commit from lemon

pytorch_model-00001-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32cea8040c7275f441eb30d9a496ea2ac60d9f221fe240a7eba18cac3937062a
-size 9976274983
+oid sha256:43b2691bda8520c98f2e8b47932551a824e13708155cf3b87dd8ac69e99b9e17
+size 14138055175

pytorch_model-00002-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:944cefa37c780577f1eb963d1f15c80776a9ce282cb0cb861ff269b4097f6dc6
-size 6217089795
+oid sha256:e87e65186b56f697026f9b35c86a7223cc912e2d423070d2750f1ab5677e3595
+size 12082831395

pytorch_model.bin.index.json

@@ -1,373 +1,372 @@
 {
   "metadata": {
-    "total_size": 16193241088
+    "total_size": 14138032128
   },
   "weight_map": {
-    "lm_head.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.0.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.0.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.0.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.0.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.1.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.1.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.1.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.1.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.10.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.10.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.10.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.10.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.10.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.10.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.10.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.11.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.11.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.11.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.11.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.11.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.11.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.11.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.12.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.12.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.12.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.12.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.12.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.12.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.12.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.13.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.13.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.13.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.13.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.13.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.13.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.13.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.14.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.14.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.14.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.14.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.14.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.14.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.14.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.15.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.15.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.15.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.15.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.15.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.15.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.15.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.16.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.16.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.16.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.16.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.16.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.16.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.16.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.17.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.17.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.17.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.17.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.17.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.17.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.17.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.18.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.18.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.18.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.18.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.18.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.18.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.18.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.19.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.19.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.19.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.19.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.19.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.19.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.19.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.2.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.2.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.2.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.2.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.20.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.20.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.20.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.20.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.20.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.20.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.20.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.20.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.21.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.21.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.21.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.21.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.21.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.21.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.21.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.21.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.22.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.22.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.22.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.22.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.22.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.22.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.22.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.23.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.23.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.23.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.23.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.23.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.23.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.23.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.24.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.24.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.24.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.24.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.24.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.24.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.24.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.25.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.25.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.25.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.25.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.25.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.25.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.25.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.26.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.26.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.26.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.26.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.26.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.26.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.26.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.27.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.27.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.27.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.27.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.27.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.27.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.27.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.28.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.28.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.28.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.28.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.28.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.28.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.28.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.29.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.29.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.29.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.29.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.29.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.29.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.29.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.3.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.3.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.3.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.3.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.4.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.4.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.4.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.4.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.5.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.5.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.5.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.5.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.6.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.6.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.6.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.6.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.7.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.7.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.7.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.7.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.7.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.7.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.8.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.8.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.8.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.8.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.8.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.8.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.9.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.9.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.9.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.9.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.9.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.9.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.9.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.ln_f.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.ln_f.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.word_embeddings.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.word_embeddings_layernorm.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.word_embeddings_layernorm.weight": "pytorch_model-00001-of-00002.bin"
+    "h.0.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.0.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.0.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.0.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.1.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.1.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.1.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.1.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.10.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.10.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.10.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.10.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.10.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.10.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.10.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.10.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.11.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.11.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.11.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.11.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.11.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.11.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.11.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.11.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.12.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.12.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.12.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.12.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.12.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.12.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.12.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.12.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.13.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.13.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.13.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.13.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.13.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.13.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.13.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.13.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.14.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.14.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.14.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.14.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.14.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.14.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.14.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.14.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.15.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.15.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.15.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.15.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.15.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.15.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.15.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.15.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.16.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.16.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.16.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.16.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.16.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.16.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.16.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.16.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.17.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.17.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.17.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.17.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.17.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.17.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.17.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.17.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.18.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.18.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.18.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.18.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.18.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.18.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.18.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.18.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.19.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.19.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.19.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.19.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.19.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.19.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.19.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.19.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.2.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.2.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.2.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.2.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.20.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.20.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.20.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.20.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.20.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.20.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "h.20.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "h.20.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "h.20.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "h.21.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.21.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.21.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.21.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.21.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.21.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "h.21.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "h.21.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "h.21.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "h.22.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.22.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.22.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.22.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.22.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "h.22.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "h.22.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "h.22.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "h.23.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.23.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.23.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.23.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.23.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "h.23.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "h.23.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "h.23.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "h.24.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.24.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.24.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.24.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.24.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "h.24.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "h.24.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "h.24.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "h.25.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.25.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.25.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.25.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.25.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "h.25.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "h.25.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "h.25.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "h.26.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.26.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.26.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.26.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.26.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "h.26.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "h.26.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "h.26.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "h.27.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.27.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.27.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.27.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.27.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "h.27.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "h.27.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "h.27.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "h.28.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.28.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.28.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.28.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.28.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "h.28.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "h.28.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "h.28.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "h.29.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.29.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.29.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.29.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.29.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "h.29.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "h.29.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "h.29.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "h.3.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.3.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.3.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.3.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.4.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.4.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.4.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.4.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.4.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.5.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.5.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.5.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.5.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.5.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.6.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.6.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.6.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.6.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.6.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.7.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.7.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.7.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.7.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.7.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.7.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.7.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.8.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.8.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.8.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.8.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.8.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.8.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.8.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.9.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.9.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.9.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.9.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.9.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.9.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.9.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.9.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "ln_f.bias": "pytorch_model-00002-of-00002.bin",
+    "ln_f.weight": "pytorch_model-00002-of-00002.bin",
+    "word_embeddings.weight": "pytorch_model-00001-of-00002.bin",
+    "word_embeddings_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "word_embeddings_layernorm.weight": "pytorch_model-00001-of-00002.bin"
   }
 }