Adding `safetensors` variant of this model

model-00001-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eb5af8c69ed2b84ff0446010134c623118b76fd18b94d8cb52cf6af0015de2f
+size 943801632

model-00002-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ba959ef40a3fb6ab14a8c29d20439a8a76a81815c290d62612d7d87e07816c4
+size 939772880

model-00003-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:525315a49f6fa15942154376af5b774d35bbf5055bc2e1ffaa93ec9a7c5167ce
+size 939764904

model-00004-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb2aaf614837eb02799f1ea60c70008f47fd2619ec1c53782b039d6d5d986b31
+size 939789760

model-00005-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84b2a4998a93bc346c28037224aaf2b0246a4e22c59e6d04edaa13103b68c1a8
+size 939772880

model-00006-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd2bde69443a7e115d3b543150e6b3c3fbe229767af75fefc21ac09c99c429d3
+size 939764912

model-00007-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a9ae2c6df1fcdc0b68ec9eff8ba0348d48db2f4f391db9989b7ebf8ed9271fb
+size 939789784

model-00008-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54acab42d4248eca38934d0d916fb8e7c66bf55a4e7d64c281a2647232dd3907
+size 939772912

model-00009-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd54759cd7569a57f549143d7c4eaba69ac6aba8b22c6ccec2aba4ca1be1a1fc
+size 939764936

model-00010-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8585f3370d060f5480d319369067ccdbdafd77549978424497b3529add510d09
+size 939789784

model-00011-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2b091d3d547c8cd80a1975a072b22842a8d159349ade7892647d049174632c7
+size 939772912

model-00012-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e0b97bc9e5df6c861ae486374a0c239baf6db801e61ab6291d79e115b5591ea
+size 939764936

model-00013-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76198746191afb07fe15b853f646e5d27c91ce0016f3de2ec7c47c2c95fe78c0
+size 939789784

model-00014-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:674848b8c48ac7340d73df8bed1719ebde9d465211799de48632337aaf1e3a51
+size 671254544

model-00015-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0315b93a1580547ad0de67dc2a836d061249bdc84034d96e8942686614bd66f
+size 809500800

