Sharded model to decrease size

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "/users/villekom/scratch/models/gpt3-finnish-13B/",
   "apply_residual_connection_post_layernorm": false,
   "architectures": [
     "BloomModel"
@@ -18,7 +19,8 @@
   "pad_token_id": 3,
   "pretraining_tp": 1,
   "slow_but_exact": false,
-  "transformers_version": "4.26.0.dev0",
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
   "use_cache": true,
   "vocab_size": 131072
 }

pytorch_model-00001-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5877a4693802b76b8655bc01d6d9fa23fe73a1e2f0bf70846cd2f2514f594c2a
+size 9816311870

pytorch_model-00002-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67708253aa250e6527b143b100708fad7cd18ce6b961c152bc1d0e3aa3e04006
+size 9648976151

pytorch_model-00003-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84f6873156bdb0fabe1d08b06f166f0f52ecf62ae02e59d1cd4fc0c180c43209
+size 9963568813

pytorch_model-00004-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f521d6625ba88818c2d366f73c9f2fce0855f10c72b02ec71fadaec2d080d38
+size 9753854207

pytorch_model-00005-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e96362d38c77971cd6ef8d0f65b91166c8c5e26ac0705218c11f73eb9011f484
+size 9648995941

pytorch_model-00006-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49daed28c41e0cd15c95dd6e961426d422bcbfd050e323a3bad286698e44a857
+size 4195175533

pytorch_model.bin.index.json

@@ -0,0 +1,492 @@
+{
+  "metadata": {
+    "total_size": 53026734080
+  },
+  "weight_map": {
+    "h.0.input_layernorm.bias": "pytorch_model-00001-of-00006.bin",
+    "h.0.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "h.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00006.bin",
+    "h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00006.bin",
+    "h.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00006.bin",
+    "h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00006.bin",
+    "h.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00006.bin",
+    "h.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "h.0.self_attention.dense.bias": "pytorch_model-00001-of-00006.bin",
+    "h.0.self_attention.dense.weight": "pytorch_model-00001-of-00006.bin",
+    "h.0.self_attention.query_key_value.bias": "pytorch_model-00001-of-00006.bin",
+    "h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00006.bin",
+    "h.1.input_layernorm.bias": "pytorch_model-00001-of-00006.bin",
+    "h.1.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "h.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00006.bin",
+    "h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00006.bin",
+    "h.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00006.bin",
+    "h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00006.bin",
+    "h.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00006.bin",
+    "h.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "h.1.self_attention.dense.bias": "pytorch_model-00001-of-00006.bin",
+    "h.1.self_attention.dense.weight": "pytorch_model-00001-of-00006.bin",
+    "h.1.self_attention.query_key_value.bias": "pytorch_model-00001-of-00006.bin",
+    "h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00006.bin",
+    "h.10.input_layernorm.bias": "pytorch_model-00002-of-00006.bin",
+    "h.10.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "h.10.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00006.bin",
+    "h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00006.bin",
+    "h.10.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00006.bin",
+    "h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00006.bin",
+    "h.10.post_attention_layernorm.bias": "pytorch_model-00002-of-00006.bin",
+    "h.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "h.10.self_attention.dense.bias": "pytorch_model-00002-of-00006.bin",
+    "h.10.self_attention.dense.weight": "pytorch_model-00002-of-00006.bin",
+    "h.10.self_attention.query_key_value.bias": "pytorch_model-00002-of-00006.bin",
+    "h.10.self_attention.query_key_value.weight": "pytorch_model-00002-of-00006.bin",
+    "h.11.input_layernorm.bias": "pytorch_model-00002-of-00006.bin",
+    "h.11.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "h.11.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00006.bin",
+    "h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00006.bin",
+    "h.11.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00006.bin",
+    "h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00006.bin",
+    "h.11.post_attention_layernorm.bias": "pytorch_model-00002-of-00006.bin",
