Adding `safetensors` variant of this model

This is an automated PR created with https://huggingface.co/spaces/safetensors/convert

This new file is equivalent to `pytorch_model.bin` but safe in the sense that
no arbitrary code can be put into it.

These files also happen to load much faster than their pytorch counterpart:
https://colab.research.google.com/github/huggingface/notebooks/blob/main/safetensors_doc/en/speed.ipynb

The widgets on your model page will run using this model even if this is not merged
making sure the file actually works.

If you find any issues: please report here: https://huggingface.co/spaces/safetensors/convert/discussions

Feel free to ignore this PR.

model-00002-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c65a50376703366dc51fb9ee873cc3fad294c10817aef79d79094c21485cf32
+size 2055209112

model-00003-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3d05468ae1aec2a58b3b62bead11a0d64b439a394d7b85a769ca47510f5b491
+size 939822984

model-00004-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ce0e89badf601dae38374d2226590c7cb3a85c98935c2eab8d45e02ab638c5f
+size 939772912

model-00005-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d685ec6b7f9415e1e7846ccd7c6054d6d8f726e90f413a9df6d64e5787e1082
+size 939764936

model-00006-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dac65e0a469aa71306c0462723d97fdc0af66fe013619bdf46b7cf6becaf3cbd
+size 939789784

model-00007-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c10112448bdfa27f6e84f877d59f678f4e0d8e0154f2814b374e5c79e0c73421
+size 939772912

model-00008-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea0681c2e07938949dcc74060d8f2915fd30d44bbf25081c12d0000e23c7fdcc
+size 939764960

model-00009-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60768073cbe61e62efe18739c3c6ce25f83a92c3c8bfcabc3fe2e219ac94221d
+size 939789816

model-00010-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eb049c2cde525fef3c7e1fc9b66fa45118ed742bb6586d18c12a3c68c57bee5
+size 939772936

model-00011-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29fea165eb6f0cef2d1771d14e45c3b4db6e1914bfb120e7c789d201dd0dc19f
+size 939764960

model-00012-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0782f16a5ac7ea314c0b859964c04dcf444468005ad3a0fbd421223e6c617ce6
+size 939789816

model-00013-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8cac600245e591c7073fd773ebcb5466e791331163b9dc9bcd6981789b830ed
+size 939772936

model-00014-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f8ccf3b251ca1dd0974d4905de8c8b7a170162eb78f329be64e934ec56bc6be
+size 939764960

model-00015-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ee96bcd9004358dfc883f7f4234ebe33e18e7ba24f5f351420fdca32ed21238
+size 805522176

model-00016-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ee917375f8c00570027f0cb18f2b30192e95197b07705cb830c8740ed0b35b2
+size 2055209088