model.safetensors.index.json

@@ -0,0 +1,373 @@
+{
+    "metadata": {
+        "total_size": 13701824512
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00015-of-00015.safetensors",
+        "transformer.h.0.input_layernorm.bias": "model-00001-of-00015.safetensors",
+        "transformer.h.0.input_layernorm.weight": "model-00001-of-00015.safetensors",
+        "transformer.h.0.mlp.dense_4h_to_h.bias": "model-00002-of-00015.safetensors",
+        "transformer.h.0.mlp.dense_4h_to_h.weight": "model-00002-of-00015.safetensors",
+        "transformer.h.0.mlp.dense_h_to_4h.bias": "model-00002-of-00015.safetensors",
+        "transformer.h.0.mlp.dense_h_to_4h.weight": "model-00002-of-00015.safetensors",
+        "transformer.h.0.post_attention_layernorm.bias": "model-00001-of-00015.safetensors",
+        "transformer.h.0.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
+        "transformer.h.0.self_attention.dense.bias": "model-00001-of-00015.safetensors",
+        "transformer.h.0.self_attention.dense.weight": "model-00001-of-00015.safetensors",
+        "transformer.h.0.self_attention.query_key_value.bias": "model-00001-of-00015.safetensors",
+        "transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00015.safetensors",
+        "transformer.h.1.input_layernorm.bias": "model-00002-of-00015.safetensors",
+        "transformer.h.1.input_layernorm.weight": "model-00002-of-00015.safetensors",
+        "transformer.h.1.mlp.dense_4h_to_h.bias": "model-00002-of-00015.safetensors",
+        "transformer.h.1.mlp.dense_4h_to_h.weight": "model-00002-of-00015.safetensors",
+        "transformer.h.1.mlp.dense_h_to_4h.bias": "model-00002-of-00015.safetensors",
+        "transformer.h.1.mlp.dense_h_to_4h.weight": "model-00002-of-00015.safetensors",
+        "transformer.h.1.post_attention_layernorm.bias": "model-00002-of-00015.safetensors",
+        "transformer.h.1.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+        "transformer.h.1.self_attention.dense.bias": "model-00002-of-00015.safetensors",
+        "transformer.h.1.self_attention.dense.weight": "model-00002-of-00015.safetensors",
+        "transformer.h.1.self_attention.query_key_value.bias": "model-00002-of-00015.safetensors",
+        "transformer.h.1.self_attention.query_key_value.weight": "model-00002-of-00015.safetensors",
+        "transformer.h.10.input_layernorm.bias": "model-00006-of-00015.safetensors",
+        "transformer.h.10.input_layernorm.weight": "model-00006-of-00015.safetensors",
+        "transformer.h.10.mlp.dense_4h_to_h.bias": "model-00006-of-00015.safetensors",
+        "transformer.h.10.mlp.dense_4h_to_h.weight": "model-00006-of-00015.safetensors",
+        "transformer.h.10.mlp.dense_h_to_4h.bias": "model-00006-of-00015.safetensors",
+        "transformer.h.10.mlp.dense_h_to_4h.weight": "model-00006-of-00015.safetensors",
+        "transformer.h.10.post_attention_layernorm.bias": "model-00006-of-00015.safetensors",
+        "transformer.h.10.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+        "transformer.h.10.self_attention.dense.bias": "model-00006-of-00015.safetensors",
+        "transformer.h.10.self_attention.dense.weight": "model-00006-of-00015.safetensors",
+        "transformer.h.10.self_attention.query_key_value.bias": "model-00006-of-00015.safetensors",
+        "transformer.h.10.self_attention.query_key_value.weight": "model-00006-of-00015.safetensors",
+        "transformer.h.11.input_layernorm.bias": "model-00006-of-00015.safetensors",
+        "transformer.h.11.input_layernorm.weight": "model-00006-of-00015.safetensors",
+        "transformer.h.11.mlp.dense_4h_to_h.bias": "model-00006-of-00015.safetensors",
+        "transformer.h.11.mlp.dense_4h_to_h.weight": "model-00006-of-00015.safetensors",
+        "transformer.h.11.mlp.dense_h_to_4h.bias": "model-00006-of-00015.safetensors",
+        "transformer.h.11.mlp.dense_h_to_4h.weight": "model-00006-of-00015.safetensors",
+        "transformer.h.11.post_attention_layernorm.bias": "model-00006-of-00015.safetensors",
+        "transformer.h.11.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+        "transformer.h.11.self_attention.dense.bias": "model-00006-of-00015.safetensors",
+        "transformer.h.11.self_attention.dense.weight": "model-00006-of-00015.safetensors",
+        "transformer.h.11.self_attention.query_key_value.bias": "model-00006-of-00015.safetensors",
+        "transformer.h.11.self_attention.query_key_value.weight": "model-00006-of-00015.safetensors",
+        "transformer.h.12.input_layernorm.bias": "model-00006-of-00015.safetensors",
+        "transformer.h.12.input_layernorm.weight": "model-00006-of-00015.safetensors",
+        "transformer.h.12.mlp.dense_4h_to_h.bias": "model-00007-of-00015.safetensors",