+    "h.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "h.11.self_attention.dense.bias": "pytorch_model-00002-of-00006.bin",
+    "h.11.self_attention.dense.weight": "pytorch_model-00002-of-00006.bin",
+    "h.11.self_attention.query_key_value.bias": "pytorch_model-00002-of-00006.bin",
+    "h.11.self_attention.query_key_value.weight": "pytorch_model-00002-of-00006.bin",
+    "h.12.input_layernorm.bias": "pytorch_model-00002-of-00006.bin",
+    "h.12.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "h.12.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00006.bin",
+    "h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00006.bin",
+    "h.12.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00006.bin",
+    "h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00006.bin",
+    "h.12.post_attention_layernorm.bias": "pytorch_model-00002-of-00006.bin",
+    "h.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "h.12.self_attention.dense.bias": "pytorch_model-00002-of-00006.bin",
+    "h.12.self_attention.dense.weight": "pytorch_model-00002-of-00006.bin",
+    "h.12.self_attention.query_key_value.bias": "pytorch_model-00002-of-00006.bin",
+    "h.12.self_attention.query_key_value.weight": "pytorch_model-00002-of-00006.bin",
+    "h.13.input_layernorm.bias": "pytorch_model-00002-of-00006.bin",
+    "h.13.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "h.13.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00006.bin",
+    "h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00006.bin",
+    "h.13.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00006.bin",
+    "h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00006.bin",
+    "h.13.post_attention_layernorm.bias": "pytorch_model-00002-of-00006.bin",
+    "h.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "h.13.self_attention.dense.bias": "pytorch_model-00002-of-00006.bin",
+    "h.13.self_attention.dense.weight": "pytorch_model-00002-of-00006.bin",
+    "h.13.self_attention.query_key_value.bias": "pytorch_model-00002-of-00006.bin",
+    "h.13.self_attention.query_key_value.weight": "pytorch_model-00002-of-00006.bin",
+    "h.14.input_layernorm.bias": "pytorch_model-00003-of-00006.bin",
+    "h.14.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "h.14.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00006.bin",
+    "h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00006.bin",
+    "h.14.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00006.bin",
+    "h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00006.bin",
+    "h.14.post_attention_layernorm.bias": "pytorch_model-00003-of-00006.bin",
+    "h.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "h.14.self_attention.dense.bias": "pytorch_model-00003-of-00006.bin",
+    "h.14.self_attention.dense.weight": "pytorch_model-00003-of-00006.bin",
+    "h.14.self_attention.query_key_value.bias": "pytorch_model-00003-of-00006.bin",
+    "h.14.self_attention.query_key_value.weight": "pytorch_model-00003-of-00006.bin",
+    "h.15.input_layernorm.bias": "pytorch_model-00003-of-00006.bin",
+    "h.15.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "h.15.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00006.bin",
+    "h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00006.bin",
+    "h.15.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00006.bin",
+    "h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00006.bin",
+    "h.15.post_attention_layernorm.bias": "pytorch_model-00003-of-00006.bin",
+    "h.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "h.15.self_attention.dense.bias": "pytorch_model-00003-of-00006.bin",
+    "h.15.self_attention.dense.weight": "pytorch_model-00003-of-00006.bin",
+    "h.15.self_attention.query_key_value.bias": "pytorch_model-00003-of-00006.bin",
+    "h.15.self_attention.query_key_value.weight": "pytorch_model-00003-of-00006.bin",
+    "h.16.input_layernorm.bias": "pytorch_model-00003-of-00006.bin",
+    "h.16.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "h.16.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00006.bin",
+    "h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00006.bin",
+    "h.16.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00006.bin",
+    "h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00006.bin",
+    "h.16.post_attention_layernorm.bias": "pytorch_model-00003-of-00006.bin",
+    "h.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "h.16.self_attention.dense.bias": "pytorch_model-00003-of-00006.bin",
+    "h.16.self_attention.dense.weight": "pytorch_model-00003-of-00006.bin",
