Upload OPTForCausalLM

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "checkpoint-1500",
+  "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "eos_token_id": 2,
+  "ffn_dim": 28672,
+  "hidden_size": 7168,
+  "init_std": 0.02,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
+  "num_attention_heads": 56,
+  "num_hidden_layers": 48,
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50265,
+  "word_embed_proj_dim": 7168
+}

pytorch_model-00001-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73e174696588922c9c65b62612a8fd557ee9bc9a1af0ed27155cb010d9b5460e
+size 9722178811

pytorch_model-00002-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c14f9eb22a70bee103f7f4a29205ab1f9d3f697a79f4adbd5e74ee7230cc0b2
+size 9866514441

pytorch_model-00003-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f7cb1c9df1dc49c8fc16be30d7a156d029dd0a65b20b35d53198aebf9b93070
+size 9866514441

pytorch_model-00004-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2350efd89c548d8c3bc708075d96e43bbe0cd7e85cc52c821223f5452b482775
+size 9866514505

pytorch_model-00005-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fae7ffa389a66474529d19c14443e9ca78bb3c2d47c3307c2881abb4328b30f6
+size 9866514505

pytorch_model-00006-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cbf41934740d9cd9a06bd436ab35822238a53d1362c385717cbc80744bea9b4
+size 9866514505

pytorch_model-00007-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8be34859dbcfb9648d0d5090ae7719de1dd5352fa9d2d9140f0d0687b09bffd6
+size 9866514505

pytorch_model-00008-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be28fa0e2f2c8bb44aa0910fa22651c2409cee2c62a30a4fe269c90be72ccb50
+size 9866514505

pytorch_model-00009-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c81d15890c02c43d65e0786d0af70d9b16958fa78c725ca941749400ac9bebbd
+size 9866514505

pytorch_model-00010-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b2fba8f49691057fce61c2bebe19cc19108e8a45db91e65da907376df7dec1b
+size 9866514505

pytorch_model-00011-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6e8a4c1a522c0507b77538722a8ddc2817643a85bf2474f4ea39cebd335b7b0
+size 9866514505

pytorch_model-00012-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae8c869c6b0b8ae41ec73e47ce9b0c3e6247470eacb17cd51dba205d70365edc
+size 9866514505

pytorch_model-00013-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceded9bdf0794f1ad26f5a37106e1d55cb7c8d3b0e8b87eb71e246f10027529f
+size 3085568083