model.safetensors.index.json

@@ -0,0 +1,373 @@
+{
+    "metadata": {
+        "total_size": 16193241088
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00016-of-00016.safetensors",
+        "transformer.h.0.input_layernorm.bias": "model-00003-of-00016.safetensors",
+        "transformer.h.0.input_layernorm.weight": "model-00003-of-00016.safetensors",
+        "transformer.h.0.mlp.dense_4h_to_h.bias": "model-00003-of-00016.safetensors",
+        "transformer.h.0.mlp.dense_4h_to_h.weight": "model-00003-of-00016.safetensors",
+        "transformer.h.0.mlp.dense_h_to_4h.bias": "model-00003-of-00016.safetensors",
+        "transformer.h.0.mlp.dense_h_to_4h.weight": "model-00003-of-00016.safetensors",
+        "transformer.h.0.post_attention_layernorm.bias": "model-00003-of-00016.safetensors",
+        "transformer.h.0.post_attention_layernorm.weight": "model-00003-of-00016.safetensors",
+        "transformer.h.0.self_attention.dense.bias": "model-00003-of-00016.safetensors",
+        "transformer.h.0.self_attention.dense.weight": "model-00003-of-00016.safetensors",
+        "transformer.h.0.self_attention.query_key_value.bias": "model-00003-of-00016.safetensors",
+        "transformer.h.0.self_attention.query_key_value.weight": "model-00003-of-00016.safetensors",
+        "transformer.h.1.input_layernorm.bias": "model-00003-of-00016.safetensors",
+        "transformer.h.1.input_layernorm.weight": "model-00003-of-00016.safetensors",
+        "transformer.h.1.mlp.dense_4h_to_h.bias": "model-00003-of-00016.safetensors",
+        "transformer.h.1.mlp.dense_4h_to_h.weight": "model-00003-of-00016.safetensors",
+        "transformer.h.1.mlp.dense_h_to_4h.bias": "model-00003-of-00016.safetensors",
+        "transformer.h.1.mlp.dense_h_to_4h.weight": "model-00003-of-00016.safetensors",
+        "transformer.h.1.post_attention_layernorm.bias": "model-00003-of-00016.safetensors",
+        "transformer.h.1.post_attention_layernorm.weight": "model-00003-of-00016.safetensors",
+        "transformer.h.1.self_attention.dense.bias": "model-00003-of-00016.safetensors",
+        "transformer.h.1.self_attention.dense.weight": "model-00003-of-00016.safetensors",
+        "transformer.h.1.self_attention.query_key_value.bias": "model-00003-of-00016.safetensors",
+        "transformer.h.1.self_attention.query_key_value.weight": "model-00003-of-00016.safetensors",
+        "transformer.h.10.input_layernorm.bias": "model-00007-of-00016.safetensors",
+        "transformer.h.10.input_layernorm.weight": "model-00007-of-00016.safetensors",
+        "transformer.h.10.mlp.dense_4h_to_h.bias": "model-00007-of-00016.safetensors",
+        "transformer.h.10.mlp.dense_4h_to_h.weight": "model-00007-of-00016.safetensors",
+        "transformer.h.10.mlp.dense_h_to_4h.bias": "model-00007-of-00016.safetensors",
+        "transformer.h.10.mlp.dense_h_to_4h.weight": "model-00007-of-00016.safetensors",
+        "transformer.h.10.post_attention_layernorm.bias": "model-00007-of-00016.safetensors",
+        "transformer.h.10.post_attention_layernorm.weight": "model-00007-of-00016.safetensors",
+        "transformer.h.10.self_attention.dense.bias": "model-00007-of-00016.safetensors",
+        "transformer.h.10.self_attention.dense.weight": "model-00007-of-00016.safetensors",
+        "transformer.h.10.self_attention.query_key_value.bias": "model-00007-of-00016.safetensors",
+        "transformer.h.10.self_attention.query_key_value.weight": "model-00007-of-00016.safetensors",
+        "transformer.h.11.input_layernorm.bias": "model-00007-of-00016.safetensors",
+        "transformer.h.11.input_layernorm.weight": "model-00007-of-00016.safetensors",
+        "transformer.h.11.mlp.dense_4h_to_h.bias": "model-00008-of-00016.safetensors",
+        "transformer.h.11.mlp.dense_4h_to_h.weight": "model-00008-of-00016.safetensors",
+        "transformer.h.11.mlp.dense_h_to_4h.bias": "model-00007-of-00016.safetensors",
+        "transformer.h.11.mlp.dense_h_to_4h.weight": "model-00007-of-00016.safetensors",
+        "transformer.h.11.post_attention_layernorm.bias": "model-00007-of-00016.safetensors",
+        "transformer.h.11.post_attention_layernorm.weight": "model-00007-of-00016.safetensors",
+        "transformer.h.11.self_attention.dense.bias": "model-00007-of-00016.safetensors",
+        "transformer.h.11.self_attention.dense.weight": "model-00007-of-00016.safetensors",
+        "transformer.h.11.self_attention.query_key_value.bias": "model-00007-of-00016.safetensors",
+        "transformer.h.11.self_attention.query_key_value.weight": "model-00007-of-00016.safetensors",
+        "transformer.h.12.input_layernorm.bias": "model-00008-of-00016.safetensors",
+        "transformer.h.12.input_layernorm.weight": "model-00008-of-00016.safetensors",
+        "transformer.h.12.mlp.dense_4h_to_h.bias": "model-00008-of-00016.safetensors",