+    "h.16.self_attention.query_key_value.bias": "pytorch_model-00003-of-00006.bin",
+    "h.16.self_attention.query_key_value.weight": "pytorch_model-00003-of-00006.bin",
+    "h.17.input_layernorm.bias": "pytorch_model-00003-of-00006.bin",
+    "h.17.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "h.17.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00006.bin",
+    "h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00006.bin",
+    "h.17.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00006.bin",
+    "h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00006.bin",
+    "h.17.post_attention_layernorm.bias": "pytorch_model-00003-of-00006.bin",
+    "h.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "h.17.self_attention.dense.bias": "pytorch_model-00003-of-00006.bin",
+    "h.17.self_attention.dense.weight": "pytorch_model-00003-of-00006.bin",
+    "h.17.self_attention.query_key_value.bias": "pytorch_model-00003-of-00006.bin",
+    "h.17.self_attention.query_key_value.weight": "pytorch_model-00003-of-00006.bin",
+    "h.18.input_layernorm.bias": "pytorch_model-00003-of-00006.bin",
+    "h.18.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "h.18.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00006.bin",
+    "h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00006.bin",
+    "h.18.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00006.bin",
+    "h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00006.bin",
+    "h.18.post_attention_layernorm.bias": "pytorch_model-00003-of-00006.bin",
+    "h.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "h.18.self_attention.dense.bias": "pytorch_model-00003-of-00006.bin",
+    "h.18.self_attention.dense.weight": "pytorch_model-00003-of-00006.bin",
+    "h.18.self_attention.query_key_value.bias": "pytorch_model-00003-of-00006.bin",
+    "h.18.self_attention.query_key_value.weight": "pytorch_model-00003-of-00006.bin",
+    "h.19.input_layernorm.bias": "pytorch_model-00003-of-00006.bin",
+    "h.19.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "h.19.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00006.bin",
+    "h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00006.bin",
+    "h.19.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00006.bin",
+    "h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00006.bin",
+    "h.19.post_attention_layernorm.bias": "pytorch_model-00003-of-00006.bin",
+    "h.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "h.19.self_attention.dense.bias": "pytorch_model-00003-of-00006.bin",
+    "h.19.self_attention.dense.weight": "pytorch_model-00003-of-00006.bin",
+    "h.19.self_attention.query_key_value.bias": "pytorch_model-00003-of-00006.bin",
+    "h.19.self_attention.query_key_value.weight": "pytorch_model-00003-of-00006.bin",
+    "h.2.input_layernorm.bias": "pytorch_model-00001-of-00006.bin",
+    "h.2.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "h.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00006.bin",
+    "h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00006.bin",
+    "h.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00006.bin",
+    "h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00006.bin",
+    "h.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00006.bin",
+    "h.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "h.2.self_attention.dense.bias": "pytorch_model-00001-of-00006.bin",
+    "h.2.self_attention.dense.weight": "pytorch_model-00001-of-00006.bin",
+    "h.2.self_attention.query_key_value.bias": "pytorch_model-00001-of-00006.bin",
+    "h.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00006.bin",
+    "h.20.input_layernorm.bias": "pytorch_model-00003-of-00006.bin",
+    "h.20.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "h.20.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00006.bin",
+    "h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00006.bin",
+    "h.20.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00006.bin",
+    "h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00006.bin",
+    "h.20.post_attention_layernorm.bias": "pytorch_model-00003-of-00006.bin",
+    "h.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "h.20.self_attention.dense.bias": "pytorch_model-00003-of-00006.bin",
+    "h.20.self_attention.dense.weight": "pytorch_model-00003-of-00006.bin",
+    "h.20.self_attention.query_key_value.bias": "pytorch_model-00003-of-00006.bin",
+    "h.20.self_attention.query_key_value.weight": "pytorch_model-00003-of-00006.bin",
+    "h.21.input_layernorm.bias": "pytorch_model-00003-of-00006.bin",