pytorch_model.bin.index.json

@@ -0,0 +1,780 @@
+{
+  "metadata": {
+    "total_size": 121339158528
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00013-of-00013.bin",
+    "model.decoder.embed_positions.weight": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.embed_tokens.weight": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.final_layer_norm.bias": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.final_layer_norm.weight": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.0.fc1.bias": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.0.fc1.weight": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.0.fc2.bias": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.0.fc2.weight": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.0.final_layer_norm.bias": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.0.final_layer_norm.weight": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.0.self_attn_layer_norm.bias": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.0.self_attn_layer_norm.weight": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.1.fc1.bias": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.1.fc1.weight": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.1.fc2.bias": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.1.fc2.weight": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.1.final_layer_norm.bias": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.1.final_layer_norm.weight": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.1.self_attn_layer_norm.bias": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.1.self_attn_layer_norm.weight": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.10.fc1.bias": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.10.fc1.weight": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.10.fc2.bias": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.10.fc2.weight": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.10.final_layer_norm.bias": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.10.final_layer_norm.weight": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.10.self_attn_layer_norm.bias": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.10.self_attn_layer_norm.weight": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.11.fc1.bias": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.11.fc1.weight": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.11.fc2.bias": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.11.fc2.weight": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.11.final_layer_norm.bias": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.11.final_layer_norm.weight": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.11.self_attn_layer_norm.bias": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.11.self_attn_layer_norm.weight": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.12.fc1.bias": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.12.fc1.weight": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.12.fc2.bias": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.12.fc2.weight": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.12.final_layer_norm.bias": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.12.final_layer_norm.weight": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.12.self_attn_layer_norm.bias": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.12.self_attn_layer_norm.weight": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.13.fc1.bias": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.13.fc1.weight": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.13.fc2.bias": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.13.fc2.weight": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.13.final_layer_norm.bias": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.13.final_layer_norm.weight": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.13.self_attn_layer_norm.bias": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.13.self_attn_layer_norm.weight": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.14.fc1.bias": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.14.fc1.weight": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.14.fc2.bias": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.14.fc2.weight": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.14.final_layer_norm.bias": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.14.final_layer_norm.weight": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.14.self_attn_layer_norm.bias": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.14.self_attn_layer_norm.weight": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.15.fc1.bias": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.15.fc1.weight": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.15.fc2.bias": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.15.fc2.weight": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.15.final_layer_norm.bias": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.15.final_layer_norm.weight": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.15.self_attn_layer_norm.bias": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.15.self_attn_layer_norm.weight": "pytorch_model-00004-of-00013.bin",
+    "model.decoder.layers.16.fc1.bias": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.16.fc1.weight": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.16.fc2.bias": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.16.fc2.weight": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.16.final_layer_norm.bias": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.16.final_layer_norm.weight": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.16.self_attn_layer_norm.bias": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.16.self_attn_layer_norm.weight": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.17.fc1.bias": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.17.fc1.weight": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.17.fc2.bias": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.17.fc2.weight": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.17.final_layer_norm.bias": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.17.final_layer_norm.weight": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.17.self_attn_layer_norm.bias": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.17.self_attn_layer_norm.weight": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.18.fc1.bias": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.18.fc1.weight": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.18.fc2.bias": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.18.fc2.weight": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.18.final_layer_norm.bias": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.18.final_layer_norm.weight": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.18.self_attn_layer_norm.bias": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.18.self_attn_layer_norm.weight": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.19.fc1.bias": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.19.fc1.weight": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.19.fc2.bias": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.19.fc2.weight": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.19.final_layer_norm.bias": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.19.final_layer_norm.weight": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.19.self_attn_layer_norm.bias": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.19.self_attn_layer_norm.weight": "pytorch_model-00005-of-00013.bin",