+        "transformer.h.12.mlp.dense_4h_to_h.weight": "model-00007-of-00015.safetensors",
+        "transformer.h.12.mlp.dense_h_to_4h.bias": "model-00007-of-00015.safetensors",
+        "transformer.h.12.mlp.dense_h_to_4h.weight": "model-00007-of-00015.safetensors",
+        "transformer.h.12.post_attention_layernorm.bias": "model-00007-of-00015.safetensors",
+        "transformer.h.12.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+        "transformer.h.12.self_attention.dense.bias": "model-00007-of-00015.safetensors",
+        "transformer.h.12.self_attention.dense.weight": "model-00007-of-00015.safetensors",
+        "transformer.h.12.self_attention.query_key_value.bias": "model-00007-of-00015.safetensors",
+        "transformer.h.12.self_attention.query_key_value.weight": "model-00007-of-00015.safetensors",
+        "transformer.h.13.input_layernorm.bias": "model-00007-of-00015.safetensors",
+        "transformer.h.13.input_layernorm.weight": "model-00007-of-00015.safetensors",
+        "transformer.h.13.mlp.dense_4h_to_h.bias": "model-00007-of-00015.safetensors",
+        "transformer.h.13.mlp.dense_4h_to_h.weight": "model-00007-of-00015.safetensors",
+        "transformer.h.13.mlp.dense_h_to_4h.bias": "model-00007-of-00015.safetensors",
+        "transformer.h.13.mlp.dense_h_to_4h.weight": "model-00007-of-00015.safetensors",
+        "transformer.h.13.post_attention_layernorm.bias": "model-00007-of-00015.safetensors",
+        "transformer.h.13.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+        "transformer.h.13.self_attention.dense.bias": "model-00007-of-00015.safetensors",
+        "transformer.h.13.self_attention.dense.weight": "model-00007-of-00015.safetensors",
+        "transformer.h.13.self_attention.query_key_value.bias": "model-00007-of-00015.safetensors",
+        "transformer.h.13.self_attention.query_key_value.weight": "model-00007-of-00015.safetensors",
+        "transformer.h.14.input_layernorm.bias": "model-00007-of-00015.safetensors",
+        "transformer.h.14.input_layernorm.weight": "model-00007-of-00015.safetensors",
+        "transformer.h.14.mlp.dense_4h_to_h.bias": "model-00008-of-00015.safetensors",
+        "transformer.h.14.mlp.dense_4h_to_h.weight": "model-00008-of-00015.safetensors",
+        "transformer.h.14.mlp.dense_h_to_4h.bias": "model-00008-of-00015.safetensors",
+        "transformer.h.14.mlp.dense_h_to_4h.weight": "model-00008-of-00015.safetensors",
+        "transformer.h.14.post_attention_layernorm.bias": "model-00007-of-00015.safetensors",
+        "transformer.h.14.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+        "transformer.h.14.self_attention.dense.bias": "model-00007-of-00015.safetensors",
+        "transformer.h.14.self_attention.dense.weight": "model-00007-of-00015.safetensors",
+        "transformer.h.14.self_attention.query_key_value.bias": "model-00007-of-00015.safetensors",
+        "transformer.h.14.self_attention.query_key_value.weight": "model-00007-of-00015.safetensors",
+        "transformer.h.15.input_layernorm.bias": "model-00008-of-00015.safetensors",
+        "transformer.h.15.input_layernorm.weight": "model-00008-of-00015.safetensors",
+        "transformer.h.15.mlp.dense_4h_to_h.bias": "model-00008-of-00015.safetensors",
+        "transformer.h.15.mlp.dense_4h_to_h.weight": "model-00008-of-00015.safetensors",
+        "transformer.h.15.mlp.dense_h_to_4h.bias": "model-00008-of-00015.safetensors",
+        "transformer.h.15.mlp.dense_h_to_4h.weight": "model-00008-of-00015.safetensors",
+        "transformer.h.15.post_attention_layernorm.bias": "model-00008-of-00015.safetensors",
+        "transformer.h.15.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+        "transformer.h.15.self_attention.dense.bias": "model-00008-of-00015.safetensors",
+        "transformer.h.15.self_attention.dense.weight": "model-00008-of-00015.safetensors",
+        "transformer.h.15.self_attention.query_key_value.bias": "model-00008-of-00015.safetensors",
+        "transformer.h.15.self_attention.query_key_value.weight": "model-00008-of-00015.safetensors",
+        "transformer.h.16.input_layernorm.bias": "model-00008-of-00015.safetensors",
+        "transformer.h.16.input_layernorm.weight": "model-00008-of-00015.safetensors",
+        "transformer.h.16.mlp.dense_4h_to_h.bias": "model-00009-of-00015.safetensors",
+        "transformer.h.16.mlp.dense_4h_to_h.weight": "model-00009-of-00015.safetensors",
+        "transformer.h.16.mlp.dense_h_to_4h.bias": "model-00008-of-00015.safetensors",
+        "transformer.h.16.mlp.dense_h_to_4h.weight": "model-00008-of-00015.safetensors",
+        "transformer.h.16.post_attention_layernorm.bias": "model-00008-of-00015.safetensors",
