Adding `safetensors` variant of this model

model-00001-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:819cba204085f980a78da346b87cb2dff21190eb485ec6455718a812d31cd0f4
+size 978366064

model-00002-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae35af6209faf608ac6f95213c548057f921680f3d424c61e3c5a85ba23dc0d5
+size 849408096

model-00003-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca205eb6fb442c5d0e6cd0ccc739c0f9e98efe4811fb6c2cd98e5a3f4d297abf
+size 815845208

model-00004-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c80bb9eeb4b95930e4d20ba5e8b86b4e30bd92de1d5084a7de52b8fa9cc2fd53
+size 815845208

model-00005-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da15d1156509118174943302f575b40ef24f69433d982d1bf8878ce2020034e1
+size 815845208

model-00006-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2951c5ed98f0b1a14918bf0d348ffca8190ffbb95b29b750d1b3b012ba755dbe
+size 815845208

model-00007-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c052449b63c0297e7ef1a60e1f280de4926597f17aad17dbecaeed8b729010f
+size 815845224

model-00008-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b429bafd4eb8a60925187cea62af11376d1262476cd7ad6526756265ea1bdd17
+size 815845224

model-00009-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1084793ef3e101a9e69589afffc9c080fa373dc7e05c3dd9bed16d97d50d91ad
+size 815845224

model-00010-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1882c72049989d1a1081a540527dfcad98491ef9f23e6a1d52447c9779039897
+size 815845224

model-00011-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e34aaeeb055938728a213c84d50e428fcb5a8856007d3a900d97a8d9ea9a5198
+size 815845224

model-00012-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a7ef65d05c15de7db062ba8943207acc3ab3559a5fdaaf4a635da5e5e913165
+size 815845224

model-00013-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52c51ad22df1193d04f824c76a123d40a3a41739f8784c0292acb773f7f0114a
+size 815845224

model-00014-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ff4febe88b66a470a2dd195803878ae36965ff3bfcf6bfcad24b9ffb85eaa4b
+size 815845224

model-00015-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29937e1cbfd9ac9e0110e76879439911e25f043a6b2f07f9b164b82323d8ecd0
+size 869278248

