diff --git "a/model.safetensors.index.json" "b/model.safetensors.index.json"
new file mode 100644--- /dev/null
+++ "b/model.safetensors.index.json"
@@ -0,0 +1,1129 @@
+{
+  "metadata": {
+    "total_size": 25466005224
+  },
+  "weight_map": {
+    "text_encoder.bert.embeddings.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.embeddings.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.embeddings.position_embeddings.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.embeddings.position_ids": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.embeddings.token_type_embeddings.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.embeddings.word_embeddings.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.0.attention.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.0.attention.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.0.attention.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.0.attention.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.0.attention.self.key.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.0.attention.self.key.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.0.attention.self.query.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.0.attention.self.query.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.0.attention.self.value.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.0.attention.self.value.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.0.intermediate.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.0.intermediate.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.0.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.0.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.0.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.0.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.1.attention.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.1.attention.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.1.attention.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.1.attention.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.1.attention.self.key.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.1.attention.self.key.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.1.attention.self.query.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.1.attention.self.query.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.1.attention.self.value.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.1.attention.self.value.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.1.intermediate.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.1.intermediate.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.1.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.1.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.1.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.1.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.10.attention.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.10.attention.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.10.attention.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.10.attention.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.10.attention.self.key.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.10.attention.self.key.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.10.attention.self.query.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.10.attention.self.query.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.10.attention.self.value.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.10.attention.self.value.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.10.intermediate.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.10.intermediate.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.10.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.10.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.10.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.10.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.11.attention.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.11.attention.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.11.attention.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.11.attention.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.11.attention.self.key.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.11.attention.self.key.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.11.attention.self.query.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.11.attention.self.query.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.11.attention.self.value.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.11.attention.self.value.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.11.intermediate.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.11.intermediate.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.11.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.11.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.11.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.11.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.12.attention.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.12.attention.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.12.attention.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.12.attention.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.12.attention.self.key.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.12.attention.self.key.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.12.attention.self.query.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.12.attention.self.query.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.12.attention.self.value.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.12.attention.self.value.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.12.intermediate.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.12.intermediate.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.12.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.12.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.12.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.12.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.13.attention.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.13.attention.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.13.attention.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.13.attention.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.13.attention.self.key.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.13.attention.self.key.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.13.attention.self.query.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.13.attention.self.query.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.13.attention.self.value.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.13.attention.self.value.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.13.intermediate.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.13.intermediate.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.13.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.13.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.13.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.13.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.14.attention.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.14.attention.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.14.attention.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.14.attention.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.14.attention.self.key.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.14.attention.self.key.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.14.attention.self.query.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.14.attention.self.query.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.14.attention.self.value.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.14.attention.self.value.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.14.intermediate.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.14.intermediate.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.14.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.14.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.14.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.14.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.15.attention.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.15.attention.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.15.attention.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.15.attention.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.15.attention.self.key.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.15.attention.self.key.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.15.attention.self.query.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.15.attention.self.query.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.15.attention.self.value.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.15.attention.self.value.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.15.intermediate.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.15.intermediate.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.15.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.15.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.15.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.15.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.16.attention.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.16.attention.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.16.attention.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.16.attention.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.16.attention.self.key.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.16.attention.self.key.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.16.attention.self.query.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.16.attention.self.query.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.16.attention.self.value.