diff --git "a/pytorch_model.bin.index.json" "b/pytorch_model.bin.index.json"
new file mode 100644--- /dev/null
+++ "b/pytorch_model.bin.index.json"
@@ -0,0 +1,1373 @@
+{
+  "metadata": {
+    "total_size": 25146781184
+  },
+  "weight_map": {
+    "language_model.decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.0.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.0.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.0.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.0.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.0.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.0.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.1.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.1.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.1.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.1.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.1.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.1.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.10.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.10.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.10.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.10.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.10.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.10.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.11.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.11.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.11.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.11.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.11.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.11.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.12.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.12.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.12.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.12.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.12.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.12.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.13.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.13.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.13.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.13.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.13.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.13.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.14.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.14.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.14.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.14.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.14.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.14.layer.2.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.15.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.15.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.15.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.15.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.15.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.15.layer.2.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.16.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.16.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.16.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.16.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.16.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.16.layer.2.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.17.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.17.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.17.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.17.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.17.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.17.layer.2.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.18.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.18.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.18.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.18.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.18.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.18.layer.2.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.19.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.19.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.19.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.19.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.19.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.19.layer.2.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.2.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.2.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.2.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.2.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.2.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.2.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.20.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.20.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.20.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.20.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.20.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.20.layer.2.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.21.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.21.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.21.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.21.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.21.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.21.layer.2.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.22.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.22.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.22.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.22.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.22.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.22.layer.2.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.23.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.23.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.23.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.23.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.23.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.23.layer.2.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.decoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.3.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.3.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.3.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.3.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.3.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.3.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.4.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.4.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.4.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.4.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.4.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.4.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.5.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.5.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.5.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.5.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.5.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.5.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.6.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.6.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.6.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.6.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.6.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.6.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.7.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.7.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.7.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.7.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.7.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.7.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.8.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.8.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.8.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.8.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.8.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.8.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.9.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.9.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.9.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.9.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.9.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.block.9.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.embed_tokens.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.decoder.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
+    "language_model.encoder.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "language_model.lm_head.weight": "pytorch_model-00003-of-00003.bin",
+    "language_model.shared.weight": "pytorch_model-00001-of-00003.bin",
+    "language_projection.bias": "pytorch_model-00001-of-00003.bin",
+    "language_projection.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.embeddings.layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.embeddings.layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.embeddings.position_embeddings.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.embeddings.position_ids": "pytorch_model-00001-of-00003.bin",
+    "qformer.embeddings.word_embeddings.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.attention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.attention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.attention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.attention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.attention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.attention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.crossattention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.crossattention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.crossattention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.crossattention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.crossattention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.crossattention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.intermediate_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.intermediate_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.output_query.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.output_query.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.output_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.0.output_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.attention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.attention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.attention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.attention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.attention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.attention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.intermediate_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.intermediate_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.output_query.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.output_query.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.output_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.1.output_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.attention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.attention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.attention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.attention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.attention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.attention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.crossattention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.crossattention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.crossattention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.crossattention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.crossattention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.crossattention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.intermediate_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.intermediate_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.output_query.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.output_query.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.output_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.10.output_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.attention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.attention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.attention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.attention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.attention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.attention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.intermediate_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.intermediate_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.output_query.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.output_query.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.output_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.11.output_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.attention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.attention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.attention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.attention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.attention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.attention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.crossattention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.crossattention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.crossattention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.crossattention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.crossattention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.crossattention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.intermediate_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.intermediate_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.output_query.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.output_query.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.output_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.2.output_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.attention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.attention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.attention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.attention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.attention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.attention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.intermediate_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.intermediate_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.output_query.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.output_query.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.output_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.3.output_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.attention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.attention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.attention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.attention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.attention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.attention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.crossattention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.crossattention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.crossattention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.crossattention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.crossattention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.crossattention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.intermediate_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.intermediate_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.output_query.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.output_query.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.output_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.4.output_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.attention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.attention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.attention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.attention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.attention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.attention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.intermediate_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.intermediate_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.output_query.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.output_query.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.output_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.5.output_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.attention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.attention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.attention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.attention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.attention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.attention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.crossattention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.crossattention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.crossattention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.crossattention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.crossattention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.crossattention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.intermediate_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.intermediate_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.output_query.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.output_query.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.output_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.6.output_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.attention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.attention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.attention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.attention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.attention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.attention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.intermediate_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.intermediate_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.output_query.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.output_query.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.output_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.7.output_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.attention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.attention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.attention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.attention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.attention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.attention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.crossattention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.crossattention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.crossattention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.crossattention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.crossattention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.crossattention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.intermediate_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.intermediate_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.output_query.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.output_query.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.output_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.8.output_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.attention.attention.key.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.attention.attention.key.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.attention.attention.query.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.attention.attention.query.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.attention.attention.value.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.attention.attention.value.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.intermediate_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.intermediate_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.output_query.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.output_query.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.output_query.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "qformer.encoder.layer.9.output_query.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "query_tokens": "pytorch_model-00001-of-00003.bin",