+    "model.decoder.layers.2.fc1.bias": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.2.fc1.weight": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.2.fc2.bias": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.2.fc2.weight": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.2.final_layer_norm.bias": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.2.final_layer_norm.weight": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.2.self_attn_layer_norm.bias": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.2.self_attn_layer_norm.weight": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.20.fc1.bias": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.20.fc1.weight": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.20.fc2.bias": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.20.fc2.weight": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.20.final_layer_norm.bias": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.20.final_layer_norm.weight": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.20.self_attn_layer_norm.bias": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.20.self_attn_layer_norm.weight": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.21.fc1.bias": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.21.fc1.weight": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.21.fc2.bias": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.21.fc2.weight": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.21.final_layer_norm.bias": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.21.final_layer_norm.weight": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.21.self_attn_layer_norm.bias": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.21.self_attn_layer_norm.weight": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.22.fc1.bias": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.22.fc1.weight": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.22.fc2.bias": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.22.fc2.weight": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.22.final_layer_norm.bias": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.22.final_layer_norm.weight": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.22.self_attn_layer_norm.bias": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.22.self_attn_layer_norm.weight": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.23.fc1.bias": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.23.fc1.weight": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.23.fc2.bias": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.23.fc2.weight": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.23.final_layer_norm.bias": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.23.final_layer_norm.weight": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.23.self_attn_layer_norm.bias": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.23.self_attn_layer_norm.weight": "pytorch_model-00006-of-00013.bin",
+    "model.decoder.layers.24.fc1.bias": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.24.fc1.weight": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.24.fc2.bias": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.24.fc2.weight": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.24.final_layer_norm.bias": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.24.final_layer_norm.weight": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.24.self_attn.k_proj.bias": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.24.self_attn.k_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.24.self_attn.out_proj.bias": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.24.self_attn.out_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.24.self_attn.q_proj.bias": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.24.self_attn.q_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.24.self_attn.v_proj.bias": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.24.self_attn.v_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.24.self_attn_layer_norm.bias": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.24.self_attn_layer_norm.weight": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.25.fc1.bias": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.25.fc1.weight": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.25.fc2.bias": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.25.fc2.weight": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.25.final_layer_norm.bias": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.25.final_layer_norm.weight": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.25.self_attn.k_proj.bias": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.25.self_attn.k_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.25.self_attn.out_proj.bias": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.25.self_attn.out_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.25.self_attn.q_proj.bias": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.25.self_attn.q_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.25.self_attn.v_proj.bias": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.25.self_attn.v_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.25.self_attn_layer_norm.bias": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.25.self_attn_layer_norm.weight": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.26.fc1.bias": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.26.fc1.weight": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.26.fc2.bias": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.26.fc2.weight": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.26.final_layer_norm.bias": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.26.final_layer_norm.weight": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.26.self_attn.k_proj.bias": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.26.self_attn.k_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.26.self_attn.out_proj.bias": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.26.self_attn.out_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.26.self_attn.q_proj.bias": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.26.self_attn.q_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.26.self_attn.v_proj.bias": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.26.self_attn.v_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.26.self_attn_layer_norm.bias": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.26.self_attn_layer_norm.weight": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.27.fc1.bias": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.27.fc1.weight": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.27.fc2.bias": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.27.fc2.weight": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.27.final_layer_norm.bias": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.27.final_layer_norm.weight": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.27.self_attn.k_proj.bias": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.27.self_attn.k_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.27.self_attn.out_proj.bias": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.27.self_attn.out_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.27.self_attn.q_proj.bias": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.27.self_attn.q_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.27.self_attn.v_proj.bias": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.27.self_attn.v_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.27.self_attn_layer_norm.bias": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.27.self_attn_layer_norm.weight": "pytorch_model-00007-of-00013.bin",
+    "model.decoder.layers.28.fc1.bias": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.28.fc1.weight": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.28.fc2.bias": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.28.fc2.weight": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.28.final_layer_norm.bias": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.28.final_layer_norm.weight": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.28.self_attn.k_proj.bias": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.28.self_attn.k_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.28.self_attn.out_proj.bias": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.28.self_attn.out_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.28.self_attn.q_proj.bias": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.28.self_attn.q_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.28.self_attn.v_proj.bias": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.28.self_attn.v_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.28.self_attn_layer_norm.bias": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.28.self_attn_layer_norm.weight": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.29.fc1.bias": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.29.fc1.weight": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.29.fc2.bias": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.29.fc2.weight": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.29.final_layer_norm.bias": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.29.final_layer_norm.weight": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.29.self_attn.k_proj.bias": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.29.self_attn.k_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.29.self_attn.out_proj.bias": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.29.self_attn.out_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.29.self_attn.q_proj.bias": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.29.self_attn.q_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.29.self_attn.v_proj.bias": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.29.self_attn.v_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.29.self_attn_layer_norm.bias": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.29.self_attn_layer_norm.weight": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.3.fc1.bias": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.3.fc1.weight": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.3.fc2.bias": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.3.fc2.weight": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.3.final_layer_norm.bias": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.3.final_layer_norm.weight": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.3.self_attn_layer_norm.bias": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.3.self_attn_layer_norm.weight": "pytorch_model-00001-of-00013.bin",