+        "transformer.h.12.mlp.dense_4h_to_h.weight": "model-00008-of-00016.safetensors",
+        "transformer.h.12.mlp.dense_h_to_4h.bias": "model-00008-of-00016.safetensors",
+        "transformer.h.12.mlp.dense_h_to_4h.weight": "model-00008-of-00016.safetensors",
+        "transformer.h.12.post_attention_layernorm.bias": "model-00008-of-00016.safetensors",
+        "transformer.h.12.post_attention_layernorm.weight": "model-00008-of-00016.safetensors",
+        "transformer.h.12.self_attention.dense.bias": "model-00008-of-00016.safetensors",
+        "transformer.h.12.self_attention.dense.weight": "model-00008-of-00016.safetensors",
+        "transformer.h.12.self_attention.query_key_value.bias": "model-00008-of-00016.safetensors",
+        "transformer.h.12.self_attention.query_key_value.weight": "model-00008-of-00016.safetensors",
+        "transformer.h.13.input_layernorm.bias": "model-00008-of-00016.safetensors",
+        "transformer.h.13.input_layernorm.weight": "model-00008-of-00016.safetensors",
+        "transformer.h.13.mlp.dense_4h_to_h.bias": "model-00008-of-00016.safetensors",
+        "transformer.h.13.mlp.dense_4h_to_h.weight": "model-00008-of-00016.safetensors",
+        "transformer.h.13.mlp.dense_h_to_4h.bias": "model-00008-of-00016.safetensors",
+        "transformer.h.13.mlp.dense_h_to_4h.weight": "model-00008-of-00016.safetensors",
+        "transformer.h.13.post_attention_layernorm.bias": "model-00008-of-00016.safetensors",
+        "transformer.h.13.post_attention_layernorm.weight": "model-00008-of-00016.safetensors",
+        "transformer.h.13.self_attention.dense.bias": "model-00008-of-00016.safetensors",
+        "transformer.h.13.self_attention.dense.weight": "model-00008-of-00016.safetensors",
+        "transformer.h.13.self_attention.query_key_value.bias": "model-00008-of-00016.safetensors",
+        "transformer.h.13.self_attention.query_key_value.weight": "model-00008-of-00016.safetensors",
+        "transformer.h.14.input_layernorm.bias": "model-00008-of-00016.safetensors",
+        "transformer.h.14.input_layernorm.weight": "model-00008-of-00016.safetensors",
+        "transformer.h.14.mlp.dense_4h_to_h.bias": "model-00009-of-00016.safetensors",
+        "transformer.h.14.mlp.dense_4h_to_h.weight": "model-00009-of-00016.safetensors",
+        "transformer.h.14.mlp.dense_h_to_4h.bias": "model-00009-of-00016.safetensors",
+        "transformer.h.14.mlp.dense_h_to_4h.weight": "model-00009-of-00016.safetensors",
+        "transformer.h.14.post_attention_layernorm.bias": "model-00009-of-00016.safetensors",
+        "transformer.h.14.post_attention_layernorm.weight": "model-00009-of-00016.safetensors",
+        "transformer.h.14.self_attention.dense.bias": "model-00009-of-00016.safetensors",
+        "transformer.h.14.self_attention.dense.weight": "model-00009-of-00016.safetensors",
+        "transformer.h.14.self_attention.query_key_value.bias": "model-00009-of-00016.safetensors",
+        "transformer.h.14.self_attention.query_key_value.weight": "model-00009-of-00016.safetensors",
+        "transformer.h.15.input_layernorm.bias": "model-00009-of-00016.safetensors",
+        "transformer.h.15.input_layernorm.weight": "model-00009-of-00016.safetensors",
+        "transformer.h.15.mlp.dense_4h_to_h.bias": "model-00009-of-00016.safetensors",
+        "transformer.h.15.mlp.dense_4h_to_h.weight": "model-00009-of-00016.safetensors",
+        "transformer.h.15.mlp.dense_h_to_4h.bias": "model-00009-of-00016.safetensors",
+        "transformer.h.15.mlp.dense_h_to_4h.weight": "model-00009-of-00016.safetensors",
+        "transformer.h.15.post_attention_layernorm.bias": "model-00009-of-00016.safetensors",
+        "transformer.h.15.post_attention_layernorm.weight": "model-00009-of-00016.safetensors",
+        "transformer.h.15.self_attention.dense.bias": "model-00009-of-00016.safetensors",
+        "transformer.h.15.self_attention.dense.weight": "model-00009-of-00016.safetensors",
+        "transformer.h.15.self_attention.query_key_value.bias": "model-00009-of-00016.safetensors",
+        "transformer.h.15.self_attention.query_key_value.weight": "model-00009-of-00016.safetensors",
+        "transformer.h.16.input_layernorm.bias": "model-00009-of-00016.safetensors",
+        "transformer.h.16.input_layernorm.weight": "model-00009-of-00016.safetensors",
+        "transformer.h.16.mlp.dense_4h_to_h.bias": "model-00010-of-00016.safetensors",
+        "transformer.h.16.mlp.dense_4h_to_h.weight": "model-00010-of-00016.safetensors",
+        "transformer.h.16.mlp.dense_h_to_4h.bias": "model-00010-of-00016.safetensors",
+        "transformer.h.16.mlp.dense_h_to_4h.weight": "model-00010-of-00016.safetensors",
+        "transformer.h.16.post_attention_layernorm.bias": "model-00009-of-00016.safetensors",