+    "h.21.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "h.21.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00006.bin",
+    "h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00006.bin",
+    "h.21.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00006.bin",
+    "h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00006.bin",
+    "h.21.post_attention_layernorm.bias": "pytorch_model-00004-of-00006.bin",
+    "h.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "h.21.self_attention.dense.bias": "pytorch_model-00004-of-00006.bin",
+    "h.21.self_attention.dense.weight": "pytorch_model-00004-of-00006.bin",
+    "h.21.self_attention.query_key_value.bias": "pytorch_model-00003-of-00006.bin",
+    "h.21.self_attention.query_key_value.weight": "pytorch_model-00003-of-00006.bin",
+    "h.22.input_layernorm.bias": "pytorch_model-00004-of-00006.bin",
+    "h.22.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "h.22.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00006.bin",
+    "h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00006.bin",
+    "h.22.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00006.bin",
+    "h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00006.bin",
+    "h.22.post_attention_layernorm.bias": "pytorch_model-00004-of-00006.bin",
+    "h.22.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "h.22.self_attention.dense.bias": "pytorch_model-00004-of-00006.bin",
+    "h.22.self_attention.dense.weight": "pytorch_model-00004-of-00006.bin",
+    "h.22.self_attention.query_key_value.bias": "pytorch_model-00004-of-00006.bin",
+    "h.22.self_attention.query_key_value.weight": "pytorch_model-00004-of-00006.bin",
+    "h.23.input_layernorm.bias": "pytorch_model-00004-of-00006.bin",
+    "h.23.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "h.23.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00006.bin",
+    "h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00006.bin",
+    "h.23.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00006.bin",
+    "h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00006.bin",
+    "h.23.post_attention_layernorm.bias": "pytorch_model-00004-of-00006.bin",
+    "h.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "h.23.self_attention.dense.bias": "pytorch_model-00004-of-00006.bin",
+    "h.23.self_attention.dense.weight": "pytorch_model-00004-of-00006.bin",
+    "h.23.self_attention.query_key_value.bias": "pytorch_model-00004-of-00006.bin",
+    "h.23.self_attention.query_key_value.weight": "pytorch_model-00004-of-00006.bin",
+    "h.24.input_layernorm.bias": "pytorch_model-00004-of-00006.bin",
+    "h.24.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "h.24.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00006.bin",
+    "h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00006.bin",
+    "h.24.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00006.bin",
+    "h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00006.bin",
+    "h.24.post_attention_layernorm.bias": "pytorch_model-00004-of-00006.bin",
+    "h.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "h.24.self_attention.dense.bias": "pytorch_model-00004-of-00006.bin",
+    "h.24.self_attention.dense.weight": "pytorch_model-00004-of-00006.bin",
+    "h.24.self_attention.query_key_value.bias": "pytorch_model-00004-of-00006.bin",
+    "h.24.self_attention.query_key_value.weight": "pytorch_model-00004-of-00006.bin",
+    "h.25.input_layernorm.bias": "pytorch_model-00004-of-00006.bin",
+    "h.25.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "h.25.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00006.bin",
+    "h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00006.bin",
+    "h.25.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00006.bin",
+    "h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00006.bin",
+    "h.25.post_attention_layernorm.bias": "pytorch_model-00004-of-00006.bin",
+    "h.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "h.25.self_attention.dense.bias": "pytorch_model-00004-of-00006.bin",
+    "h.25.self_attention.dense.weight": "pytorch_model-00004-of-00006.bin",
+    "h.25.self_attention.query_key_value.bias": "pytorch_model-00004-of-00006.bin",
+    "h.25.self_attention.query_key_value.weight": "pytorch_model-00004-of-00006.bin",
+    "h.26.input_layernorm.bias": "pytorch_model-00004-of-00006.bin",
+    "h.26.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "h.26.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00006.bin",
+    "h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00006.bin",
+    "h.26.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00006.bin",