+        "transformer.h.16.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+        "transformer.h.16.self_attention.dense.bias": "model-00008-of-00015.safetensors",
+        "transformer.h.16.self_attention.dense.weight": "model-00008-of-00015.safetensors",
+        "transformer.h.16.self_attention.query_key_value.bias": "model-00008-of-00015.safetensors",
+        "transformer.h.16.self_attention.query_key_value.weight": "model-00008-of-00015.safetensors",
+        "transformer.h.17.input_layernorm.bias": "model-00009-of-00015.safetensors",
+        "transformer.h.17.input_layernorm.weight": "model-00009-of-00015.safetensors",
+        "transformer.h.17.mlp.dense_4h_to_h.bias": "model-00009-of-00015.safetensors",
+        "transformer.h.17.mlp.dense_4h_to_h.weight": "model-00009-of-00015.safetensors",
+        "transformer.h.17.mlp.dense_h_to_4h.bias": "model-00009-of-00015.safetensors",
+        "transformer.h.17.mlp.dense_h_to_4h.weight": "model-00009-of-00015.safetensors",
+        "transformer.h.17.post_attention_layernorm.bias": "model-00009-of-00015.safetensors",
+        "transformer.h.17.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+        "transformer.h.17.self_attention.dense.bias": "model-00009-of-00015.safetensors",
+        "transformer.h.17.self_attention.dense.weight": "model-00009-of-00015.safetensors",
+        "transformer.h.17.self_attention.query_key_value.bias": "model-00009-of-00015.safetensors",
+        "transformer.h.17.self_attention.query_key_value.weight": "model-00009-of-00015.safetensors",
+        "transformer.h.18.input_layernorm.bias": "model-00009-of-00015.safetensors",
+        "transformer.h.18.input_layernorm.weight": "model-00009-of-00015.safetensors",
+        "transformer.h.18.mlp.dense_4h_to_h.bias": "model-00009-of-00015.safetensors",
+        "transformer.h.18.mlp.dense_4h_to_h.weight": "model-00009-of-00015.safetensors",
+        "transformer.h.18.mlp.dense_h_to_4h.bias": "model-00009-of-00015.safetensors",
+        "transformer.h.18.mlp.dense_h_to_4h.weight": "model-00009-of-00015.safetensors",
+        "transformer.h.18.post_attention_layernorm.bias": "model-00009-of-00015.safetensors",
+        "transformer.h.18.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+        "transformer.h.18.self_attention.dense.bias": "model-00009-of-00015.safetensors",
+        "transformer.h.18.self_attention.dense.weight": "model-00009-of-00015.safetensors",
+        "transformer.h.18.self_attention.query_key_value.bias": "model-00009-of-00015.safetensors",
+        "transformer.h.18.self_attention.query_key_value.weight": "model-00009-of-00015.safetensors",
+        "transformer.h.19.input_layernorm.bias": "model-00009-of-00015.safetensors",
+        "transformer.h.19.input_layernorm.weight": "model-00009-of-00015.safetensors",
+        "transformer.h.19.mlp.dense_4h_to_h.bias": "model-00010-of-00015.safetensors",
+        "transformer.h.19.mlp.dense_4h_to_h.weight": "model-00010-of-00015.safetensors",
+        "transformer.h.19.mlp.dense_h_to_4h.bias": "model-00010-of-00015.safetensors",
+        "transformer.h.19.mlp.dense_h_to_4h.weight": "model-00010-of-00015.safetensors",
+        "transformer.h.19.post_attention_layernorm.bias": "model-00010-of-00015.safetensors",
+        "transformer.h.19.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+        "transformer.h.19.self_attention.dense.bias": "model-00010-of-00015.safetensors",
+        "transformer.h.19.self_attention.dense.weight": "model-00010-of-00015.safetensors",
+        "transformer.h.19.self_attention.query_key_value.bias": "model-00010-of-00015.safetensors",
+        "transformer.h.19.self_attention.query_key_value.weight": "model-00010-of-00015.safetensors",
+        "transformer.h.2.input_layernorm.bias": "model-00002-of-00015.safetensors",
+        "transformer.h.2.input_layernorm.weight": "model-00002-of-00015.safetensors",
+        "transformer.h.2.mlp.dense_4h_to_h.bias": "model-00003-of-00015.safetensors",
+        "transformer.h.2.mlp.dense_4h_to_h.weight": "model-00003-of-00015.safetensors",
+        "transformer.h.2.mlp.dense_h_to_4h.bias": "model-00002-of-00015.safetensors",
+        "transformer.h.2.mlp.dense_h_to_4h.weight": "model-00002-of-00015.safetensors",
+        "transformer.h.2.post_attention_layernorm.bias": "model-00002-of-00015.safetensors",
+        "transformer.h.2.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+        "transformer.h.2.self_attention.dense.bias": "model-00002-of-00015.safetensors",
+        "transformer.h.2.self_attention.dense.weight": "model-00002-of-00015.safetensors",
+        "transformer.h.2.self_attention.query_key_value.bias": "model-00002-of-00015.safetensors",
