_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.1.cross_attn.output_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.1.cross_attn.sampling_offsets.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.1.cross_attn.sampling_offsets.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.1.cross_attn.value_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.1.cross_attn.value_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.1.linear1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.1.linear1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.1.linear2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.1.linear2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.1.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.1.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.1.self_attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.1.self_attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.2.ca_text.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.2.ca_text.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.2.ca_text.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.2.ca_text.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.2.catext_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.2.catext_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.2.cross_attn.attention_weights.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.2.cross_attn.attention_weights.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.2.cross_attn.output_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.2.cross_attn.output_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.2.cross_attn.sampling_offsets.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.2.cross_attn.sampling_offsets.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.2.cross_attn.value_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.2.cross_attn.value_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.2.linear1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.2.linear1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.2.linear2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.2.linear2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.2.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.2.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.2.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.2.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.2.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.2.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.2.self_attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.2.self_attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.3.ca_text.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.3.ca_text.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.3.ca_text.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.3.ca_text.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.3.catext_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.3.catext_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.3.cross_attn.attention_weights.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.3.cross_attn.attention_weights.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.3.cross_attn.output_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.3.cross_attn.output_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.3.cross_attn.sampling_offsets.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.3.cross_attn.sampling_offsets.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.3.cross_attn.value_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.3.cross_attn.value_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.3.linear1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.3.linear1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.3.linear2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.3.linear2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.3.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.3.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.3.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.3.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.3.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.3.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.3.self_attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.3.self_attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.4.ca_text.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.4.ca_text.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.4.ca_text.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.4.ca_text.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.4.catext_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.4.catext_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.4.cross_attn.attention_weights.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.4.cross_attn.attention_weights.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.4.cross_attn.output_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.4.cross_attn.output_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.4.cross_attn.sampling_offsets.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.4.cross_attn.sampling_offsets.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.4.cross_attn.value_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.4.cross_attn.value_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.4.linear1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.4.linear1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.4.linear2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.4.linear2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.4.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.4.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.4.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.4.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.4.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.4.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.4.self_attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.4.self_attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.5.ca_text.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.5.ca_text.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.5.ca_text.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.5.ca_text.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.5.catext_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.5.catext_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.5.cross_attn.attention_weights.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.5.cross_attn.attention_weights.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.5.cross_attn.output_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.5.cross_attn.output_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.5.cross_attn.sampling_offsets.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.5.cross_attn.sampling_offsets.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.5.cross_attn.value_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.5.cross_attn.value_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.5.linear1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.5.linear1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.5.linear2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.5.linear2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.5.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.5.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.5.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.5.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.5.norm3.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.5.norm3.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.5.self_attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.5.self_attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_embed.0.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_embed.0.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_embed.0.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_embed.0.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_embed.0.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_embed.0.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_embed.1.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_embed.1.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_embed.1.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_embed.1.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_embed.1.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_embed.1.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_embed.2.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_embed.2.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_embed.2.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_embed.2.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_embed.2.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_embed.2.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_embed.3.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_embed.3.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_embed.3.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_embed.3.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_embed.3.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_embed.3.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_embed.4.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_embed.4.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_embed.4.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_embed.4.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_embed.4.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_embed.4.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_hw_embed.0.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_hw_embed.0.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_hw_embed.0.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_hw_embed.0.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_hw_embed.0.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_hw_embed.0.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_hw_embed.1.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_hw_embed.1.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_hw_embed.1.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_hw_embed.1.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_hw_embed.1.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_hw_embed.1.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_hw_embed.2.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_hw_embed.2.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_hw_embed.2.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_hw_embed.2.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_hw_embed.2.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_hw_embed.2.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_hw_embed.3.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_hw_embed.3.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_hw_embed.3.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_hw_embed.3.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_hw_embed.3.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.pose_hw_embed.3.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.ref_point_head.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.ref_point_head.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.ref_point_head.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.decoder.ref_point_head.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.enc_out_bbox_embed.layers.0.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.enc_out_bbox_embed.layers.0.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.enc_out_bbox_embed.layers.1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.enc_out_bbox_embed.layers.1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.enc_out_bbox_embed.layers.2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.enc_out_bbox_embed.layers.2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.enc_output.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.enc_output.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.enc_output_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.enc_output_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.0.attn.l_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.0.attn.l_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.0.attn.out_l_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.0.attn.out_l_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.0.attn.out_v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.0.attn.out_v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.0.attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.0.attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.0.attn.values_l_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.0.attn.values_l_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.0.attn.values_v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.0.attn.values_v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.0.gam_l": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.0.gam_v": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.0.layer_norm_l.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.0.layer_norm_l.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.0.layer_norm_v.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.0.layer_norm_v.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.1.attn.l_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.1.attn.l_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.1.attn.out_l_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.1.attn.out_l_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.1.attn.out_v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.1.attn.out_v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.1.attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.1.attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.1.attn.values_l_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.1.attn.values_l_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.1.attn.values_v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.1.attn.values_v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.1.gam_l": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.1.gam_v": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.1.layer_norm_l.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.1.layer_norm_l.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.1.layer_norm_v.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.1.layer_norm_v.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.2.attn.l_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.2.attn.l_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.2.attn.out_l_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.2.attn.out_l_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.2.attn.out_v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.2.attn.out_v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.2.attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.2.attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.2.attn.values_l_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.2.attn.values_l_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.2.attn.values_v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.2.attn.values_v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.2.gam_l": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.2.gam_v": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.2.layer_norm_l.