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.16.attention.self.value.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.16.intermediate.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.16.intermediate.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.16.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.16.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.16.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.16.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.17.attention.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.17.attention.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.17.attention.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.17.attention.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.17.attention.self.key.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.17.attention.self.key.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.17.attention.self.query.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.17.attention.self.query.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.17.attention.self.value.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.17.attention.self.value.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.17.intermediate.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.17.intermediate.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.17.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.17.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.17.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.17.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.18.attention.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.18.attention.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.18.attention.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.18.attention.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.18.attention.self.key.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.18.attention.self.key.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.18.attention.self.query.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.18.attention.self.query.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.18.attention.self.value.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.18.attention.self.value.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.18.intermediate.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.18.intermediate.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.18.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.18.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.18.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.18.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.19.attention.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.19.attention.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.19.attention.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.19.attention.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.19.attention.self.key.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.19.attention.self.key.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.19.attention.self.query.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.19.attention.self.query.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.19.attention.self.value.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.19.attention.self.value.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.19.crossattention.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.19.crossattention.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.19.crossattention.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.19.crossattention.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.19.crossattention.self.key.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.19.crossattention.self.key.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.19.crossattention.self.query.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.19.crossattention.self.query.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.19.crossattention.self.value.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.19.crossattention.self.value.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.19.intermediate.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.19.intermediate.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.19.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.19.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.19.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.19.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.2.attention.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.2.attention.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.2.attention.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.2.attention.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.2.attention.self.key.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.2.attention.self.key.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.2.attention.self.query.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.2.attention.self.query.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.2.attention.self.value.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.2.attention.self.value.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.2.intermediate.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.2.intermediate.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.2.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.2.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.2.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.2.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.20.attention.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.20.attention.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.20.attention.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.20.attention.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.20.attention.self.key.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.20.attention.self.key.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.20.attention.self.query.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.20.attention.self.query.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.20.attention.self.value.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.20.attention.self.value.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.20.crossattention.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.20.crossattention.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.20.crossattention.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.20.crossattention.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.20.crossattention.self.key.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.20.crossattention.self.key.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.20.crossattention.self.query.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.20.crossattention.self.query.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.20.crossattention.self.value.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.20.crossattention.self.value.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.20.intermediate.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.20.intermediate.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.20.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.20.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.20.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.20.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.21.attention.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.21.attention.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.21.attention.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.21.attention.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.21.attention.self.key.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.21.attention.self.key.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.21.attention.self.query.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.21.attention.self.query.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.21.attention.self.value.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.21.attention.self.value.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.21.crossattention.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.21.crossattention.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.21.crossattention.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.21.crossattention.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.21.crossattention.self.key.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.21.crossattention.self.key.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.21.crossattention.self.query.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.21.crossattention.self.query.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.21.crossattention.self.value.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.21.crossattention.self.value.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.21.intermediate.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.21.intermediate.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.21.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.21.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.21.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.21.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.22.attention.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.22.attention.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.22.attention.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.22.attention.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.22.attention.self.key.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.22.attention.self.key.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.22.attention.self.query.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.22.attention.self.query.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.22.attention.self.value.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.22.attention.self.value.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.22.crossattention.