+        "transformer.h.2.self_attention.query_key_value.weight": "model-00002-of-00015.safetensors",
+        "transformer.h.20.input_layernorm.bias": "model-00010-of-00015.safetensors",
+        "transformer.h.20.input_layernorm.weight": "model-00010-of-00015.safetensors",
+        "transformer.h.20.mlp.dense_4h_to_h.bias": "model-00010-of-00015.safetensors",
+        "transformer.h.20.mlp.dense_4h_to_h.weight": "model-00010-of-00015.safetensors",
+        "transformer.h.20.mlp.dense_h_to_4h.bias": "model-00010-of-00015.safetensors",
+        "transformer.h.20.mlp.dense_h_to_4h.weight": "model-00010-of-00015.safetensors",
+        "transformer.h.20.post_attention_layernorm.bias": "model-00010-of-00015.safetensors",
+        "transformer.h.20.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+        "transformer.h.20.self_attention.dense.bias": "model-00010-of-00015.safetensors",
+        "transformer.h.20.self_attention.dense.weight": "model-00010-of-00015.safetensors",
+        "transformer.h.20.self_attention.query_key_value.bias": "model-00010-of-00015.safetensors",
+        "transformer.h.20.self_attention.query_key_value.weight": "model-00010-of-00015.safetensors",
+        "transformer.h.21.input_layernorm.bias": "model-00010-of-00015.safetensors",
+        "transformer.h.21.input_layernorm.weight": "model-00010-of-00015.safetensors",
+        "transformer.h.21.mlp.dense_4h_to_h.bias": "model-00011-of-00015.safetensors",
+        "transformer.h.21.mlp.dense_4h_to_h.weight": "model-00011-of-00015.safetensors",
+        "transformer.h.21.mlp.dense_h_to_4h.bias": "model-00011-of-00015.safetensors",
+        "transformer.h.21.mlp.dense_h_to_4h.weight": "model-00011-of-00015.safetensors",
+        "transformer.h.21.post_attention_layernorm.bias": "model-00010-of-00015.safetensors",
+        "transformer.h.21.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+        "transformer.h.21.self_attention.dense.bias": "model-00010-of-00015.safetensors",
+        "transformer.h.21.self_attention.dense.weight": "model-00010-of-00015.safetensors",
+        "transformer.h.21.self_attention.query_key_value.bias": "model-00010-of-00015.safetensors",
+        "transformer.h.21.self_attention.query_key_value.weight": "model-00010-of-00015.safetensors",
+        "transformer.h.22.input_layernorm.bias": "model-00011-of-00015.safetensors",
+        "transformer.h.22.input_layernorm.weight": "model-00011-of-00015.safetensors",
+        "transformer.h.22.mlp.dense_4h_to_h.bias": "model-00011-of-00015.safetensors",
+        "transformer.h.22.mlp.dense_4h_to_h.weight": "model-00011-of-00015.safetensors",
+        "transformer.h.22.mlp.dense_h_to_4h.bias": "model-00011-of-00015.safetensors",
+        "transformer.h.22.mlp.dense_h_to_4h.weight": "model-00011-of-00015.safetensors",
+        "transformer.h.22.post_attention_layernorm.bias": "model-00011-of-00015.safetensors",
+        "transformer.h.22.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+        "transformer.h.22.self_attention.dense.bias": "model-00011-of-00015.safetensors",
+        "transformer.h.22.self_attention.dense.weight": "model-00011-of-00015.safetensors",
+        "transformer.h.22.self_attention.query_key_value.bias": "model-00011-of-00015.safetensors",
+        "transformer.h.22.self_attention.query_key_value.weight": "model-00011-of-00015.safetensors",
+        "transformer.h.23.input_layernorm.bias": "model-00011-of-00015.safetensors",
+        "transformer.h.23.input_layernorm.weight": "model-00011-of-00015.safetensors",
+        "transformer.h.23.mlp.dense_4h_to_h.bias": "model-00012-of-00015.safetensors",
+        "transformer.h.23.mlp.dense_4h_to_h.weight": "model-00012-of-00015.safetensors",
+        "transformer.h.23.mlp.dense_h_to_4h.bias": "model-00011-of-00015.safetensors",
+        "transformer.h.23.mlp.dense_h_to_4h.weight": "model-00011-of-00015.safetensors",
+        "transformer.h.23.post_attention_layernorm.bias": "model-00011-of-00015.safetensors",
+        "transformer.h.23.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+        "transformer.h.23.self_attention.dense.bias": "model-00011-of-00015.safetensors",
+        "transformer.h.23.self_attention.dense.weight": "model-00011-of-00015.safetensors",
+        "transformer.h.23.self_attention.query_key_value.bias": "model-00011-of-00015.safetensors",
+        "transformer.h.23.self_attention.query_key_value.weight": "model-00011-of-00015.safetensors",
+        "transformer.h.24.input_layernorm.bias": "model-00012-of-00015.safetensors",
+        "transformer.h.24.input_layernorm.weight": "model-00012-of-00015.safetensors",
+        "transformer.h.24.mlp.dense_4h_to_h.bias": "model-00012-of-00015.safetensors",