+        "transformer.h.16.post_attention_layernorm.weight": "model-00009-of-00016.safetensors",
+        "transformer.h.16.self_attention.dense.bias": "model-00009-of-00016.safetensors",
+        "transformer.h.16.self_attention.dense.weight": "model-00009-of-00016.safetensors",
+        "transformer.h.16.self_attention.query_key_value.bias": "model-00009-of-00016.safetensors",
+        "transformer.h.16.self_attention.query_key_value.weight": "model-00009-of-00016.safetensors",
+        "transformer.h.17.input_layernorm.bias": "model-00010-of-00016.safetensors",
+        "transformer.h.17.input_layernorm.weight": "model-00010-of-00016.safetensors",
+        "transformer.h.17.mlp.dense_4h_to_h.bias": "model-00010-of-00016.safetensors",
+        "transformer.h.17.mlp.dense_4h_to_h.weight": "model-00010-of-00016.safetensors",
+        "transformer.h.17.mlp.dense_h_to_4h.bias": "model-00010-of-00016.safetensors",
+        "transformer.h.17.mlp.dense_h_to_4h.weight": "model-00010-of-00016.safetensors",
+        "transformer.h.17.post_attention_layernorm.bias": "model-00010-of-00016.safetensors",
+        "transformer.h.17.post_attention_layernorm.weight": "model-00010-of-00016.safetensors",
+        "transformer.h.17.self_attention.dense.bias": "model-00010-of-00016.safetensors",
+        "transformer.h.17.self_attention.dense.weight": "model-00010-of-00016.safetensors",
+        "transformer.h.17.self_attention.query_key_value.bias": "model-00010-of-00016.safetensors",
+        "transformer.h.17.self_attention.query_key_value.weight": "model-00010-of-00016.safetensors",
+        "transformer.h.18.input_layernorm.bias": "model-00010-of-00016.safetensors",
+        "transformer.h.18.input_layernorm.weight": "model-00010-of-00016.safetensors",
+        "transformer.h.18.mlp.dense_4h_to_h.bias": "model-00011-of-00016.safetensors",
+        "transformer.h.18.mlp.dense_4h_to_h.weight": "model-00011-of-00016.safetensors",
+        "transformer.h.18.mlp.dense_h_to_4h.bias": "model-00010-of-00016.safetensors",
+        "transformer.h.18.mlp.dense_h_to_4h.weight": "model-00010-of-00016.safetensors",
+        "transformer.h.18.post_attention_layernorm.bias": "model-00010-of-00016.safetensors",
+        "transformer.h.18.post_attention_layernorm.weight": "model-00010-of-00016.safetensors",
+        "transformer.h.18.self_attention.dense.bias": "model-00010-of-00016.safetensors",
+        "transformer.h.18.self_attention.dense.weight": "model-00010-of-00016.safetensors",
+        "transformer.h.18.self_attention.query_key_value.bias": "model-00010-of-00016.safetensors",
+        "transformer.h.18.self_attention.query_key_value.weight": "model-00010-of-00016.safetensors",
+        "transformer.h.19.input_layernorm.bias": "model-00011-of-00016.safetensors",
+        "transformer.h.19.input_layernorm.weight": "model-00011-of-00016.safetensors",
+        "transformer.h.19.mlp.dense_4h_to_h.bias": "model-00011-of-00016.safetensors",
+        "transformer.h.19.mlp.dense_4h_to_h.weight": "model-00011-of-00016.safetensors",
+        "transformer.h.19.mlp.dense_h_to_4h.bias": "model-00011-of-00016.safetensors",
+        "transformer.h.19.mlp.dense_h_to_4h.weight": "model-00011-of-00016.safetensors",
+        "transformer.h.19.post_attention_layernorm.bias": "model-00011-of-00016.safetensors",
+        "transformer.h.19.post_attention_layernorm.weight": "model-00011-of-00016.safetensors",
+        "transformer.h.19.self_attention.dense.bias": "model-00011-of-00016.safetensors",
+        "transformer.h.19.self_attention.dense.weight": "model-00011-of-00016.safetensors",
+        "transformer.h.19.self_attention.query_key_value.bias": "model-00011-of-00016.safetensors",
+        "transformer.h.19.self_attention.query_key_value.weight": "model-00011-of-00016.safetensors",
+        "transformer.h.2.input_layernorm.bias": "model-00003-of-00016.safetensors",
+        "transformer.h.2.input_layernorm.weight": "model-00003-of-00016.safetensors",
+        "transformer.h.2.mlp.dense_4h_to_h.bias": "model-00004-of-00016.safetensors",
+        "transformer.h.2.mlp.dense_4h_to_h.weight": "model-00004-of-00016.safetensors",
+        "transformer.h.2.mlp.dense_h_to_4h.bias": "model-00004-of-00016.safetensors",
+        "transformer.h.2.mlp.dense_h_to_4h.weight": "model-00004-of-00016.safetensors",
+        "transformer.h.2.post_attention_layernorm.bias": "model-00003-of-00016.safetensors",
+        "transformer.h.2.post_attention_layernorm.weight": "model-00003-of-00016.safetensors",
+        "transformer.h.2.self_attention.dense.bias": "model-00003-of-00016.safetensors",
+        "transformer.h.2.self_attention.dense.weight": "model-00003-of-00016.safetensors",
+        "transformer.h.2.self_attention.query_key_value.bias": "model-00003-of-00016.safetensors",