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.2.layer_norm_l.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.2.layer_norm_v.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.2.layer_norm_v.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.3.attn.l_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.3.attn.l_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.3.attn.out_l_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.3.attn.out_l_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.3.attn.out_v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.3.attn.out_v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.3.attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.3.attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.3.attn.values_l_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.3.attn.values_l_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.3.attn.values_v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.3.attn.values_v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.3.gam_l": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.3.gam_v": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.3.layer_norm_l.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.3.layer_norm_l.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.3.layer_norm_v.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.3.layer_norm_v.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.4.attn.l_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.4.attn.l_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.4.attn.out_l_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.4.attn.out_l_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.4.attn.out_v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.4.attn.out_v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.4.attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.4.attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.4.attn.values_l_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.4.attn.values_l_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.4.attn.values_v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.4.attn.values_v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.4.gam_l": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.4.gam_v": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.4.layer_norm_l.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.4.layer_norm_l.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.4.layer_norm_v.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.4.layer_norm_v.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.5.attn.l_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.5.attn.l_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.5.attn.out_l_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.5.attn.out_l_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.5.attn.out_v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.5.attn.out_v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.5.attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.5.attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.5.attn.values_l_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.5.attn.values_l_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.5.attn.values_v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.5.attn.values_v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.5.gam_l": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.5.gam_v": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.5.layer_norm_l.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.5.layer_norm_l.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.5.layer_norm_v.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.fusion_layers.5.layer_norm_v.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.0.linear1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.0.linear1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.0.linear2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.0.linear2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.0.self_attn.attention_weights.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.0.self_attn.attention_weights.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.0.self_attn.output_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.0.self_attn.output_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.0.self_attn.sampling_offsets.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.0.self_attn.sampling_offsets.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.0.self_attn.value_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.0.self_attn.value_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.1.linear1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.1.linear1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.1.linear2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.1.linear2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.1.self_attn.attention_weights.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.1.self_attn.attention_weights.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.1.self_attn.output_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.1.self_attn.output_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.1.self_attn.sampling_offsets.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.1.self_attn.sampling_offsets.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.1.self_attn.value_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.1.self_attn.value_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.2.linear1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.2.linear1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.2.linear2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.2.linear2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.2.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.2.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.2.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.2.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.2.self_attn.attention_weights.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.2.self_attn.attention_weights.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.2.self_attn.output_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.2.self_attn.output_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.2.self_attn.sampling_offsets.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.2.self_attn.sampling_offsets.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.2.self_attn.value_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.2.self_attn.value_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.3.linear1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.3.linear1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.3.linear2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.3.linear2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.3.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.3.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.3.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.3.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.3.self_attn.attention_weights.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.3.self_attn.attention_weights.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.3.self_attn.output_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.3.self_attn.output_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.3.self_attn.sampling_offsets.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.3.self_attn.sampling_offsets.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.3.self_attn.value_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.3.self_attn.value_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.4.linear1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.4.linear1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.4.linear2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.4.linear2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.4.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.4.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.4.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.4.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.4.self_attn.attention_weights.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.4.self_attn.attention_weights.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.4.self_attn.output_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.4.self_attn.output_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.4.self_attn.sampling_offsets.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.4.self_attn.sampling_offsets.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.4.self_attn.value_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.4.self_attn.value_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.5.linear1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.5.linear1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.5.linear2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.5.linear2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.5.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.5.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.5.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.5.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.5.self_attn.attention_weights.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.5.self_attn.attention_weights.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.5.self_attn.output_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.5.self_attn.output_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.5.self_attn.sampling_offsets.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.5.self_attn.sampling_offsets.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.5.self_attn.value_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.layers.5.self_attn.value_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.0.linear1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.0.linear1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.0.linear2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.0.linear2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.0.self_attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.0.self_attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.0.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.0.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.1.linear1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.1.linear1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.1.linear2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.1.linear2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.1.self_attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.1.self_attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.1.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.1.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.2.linear1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.2.linear1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.2.linear2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.2.linear2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.2.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.2.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.2.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.2.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.2.self_attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.2.self_attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.2.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.2.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.3.linear1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.3.linear1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.3.linear2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.3.linear2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.3.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.3.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.3.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.3.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.3.self_attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.3.self_attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.3.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.3.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.4.linear1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.4.linear1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.4.linear2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.4.linear2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.4.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.4.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.4.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.4.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.4.self_attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.4.self_attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.4.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.4.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.5.linear1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.5.linear1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.5.linear2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.5.linear2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.5.norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.5.norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.5.norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.5.norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.5.self_attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.5.self_attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.5.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.encoder.text_layers.5.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.level_embed": "pytorch_model-00002-of-00002.bin",
+    "unipose.transformer.tgt_embed.weight": "pytorch_model-00002-of-00002.bin",
+    "vis_encoder.vision_model.embeddings.class_embedding": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.embeddings.patch_embedding.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.embeddings.position_embedding.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.post_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.post_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.pre_layrnorm.bias": "pytorch_model-00001-of-00002.bin",
+    "vis_encoder.vision_model.pre_layrnorm.weight": "pytorch_model-00001-of-00002.bin",
+    "vl_bridge.0.bias": "pytorch_model-00002-of-00002.bin",
+    "vl_bridge.0.weight": "pytorch_model-00002-of-00002.bin",
+    "vl_bridge.2.bias": "pytorch_model-00002-of-00002.bin",
+    "vl_bridge.2.weight": "pytorch_model-00002-of-00002.bin"
+  }
+}