model.safetensors.index.json

@@ -0,0 +1,208 @@
+{
+    "metadata": {
+        "total_size": 12487168064
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00015-of-00015.safetensors",
+        "transformer.embedding.word_embeddings.weight": "model-00001-of-00015.safetensors",
+        "transformer.encoder.final_layernorm.weight": "model-00015-of-00015.safetensors",
+        "transformer.encoder.layers.0.input_layernorm.weight": "model-00001-of-00015.safetensors",
+        "transformer.encoder.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00015.safetensors",
+        "transformer.encoder.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00015.safetensors",
+        "transformer.encoder.layers.0.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
+        "transformer.encoder.layers.0.self_attention.dense.weight": "model-00001-of-00015.safetensors",
+        "transformer.encoder.layers.0.self_attention.query_key_value.bias": "model-00001-of-00015.safetensors",
+        "transformer.encoder.layers.0.self_attention.query_key_value.weight": "model-00001-of-00015.safetensors",
+        "transformer.encoder.layers.1.input_layernorm.weight": "model-00001-of-00015.safetensors",
+        "transformer.encoder.layers.1.mlp.dense_4h_to_h.weight": "model-00002-of-00015.safetensors",
+        "transformer.encoder.layers.1.mlp.dense_h_to_4h.weight": "model-00002-of-00015.safetensors",
+        "transformer.encoder.layers.1.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+        "transformer.encoder.layers.1.self_attention.dense.weight": "model-00002-of-00015.safetensors",
+        "transformer.encoder.layers.1.self_attention.query_key_value.bias": "model-00001-of-00015.safetensors",
+        "transformer.encoder.layers.1.self_attention.query_key_value.weight": "model-00001-of-00015.safetensors",
+        "transformer.encoder.layers.10.input_layernorm.weight": "model-00006-of-00015.safetensors",
+        "transformer.encoder.layers.10.mlp.dense_4h_to_h.weight": "model-00006-of-00015.safetensors",
+        "transformer.encoder.layers.10.mlp.dense_h_to_4h.weight": "model-00006-of-00015.safetensors",
+        "transformer.encoder.layers.10.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+        "transformer.encoder.layers.10.self_attention.dense.weight": "model-00006-of-00015.safetensors",
+        "transformer.encoder.layers.10.self_attention.query_key_value.bias": "model-00006-of-00015.safetensors",
+        "transformer.encoder.layers.10.self_attention.query_key_value.weight": "model-00006-of-00015.safetensors",
+        "transformer.encoder.layers.11.input_layernorm.weight": "model-00006-of-00015.safetensors",
+        "transformer.encoder.layers.11.mlp.dense_4h_to_h.weight": "model-00007-of-00015.safetensors",
+        "transformer.encoder.layers.11.mlp.dense_h_to_4h.weight": "model-00007-of-00015.safetensors",
+        "transformer.encoder.layers.11.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+        "transformer.encoder.layers.11.self_attention.dense.weight": "model-00006-of-00015.safetensors",
+        "transformer.encoder.layers.11.self_attention.query_key_value.bias": "model-00006-of-00015.safetensors",
+        "transformer.encoder.layers.11.self_attention.query_key_value.weight": "model-00006-of-00015.safetensors",
+        "transformer.encoder.layers.12.input_layernorm.weight": "model-00007-of-00015.safetensors",
+        "transformer.encoder.layers.12.mlp.dense_4h_to_h.weight": "model-00007-of-00015.safetensors",
+        "transformer.encoder.layers.12.mlp.dense_h_to_4h.weight": "model-00007-of-00015.safetensors",
+        "transformer.encoder.layers.12.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+        "transformer.encoder.layers.12.self_attention.dense.weight": "model-00007-of-00015.safetensors",
+        "transformer.encoder.layers.12.self_attention.query_key_value.bias": "model-00007-of-00015.safetensors",
+        "transformer.encoder.layers.12.self_attention.query_key_value.weight": "model-00007-of-00015.safetensors",
+        "transformer.encoder.layers.13.input_layernorm.weight": "model-00007-of-00015.safetensors",
+        "transformer.encoder.layers.13.mlp.dense_4h_to_h.weight": "model-00008-of-00015.safetensors",