+        "transformer.h.24.mlp.dense_4h_to_h.weight": "model-00012-of-00015.safetensors",
+        "transformer.h.24.mlp.dense_h_to_4h.bias": "model-00012-of-00015.safetensors",
+        "transformer.h.24.mlp.dense_h_to_4h.weight": "model-00012-of-00015.safetensors",
+        "transformer.h.24.post_attention_layernorm.bias": "model-00012-of-00015.safetensors",
+        "transformer.h.24.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+        "transformer.h.24.self_attention.dense.bias": "model-00012-of-00015.safetensors",
+        "transformer.h.24.self_attention.dense.weight": "model-00012-of-00015.safetensors",
+        "transformer.h.24.self_attention.query_key_value.bias": "model-00012-of-00015.safetensors",
+        "transformer.h.24.self_attention.query_key_value.weight": "model-00012-of-00015.safetensors",
+        "transformer.h.25.input_layernorm.bias": "model-00012-of-00015.safetensors",
+        "transformer.h.25.input_layernorm.weight": "model-00012-of-00015.safetensors",
+        "transformer.h.25.mlp.dense_4h_to_h.bias": "model-00012-of-00015.safetensors",
+        "transformer.h.25.mlp.dense_4h_to_h.weight": "model-00012-of-00015.safetensors",
+        "transformer.h.25.mlp.dense_h_to_4h.bias": "model-00012-of-00015.safetensors",
+        "transformer.h.25.mlp.dense_h_to_4h.weight": "model-00012-of-00015.safetensors",
+        "transformer.h.25.post_attention_layernorm.bias": "model-00012-of-00015.safetensors",
+        "transformer.h.25.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+        "transformer.h.25.self_attention.dense.bias": "model-00012-of-00015.safetensors",
+        "transformer.h.25.self_attention.dense.weight": "model-00012-of-00015.safetensors",
+        "transformer.h.25.self_attention.query_key_value.bias": "model-00012-of-00015.safetensors",
+        "transformer.h.25.self_attention.query_key_value.weight": "model-00012-of-00015.safetensors",
+        "transformer.h.26.input_layernorm.bias": "model-00012-of-00015.safetensors",
+        "transformer.h.26.input_layernorm.weight": "model-00012-of-00015.safetensors",
+        "transformer.h.26.mlp.dense_4h_to_h.bias": "model-00013-of-00015.safetensors",
+        "transformer.h.26.mlp.dense_4h_to_h.weight": "model-00013-of-00015.safetensors",
+        "transformer.h.26.mlp.dense_h_to_4h.bias": "model-00013-of-00015.safetensors",
+        "transformer.h.26.mlp.dense_h_to_4h.weight": "model-00013-of-00015.safetensors",
+        "transformer.h.26.post_attention_layernorm.bias": "model-00013-of-00015.safetensors",
+        "transformer.h.26.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+        "transformer.h.26.self_attention.dense.bias": "model-00013-of-00015.safetensors",
+        "transformer.h.26.self_attention.dense.weight": "model-00013-of-00015.safetensors",
+        "transformer.h.26.self_attention.query_key_value.bias": "model-00013-of-00015.safetensors",
+        "transformer.h.26.self_attention.query_key_value.weight": "model-00013-of-00015.safetensors",
+        "transformer.h.27.input_layernorm.bias": "model-00013-of-00015.safetensors",
+        "transformer.h.27.input_layernorm.weight": "model-00013-of-00015.safetensors",
+        "transformer.h.27.mlp.dense_4h_to_h.bias": "model-00013-of-00015.safetensors",
+        "transformer.h.27.mlp.dense_4h_to_h.weight": "model-00013-of-00015.safetensors",
+        "transformer.h.27.mlp.dense_h_to_4h.bias": "model-00013-of-00015.safetensors",
+        "transformer.h.27.mlp.dense_h_to_4h.weight": "model-00013-of-00015.safetensors",
+        "transformer.h.27.post_attention_layernorm.bias": "model-00013-of-00015.safetensors",
+        "transformer.h.27.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+        "transformer.h.27.self_attention.dense.bias": "model-00013-of-00015.safetensors",
+        "transformer.h.27.self_attention.dense.weight": "model-00013-of-00015.safetensors",
+        "transformer.h.27.self_attention.query_key_value.bias": "model-00013-of-00015.safetensors",
+        "transformer.h.27.self_attention.query_key_value.weight": "model-00013-of-00015.safetensors",
+        "transformer.h.28.input_layernorm.bias": "model-00013-of-00015.safetensors",
+        "transformer.h.28.input_layernorm.weight": "model-00013-of-00015.safetensors",
+        "transformer.h.28.mlp.dense_4h_to_h.bias": "model-00014-of-00015.safetensors",
+        "transformer.h.28.mlp.dense_4h_to_h.weight": "model-00014-of-00015.safetensors",
+        "transformer.h.28.mlp.dense_h_to_4h.bias": "model-00014-of-00015.safetensors",
+        "transformer.h.28.mlp.dense_h_to_4h.weight": "model-00014-of-00015.safetensors",
+        "transformer.h.28.post_attention_layernorm.bias": "model-00013-of-00015.safetensors",