+        "transformer.h.2.self_attention.query_key_value.weight": "model-00003-of-00016.safetensors",
+        "transformer.h.20.input_layernorm.bias": "model-00011-of-00016.safetensors",
+        "transformer.h.20.input_layernorm.weight": "model-00011-of-00016.safetensors",
+        "transformer.h.20.mlp.dense_4h_to_h.bias": "model-00011-of-00016.safetensors",
+        "transformer.h.20.mlp.dense_4h_to_h.weight": "model-00011-of-00016.safetensors",
+        "transformer.h.20.mlp.dense_h_to_4h.bias": "model-00011-of-00016.safetensors",
+        "transformer.h.20.mlp.dense_h_to_4h.weight": "model-00011-of-00016.safetensors",
+        "transformer.h.20.post_attention_layernorm.bias": "model-00011-of-00016.safetensors",
+        "transformer.h.20.post_attention_layernorm.weight": "model-00011-of-00016.safetensors",
+        "transformer.h.20.self_attention.dense.bias": "model-00011-of-00016.safetensors",
+        "transformer.h.20.self_attention.dense.weight": "model-00011-of-00016.safetensors",
+        "transformer.h.20.self_attention.query_key_value.bias": "model-00011-of-00016.safetensors",
+        "transformer.h.20.self_attention.query_key_value.weight": "model-00011-of-00016.safetensors",
+        "transformer.h.21.input_layernorm.bias": "model-00011-of-00016.safetensors",
+        "transformer.h.21.input_layernorm.weight": "model-00011-of-00016.safetensors",
+        "transformer.h.21.mlp.dense_4h_to_h.bias": "model-00012-of-00016.safetensors",
+        "transformer.h.21.mlp.dense_4h_to_h.weight": "model-00012-of-00016.safetensors",
+        "transformer.h.21.mlp.dense_h_to_4h.bias": "model-00012-of-00016.safetensors",
+        "transformer.h.21.mlp.dense_h_to_4h.weight": "model-00012-of-00016.safetensors",
+        "transformer.h.21.post_attention_layernorm.bias": "model-00012-of-00016.safetensors",
+        "transformer.h.21.post_attention_layernorm.weight": "model-00012-of-00016.safetensors",
+        "transformer.h.21.self_attention.dense.bias": "model-00012-of-00016.safetensors",
+        "transformer.h.21.self_attention.dense.weight": "model-00012-of-00016.safetensors",
+        "transformer.h.21.self_attention.query_key_value.bias": "model-00012-of-00016.safetensors",
+        "transformer.h.21.self_attention.query_key_value.weight": "model-00012-of-00016.safetensors",
+        "transformer.h.22.input_layernorm.bias": "model-00012-of-00016.safetensors",
+        "transformer.h.22.input_layernorm.weight": "model-00012-of-00016.safetensors",
+        "transformer.h.22.mlp.dense_4h_to_h.bias": "model-00012-of-00016.safetensors",
+        "transformer.h.22.mlp.dense_4h_to_h.weight": "model-00012-of-00016.safetensors",
+        "transformer.h.22.mlp.dense_h_to_4h.bias": "model-00012-of-00016.safetensors",
+        "transformer.h.22.mlp.dense_h_to_4h.weight": "model-00012-of-00016.safetensors",
+        "transformer.h.22.post_attention_layernorm.bias": "model-00012-of-00016.safetensors",
+        "transformer.h.22.post_attention_layernorm.weight": "model-00012-of-00016.safetensors",
+        "transformer.h.22.self_attention.dense.bias": "model-00012-of-00016.safetensors",
+        "transformer.h.22.self_attention.dense.weight": "model-00012-of-00016.safetensors",
+        "transformer.h.22.self_attention.query_key_value.bias": "model-00012-of-00016.safetensors",
+        "transformer.h.22.self_attention.query_key_value.weight": "model-00012-of-00016.safetensors",
+        "transformer.h.23.input_layernorm.bias": "model-00012-of-00016.safetensors",
+        "transformer.h.23.input_layernorm.weight": "model-00012-of-00016.safetensors",
+        "transformer.h.23.mlp.dense_4h_to_h.bias": "model-00013-of-00016.safetensors",
+        "transformer.h.23.mlp.dense_4h_to_h.weight": "model-00013-of-00016.safetensors",
+        "transformer.h.23.mlp.dense_h_to_4h.bias": "model-00013-of-00016.safetensors",
+        "transformer.h.23.mlp.dense_h_to_4h.weight": "model-00013-of-00016.safetensors",
+        "transformer.h.23.post_attention_layernorm.bias": "model-00012-of-00016.safetensors",
+        "transformer.h.23.post_attention_layernorm.weight": "model-00012-of-00016.safetensors",
+        "transformer.h.23.self_attention.dense.bias": "model-00012-of-00016.safetensors",
+        "transformer.h.23.self_attention.dense.weight": "model-00012-of-00016.safetensors",
+        "transformer.h.23.self_attention.query_key_value.bias": "model-00012-of-00016.safetensors",
+        "transformer.h.23.self_attention.query_key_value.weight": "model-00012-of-00016.safetensors",
+        "transformer.h.24.input_layernorm.bias": "model-00013-of-00016.safetensors",
+        "transformer.h.24.input_layernorm.weight": "model-00013-of-00016.safetensors",
+        "transformer.h.24.mlp.dense_4h_to_h.bias": "model-00013-of-00016.safetensors",