+        "transformer.encoder.layers.13.mlp.dense_h_to_4h.weight": "model-00008-of-00015.safetensors",
+        "transformer.encoder.layers.13.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+        "transformer.encoder.layers.13.self_attention.dense.weight": "model-00007-of-00015.safetensors",
+        "transformer.encoder.layers.13.self_attention.query_key_value.bias": "model-00007-of-00015.safetensors",
+        "transformer.encoder.layers.13.self_attention.query_key_value.weight": "model-00007-of-00015.safetensors",
+        "transformer.encoder.layers.14.input_layernorm.weight": "model-00008-of-00015.safetensors",
+        "transformer.encoder.layers.14.mlp.dense_4h_to_h.weight": "model-00008-of-00015.safetensors",
+        "transformer.encoder.layers.14.mlp.dense_h_to_4h.weight": "model-00008-of-00015.safetensors",
+        "transformer.encoder.layers.14.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+        "transformer.encoder.layers.14.self_attention.dense.weight": "model-00008-of-00015.safetensors",
+        "transformer.encoder.layers.14.self_attention.query_key_value.bias": "model-00008-of-00015.safetensors",
+        "transformer.encoder.layers.14.self_attention.query_key_value.weight": "model-00008-of-00015.safetensors",
+        "transformer.encoder.layers.15.input_layernorm.weight": "model-00008-of-00015.safetensors",
+        "transformer.encoder.layers.15.mlp.dense_4h_to_h.weight": "model-00009-of-00015.safetensors",
+        "transformer.encoder.layers.15.mlp.dense_h_to_4h.weight": "model-00009-of-00015.safetensors",
+        "transformer.encoder.layers.15.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+        "transformer.encoder.layers.15.self_attention.dense.weight": "model-00008-of-00015.safetensors",
+        "transformer.encoder.layers.15.self_attention.query_key_value.bias": "model-00008-of-00015.safetensors",
+        "transformer.encoder.layers.15.self_attention.query_key_value.weight": "model-00008-of-00015.safetensors",
+        "transformer.encoder.layers.16.input_layernorm.weight": "model-00009-of-00015.safetensors",
+        "transformer.encoder.layers.16.mlp.dense_4h_to_h.weight": "model-00009-of-00015.safetensors",
+        "transformer.encoder.layers.16.mlp.dense_h_to_4h.weight": "model-00009-of-00015.safetensors",
+        "transformer.encoder.layers.16.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+        "transformer.encoder.layers.16.self_attention.dense.weight": "model-00009-of-00015.safetensors",
+        "transformer.encoder.layers.16.self_attention.query_key_value.bias": "model-00009-of-00015.safetensors",
+        "transformer.encoder.layers.16.self_attention.query_key_value.weight": "model-00009-of-00015.safetensors",
+        "transformer.encoder.layers.17.input_layernorm.weight": "model-00009-of-00015.safetensors",
+        "transformer.encoder.layers.17.mlp.dense_4h_to_h.weight": "model-00010-of-00015.safetensors",
+        "transformer.encoder.layers.17.mlp.dense_h_to_4h.weight": "model-00010-of-00015.safetensors",
+        "transformer.encoder.layers.17.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+        "transformer.encoder.layers.17.self_attention.dense.weight": "model-00009-of-00015.safetensors",
+        "transformer.encoder.layers.17.self_attention.query_key_value.bias": "model-00009-of-00015.safetensors",
+        "transformer.encoder.layers.17.self_attention.query_key_value.weight": "model-00009-of-00015.safetensors",
+        "transformer.encoder.layers.18.input_layernorm.weight": "model-00010-of-00015.safetensors",
+        "transformer.encoder.layers.18.mlp.dense_4h_to_h.weight": "model-00010-of-00015.safetensors",
+        "transformer.encoder.layers.18.mlp.dense_h_to_4h.weight": "model-00010-of-00015.safetensors",
+        "transformer.encoder.layers.18.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+        "transformer.encoder.layers.18.self_attention.dense.weight": "model-00010-of-00015.safetensors",
+        "transformer.encoder.layers.18.self_attention.query_key_value.bias": "model-00010-of-00015.safetensors",
+        "transformer.encoder.layers.18.self_attention.query_key_value.weight": "model-00010-of-00015.safetensors",