+    "h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00006.bin",
+    "h.26.post_attention_layernorm.bias": "pytorch_model-00004-of-00006.bin",
+    "h.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "h.26.self_attention.dense.bias": "pytorch_model-00004-of-00006.bin",
+    "h.26.self_attention.dense.weight": "pytorch_model-00004-of-00006.bin",
+    "h.26.self_attention.query_key_value.bias": "pytorch_model-00004-of-00006.bin",
+    "h.26.self_attention.query_key_value.weight": "pytorch_model-00004-of-00006.bin",
+    "h.27.input_layernorm.bias": "pytorch_model-00004-of-00006.bin",
+    "h.27.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "h.27.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00006.bin",
+    "h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00006.bin",
+    "h.27.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00006.bin",
+    "h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00006.bin",
+    "h.27.post_attention_layernorm.bias": "pytorch_model-00004-of-00006.bin",
+    "h.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "h.27.self_attention.dense.bias": "pytorch_model-00004-of-00006.bin",
+    "h.27.self_attention.dense.weight": "pytorch_model-00004-of-00006.bin",
+    "h.27.self_attention.query_key_value.bias": "pytorch_model-00004-of-00006.bin",
+    "h.27.self_attention.query_key_value.weight": "pytorch_model-00004-of-00006.bin",
+    "h.28.input_layernorm.bias": "pytorch_model-00004-of-00006.bin",
+    "h.28.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "h.28.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00006.bin",
+    "h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00006.bin",
+    "h.28.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00006.bin",
+    "h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00006.bin",
+    "h.28.post_attention_layernorm.bias": "pytorch_model-00004-of-00006.bin",
+    "h.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "h.28.self_attention.dense.bias": "pytorch_model-00004-of-00006.bin",
+    "h.28.self_attention.dense.weight": "pytorch_model-00004-of-00006.bin",
+    "h.28.self_attention.query_key_value.bias": "pytorch_model-00004-of-00006.bin",
+    "h.28.self_attention.query_key_value.weight": "pytorch_model-00004-of-00006.bin",
+    "h.29.input_layernorm.bias": "pytorch_model-00004-of-00006.bin",
+    "h.29.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "h.29.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00006.bin",
+    "h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00006.bin",
+    "h.29.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00006.bin",
+    "h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00006.bin",
+    "h.29.post_attention_layernorm.bias": "pytorch_model-00005-of-00006.bin",
+    "h.29.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "h.29.self_attention.dense.bias": "pytorch_model-00005-of-00006.bin",
+    "h.29.self_attention.dense.weight": "pytorch_model-00005-of-00006.bin",
+    "h.29.self_attention.query_key_value.bias": "pytorch_model-00005-of-00006.bin",
+    "h.29.self_attention.query_key_value.weight": "pytorch_model-00005-of-00006.bin",
+    "h.3.input_layernorm.bias": "pytorch_model-00001-of-00006.bin",
+    "h.3.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "h.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00006.bin",
+    "h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00006.bin",
+    "h.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00006.bin",
+    "h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00006.bin",
+    "h.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00006.bin",
+    "h.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "h.3.self_attention.dense.bias": "pytorch_model-00001-of-00006.bin",
+    "h.3.self_attention.dense.weight": "pytorch_model-00001-of-00006.bin",
+    "h.3.self_attention.query_key_value.bias": "pytorch_model-00001-of-00006.bin",
+    "h.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00006.bin",
+    "h.30.input_layernorm.bias": "pytorch_model-00005-of-00006.bin",
+    "h.30.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "h.30.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00006.bin",
+    "h.30.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00006.bin",
+    "h.30.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00006.bin",
+    "h.30.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00006.bin",
+    "h.30.post_attention_layernorm.bias": "pytorch_model-00005-of-00006.bin",
+    "h.30.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "h.30.self_attention.dense.bias": "pytorch_model-00005-of-00006.bin",