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.22.crossattention.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.22.crossattention.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.22.crossattention.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.22.crossattention.self.key.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.22.crossattention.self.key.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.22.crossattention.self.query.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.22.crossattention.self.query.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.22.crossattention.self.value.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.22.crossattention.self.value.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.22.intermediate.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.22.intermediate.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.22.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.22.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.22.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.22.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.23.attention.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.23.attention.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.23.attention.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.23.attention.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.23.attention.self.key.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.23.attention.self.key.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.23.attention.self.query.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.23.attention.self.query.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.23.attention.self.value.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.23.attention.self.value.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.23.crossattention.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.23.crossattention.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.23.crossattention.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.23.crossattention.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.23.crossattention.self.key.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.23.crossattention.self.key.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.23.crossattention.self.query.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.23.crossattention.self.query.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.23.crossattention.self.value.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.23.crossattention.self.value.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.23.intermediate.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.23.intermediate.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.23.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.23.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.23.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.23.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.3.attention.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.3.attention.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.3.attention.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.3.attention.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.3.attention.self.key.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.3.attention.self.key.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.3.attention.self.query.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.3.attention.self.query.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.3.attention.self.value.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.3.attention.self.value.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.3.intermediate.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.3.intermediate.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.3.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.3.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.3.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.3.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.4.attention.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.4.attention.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.4.attention.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.4.attention.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.4.attention.self.key.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.4.attention.self.key.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.4.attention.self.query.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.4.attention.self.query.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.4.attention.self.value.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.4.attention.self.value.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.4.intermediate.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.4.intermediate.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.4.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.4.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.4.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.4.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.5.attention.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.5.attention.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.5.attention.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.5.attention.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.5.attention.self.key.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.5.attention.self.key.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.5.attention.self.query.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.5.attention.self.query.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.5.attention.self.value.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.5.attention.self.value.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.5.intermediate.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.5.intermediate.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.5.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.5.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.5.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.5.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.6.attention.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.6.attention.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.6.attention.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.6.attention.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.6.attention.self.key.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.6.attention.self.key.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.6.attention.self.query.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.6.attention.self.query.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.6.attention.self.value.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.6.attention.self.value.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.6.intermediate.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.6.intermediate.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.6.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.6.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.6.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.6.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.7.attention.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.7.attention.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.7.attention.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.7.attention.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.7.attention.self.key.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.7.attention.self.key.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.7.attention.self.query.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.7.attention.self.query.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.7.attention.self.value.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.7.attention.self.value.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.7.intermediate.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.7.intermediate.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.7.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.7.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.7.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.7.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.8.attention.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.8.attention.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.8.attention.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.8.attention.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.8.attention.self.key.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.8.attention.self.key.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.8.attention.self.query.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.8.attention.self.query.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.8.attention.self.value.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.8.attention.self.value.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.8.intermediate.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.8.intermediate.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.8.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.8.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.8.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.8.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.9.attention.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.9.attention.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.9.attention.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.9.attention.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.9.attention.self.key.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.9.attention.self.key.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.9.attention.self.query.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.9.attention.self.query.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.9.attention.self.value.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.9.attention.self.value.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.9.intermediate.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.9.intermediate.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.9.output.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.9.output.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.9.output.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.bert.encoder.layer.9.output.dense.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.cls.predictions.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.cls.predictions.transform.LayerNorm.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.cls.predictions.transform.LayerNorm.weight": "model-00013-of-00013.safetensors",