+        "transformer.encoder.layers.19.input_layernorm.weight": "model-00010-of-00015.safetensors",
+        "transformer.encoder.layers.19.mlp.dense_4h_to_h.weight": "model-00011-of-00015.safetensors",
+        "transformer.encoder.layers.19.mlp.dense_h_to_4h.weight": "model-00011-of-00015.safetensors",
+        "transformer.encoder.layers.19.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+        "transformer.encoder.layers.19.self_attention.dense.weight": "model-00010-of-00015.safetensors",
+        "transformer.encoder.layers.19.self_attention.query_key_value.bias": "model-00010-of-00015.safetensors",
+        "transformer.encoder.layers.19.self_attention.query_key_value.weight": "model-00010-of-00015.safetensors",
+        "transformer.encoder.layers.2.input_layernorm.weight": "model-00002-of-00015.safetensors",
+        "transformer.encoder.layers.2.mlp.dense_4h_to_h.weight": "model-00002-of-00015.safetensors",
+        "transformer.encoder.layers.2.mlp.dense_h_to_4h.weight": "model-00002-of-00015.safetensors",
+        "transformer.encoder.layers.2.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+        "transformer.encoder.layers.2.self_attention.dense.weight": "model-00002-of-00015.safetensors",
+        "transformer.encoder.layers.2.self_attention.query_key_value.bias": "model-00002-of-00015.safetensors",
+        "transformer.encoder.layers.2.self_attention.query_key_value.weight": "model-00002-of-00015.safetensors",
+        "transformer.encoder.layers.20.input_layernorm.weight": "model-00011-of-00015.safetensors",
+        "transformer.encoder.layers.20.mlp.dense_4h_to_h.weight": "model-00011-of-00015.safetensors",
+        "transformer.encoder.layers.20.mlp.dense_h_to_4h.weight": "model-00011-of-00015.safetensors",
+        "transformer.encoder.layers.20.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+        "transformer.encoder.layers.20.self_attention.dense.weight": "model-00011-of-00015.safetensors",
+        "transformer.encoder.layers.20.self_attention.query_key_value.bias": "model-00011-of-00015.safetensors",
+        "transformer.encoder.layers.20.self_attention.query_key_value.weight": "model-00011-of-00015.safetensors",
+        "transformer.encoder.layers.21.input_layernorm.weight": "model-00011-of-00015.safetensors",
+        "transformer.encoder.layers.21.mlp.dense_4h_to_h.weight": "model-00012-of-00015.safetensors",
+        "transformer.encoder.layers.21.mlp.dense_h_to_4h.weight": "model-00012-of-00015.safetensors",
+        "transformer.encoder.layers.21.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+        "transformer.encoder.layers.21.self_attention.dense.weight": "model-00011-of-00015.safetensors",
+        "transformer.encoder.layers.21.self_attention.query_key_value.bias": "model-00011-of-00015.safetensors",
+        "transformer.encoder.layers.21.self_attention.query_key_value.weight": "model-00011-of-00015.safetensors",
+        "transformer.encoder.layers.22.input_layernorm.weight": "model-00012-of-00015.safetensors",
+        "transformer.encoder.layers.22.mlp.dense_4h_to_h.weight": "model-00012-of-00015.safetensors",
+        "transformer.encoder.layers.22.mlp.dense_h_to_4h.weight": "model-00012-of-00015.safetensors",
+        "transformer.encoder.layers.22.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+        "transformer.encoder.layers.22.self_attention.dense.weight": "model-00012-of-00015.safetensors",
+        "transformer.encoder.layers.22.self_attention.query_key_value.bias": "model-00012-of-00015.safetensors",
+        "transformer.encoder.layers.22.self_attention.query_key_value.weight": "model-00012-of-00015.safetensors",
+        "transformer.encoder.layers.23.input_layernorm.weight": "model-00012-of-00015.safetensors",
+        "transformer.encoder.layers.23.mlp.dense_4h_to_h.weight": "model-00013-of-00015.safetensors",
+        "transformer.encoder.layers.23.mlp.dense_h_to_4h.weight": "model-00013-of-00015.safetensors",
+        "transformer.encoder.layers.23.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+        "transformer.encoder.layers.23.self_attention.dense.weight": "model-00012-of-00015.safetensors",