+    "h.30.self_attention.dense.weight": "pytorch_model-00005-of-00006.bin",
+    "h.30.self_attention.query_key_value.bias": "pytorch_model-00005-of-00006.bin",
+    "h.30.self_attention.query_key_value.weight": "pytorch_model-00005-of-00006.bin",
+    "h.31.input_layernorm.bias": "pytorch_model-00005-of-00006.bin",
+    "h.31.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "h.31.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00006.bin",
+    "h.31.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00006.bin",
+    "h.31.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00006.bin",
+    "h.31.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00006.bin",
+    "h.31.post_attention_layernorm.bias": "pytorch_model-00005-of-00006.bin",
+    "h.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "h.31.self_attention.dense.bias": "pytorch_model-00005-of-00006.bin",
+    "h.31.self_attention.dense.weight": "pytorch_model-00005-of-00006.bin",
+    "h.31.self_attention.query_key_value.bias": "pytorch_model-00005-of-00006.bin",
+    "h.31.self_attention.query_key_value.weight": "pytorch_model-00005-of-00006.bin",
+    "h.32.input_layernorm.bias": "pytorch_model-00005-of-00006.bin",
+    "h.32.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "h.32.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00006.bin",
+    "h.32.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00006.bin",
+    "h.32.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00006.bin",
+    "h.32.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00006.bin",
+    "h.32.post_attention_layernorm.bias": "pytorch_model-00005-of-00006.bin",
+    "h.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "h.32.self_attention.dense.bias": "pytorch_model-00005-of-00006.bin",
+    "h.32.self_attention.dense.weight": "pytorch_model-00005-of-00006.bin",
+    "h.32.self_attention.query_key_value.bias": "pytorch_model-00005-of-00006.bin",
+    "h.32.self_attention.query_key_value.weight": "pytorch_model-00005-of-00006.bin",
+    "h.33.input_layernorm.bias": "pytorch_model-00005-of-00006.bin",
+    "h.33.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "h.33.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00006.bin",
+    "h.33.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00006.bin",
+    "h.33.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00006.bin",
+    "h.33.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00006.bin",
+    "h.33.post_attention_layernorm.bias": "pytorch_model-00005-of-00006.bin",
+    "h.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "h.33.self_attention.dense.bias": "pytorch_model-00005-of-00006.bin",
+    "h.33.self_attention.dense.weight": "pytorch_model-00005-of-00006.bin",
+    "h.33.self_attention.query_key_value.bias": "pytorch_model-00005-of-00006.bin",
+    "h.33.self_attention.query_key_value.weight": "pytorch_model-00005-of-00006.bin",
+    "h.34.input_layernorm.bias": "pytorch_model-00005-of-00006.bin",
+    "h.34.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "h.34.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00006.bin",
+    "h.34.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00006.bin",
+    "h.34.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00006.bin",
+    "h.34.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00006.bin",
+    "h.34.post_attention_layernorm.bias": "pytorch_model-00005-of-00006.bin",
+    "h.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "h.34.self_attention.dense.bias": "pytorch_model-00005-of-00006.bin",
+    "h.34.self_attention.dense.weight": "pytorch_model-00005-of-00006.bin",
+    "h.34.self_attention.query_key_value.bias": "pytorch_model-00005-of-00006.bin",
+    "h.34.self_attention.query_key_value.weight": "pytorch_model-00005-of-00006.bin",
+    "h.35.input_layernorm.bias": "pytorch_model-00005-of-00006.bin",
+    "h.35.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "h.35.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00006.bin",
+    "h.35.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00006.bin",
+    "h.35.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00006.bin",
+    "h.35.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00006.bin",
+    "h.35.post_attention_layernorm.bias": "pytorch_model-00005-of-00006.bin",
+    "h.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "h.35.self_attention.dense.bias": "pytorch_model-00005-of-00006.bin",
+    "h.35.self_attention.dense.weight": "pytorch_model-00005-of-00006.bin",