+    "model.decoder.layers.30.fc1.bias": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.30.fc1.weight": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.30.fc2.bias": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.30.fc2.weight": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.30.final_layer_norm.bias": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.30.final_layer_norm.weight": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.30.self_attn.k_proj.bias": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.30.self_attn.k_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.30.self_attn.out_proj.bias": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.30.self_attn.out_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.30.self_attn.q_proj.bias": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.30.self_attn.q_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.30.self_attn.v_proj.bias": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.30.self_attn.v_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.30.self_attn_layer_norm.bias": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.30.self_attn_layer_norm.weight": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.31.fc1.bias": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.31.fc1.weight": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.31.fc2.bias": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.31.fc2.weight": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.31.final_layer_norm.bias": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.31.final_layer_norm.weight": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.31.self_attn.k_proj.bias": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.31.self_attn.k_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.31.self_attn.out_proj.bias": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.31.self_attn.out_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.31.self_attn.q_proj.bias": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.31.self_attn.q_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.31.self_attn.v_proj.bias": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.31.self_attn.v_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.31.self_attn_layer_norm.bias": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.31.self_attn_layer_norm.weight": "pytorch_model-00008-of-00013.bin",
+    "model.decoder.layers.32.fc1.bias": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.32.fc1.weight": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.32.fc2.bias": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.32.fc2.weight": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.32.final_layer_norm.bias": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.32.final_layer_norm.weight": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.32.self_attn.k_proj.bias": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.32.self_attn.k_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.32.self_attn.out_proj.bias": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.32.self_attn.out_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.32.self_attn.q_proj.bias": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.32.self_attn.q_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.32.self_attn.v_proj.bias": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.32.self_attn.v_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.32.self_attn_layer_norm.bias": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.32.self_attn_layer_norm.weight": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.33.fc1.bias": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.33.fc1.weight": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.33.fc2.bias": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.33.fc2.weight": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.33.final_layer_norm.bias": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.33.final_layer_norm.weight": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.33.self_attn.k_proj.bias": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.33.self_attn.k_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.33.self_attn.out_proj.bias": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.33.self_attn.out_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.33.self_attn.q_proj.bias": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.33.self_attn.q_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.33.self_attn.v_proj.bias": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.33.self_attn.v_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.33.self_attn_layer_norm.bias": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.33.self_attn_layer_norm.weight": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.34.fc1.bias": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.34.fc1.weight": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.34.fc2.bias": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.34.fc2.weight": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.34.final_layer_norm.bias": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.34.final_layer_norm.weight": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.34.self_attn.k_proj.bias": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.34.self_attn.k_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.34.self_attn.out_proj.bias": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.34.self_attn.out_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.34.self_attn.q_proj.bias": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.34.self_attn.q_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.34.self_attn.v_proj.bias": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.34.self_attn.v_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.34.self_attn_layer_norm.bias": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.34.self_attn_layer_norm.weight": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.35.fc1.bias": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.35.fc1.weight": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.35.fc2.bias": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.35.fc2.weight": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.35.final_layer_norm.bias": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.35.final_layer_norm.weight": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.35.self_attn.k_proj.bias": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.35.self_attn.k_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.35.self_attn.out_proj.bias": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.35.self_attn.out_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.35.self_attn.q_proj.bias": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.35.self_attn.q_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.35.self_attn.v_proj.bias": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.35.self_attn.v_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.35.self_attn_layer_norm.bias": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.35.self_attn_layer_norm.weight": "pytorch_model-00009-of-00013.bin",