+    "text_encoder.cls.predictions.transform.dense.bias": "model-00013-of-00013.safetensors",
+    "text_encoder.cls.predictions.transform.dense.weight": "model-00013-of-00013.safetensors",
+    "text_proj.bias": "model-00013-of-00013.safetensors",
+    "text_proj.weight": "model-00013-of-00013.safetensors",
+    "vision_encoder.blocks.0.attn.k_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.0.attn.proj.bias": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.0.attn.proj.weight": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.0.attn.q_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.0.attn.qkv.weight": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.0.ls1.gamma": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.0.ls2.gamma": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.0.mlp.fc1.bias": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.0.mlp.fc1.weight": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.0.mlp.fc2.bias": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.0.mlp.fc2.weight": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.0.norm1.weight": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.0.norm2.weight": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.1.attn.k_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.1.attn.proj.bias": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.1.attn.proj.weight": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.1.attn.q_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.1.attn.qkv.weight": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.1.ls1.gamma": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.1.ls2.gamma": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.1.mlp.fc1.bias": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.1.mlp.fc1.weight": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.1.mlp.fc2.bias": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.1.mlp.fc2.weight": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.1.norm1.weight": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.1.norm2.weight": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.10.attn.k_norm.weight": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.10.attn.proj.bias": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.10.attn.proj.weight": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.10.attn.q_norm.weight": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.10.attn.qkv.weight": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.10.ls1.gamma": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.10.ls2.gamma": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.10.mlp.fc1.bias": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.10.mlp.fc1.weight": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.10.mlp.fc2.bias": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.10.mlp.fc2.weight": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.10.norm1.weight": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.10.norm2.weight": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.11.attn.k_norm.weight": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.11.attn.proj.bias": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.11.attn.proj.weight": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.11.attn.q_norm.weight": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.11.attn.qkv.weight": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.11.ls1.gamma": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.11.ls2.gamma": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.11.mlp.fc1.bias": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.11.mlp.fc1.weight": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.11.mlp.fc2.bias": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.11.mlp.fc2.weight": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.11.norm1.weight": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.11.norm2.weight": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.12.attn.k_norm.weight": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.12.attn.proj.bias": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.12.attn.proj.weight": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.12.attn.q_norm.weight": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.12.attn.qkv.weight": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.12.ls1.gamma": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.12.ls2.gamma": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.12.mlp.fc1.bias": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.12.mlp.fc1.weight": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.12.mlp.fc2.bias": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.12.mlp.fc2.weight": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.12.norm1.weight": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.12.norm2.weight": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.13.attn.k_norm.weight": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.13.attn.proj.bias": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.13.attn.proj.weight": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.13.attn.q_norm.weight": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.13.attn.qkv.weight": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.13.ls1.gamma": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.13.ls2.gamma": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.13.mlp.fc1.bias": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.13.mlp.fc1.weight": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.13.mlp.fc2.bias": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.13.mlp.fc2.weight": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.13.norm1.weight": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.13.norm2.weight": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.14.attn.k_norm.weight": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.14.attn.proj.bias": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.14.attn.proj.weight": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.14.attn.q_norm.weight": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.14.attn.qkv.weight": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.14.ls1.gamma": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.14.ls2.gamma": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.14.mlp.fc1.bias": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.14.mlp.fc1.weight": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.14.mlp.fc2.bias": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.14.mlp.fc2.weight": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.14.norm1.weight": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.14.norm2.weight": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.15.attn.k_norm.weight": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.15.attn.proj.bias": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.15.attn.proj.weight": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.15.attn.q_norm.weight": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.15.attn.qkv.weight": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.15.ls1.gamma": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.15.ls2.gamma": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.15.mlp.fc1.bias": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.15.mlp.fc1.weight": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.15.mlp.fc2.bias": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.15.mlp.fc2.weight": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.15.norm1.weight": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.15.norm2.weight": "model-00004-of-00013.safetensors",
+    "vision_encoder.blocks.16.attn.k_norm.weight": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.16.attn.proj.bias": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.16.attn.proj.weight": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.16.attn.q_norm.weight": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.16.attn.qkv.weight": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.16.ls1.gamma": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.16.ls2.gamma": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.16.mlp.fc1.bias": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.16.mlp.fc1.weight": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.16.mlp.fc2.bias": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.16.mlp.fc2.weight": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.16.norm1.weight": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.16.norm2.weight": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.17.attn.k_norm.weight": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.17.attn.proj.bias": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.17.attn.proj.weight": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.17.attn.q_norm.weight": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.17.attn.qkv.weight": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.17.ls1.gamma": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.17.ls2.gamma": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.17.mlp.fc1.bias": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