+    "vision_model.embeddings.class_embedding": "pytorch_model-00001-of-00003.bin",
+    "vision_model.embeddings.patch_embedding.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.embeddings.patch_embedding.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.embeddings.position_embedding": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.0.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.0.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.0.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.0.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.1.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.1.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.1.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.1.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.10.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.10.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.10.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.10.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.11.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.11.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.11.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.11.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.12.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.12.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.12.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.12.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.13.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.13.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.13.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.13.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.14.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.14.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.14.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.14.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.15.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.15.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.15.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.15.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.16.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.16.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.16.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.16.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.17.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.17.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.17.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.17.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.18.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.18.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.18.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.18.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.19.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.19.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.19.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.19.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.2.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.2.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.2.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.2.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.20.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.20.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.20.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.20.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.21.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.21.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.21.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.21.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.22.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.22.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.22.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.22.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.23.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.23.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.23.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.23.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.24.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.24.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.24.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.24.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.24.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.24.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.24.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.24.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.24.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.24.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.24.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.24.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.25.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.25.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.25.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.25.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.25.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.25.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.25.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.25.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.25.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.25.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.25.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.25.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.26.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.26.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.26.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.26.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.26.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.26.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.26.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.26.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.26.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.26.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.26.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.26.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.27.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.27.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.27.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.27.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.27.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.27.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.27.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.27.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.27.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.27.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.27.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.27.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.28.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.28.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.28.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.28.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.28.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.28.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.28.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.28.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.28.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.28.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.28.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.28.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.29.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.29.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.29.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.29.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.29.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.29.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.29.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.29.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.29.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.29.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.29.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.29.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.3.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.3.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.3.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.3.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.30.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.30.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.30.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.30.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.30.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.30.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.30.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.30.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.30.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.30.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.30.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.30.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.31.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.31.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.31.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.31.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.31.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.31.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.31.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.31.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.31.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.31.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.31.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.31.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.32.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.32.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.32.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.32.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.32.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.32.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.32.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.32.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.32.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.32.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.32.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.32.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.33.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.33.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.33.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.33.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.33.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.33.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.33.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.33.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.33.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.33.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.33.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.33.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.34.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.34.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.34.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.34.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.34.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.34.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.34.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.34.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.34.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.34.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.34.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.34.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.35.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.35.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.35.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.35.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.35.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.35.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.35.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.35.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.35.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.35.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.35.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.35.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.36.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.36.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.36.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.36.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.36.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.36.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.36.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.36.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.36.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.36.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.36.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.36.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.37.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.37.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.37.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.37.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.37.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.37.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.37.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.37.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.37.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.37.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.37.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.37.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.38.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.38.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.38.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.38.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.38.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.38.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.38.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.38.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.38.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.38.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.38.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.38.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.4.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.4.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.4.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.4.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.5.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.5.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.5.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.5.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.6.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.6.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.6.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.6.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.7.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.7.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.7.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.7.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.8.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.8.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.8.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.8.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.9.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.9.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.9.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.encoder.layers.9.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
+    "vision_model.post_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "vision_model.post_layernorm.weight": "pytorch_model-00001-of-00003.bin"
+  }
+}