+        "transformer.h.28.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+        "transformer.h.28.self_attention.dense.bias": "model-00013-of-00015.safetensors",
+        "transformer.h.28.self_attention.dense.weight": "model-00013-of-00015.safetensors",
+        "transformer.h.28.self_attention.query_key_value.bias": "model-00013-of-00015.safetensors",
+        "transformer.h.28.self_attention.query_key_value.weight": "model-00013-of-00015.safetensors",
+        "transformer.h.29.input_layernorm.bias": "model-00014-of-00015.safetensors",
+        "transformer.h.29.input_layernorm.weight": "model-00014-of-00015.safetensors",
+        "transformer.h.29.mlp.dense_4h_to_h.bias": "model-00014-of-00015.safetensors",
+        "transformer.h.29.mlp.dense_4h_to_h.weight": "model-00014-of-00015.safetensors",
+        "transformer.h.29.mlp.dense_h_to_4h.bias": "model-00014-of-00015.safetensors",
+        "transformer.h.29.mlp.dense_h_to_4h.weight": "model-00014-of-00015.safetensors",
+        "transformer.h.29.post_attention_layernorm.bias": "model-00014-of-00015.safetensors",
+        "transformer.h.29.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+        "transformer.h.29.self_attention.dense.bias": "model-00014-of-00015.safetensors",
+        "transformer.h.29.self_attention.dense.weight": "model-00014-of-00015.safetensors",
+        "transformer.h.29.self_attention.query_key_value.bias": "model-00014-of-00015.safetensors",
+        "transformer.h.29.self_attention.query_key_value.weight": "model-00014-of-00015.safetensors",
+        "transformer.h.3.input_layernorm.bias": "model-00003-of-00015.safetensors",
+        "transformer.h.3.input_layernorm.weight": "model-00003-of-00015.safetensors",
+        "transformer.h.3.mlp.dense_4h_to_h.bias": "model-00003-of-00015.safetensors",
+        "transformer.h.3.mlp.dense_4h_to_h.weight": "model-00003-of-00015.safetensors",
+        "transformer.h.3.mlp.dense_h_to_4h.bias": "model-00003-of-00015.safetensors",
+        "transformer.h.3.mlp.dense_h_to_4h.weight": "model-00003-of-00015.safetensors",
+        "transformer.h.3.post_attention_layernorm.bias": "model-00003-of-00015.safetensors",
+        "transformer.h.3.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+        "transformer.h.3.self_attention.dense.bias": "model-00003-of-00015.safetensors",
+        "transformer.h.3.self_attention.dense.weight": "model-00003-of-00015.safetensors",
+        "transformer.h.3.self_attention.query_key_value.bias": "model-00003-of-00015.safetensors",
+        "transformer.h.3.self_attention.query_key_value.weight": "model-00003-of-00015.safetensors",
+        "transformer.h.4.input_layernorm.bias": "model-00003-of-00015.safetensors",
+        "transformer.h.4.input_layernorm.weight": "model-00003-of-00015.safetensors",
+        "transformer.h.4.mlp.dense_4h_to_h.bias": "model-00003-of-00015.safetensors",
+        "transformer.h.4.mlp.dense_4h_to_h.weight": "model-00003-of-00015.safetensors",
+        "transformer.h.4.mlp.dense_h_to_4h.bias": "model-00003-of-00015.safetensors",
+        "transformer.h.4.mlp.dense_h_to_4h.weight": "model-00003-of-00015.safetensors",
+        "transformer.h.4.post_attention_layernorm.bias": "model-00003-of-00015.safetensors",
+        "transformer.h.4.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+        "transformer.h.4.self_attention.dense.bias": "model-00003-of-00015.safetensors",
+        "transformer.h.4.self_attention.dense.weight": "model-00003-of-00015.safetensors",
+        "transformer.h.4.self_attention.query_key_value.bias": "model-00003-of-00015.safetensors",
+        "transformer.h.4.self_attention.query_key_value.weight": "model-00003-of-00015.safetensors",
+        "transformer.h.5.input_layernorm.bias": "model-00003-of-00015.safetensors",
+        "transformer.h.5.input_layernorm.weight": "model-00003-of-00015.safetensors",
+        "transformer.h.5.mlp.dense_4h_to_h.bias": "model-00004-of-00015.safetensors",
+        "transformer.h.5.mlp.dense_4h_to_h.weight": "model-00004-of-00015.safetensors",
+        "transformer.h.5.mlp.dense_h_to_4h.bias": "model-00004-of-00015.safetensors",
+        "transformer.h.5.mlp.dense_h_to_4h.weight": "model-00004-of-00015.safetensors",
+        "transformer.h.5.post_attention_layernorm.bias": "model-00004-of-00015.safetensors",
+        "transformer.h.5.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+        "transformer.h.5.self_attention.dense.bias": "model-00004-of-00015.safetensors",
+        "transformer.h.5.self_attention.dense.weight": "model-00004-of-00015.safetensors",
+        "transformer.h.5.self_attention.query_key_value.bias": "model-00004-of-00015.safetensors",
+        "transformer.h.5.self_attention.query_key_value.weight": "model-00004-of-00015.safetensors",