+        "transformer.h.24.mlp.dense_4h_to_h.weight": "model-00013-of-00016.safetensors",
+        "transformer.h.24.mlp.dense_h_to_4h.bias": "model-00013-of-00016.safetensors",
+        "transformer.h.24.mlp.dense_h_to_4h.weight": "model-00013-of-00016.safetensors",
+        "transformer.h.24.post_attention_layernorm.bias": "model-00013-of-00016.safetensors",
+        "transformer.h.24.post_attention_layernorm.weight": "model-00013-of-00016.safetensors",
+        "transformer.h.24.self_attention.dense.bias": "model-00013-of-00016.safetensors",
+        "transformer.h.24.self_attention.dense.weight": "model-00013-of-00016.safetensors",
+        "transformer.h.24.self_attention.query_key_value.bias": "model-00013-of-00016.safetensors",
+        "transformer.h.24.self_attention.query_key_value.weight": "model-00013-of-00016.safetensors",
+        "transformer.h.25.input_layernorm.bias": "model-00013-of-00016.safetensors",
+        "transformer.h.25.input_layernorm.weight": "model-00013-of-00016.safetensors",
+        "transformer.h.25.mlp.dense_4h_to_h.bias": "model-00014-of-00016.safetensors",
+        "transformer.h.25.mlp.dense_4h_to_h.weight": "model-00014-of-00016.safetensors",
+        "transformer.h.25.mlp.dense_h_to_4h.bias": "model-00013-of-00016.safetensors",
+        "transformer.h.25.mlp.dense_h_to_4h.weight": "model-00013-of-00016.safetensors",
+        "transformer.h.25.post_attention_layernorm.bias": "model-00013-of-00016.safetensors",
+        "transformer.h.25.post_attention_layernorm.weight": "model-00013-of-00016.safetensors",
+        "transformer.h.25.self_attention.dense.bias": "model-00013-of-00016.safetensors",
+        "transformer.h.25.self_attention.dense.weight": "model-00013-of-00016.safetensors",
+        "transformer.h.25.self_attention.query_key_value.bias": "model-00013-of-00016.safetensors",
+        "transformer.h.25.self_attention.query_key_value.weight": "model-00013-of-00016.safetensors",
+        "transformer.h.26.input_layernorm.bias": "model-00014-of-00016.safetensors",
+        "transformer.h.26.input_layernorm.weight": "model-00014-of-00016.safetensors",
+        "transformer.h.26.mlp.dense_4h_to_h.bias": "model-00014-of-00016.safetensors",
+        "transformer.h.26.mlp.dense_4h_to_h.weight": "model-00014-of-00016.safetensors",
+        "transformer.h.26.mlp.dense_h_to_4h.bias": "model-00014-of-00016.safetensors",
+        "transformer.h.26.mlp.dense_h_to_4h.weight": "model-00014-of-00016.safetensors",
+        "transformer.h.26.post_attention_layernorm.bias": "model-00014-of-00016.safetensors",
+        "transformer.h.26.post_attention_layernorm.weight": "model-00014-of-00016.safetensors",
+        "transformer.h.26.self_attention.dense.bias": "model-00014-of-00016.safetensors",
+        "transformer.h.26.self_attention.dense.weight": "model-00014-of-00016.safetensors",
+        "transformer.h.26.self_attention.query_key_value.bias": "model-00014-of-00016.safetensors",
+        "transformer.h.26.self_attention.query_key_value.weight": "model-00014-of-00016.safetensors",
+        "transformer.h.27.input_layernorm.bias": "model-00014-of-00016.safetensors",
+        "transformer.h.27.input_layernorm.weight": "model-00014-of-00016.safetensors",
+        "transformer.h.27.mlp.dense_4h_to_h.bias": "model-00014-of-00016.safetensors",
+        "transformer.h.27.mlp.dense_4h_to_h.weight": "model-00014-of-00016.safetensors",
+        "transformer.h.27.mlp.dense_h_to_4h.bias": "model-00014-of-00016.safetensors",
+        "transformer.h.27.mlp.dense_h_to_4h.weight": "model-00014-of-00016.safetensors",
+        "transformer.h.27.post_attention_layernorm.bias": "model-00014-of-00016.safetensors",
+        "transformer.h.27.post_attention_layernorm.weight": "model-00014-of-00016.safetensors",
+        "transformer.h.27.self_attention.dense.bias": "model-00014-of-00016.safetensors",
+        "transformer.h.27.self_attention.dense.weight": "model-00014-of-00016.safetensors",
+        "transformer.h.27.self_attention.query_key_value.bias": "model-00014-of-00016.safetensors",
+        "transformer.h.27.self_attention.query_key_value.weight": "model-00014-of-00016.safetensors",
+        "transformer.h.28.input_layernorm.bias": "model-00014-of-00016.safetensors",
+        "transformer.h.28.input_layernorm.weight": "model-00014-of-00016.safetensors",
+        "transformer.h.28.mlp.dense_4h_to_h.bias": "model-00015-of-00016.safetensors",
+        "transformer.h.28.mlp.dense_4h_to_h.weight": "model-00015-of-00016.safetensors",
+        "transformer.h.28.mlp.dense_h_to_4h.bias": "model-00015-of-00016.safetensors",
+        "transformer.h.28.mlp.dense_h_to_4h.weight": "model-00015-of-00016.safetensors",
+        "transformer.h.28.post_attention_layernorm.bias": "model-00015-of-00016.safetensors",