.17.mlp.fc1.weight": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.17.mlp.fc2.bias": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.17.mlp.fc2.weight": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.17.norm1.weight": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.17.norm2.weight": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.18.attn.k_norm.weight": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.18.attn.proj.bias": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.18.attn.proj.weight": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.18.attn.q_norm.weight": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.18.attn.qkv.weight": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.18.ls1.gamma": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.18.ls2.gamma": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.18.mlp.fc1.bias": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.18.mlp.fc1.weight": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.18.mlp.fc2.bias": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.18.mlp.fc2.weight": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.18.norm1.weight": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.18.norm2.weight": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.19.attn.k_norm.weight": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.19.attn.proj.bias": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.19.attn.proj.weight": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.19.attn.q_norm.weight": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.19.attn.qkv.weight": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.19.ls1.gamma": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.19.ls2.gamma": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.19.mlp.fc1.bias": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.19.mlp.fc1.weight": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.19.mlp.fc2.bias": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.19.mlp.fc2.weight": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.19.norm1.weight": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.19.norm2.weight": "model-00005-of-00013.safetensors",
+    "vision_encoder.blocks.2.attn.k_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.2.attn.proj.bias": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.2.attn.proj.weight": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.2.attn.q_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.2.attn.qkv.weight": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.2.ls1.gamma": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.2.ls2.gamma": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.2.mlp.fc1.bias": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.2.mlp.fc1.weight": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.2.mlp.fc2.bias": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.2.mlp.fc2.weight": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.2.norm1.weight": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.2.norm2.weight": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.20.attn.k_norm.weight": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.20.attn.proj.bias": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.20.attn.proj.weight": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.20.attn.q_norm.weight": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.20.attn.qkv.weight": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.20.ls1.gamma": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.20.ls2.gamma": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.20.mlp.fc1.bias": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.20.mlp.fc1.weight": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.20.mlp.fc2.bias": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.20.mlp.fc2.weight": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.20.norm1.weight": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.20.norm2.weight": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.21.attn.k_norm.weight": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.21.attn.proj.bias": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.21.attn.proj.weight": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.21.attn.q_norm.weight": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.21.attn.qkv.weight": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.21.ls1.gamma": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.21.ls2.gamma": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.21.mlp.fc1.bias": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.21.mlp.fc1.weight": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.21.mlp.fc2.bias": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.21.mlp.fc2.weight": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.21.norm1.weight": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.21.norm2.weight": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.22.attn.k_norm.weight": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.22.attn.proj.bias": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.22.attn.proj.weight": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.22.attn.q_norm.weight": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.22.attn.qkv.weight": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.22.ls1.gamma": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.22.ls2.gamma": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.22.mlp.fc1.bias": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.22.mlp.fc1.weight": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.22.mlp.fc2.bias": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.22.mlp.fc2.weight": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.22.norm1.weight": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.22.norm2.weight": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.23.attn.k_norm.weight": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.23.attn.proj.bias": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.23.attn.proj.weight": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.23.attn.q_norm.weight": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.23.attn.qkv.weight": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.23.ls1.gamma": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.23.ls2.gamma": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.23.mlp.fc1.bias": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.23.mlp.fc1.weight": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.23.mlp.fc2.bias": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.23.mlp.fc2.weight": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.23.norm1.weight": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.23.norm2.weight": "model-00006-of-00013.safetensors",
+    "vision_encoder.blocks.24.attn.k_norm.weight": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.24.attn.proj.bias": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.24.attn.proj.weight": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.24.attn.q_norm.weight": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.24.attn.qkv.weight": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.24.ls1.gamma": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.24.ls2.gamma": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.24.mlp.fc1.bias": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.24.mlp.fc1.weight": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.24.mlp.fc2.bias": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.24.mlp.fc2.weight": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.24.norm1.weight": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.24.norm2.weight": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.25.attn.k_norm.weight": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.25.attn.proj.bias": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.25.attn.proj.weight": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.25.attn.q_norm.weight": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.25.attn.qkv.weight": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.25.ls1.gamma": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.25.ls2.gamma": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.25.mlp.fc1.bias": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.25.mlp.fc1.weight": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.25.mlp.fc2.bias": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.25.mlp.fc2.weight": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.25.norm1.weight": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.25.norm2.weight": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.26.attn.k_norm.weight": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.26.attn.proj.bias": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.26.attn.proj.weight": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.26.attn.q_norm.weight": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.26.attn.qkv.weight": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.26.ls1.gamma": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.26.ls2.gamma": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.26.mlp.fc1.bias": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.26.mlp.fc1.weight": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.26.mlp.fc2.bias": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.26.mlp.fc2.weight": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.26.norm1.weight": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.26.norm2.weight": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.27.attn.k_norm.weight": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.27.attn.proj.bias": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.27.attn.proj.weight": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.27.attn.q_norm.weight": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.27.attn.qkv.weight": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.27.ls1.gamma": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.27.ls2.gamma": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.27.mlp.fc1.bias": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.27.mlp.fc1.weight": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.27.mlp.fc2.bias": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.27.mlp.fc2.weight": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.27.norm1.weight": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.27.norm2.weight": "model-00007-of-00013.safetensors",