+    "h.35.self_attention.query_key_value.bias": "pytorch_model-00005-of-00006.bin",
+    "h.35.self_attention.query_key_value.weight": "pytorch_model-00005-of-00006.bin",
+    "h.36.input_layernorm.bias": "pytorch_model-00005-of-00006.bin",
+    "h.36.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "h.36.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00006.bin",
+    "h.36.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00006.bin",
+    "h.36.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00006.bin",
+    "h.36.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00006.bin",
+    "h.36.post_attention_layernorm.bias": "pytorch_model-00005-of-00006.bin",
+    "h.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "h.36.self_attention.dense.bias": "pytorch_model-00005-of-00006.bin",
+    "h.36.self_attention.dense.weight": "pytorch_model-00005-of-00006.bin",
+    "h.36.self_attention.query_key_value.bias": "pytorch_model-00005-of-00006.bin",
+    "h.36.self_attention.query_key_value.weight": "pytorch_model-00005-of-00006.bin",
+    "h.37.input_layernorm.bias": "pytorch_model-00006-of-00006.bin",
+    "h.37.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "h.37.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00006.bin",
+    "h.37.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00006.bin",
+    "h.37.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00006.bin",
+    "h.37.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00006.bin",
+    "h.37.post_attention_layernorm.bias": "pytorch_model-00006-of-00006.bin",
+    "h.37.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "h.37.self_attention.dense.bias": "pytorch_model-00006-of-00006.bin",
+    "h.37.self_attention.dense.weight": "pytorch_model-00006-of-00006.bin",
+    "h.37.self_attention.query_key_value.bias": "pytorch_model-00006-of-00006.bin",
+    "h.37.self_attention.query_key_value.weight": "pytorch_model-00006-of-00006.bin",
+    "h.38.input_layernorm.bias": "pytorch_model-00006-of-00006.bin",
+    "h.38.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "h.38.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00006.bin",
+    "h.38.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00006.bin",
+    "h.38.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00006.bin",
+    "h.38.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00006.bin",
+    "h.38.post_attention_layernorm.bias": "pytorch_model-00006-of-00006.bin",
+    "h.38.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "h.38.self_attention.dense.bias": "pytorch_model-00006-of-00006.bin",
+    "h.38.self_attention.dense.weight": "pytorch_model-00006-of-00006.bin",
+    "h.38.self_attention.query_key_value.bias": "pytorch_model-00006-of-00006.bin",
+    "h.38.self_attention.query_key_value.weight": "pytorch_model-00006-of-00006.bin",
+    "h.39.input_layernorm.bias": "pytorch_model-00006-of-00006.bin",
+    "h.39.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "h.39.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00006.bin",
+    "h.39.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00006.bin",
+    "h.39.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00006.bin",
+    "h.39.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00006.bin",
+    "h.39.post_attention_layernorm.bias": "pytorch_model-00006-of-00006.bin",
+    "h.39.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "h.39.self_attention.dense.bias": "pytorch_model-00006-of-00006.bin",
+    "h.39.self_attention.dense.weight": "pytorch_model-00006-of-00006.bin",
+    "h.39.self_attention.query_key_value.bias": "pytorch_model-00006-of-00006.bin",
+    "h.39.self_attention.query_key_value.weight": "pytorch_model-00006-of-00006.bin",
+    "h.4.input_layernorm.bias": "pytorch_model-00001-of-00006.bin",
+    "h.4.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "h.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00006.bin",
+    "h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00006.bin",
+    "h.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00006.bin",
+    "h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00006.bin",
+    "h.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00006.bin",
+    "h.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "h.4.self_attention.dense.bias": "pytorch_model-00001-of-00006.bin",
+    "h.4.self_attention.dense.weight": "pytorch_model-00001-of-00006.bin",
+    "h.4.self_attention.query_key_value.bias": "pytorch_model-00001-of-00006.bin",
+    "h.4.self_attention.query_key_value.weight": "pytorch_model-00001-of-00006.bin",
+    "h.5.input_layernorm.bias": "pytorch_model-00001-of-00006.bin",