+        "transformer.h.28.post_attention_layernorm.weight": "model-00015-of-00016.safetensors",
+        "transformer.h.28.self_attention.dense.bias": "model-00015-of-00016.safetensors",
+        "transformer.h.28.self_attention.dense.weight": "model-00015-of-00016.safetensors",
+        "transformer.h.28.self_attention.query_key_value.bias": "model-00015-of-00016.safetensors",
+        "transformer.h.28.self_attention.query_key_value.weight": "model-00015-of-00016.safetensors",
+        "transformer.h.29.input_layernorm.bias": "model-00015-of-00016.safetensors",
+        "transformer.h.29.input_layernorm.weight": "model-00015-of-00016.safetensors",
+        "transformer.h.29.mlp.dense_4h_to_h.bias": "model-00015-of-00016.safetensors",
+        "transformer.h.29.mlp.dense_4h_to_h.weight": "model-00015-of-00016.safetensors",
+        "transformer.h.29.mlp.dense_h_to_4h.bias": "model-00015-of-00016.safetensors",
+        "transformer.h.29.mlp.dense_h_to_4h.weight": "model-00015-of-00016.safetensors",
+        "transformer.h.29.post_attention_layernorm.bias": "model-00015-of-00016.safetensors",
+        "transformer.h.29.post_attention_layernorm.weight": "model-00015-of-00016.safetensors",
+        "transformer.h.29.self_attention.dense.bias": "model-00015-of-00016.safetensors",
+        "transformer.h.29.self_attention.dense.weight": "model-00015-of-00016.safetensors",
+        "transformer.h.29.self_attention.query_key_value.bias": "model-00015-of-00016.safetensors",
+        "transformer.h.29.self_attention.query_key_value.weight": "model-00015-of-00016.safetensors",
+        "transformer.h.3.input_layernorm.bias": "model-00004-of-00016.safetensors",
+        "transformer.h.3.input_layernorm.weight": "model-00004-of-00016.safetensors",
+        "transformer.h.3.mlp.dense_4h_to_h.bias": "model-00004-of-00016.safetensors",
+        "transformer.h.3.mlp.dense_4h_to_h.weight": "model-00004-of-00016.safetensors",
+        "transformer.h.3.mlp.dense_h_to_4h.bias": "model-00004-of-00016.safetensors",
+        "transformer.h.3.mlp.dense_h_to_4h.weight": "model-00004-of-00016.safetensors",
+        "transformer.h.3.post_attention_layernorm.bias": "model-00004-of-00016.safetensors",
+        "transformer.h.3.post_attention_layernorm.weight": "model-00004-of-00016.safetensors",
+        "transformer.h.3.self_attention.dense.bias": "model-00004-of-00016.safetensors",
+        "transformer.h.3.self_attention.dense.weight": "model-00004-of-00016.safetensors",
+        "transformer.h.3.self_attention.query_key_value.bias": "model-00004-of-00016.safetensors",
+        "transformer.h.3.self_attention.query_key_value.weight": "model-00004-of-00016.safetensors",
+        "transformer.h.4.input_layernorm.bias": "model-00004-of-00016.safetensors",
+        "transformer.h.4.input_layernorm.weight": "model-00004-of-00016.safetensors",
+        "transformer.h.4.mlp.dense_4h_to_h.bias": "model-00005-of-00016.safetensors",
+        "transformer.h.4.mlp.dense_4h_to_h.weight": "model-00005-of-00016.safetensors",
+        "transformer.h.4.mlp.dense_h_to_4h.bias": "model-00004-of-00016.safetensors",
+        "transformer.h.4.mlp.dense_h_to_4h.weight": "model-00004-of-00016.safetensors",
+        "transformer.h.4.post_attention_layernorm.bias": "model-00004-of-00016.safetensors",
+        "transformer.h.4.post_attention_layernorm.weight": "model-00004-of-00016.safetensors",
+        "transformer.h.4.self_attention.dense.bias": "model-00004-of-00016.safetensors",
+        "transformer.h.4.self_attention.dense.weight": "model-00004-of-00016.safetensors",
+        "transformer.h.4.self_attention.query_key_value.bias": "model-00004-of-00016.safetensors",
+        "transformer.h.4.self_attention.query_key_value.weight": "model-00004-of-00016.safetensors",
+        "transformer.h.5.input_layernorm.bias": "model-00005-of-00016.safetensors",
+        "transformer.h.5.input_layernorm.weight": "model-00005-of-00016.safetensors",
+        "transformer.h.5.mlp.dense_4h_to_h.bias": "model-00005-of-00016.safetensors",
+        "transformer.h.5.mlp.dense_4h_to_h.weight": "model-00005-of-00016.safetensors",
+        "transformer.h.5.mlp.dense_h_to_4h.bias": "model-00005-of-00016.safetensors",
+        "transformer.h.5.mlp.dense_h_to_4h.weight": "model-00005-of-00016.safetensors",
+        "transformer.h.5.post_attention_layernorm.bias": "model-00005-of-00016.safetensors",
+        "transformer.h.5.post_attention_layernorm.weight": "model-00005-of-00016.safetensors",
+        "transformer.h.5.self_attention.dense.bias": "model-00005-of-00016.safetensors",
+        "transformer.h.5.self_attention.dense.weight": "model-00005-of-00016.safetensors",
+        "transformer.h.5.self_attention.query_key_value.bias": "model-00005-of-00016.safetensors",
+        "transformer.h.5.self_attention.query_key_value.weight": "model-00005-of-00016.safetensors",