+    "vision_encoder.blocks.28.attn.k_norm.weight": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.28.attn.proj.bias": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.28.attn.proj.weight": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.28.attn.q_norm.weight": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.28.attn.qkv.weight": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.28.ls1.gamma": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.28.ls2.gamma": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.28.mlp.fc1.bias": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.28.mlp.fc1.weight": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.28.mlp.fc2.bias": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.28.mlp.fc2.weight": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.28.norm1.weight": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.28.norm2.weight": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.29.attn.k_norm.weight": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.29.attn.proj.bias": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.29.attn.proj.weight": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.29.attn.q_norm.weight": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.29.attn.qkv.weight": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.29.ls1.gamma": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.29.ls2.gamma": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.29.mlp.fc1.bias": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.29.mlp.fc1.weight": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.29.mlp.fc2.bias": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.29.mlp.fc2.weight": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.29.norm1.weight": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.29.norm2.weight": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.3.attn.k_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.3.attn.proj.bias": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.3.attn.proj.weight": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.3.attn.q_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.3.attn.qkv.weight": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.3.ls1.gamma": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.3.ls2.gamma": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.3.mlp.fc1.bias": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.3.mlp.fc1.weight": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.3.mlp.fc2.bias": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.3.mlp.fc2.weight": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.3.norm1.weight": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.3.norm2.weight": "model-00001-of-00013.safetensors",
+    "vision_encoder.blocks.30.attn.k_norm.weight": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.30.attn.proj.bias": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.30.attn.proj.weight": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.30.attn.q_norm.weight": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.30.attn.qkv.weight": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.30.ls1.gamma": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.30.ls2.gamma": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.30.mlp.fc1.bias": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.30.mlp.fc1.weight": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.30.mlp.fc2.bias": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.30.mlp.fc2.weight": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.30.norm1.weight": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.30.norm2.weight": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.31.attn.k_norm.weight": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.31.attn.proj.bias": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.31.attn.proj.weight": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.31.attn.q_norm.weight": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.31.attn.qkv.weight": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.31.ls1.gamma": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.31.ls2.gamma": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.31.mlp.fc1.bias": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.31.mlp.fc1.weight": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.31.mlp.fc2.bias": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.31.mlp.fc2.weight": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.31.norm1.weight": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.31.norm2.weight": "model-00008-of-00013.safetensors",
+    "vision_encoder.blocks.32.attn.k_norm.weight": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.32.attn.proj.bias": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.32.attn.proj.weight": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.32.attn.q_norm.weight": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.32.attn.qkv.weight": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.32.ls1.gamma": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.32.ls2.gamma": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.32.mlp.fc1.bias": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.32.mlp.fc1.weight": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.32.mlp.fc2.bias": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.32.mlp.fc2.weight": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.32.norm1.weight": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.32.norm2.weight": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.33.attn.k_norm.weight": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.33.attn.proj.bias": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.33.attn.proj.weight": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.33.attn.q_norm.weight": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.33.attn.qkv.weight": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.33.ls1.gamma": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.33.ls2.gamma": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.33.mlp.fc1.bias": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.33.mlp.fc1.weight": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.33.mlp.fc2.bias": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.33.mlp.fc2.weight": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.33.norm1.weight": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.33.norm2.weight": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.34.attn.k_norm.weight": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.34.attn.proj.bias": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.34.attn.proj.weight": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.34.attn.q_norm.weight": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.34.attn.qkv.weight": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.34.ls1.gamma": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.34.ls2.gamma": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.34.mlp.fc1.bias": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.34.mlp.fc1.weight": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.34.mlp.fc2.bias": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.34.mlp.fc2.weight": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.34.norm1.weight": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.34.norm2.weight": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.35.attn.k_norm.weight": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.35.attn.proj.bias": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.35.attn.proj.weight": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.35.attn.q_norm.weight": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.35.attn.qkv.weight": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.35.ls1.gamma": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.35.ls2.gamma": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.35.mlp.fc1.bias": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.35.mlp.fc1.weight": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.35.mlp.fc2.bias": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.35.mlp.fc2.weight": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.35.norm1.weight": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.35.norm2.weight": "model-00009-of-00013.safetensors",