+    "h.5.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "h.5.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00006.bin",
+    "h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00006.bin",
+    "h.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00006.bin",
+    "h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00006.bin",
+    "h.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00006.bin",
+    "h.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "h.5.self_attention.dense.bias": "pytorch_model-00001-of-00006.bin",
+    "h.5.self_attention.dense.weight": "pytorch_model-00001-of-00006.bin",
+    "h.5.self_attention.query_key_value.bias": "pytorch_model-00001-of-00006.bin",
+    "h.5.self_attention.query_key_value.weight": "pytorch_model-00001-of-00006.bin",
+    "h.6.input_layernorm.bias": "pytorch_model-00002-of-00006.bin",
+    "h.6.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "h.6.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00006.bin",
+    "h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00006.bin",
+    "h.6.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00006.bin",
+    "h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00006.bin",
+    "h.6.post_attention_layernorm.bias": "pytorch_model-00002-of-00006.bin",
+    "h.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "h.6.self_attention.dense.bias": "pytorch_model-00002-of-00006.bin",
+    "h.6.self_attention.dense.weight": "pytorch_model-00002-of-00006.bin",
+    "h.6.self_attention.query_key_value.bias": "pytorch_model-00002-of-00006.bin",
+    "h.6.self_attention.query_key_value.weight": "pytorch_model-00002-of-00006.bin",
+    "h.7.input_layernorm.bias": "pytorch_model-00002-of-00006.bin",
+    "h.7.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "h.7.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00006.bin",
+    "h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00006.bin",
+    "h.7.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00006.bin",
+    "h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00006.bin",
+    "h.7.post_attention_layernorm.bias": "pytorch_model-00002-of-00006.bin",
+    "h.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "h.7.self_attention.dense.bias": "pytorch_model-00002-of-00006.bin",
+    "h.7.self_attention.dense.weight": "pytorch_model-00002-of-00006.bin",
+    "h.7.self_attention.query_key_value.bias": "pytorch_model-00002-of-00006.bin",
+    "h.7.self_attention.query_key_value.weight": "pytorch_model-00002-of-00006.bin",
+    "h.8.input_layernorm.bias": "pytorch_model-00002-of-00006.bin",
+    "h.8.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "h.8.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00006.bin",
+    "h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00006.bin",
+    "h.8.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00006.bin",
+    "h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00006.bin",
+    "h.8.post_attention_layernorm.bias": "pytorch_model-00002-of-00006.bin",
+    "h.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "h.8.self_attention.dense.bias": "pytorch_model-00002-of-00006.bin",
+    "h.8.self_attention.dense.weight": "pytorch_model-00002-of-00006.bin",
+    "h.8.self_attention.query_key_value.bias": "pytorch_model-00002-of-00006.bin",
+    "h.8.self_attention.query_key_value.weight": "pytorch_model-00002-of-00006.bin",
+    "h.9.input_layernorm.bias": "pytorch_model-00002-of-00006.bin",
+    "h.9.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "h.9.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00006.bin",
+    "h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00006.bin",
+    "h.9.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00006.bin",
+    "h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00006.bin",
+    "h.9.post_attention_layernorm.bias": "pytorch_model-00002-of-00006.bin",
+    "h.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "h.9.self_attention.dense.bias": "pytorch_model-00002-of-00006.bin",
+    "h.9.self_attention.dense.weight": "pytorch_model-00002-of-00006.bin",
+    "h.9.self_attention.query_key_value.bias": "pytorch_model-00002-of-00006.bin",
+    "h.9.self_attention.query_key_value.weight": "pytorch_model-00002-of-00006.bin",
+    "ln_f.bias": "pytorch_model-00006-of-00006.bin",
+    "ln_f.weight": "pytorch_model-00006-of-00006.bin",
+    "word_embeddings.weight": "pytorch_model-00001-of-00006.bin",
+    "word_embeddings_layernorm.bias": "pytorch_model-00001-of-00006.bin",
+    "word_embeddings_layernorm.weight": "pytorch_model-00001-of-00006.bin"
+  }
+}