+        "transformer.h.6.input_layernorm.bias": "model-00005-of-00016.safetensors",
+        "transformer.h.6.input_layernorm.weight": "model-00005-of-00016.safetensors",
+        "transformer.h.6.mlp.dense_4h_to_h.bias": "model-00005-of-00016.safetensors",
+        "transformer.h.6.mlp.dense_4h_to_h.weight": "model-00005-of-00016.safetensors",
+        "transformer.h.6.mlp.dense_h_to_4h.bias": "model-00005-of-00016.safetensors",
+        "transformer.h.6.mlp.dense_h_to_4h.weight": "model-00005-of-00016.safetensors",
+        "transformer.h.6.post_attention_layernorm.bias": "model-00005-of-00016.safetensors",
+        "transformer.h.6.post_attention_layernorm.weight": "model-00005-of-00016.safetensors",
+        "transformer.h.6.self_attention.dense.bias": "model-00005-of-00016.safetensors",
+        "transformer.h.6.self_attention.dense.weight": "model-00005-of-00016.safetensors",
+        "transformer.h.6.self_attention.query_key_value.bias": "model-00005-of-00016.safetensors",
+        "transformer.h.6.self_attention.query_key_value.weight": "model-00005-of-00016.safetensors",
+        "transformer.h.7.input_layernorm.bias": "model-00005-of-00016.safetensors",
+        "transformer.h.7.input_layernorm.weight": "model-00005-of-00016.safetensors",
+        "transformer.h.7.mlp.dense_4h_to_h.bias": "model-00006-of-00016.safetensors",
+        "transformer.h.7.mlp.dense_4h_to_h.weight": "model-00006-of-00016.safetensors",
+        "transformer.h.7.mlp.dense_h_to_4h.bias": "model-00006-of-00016.safetensors",
+        "transformer.h.7.mlp.dense_h_to_4h.weight": "model-00006-of-00016.safetensors",
+        "transformer.h.7.post_attention_layernorm.bias": "model-00006-of-00016.safetensors",
+        "transformer.h.7.post_attention_layernorm.weight": "model-00006-of-00016.safetensors",
+        "transformer.h.7.self_attention.dense.bias": "model-00006-of-00016.safetensors",
+        "transformer.h.7.self_attention.dense.weight": "model-00006-of-00016.safetensors",
+        "transformer.h.7.self_attention.query_key_value.bias": "model-00006-of-00016.safetensors",
+        "transformer.h.7.self_attention.query_key_value.weight": "model-00006-of-00016.safetensors",
+        "transformer.h.8.input_layernorm.bias": "model-00006-of-00016.safetensors",
+        "transformer.h.8.input_layernorm.weight": "model-00006-of-00016.safetensors",
+        "transformer.h.8.mlp.dense_4h_to_h.bias": "model-00006-of-00016.safetensors",
+        "transformer.h.8.mlp.dense_4h_to_h.weight": "model-00006-of-00016.safetensors",
+        "transformer.h.8.mlp.dense_h_to_4h.bias": "model-00006-of-00016.safetensors",
+        "transformer.h.8.mlp.dense_h_to_4h.weight": "model-00006-of-00016.safetensors",
+        "transformer.h.8.post_attention_layernorm.bias": "model-00006-of-00016.safetensors",
+        "transformer.h.8.post_attention_layernorm.weight": "model-00006-of-00016.safetensors",
+        "transformer.h.8.self_attention.dense.bias": "model-00006-of-00016.safetensors",
+        "transformer.h.8.self_attention.dense.weight": "model-00006-of-00016.safetensors",
+        "transformer.h.8.self_attention.query_key_value.bias": "model-00006-of-00016.safetensors",
+        "transformer.h.8.self_attention.query_key_value.weight": "model-00006-of-00016.safetensors",
+        "transformer.h.9.input_layernorm.bias": "model-00006-of-00016.safetensors",
+        "transformer.h.9.input_layernorm.weight": "model-00006-of-00016.safetensors",
+        "transformer.h.9.mlp.dense_4h_to_h.bias": "model-00007-of-00016.safetensors",
+        "transformer.h.9.mlp.dense_4h_to_h.weight": "model-00007-of-00016.safetensors",
+        "transformer.h.9.mlp.dense_h_to_4h.bias": "model-00007-of-00016.safetensors",
+        "transformer.h.9.mlp.dense_h_to_4h.weight": "model-00007-of-00016.safetensors",
+        "transformer.h.9.post_attention_layernorm.bias": "model-00006-of-00016.safetensors",
+        "transformer.h.9.post_attention_layernorm.weight": "model-00006-of-00016.safetensors",
+        "transformer.h.9.self_attention.dense.bias": "model-00006-of-00016.safetensors",
+        "transformer.h.9.self_attention.dense.weight": "model-00006-of-00016.safetensors",
+        "transformer.h.9.self_attention.query_key_value.bias": "model-00006-of-00016.safetensors",
+        "transformer.h.9.self_attention.query_key_value.weight": "model-00006-of-00016.safetensors",
+        "transformer.ln_f.bias": "model-00015-of-00016.safetensors",
+        "transformer.ln_f.weight": "model-00015-of-00016.safetensors",
+        "transformer.word_embeddings.weight": "model-00002-of-00016.safetensors",
+        "transformer.word_embeddings_layernorm.bias": "model-00003-of-00016.safetensors",
+        "transformer.word_embeddings_layernorm.weight": "model-00003-of-00016.safetensors"
+    }
+}