+        "transformer.encoder.layers.23.self_attention.query_key_value.bias": "model-00012-of-00015.safetensors",
+        "transformer.encoder.layers.23.self_attention.query_key_value.weight": "model-00012-of-00015.safetensors",
+        "transformer.encoder.layers.24.input_layernorm.weight": "model-00013-of-00015.safetensors",
+        "transformer.encoder.layers.24.mlp.dense_4h_to_h.weight": "model-00013-of-00015.safetensors",
+        "transformer.encoder.layers.24.mlp.dense_h_to_4h.weight": "model-00013-of-00015.safetensors",
+        "transformer.encoder.layers.24.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+        "transformer.encoder.layers.24.self_attention.dense.weight": "model-00013-of-00015.safetensors",
+        "transformer.encoder.layers.24.self_attention.query_key_value.bias": "model-00013-of-00015.safetensors",
+        "transformer.encoder.layers.24.self_attention.query_key_value.weight": "model-00013-of-00015.safetensors",
+        "transformer.encoder.layers.25.input_layernorm.weight": "model-00013-of-00015.safetensors",
+        "transformer.encoder.layers.25.mlp.dense_4h_to_h.weight": "model-00014-of-00015.safetensors",
+        "transformer.encoder.layers.25.mlp.dense_h_to_4h.weight": "model-00014-of-00015.safetensors",
+        "transformer.encoder.layers.25.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+        "transformer.encoder.layers.25.self_attention.dense.weight": "model-00013-of-00015.safetensors",
+        "transformer.encoder.layers.25.self_attention.query_key_value.bias": "model-00013-of-00015.safetensors",
+        "transformer.encoder.layers.25.self_attention.query_key_value.weight": "model-00013-of-00015.safetensors",
+        "transformer.encoder.layers.26.input_layernorm.weight": "model-00014-of-00015.safetensors",
+        "transformer.encoder.layers.26.mlp.dense_4h_to_h.weight": "model-00014-of-00015.safetensors",
+        "transformer.encoder.layers.26.mlp.dense_h_to_4h.weight": "model-00014-of-00015.safetensors",
+        "transformer.encoder.layers.26.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+        "transformer.encoder.layers.26.self_attention.dense.weight": "model-00014-of-00015.safetensors",
+        "transformer.encoder.layers.26.self_attention.query_key_value.bias": "model-00014-of-00015.safetensors",
+        "transformer.encoder.layers.26.self_attention.query_key_value.weight": "model-00014-of-00015.safetensors",
+        "transformer.encoder.layers.27.input_layernorm.weight": "model-00014-of-00015.safetensors",
+        "transformer.encoder.layers.27.mlp.dense_4h_to_h.weight": "model-00015-of-00015.safetensors",
+        "transformer.encoder.layers.27.mlp.dense_h_to_4h.weight": "model-00015-of-00015.safetensors",
+        "transformer.encoder.layers.27.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+        "transformer.encoder.layers.27.self_attention.dense.weight": "model-00014-of-00015.safetensors",
+        "transformer.encoder.layers.27.self_attention.query_key_value.bias": "model-00014-of-00015.safetensors",
+        "transformer.encoder.layers.27.self_attention.query_key_value.weight": "model-00014-of-00015.safetensors",
+        "transformer.encoder.layers.3.input_layernorm.weight": "model-00002-of-00015.safetensors",
+        "transformer.encoder.layers.3.mlp.dense_4h_to_h.weight": "model-00003-of-00015.safetensors",
+        "transformer.encoder.layers.3.mlp.dense_h_to_4h.weight": "model-00003-of-00015.safetensors",
+        "transformer.encoder.layers.3.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+        "transformer.encoder.layers.3.self_attention.dense.weight": "model-00002-of-00015.safetensors",
+        "transformer.encoder.layers.3.self_attention.query_key_value.bias": "model-00002-of-00015.safetensors",
+        "transformer.encoder.layers.3.self_attention.query_key_value.weight": "model-00002-of-00015.safetensors",
+        "transformer.encoder.layers.4.input_layernorm.weight": "model-00003-of-00015.safetensors",
+        "transformer.encoder.layers.4.mlp.dense_4h_to_h.weight": "model-00003-of-00015.safetensors",
+        "transformer.encoder.layers.4.mlp.dense_h_to_4h.weight": "model-00003-of-00015.safetensors",