+    "model.decoder.layers.36.fc1.bias": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.36.fc1.weight": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.36.fc2.bias": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.36.fc2.weight": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.36.final_layer_norm.bias": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.36.final_layer_norm.weight": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.36.self_attn.k_proj.bias": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.36.self_attn.k_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.36.self_attn.out_proj.bias": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.36.self_attn.out_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.36.self_attn.q_proj.bias": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.36.self_attn.q_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.36.self_attn.v_proj.bias": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.36.self_attn.v_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.36.self_attn_layer_norm.bias": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.36.self_attn_layer_norm.weight": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.37.fc1.bias": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.37.fc1.weight": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.37.fc2.bias": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.37.fc2.weight": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.37.final_layer_norm.bias": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.37.final_layer_norm.weight": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.37.self_attn.k_proj.bias": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.37.self_attn.k_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.37.self_attn.out_proj.bias": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.37.self_attn.out_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.37.self_attn.q_proj.bias": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.37.self_attn.q_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.37.self_attn.v_proj.bias": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.37.self_attn.v_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.37.self_attn_layer_norm.bias": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.37.self_attn_layer_norm.weight": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.38.fc1.bias": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.38.fc1.weight": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.38.fc2.bias": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.38.fc2.weight": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.38.final_layer_norm.bias": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.38.final_layer_norm.weight": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.38.self_attn.k_proj.bias": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.38.self_attn.k_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.38.self_attn.out_proj.bias": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.38.self_attn.out_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.38.self_attn.q_proj.bias": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.38.self_attn.q_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.38.self_attn.v_proj.bias": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.38.self_attn.v_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.38.self_attn_layer_norm.bias": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.38.self_attn_layer_norm.weight": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.39.fc1.bias": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.39.fc1.weight": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.39.fc2.bias": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.39.fc2.weight": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.39.final_layer_norm.bias": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.39.final_layer_norm.weight": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.39.self_attn.k_proj.bias": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.39.self_attn.k_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.39.self_attn.out_proj.bias": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.39.self_attn.out_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.39.self_attn.q_proj.bias": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.39.self_attn.q_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.39.self_attn.v_proj.bias": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.39.self_attn.v_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.39.self_attn_layer_norm.bias": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.39.self_attn_layer_norm.weight": "pytorch_model-00010-of-00013.bin",
+    "model.decoder.layers.4.fc1.bias": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.4.fc1.weight": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.4.fc2.bias": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.4.fc2.weight": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.4.final_layer_norm.bias": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.4.final_layer_norm.weight": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.4.self_attn_layer_norm.bias": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.4.self_attn_layer_norm.weight": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.40.fc1.bias": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.40.fc1.weight": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.40.fc2.bias": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.40.fc2.weight": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.40.final_layer_norm.bias": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.40.final_layer_norm.weight": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.40.self_attn.k_proj.bias": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.40.self_attn.k_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.40.self_attn.out_proj.bias": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.40.self_attn.out_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.40.self_attn.q_proj.bias": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.40.self_attn.q_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.40.self_attn.v_proj.bias": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.40.self_attn.v_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.40.self_attn_layer_norm.bias": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.40.self_attn_layer_norm.weight": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.41.fc1.bias": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.41.fc1.weight": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.41.fc2.bias": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.41.fc2.weight": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.41.final_layer_norm.bias": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.41.final_layer_norm.weight": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.41.self_attn.k_proj.bias": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.41.self_attn.k_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.41.self_attn.out_proj.bias": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.41.self_attn.out_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.41.self_attn.q_proj.bias": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.41.self_attn.q_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.41.self_attn.v_proj.bias": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.41.self_attn.v_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.41.self_attn_layer_norm.bias": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.41.self_attn_layer_norm.weight": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.42.fc1.bias": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.42.fc1.weight": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.42.fc2.bias": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.42.fc2.weight": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.42.final_layer_norm.bias": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.42.final_layer_norm.weight": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.42.self_attn.k_proj.bias": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.42.self_attn.k_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.42.self_attn.out_proj.bias": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.42.self_attn.out_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.42.self_attn.q_proj.bias": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.42.self_attn.q_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.42.self_attn.v_proj.bias": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.42.self_attn.v_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.42.self_attn_layer_norm.bias": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.42.self_attn_layer_norm.weight": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.43.fc1.bias": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.43.fc1.weight": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.43.fc2.bias": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.43.fc2.weight": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.43.final_layer_norm.bias": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.43.final_layer_norm.weight": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.43.self_attn.k_proj.bias": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.43.self_attn.k_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.43.self_attn.out_proj.bias": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.43.self_attn.out_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.43.self_attn.q_proj.bias": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.43.self_attn.q_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.43.self_attn.v_proj.bias": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.43.self_attn.v_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.43.self_attn_layer_norm.bias": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.43.self_attn_layer_norm.weight": "pytorch_model-00011-of-00013.bin",