+        "transformer.h.6.input_layernorm.bias": "model-00004-of-00015.safetensors",
+        "transformer.h.6.input_layernorm.weight": "model-00004-of-00015.safetensors",
+        "transformer.h.6.mlp.dense_4h_to_h.bias": "model-00004-of-00015.safetensors",
+        "transformer.h.6.mlp.dense_4h_to_h.weight": "model-00004-of-00015.safetensors",
+        "transformer.h.6.mlp.dense_h_to_4h.bias": "model-00004-of-00015.safetensors",
+        "transformer.h.6.mlp.dense_h_to_4h.weight": "model-00004-of-00015.safetensors",
+        "transformer.h.6.post_attention_layernorm.bias": "model-00004-of-00015.safetensors",
+        "transformer.h.6.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+        "transformer.h.6.self_attention.dense.bias": "model-00004-of-00015.safetensors",
+        "transformer.h.6.self_attention.dense.weight": "model-00004-of-00015.safetensors",
+        "transformer.h.6.self_attention.query_key_value.bias": "model-00004-of-00015.safetensors",
+        "transformer.h.6.self_attention.query_key_value.weight": "model-00004-of-00015.safetensors",
+        "transformer.h.7.input_layernorm.bias": "model-00004-of-00015.safetensors",
+        "transformer.h.7.input_layernorm.weight": "model-00004-of-00015.safetensors",
+        "transformer.h.7.mlp.dense_4h_to_h.bias": "model-00005-of-00015.safetensors",
+        "transformer.h.7.mlp.dense_4h_to_h.weight": "model-00005-of-00015.safetensors",
+        "transformer.h.7.mlp.dense_h_to_4h.bias": "model-00005-of-00015.safetensors",
+        "transformer.h.7.mlp.dense_h_to_4h.weight": "model-00005-of-00015.safetensors",
+        "transformer.h.7.post_attention_layernorm.bias": "model-00004-of-00015.safetensors",
+        "transformer.h.7.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+        "transformer.h.7.self_attention.dense.bias": "model-00004-of-00015.safetensors",
+        "transformer.h.7.self_attention.dense.weight": "model-00004-of-00015.safetensors",
+        "transformer.h.7.self_attention.query_key_value.bias": "model-00004-of-00015.safetensors",
+        "transformer.h.7.self_attention.query_key_value.weight": "model-00004-of-00015.safetensors",
+        "transformer.h.8.input_layernorm.bias": "model-00005-of-00015.safetensors",
+        "transformer.h.8.input_layernorm.weight": "model-00005-of-00015.safetensors",
+        "transformer.h.8.mlp.dense_4h_to_h.bias": "model-00005-of-00015.safetensors",
+        "transformer.h.8.mlp.dense_4h_to_h.weight": "model-00005-of-00015.safetensors",
+        "transformer.h.8.mlp.dense_h_to_4h.bias": "model-00005-of-00015.safetensors",
+        "transformer.h.8.mlp.dense_h_to_4h.weight": "model-00005-of-00015.safetensors",
+        "transformer.h.8.post_attention_layernorm.bias": "model-00005-of-00015.safetensors",
+        "transformer.h.8.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+        "transformer.h.8.self_attention.dense.bias": "model-00005-of-00015.safetensors",
+        "transformer.h.8.self_attention.dense.weight": "model-00005-of-00015.safetensors",
+        "transformer.h.8.self_attention.query_key_value.bias": "model-00005-of-00015.safetensors",
+        "transformer.h.8.self_attention.query_key_value.weight": "model-00005-of-00015.safetensors",
+        "transformer.h.9.input_layernorm.bias": "model-00005-of-00015.safetensors",
+        "transformer.h.9.input_layernorm.weight": "model-00005-of-00015.safetensors",
+        "transformer.h.9.mlp.dense_4h_to_h.bias": "model-00006-of-00015.safetensors",
+        "transformer.h.9.mlp.dense_4h_to_h.weight": "model-00006-of-00015.safetensors",
+        "transformer.h.9.mlp.dense_h_to_4h.bias": "model-00005-of-00015.safetensors",
+        "transformer.h.9.mlp.dense_h_to_4h.weight": "model-00005-of-00015.safetensors",
+        "transformer.h.9.post_attention_layernorm.bias": "model-00005-of-00015.safetensors",
+        "transformer.h.9.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+        "transformer.h.9.self_attention.dense.bias": "model-00005-of-00015.safetensors",
+        "transformer.h.9.self_attention.dense.weight": "model-00005-of-00015.safetensors",
+        "transformer.h.9.self_attention.query_key_value.bias": "model-00005-of-00015.safetensors",
+        "transformer.h.9.self_attention.query_key_value.weight": "model-00005-of-00015.safetensors",
+        "transformer.ln_f.bias": "model-00014-of-00015.safetensors",
+        "transformer.ln_f.weight": "model-00014-of-00015.safetensors",
+        "transformer.word_embeddings.weight": "model-00001-of-00015.safetensors",
+        "transformer.word_embeddings_layernorm.bias": "model-00001-of-00015.safetensors",
+        "transformer.word_embeddings_layernorm.weight": "model-00001-of-00015.safetensors"
+    }
+}