+        "transformer.encoder.layers.4.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+        "transformer.encoder.layers.4.self_attention.dense.weight": "model-00003-of-00015.safetensors",
+        "transformer.encoder.layers.4.self_attention.query_key_value.bias": "model-00003-of-00015.safetensors",
+        "transformer.encoder.layers.4.self_attention.query_key_value.weight": "model-00003-of-00015.safetensors",
+        "transformer.encoder.layers.5.input_layernorm.weight": "model-00003-of-00015.safetensors",
+        "transformer.encoder.layers.5.mlp.dense_4h_to_h.weight": "model-00004-of-00015.safetensors",
+        "transformer.encoder.layers.5.mlp.dense_h_to_4h.weight": "model-00004-of-00015.safetensors",
+        "transformer.encoder.layers.5.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+        "transformer.encoder.layers.5.self_attention.dense.weight": "model-00003-of-00015.safetensors",
+        "transformer.encoder.layers.5.self_attention.query_key_value.bias": "model-00003-of-00015.safetensors",
+        "transformer.encoder.layers.5.self_attention.query_key_value.weight": "model-00003-of-00015.safetensors",
+        "transformer.encoder.layers.6.input_layernorm.weight": "model-00004-of-00015.safetensors",
+        "transformer.encoder.layers.6.mlp.dense_4h_to_h.weight": "model-00004-of-00015.safetensors",
+        "transformer.encoder.layers.6.mlp.dense_h_to_4h.weight": "model-00004-of-00015.safetensors",
+        "transformer.encoder.layers.6.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+        "transformer.encoder.layers.6.self_attention.dense.weight": "model-00004-of-00015.safetensors",
+        "transformer.encoder.layers.6.self_attention.query_key_value.bias": "model-00004-of-00015.safetensors",
+        "transformer.encoder.layers.6.self_attention.query_key_value.weight": "model-00004-of-00015.safetensors",
+        "transformer.encoder.layers.7.input_layernorm.weight": "model-00004-of-00015.safetensors",
+        "transformer.encoder.layers.7.mlp.dense_4h_to_h.weight": "model-00005-of-00015.safetensors",
+        "transformer.encoder.layers.7.mlp.dense_h_to_4h.weight": "model-00005-of-00015.safetensors",
+        "transformer.encoder.layers.7.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+        "transformer.encoder.layers.7.self_attention.dense.weight": "model-00004-of-00015.safetensors",
+        "transformer.encoder.layers.7.self_attention.query_key_value.bias": "model-00004-of-00015.safetensors",
+        "transformer.encoder.layers.7.self_attention.query_key_value.weight": "model-00004-of-00015.safetensors",
+        "transformer.encoder.layers.8.input_layernorm.weight": "model-00005-of-00015.safetensors",
+        "transformer.encoder.layers.8.mlp.dense_4h_to_h.weight": "model-00005-of-00015.safetensors",
+        "transformer.encoder.layers.8.mlp.dense_h_to_4h.weight": "model-00005-of-00015.safetensors",
+        "transformer.encoder.layers.8.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+        "transformer.encoder.layers.8.self_attention.dense.weight": "model-00005-of-00015.safetensors",
+        "transformer.encoder.layers.8.self_attention.query_key_value.bias": "model-00005-of-00015.safetensors",
+        "transformer.encoder.layers.8.self_attention.query_key_value.weight": "model-00005-of-00015.safetensors",
+        "transformer.encoder.layers.9.input_layernorm.weight": "model-00005-of-00015.safetensors",
+        "transformer.encoder.layers.9.mlp.dense_4h_to_h.weight": "model-00006-of-00015.safetensors",
+        "transformer.encoder.layers.9.mlp.dense_h_to_4h.weight": "model-00006-of-00015.safetensors",
+        "transformer.encoder.layers.9.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+        "transformer.encoder.layers.9.self_attention.dense.weight": "model-00005-of-00015.safetensors",
+        "transformer.encoder.layers.9.self_attention.query_key_value.bias": "model-00005-of-00015.safetensors",
+        "transformer.encoder.layers.9.self_attention.query_key_value.weight": "model-00005-of-00015.safetensors",
+        "transformer.output_layer.weight": "model-00015-of-00015.safetensors",
+        "transformer.rotary_pos_emb.inv_freq": "model-00001-of-00015.safetensors"
+    }
+}