+    "vision_encoder.blocks.36.attn.k_norm.weight": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.36.attn.proj.bias": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.36.attn.proj.weight": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.36.attn.q_norm.weight": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.36.attn.qkv.weight": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.36.ls1.gamma": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.36.ls2.gamma": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.36.mlp.fc1.bias": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.36.mlp.fc1.weight": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.36.mlp.fc2.bias": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.36.mlp.fc2.weight": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.36.norm1.weight": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.36.norm2.weight": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.37.attn.k_norm.weight": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.37.attn.proj.bias": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.37.attn.proj.weight": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.37.attn.q_norm.weight": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.37.attn.qkv.weight": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.37.ls1.gamma": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.37.ls2.gamma": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.37.mlp.fc1.bias": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.37.mlp.fc1.weight": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.37.mlp.fc2.bias": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.37.mlp.fc2.weight": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.37.norm1.weight": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.37.norm2.weight": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.38.attn.k_norm.weight": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.38.attn.proj.bias": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.38.attn.proj.weight": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.38.attn.q_norm.weight": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.38.attn.qkv.weight": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.38.ls1.gamma": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.38.ls2.gamma": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.38.mlp.fc1.bias": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.38.mlp.fc1.weight": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.38.mlp.fc2.bias": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.38.mlp.fc2.weight": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.38.norm1.weight": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.38.norm2.weight": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.39.attn.k_norm.weight": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.39.attn.proj.bias": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.39.attn.proj.weight": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.39.attn.q_norm.weight": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.39.attn.qkv.weight": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.39.ls1.gamma": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.39.ls2.gamma": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.39.mlp.fc1.bias": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.39.mlp.fc1.weight": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.39.mlp.fc2.bias": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.39.mlp.fc2.weight": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.39.norm1.weight": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.39.norm2.weight": "model-00010-of-00013.safetensors",
+    "vision_encoder.blocks.4.attn.k_norm.weight": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.4.attn.proj.bias": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.4.attn.proj.weight": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.4.attn.q_norm.weight": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.4.attn.qkv.weight": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.4.ls1.gamma": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.4.ls2.gamma": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.4.mlp.fc1.bias": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.4.mlp.fc1.weight": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.4.mlp.fc2.bias": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.4.mlp.fc2.weight": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.4.norm1.weight": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.4.norm2.weight": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.40.attn.k_norm.weight": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.40.attn.proj.bias": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.40.attn.proj.weight": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.40.attn.q_norm.weight": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.40.attn.qkv.weight": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.40.ls1.gamma": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.40.ls2.gamma": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.40.mlp.fc1.bias": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.40.mlp.fc1.weight": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.40.mlp.fc2.bias": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.40.mlp.fc2.weight": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.40.norm1.weight": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.40.norm2.weight": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.41.attn.k_norm.weight": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.41.attn.proj.bias": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.41.attn.proj.weight": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.41.attn.q_norm.weight": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.41.attn.qkv.weight": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.41.ls1.gamma": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.41.ls2.gamma": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.41.mlp.fc1.bias": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.41.mlp.fc1.weight": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.41.mlp.fc2.bias": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.41.mlp.fc2.weight": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.41.norm1.weight": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.41.norm2.weight": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.42.attn.k_norm.weight": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.42.attn.proj.bias": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.42.attn.proj.weight": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.42.attn.q_norm.weight": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.42.attn.qkv.weight": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.42.ls1.gamma": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.42.ls2.gamma": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.42.mlp.fc1.bias": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.42.mlp.fc1.weight": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.42.mlp.fc2.bias": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.42.mlp.fc2.weight": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.42.norm1.weight": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.42.norm2.weight": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.43.attn.k_norm.weight": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.43.attn.proj.bias": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.43.attn.proj.weight": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.43.attn.q_norm.weight": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.43.attn.qkv.weight": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.43.ls1.gamma": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.43.ls2.gamma": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.43.mlp.fc1.bias": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.43.mlp.fc1.weight": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.43.mlp.fc2.bias": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.43.mlp.fc2.weight": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.43.norm1.weight": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.43.norm2.weight": "model-00011-of-00013.safetensors",
+    "vision_encoder.blocks.44.attn.k_norm.weight": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.44.attn.proj.bias": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.44.attn.proj.weight": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.44.attn.q_norm.weight": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.44.attn.qkv.weight": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.44.ls1.gamma": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.44.ls2.gamma": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.44.mlp.fc1.bias": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.44.mlp.fc1.weight": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.44.mlp.fc2.bias": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.44.mlp.fc2.weight": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.44.norm1.weight": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.44.norm2.weight": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.45.attn.k_norm.weight": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.45.attn.proj.bias": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.45.attn.proj.weight": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.45.attn.q_norm.weight": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.45.attn.qkv.weight": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.45.ls1.gamma": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.45.ls2.gamma": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.45.mlp.fc1.bias": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.45.mlp.fc1.weight": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.45.mlp.fc2.bias": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.45.mlp.fc2.weight": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.45.norm1.weight": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.45.norm2.weight": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.46.attn.k_norm.weight": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.46.attn.proj.bias": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.46.attn.proj.weight": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.46.attn.q_norm.weight": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.46.attn.qkv.weight": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.46.ls1.gamma": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.46.ls2.gamma": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.46.mlp.fc1.bias": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.46.mlp.fc1.weight": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.46.mlp.fc2.bias": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.46.mlp.fc2.weight": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.46.norm1.weight": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.46.norm2.weight": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.47.attn.k_norm.weight": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.47.attn.proj.bias": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.47.attn.proj.weight": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.47.attn.q_norm.weight": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.47.attn.qkv.weight": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.47.ls1.gamma": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.47.ls2.gamma": "model-00013-of-00013.safetensors",