+    "model.decoder.layers.44.fc1.bias": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.44.fc1.weight": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.44.fc2.bias": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.44.fc2.weight": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.44.final_layer_norm.bias": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.44.final_layer_norm.weight": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.44.self_attn.k_proj.bias": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.44.self_attn.k_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.44.self_attn.out_proj.bias": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.44.self_attn.out_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.44.self_attn.q_proj.bias": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.44.self_attn.q_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.44.self_attn.v_proj.bias": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.44.self_attn.v_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.44.self_attn_layer_norm.bias": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.44.self_attn_layer_norm.weight": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.45.fc1.bias": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.45.fc1.weight": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.45.fc2.bias": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.45.fc2.weight": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.45.final_layer_norm.bias": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.45.final_layer_norm.weight": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.45.self_attn.k_proj.bias": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.45.self_attn.k_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.45.self_attn.out_proj.bias": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.45.self_attn.out_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.45.self_attn.q_proj.bias": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.45.self_attn.q_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.45.self_attn.v_proj.bias": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.45.self_attn.v_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.45.self_attn_layer_norm.bias": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.45.self_attn_layer_norm.weight": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.46.fc1.bias": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.46.fc1.weight": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.46.fc2.bias": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.46.fc2.weight": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.46.final_layer_norm.bias": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.46.final_layer_norm.weight": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.46.self_attn.k_proj.bias": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.46.self_attn.k_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.46.self_attn.out_proj.bias": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.46.self_attn.out_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.46.self_attn.q_proj.bias": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.46.self_attn.q_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.46.self_attn.v_proj.bias": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.46.self_attn.v_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.46.self_attn_layer_norm.bias": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.46.self_attn_layer_norm.weight": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.47.fc1.bias": "pytorch_model-00013-of-00013.bin",
+    "model.decoder.layers.47.fc1.weight": "pytorch_model-00013-of-00013.bin",
+    "model.decoder.layers.47.fc2.bias": "pytorch_model-00013-of-00013.bin",
+    "model.decoder.layers.47.fc2.weight": "pytorch_model-00013-of-00013.bin",
+    "model.decoder.layers.47.final_layer_norm.bias": "pytorch_model-00013-of-00013.bin",
+    "model.decoder.layers.47.final_layer_norm.weight": "pytorch_model-00013-of-00013.bin",
+    "model.decoder.layers.47.self_attn.k_proj.bias": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.47.self_attn.k_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.47.self_attn.out_proj.bias": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.47.self_attn.out_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.47.self_attn.q_proj.bias": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.47.self_attn.q_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.47.self_attn.v_proj.bias": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.47.self_attn.v_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.47.self_attn_layer_norm.bias": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.47.self_attn_layer_norm.weight": "pytorch_model-00012-of-00013.bin",
+    "model.decoder.layers.5.fc1.bias": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.5.fc1.weight": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.5.fc2.bias": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.5.fc2.weight": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.5.final_layer_norm.bias": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.5.final_layer_norm.weight": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.5.self_attn_layer_norm.bias": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.5.self_attn_layer_norm.weight": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.6.fc1.bias": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.6.fc1.weight": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.6.fc2.bias": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.6.fc2.weight": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.6.final_layer_norm.bias": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.6.final_layer_norm.weight": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.6.self_attn_layer_norm.bias": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.6.self_attn_layer_norm.weight": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.7.fc1.bias": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.7.fc1.weight": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.7.fc2.bias": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.7.fc2.weight": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.7.final_layer_norm.bias": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.7.final_layer_norm.weight": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.7.self_attn_layer_norm.bias": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.7.self_attn_layer_norm.weight": "pytorch_model-00002-of-00013.bin",
+    "model.decoder.layers.8.fc1.bias": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.8.fc1.weight": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.8.fc2.bias": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.8.fc2.weight": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.8.final_layer_norm.bias": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.8.final_layer_norm.weight": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.8.self_attn_layer_norm.bias": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.8.self_attn_layer_norm.weight": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.9.fc1.bias": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.9.fc1.weight": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.9.fc2.bias": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.9.fc2.weight": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.9.final_layer_norm.bias": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.9.final_layer_norm.weight": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.9.self_attn_layer_norm.bias": "pytorch_model-00003-of-00013.bin",
+    "model.decoder.layers.9.self_attn_layer_norm.weight": "pytorch_model-00003-of-00013.bin"
+  }
+}