+    "vision_encoder.blocks.47.mlp.fc1.bias": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.47.mlp.fc1.weight": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.47.mlp.fc2.bias": "model-00013-of-00013.safetensors",
+    "vision_encoder.blocks.47.mlp.fc2.weight": "model-00013-of-00013.safetensors",
+    "vision_encoder.blocks.47.norm1.weight": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.47.norm2.weight": "model-00012-of-00013.safetensors",
+    "vision_encoder.blocks.5.attn.k_norm.weight": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.5.attn.proj.bias": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.5.attn.proj.weight": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.5.attn.q_norm.weight": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.5.attn.qkv.weight": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.5.ls1.gamma": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.5.ls2.gamma": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.5.mlp.fc1.bias": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.5.mlp.fc1.weight": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.5.mlp.fc2.bias": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.5.mlp.fc2.weight": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.5.norm1.weight": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.5.norm2.weight": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.6.attn.k_norm.weight": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.6.attn.proj.bias": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.6.attn.proj.weight": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.6.attn.q_norm.weight": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.6.attn.qkv.weight": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.6.ls1.gamma": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.6.ls2.gamma": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.6.mlp.fc1.bias": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.6.mlp.fc1.weight": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.6.mlp.fc2.bias": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.6.mlp.fc2.weight": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.6.norm1.weight": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.6.norm2.weight": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.7.attn.k_norm.weight": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.7.attn.proj.bias": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.7.attn.proj.weight": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.7.attn.q_norm.weight": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.7.attn.qkv.weight": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.7.ls1.gamma": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.7.ls2.gamma": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.7.mlp.fc1.bias": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.7.mlp.fc1.weight": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.7.mlp.fc2.bias": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.7.mlp.fc2.weight": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.7.norm1.weight": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.7.norm2.weight": "model-00002-of-00013.safetensors",
+    "vision_encoder.blocks.8.attn.k_norm.weight": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.8.attn.proj.bias": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.8.attn.proj.weight": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.8.attn.q_norm.weight": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.8.attn.qkv.weight": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.8.ls1.gamma": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.8.ls2.gamma": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.8.mlp.fc1.bias": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.8.mlp.fc1.weight": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.8.mlp.fc2.bias": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.8.mlp.fc2.weight": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.8.norm1.weight": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.8.norm2.weight": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.9.attn.k_norm.weight": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.9.attn.proj.bias": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.9.attn.proj.weight": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.9.attn.q_norm.weight": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.9.attn.qkv.weight": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.9.ls1.gamma": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.9.ls2.gamma": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.9.mlp.fc1.bias": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.9.mlp.fc1.weight": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.9.mlp.fc2.bias": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.9.mlp.fc2.weight": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.9.norm1.weight": "model-00003-of-00013.safetensors",
+    "vision_encoder.blocks.9.norm2.weight": "model-00003-of-00013.safetensors",
+    "vision_encoder.clip_decoder.0.head.bias": "model-00013-of-00013.safetensors",
+    "vision_encoder.clip_decoder.0.head.weight": "model-00013-of-00013.safetensors",
+    "vision_encoder.clip_decoder.0.norm.bias": "model-00013-of-00013.safetensors",
+    "vision_encoder.clip_decoder.0.norm.weight": "model-00013-of-00013.safetensors",
+    "vision_encoder.clip_decoder.1.head.bias": "model-00013-of-00013.safetensors",
+    "vision_encoder.clip_decoder.1.head.weight": "model-00013-of-00013.safetensors",
+    "vision_encoder.clip_decoder.1.norm.bias": "model-00013-of-00013.safetensors",
+    "vision_encoder.clip_decoder.1.norm.weight": "model-00013-of-00013.safetensors",
+    "vision_encoder.clip_decoder.2.head.bias": "model-00013-of-00013.safetensors",
+    "vision_encoder.clip_decoder.2.head.weight": "model-00013-of-00013.safetensors",
+    "vision_encoder.clip_decoder.2.norm.bias": "model-00013-of-00013.safetensors",
+    "vision_encoder.clip_decoder.2.norm.weight": "model-00013-of-00013.safetensors",
+    "vision_encoder.clip_decoder.3.head.bias": "model-00013-of-00013.safetensors",
+    "vision_encoder.clip_decoder.3.head.weight": "model-00013-of-00013.safetensors",
+    "vision_encoder.clip_decoder.3.norm.bias": "model-00013-of-00013.safetensors",
+    "vision_encoder.clip_decoder.3.norm.weight": "model-00013-of-00013.safetensors",
+    "vision_encoder.clip_decoder.4.head.bias": "model-00013-of-00013.safetensors",
+    "vision_encoder.clip_decoder.4.head.weight": "model-00013-of-00013.safetensors",
+    "vision_encoder.clip_decoder.4.norm.bias": "model-00013-of-00013.safetensors",
+    "vision_encoder.clip_decoder.4.norm.weight": "model-00013-of-00013.safetensors",
+    "vision_encoder.clip_decoder.5.head.bias": "model-00013-of-00013.safetensors",
+    "vision_encoder.clip_decoder.5.head.weight": "model-00013-of-00013.safetensors",
+    "vision_encoder.clip_decoder.5.norm.bias": "model-00013-of-00013.safetensors",
+    "vision_encoder.clip_decoder.5.norm.weight": "model-00013-of-00013.safetensors",
+    "vision_encoder.clip_img_pos_embed": "model-00001-of-00013.safetensors",
+    "vision_encoder.clip_pos_embed": "model-00001-of-00013.safetensors",
+    "vision_encoder.clip_projector.cross_attn.k.weight": "model-00013-of-00013.safetensors",
+    "vision_encoder.clip_projector.cross_attn.k_bias": "model-00013-of-00013.safetensors",
+    "vision_encoder.clip_projector.cross_attn.proj.bias": "model-00013-of-00013.safetensors",
+    "vision_encoder.clip_projector.cross_attn.proj.weight": "model-00013-of-00013.safetensors",
+    "vision_encoder.clip_projector.cross_attn.q.weight": "model-00013-of-00013.safetensors",
+    "vision_encoder.clip_projector.cross_attn.q_bias": "model-00013-of-00013.safetensors",
+    "vision_encoder.clip_projector.cross_attn.v.weight": "model-00013-of-00013.safetensors",
+    "vision_encoder.clip_projector.cross_attn.v_bias": "model-00013-of-00013.safetensors",
+    "vision_encoder.clip_projector.norm1_k.bias": "model-00013-of-00013.safetensors",
+    "vision_encoder.clip_projector.norm1_k.weight": "model-00013-of-00013.safetensors",
+    "vision_encoder.clip_projector.norm1_q.bias": "model-00013-of-00013.safetensors",
+    "vision_encoder.clip_projector.norm1_q.weight": "model-00013-of-00013.safetensors",
+    "vision_encoder.clip_projector.norm1_v.bias": "model-00013-of-00013.safetensors",
+    "vision_encoder.clip_projector.norm1_v.weight": "model-00013-of-00013.safetensors",
+    "vision_encoder.cls_token": "model-00001-of-00013.safetensors",
+    "vision_encoder.final_clip_decoder.head.bias": "model-00013-of-00013.safetensors",
+    "vision_encoder.final_clip_decoder.head.weight": "model-00013-of-00013.safetensors",
+    "vision_encoder.final_clip_decoder.norm.bias": "model-00013-of-00013.safetensors",
+    "vision_encoder.final_clip_decoder.norm.weight": "model-00013-of-00013.safetensors",
+    "vision_encoder.img_pos_embed": "model-00001-of-00013.safetensors",
+    "vision_encoder.patch_embed.proj.bias": "model-00001-of-00013.safetensors",
+    "vision_encoder.patch_embed.proj.weight": "model-00001-of-00013.safetensors",
+    "vision_encoder.pos_embed": "model-00001-of-00013.safetensors",
+    "vision_proj.bias": "model-00013-of-00013.safetensors",
+    "vision_proj.weight": "model-00013-of-00013.safetensors"
+  }
+}