Adding `safetensors` variant of this model

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ed118981e5da3e4541b2d0b979311124240ceb058f3131bf8bfc8162be4c095
+size 2053587144

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6971307076623c75423f8a5b2f829b399c745ab2cd04132c3cd586d3c58afda
+size 1879595928

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:239b73b2328b44200f26e961458fb6459757b180e49dcf4c3428bee6ecda888c
+size 1879554752

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a46be300b248cfd0eba7b2d243bd55dd89fe25e95068cd8f471d0ae072c483b9
+size 1980226032

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e36f079ca82537f29d264a8bd799297866727196940a682a36f885292a3ac9c6
+size 1913117408

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24d1c1e5af0528c7b5a0af18b299ec28f812e0038ffd9f73c6381797f5d7b5c3
+size 1879562784

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8438c4d7e637ac2b150dc4d4efc947a203617dfbf551dcb13b7c0e0bbd464cb
+size 1879554808

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccea4059092878ff612c3ffb41923e76fcbfcdef60354f64c1c19e24e4e13dff
+size 671254568

model.safetensors.index.json

@@ -0,0 +1,373 @@
+{
+    "metadata": {
+        "total_size": 14136410112
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00002-of-00009.safetensors",
+        "transformer.h.0.input_layernorm.bias": "model-00003-of-00009.safetensors",
+        "transformer.h.0.input_layernorm.weight": "model-00003-of-00009.safetensors",
+        "transformer.h.0.mlp.dense_4h_to_h.bias": "model-00003-of-00009.safetensors",
+        "transformer.h.0.mlp.dense_4h_to_h.weight": "model-00003-of-00009.safetensors",
+        "transformer.h.0.mlp.dense_h_to_4h.bias": "model-00003-of-00009.safetensors",
+        "transformer.h.0.mlp.dense_h_to_4h.weight": "model-00003-of-00009.safetensors",
+        "transformer.h.0.post_attention_layernorm.bias": "model-00003-of-00009.safetensors",
+        "transformer.h.0.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+        "transformer.h.0.self_attention.dense.bias": "model-00003-of-00009.safetensors",
+        "transformer.h.0.self_attention.dense.weight": "model-00003-of-00009.safetensors",
+        "transformer.h.0.self_attention.query_key_value.bias": "model-00003-of-00009.safetensors",
+        "transformer.h.0.self_attention.query_key_value.weight": "model-00003-of-00009.safetensors",
+        "transformer.h.1.input_layernorm.bias": "model-00003-of-00009.safetensors",
+        "transformer.h.1.input_layernorm.weight": "model-00003-of-00009.safetensors",
+        "transformer.h.1.mlp.dense_4h_to_h.bias": "model-00003-of-00009.safetensors",
+        "transformer.h.1.mlp.dense_4h_to_h.weight": "model-00003-of-00009.safetensors",
+        "transformer.h.1.mlp.dense_h_to_4h.bias": "model-00003-of-00009.safetensors",
+        "transformer.h.1.mlp.dense_h_to_4h.weight": "model-00003-of-00009.safetensors",
+        "transformer.h.1.post_attention_layernorm.bias": "model-00003-of-00009.safetensors",
+        "transformer.h.1.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+        "transformer.h.1.self_attention.dense.bias": "model-00003-of-00009.safetensors",
+        "transformer.h.1.self_attention.dense.weight": "model-00003-of-00009.safetensors",
+        "transformer.h.1.self_attention.query_key_value.bias": "model-00003-of-00009.safetensors",
+        "transformer.h.1.self_attention.query_key_value.weight": "model-00003-of-00009.safetensors",
+        "transformer.h.10.input_layernorm.bias": "model-00005-of-00009.safetensors",
+        "transformer.h.10.input_layernorm.weight": "model-00005-of-00009.safetensors",
+        "transformer.h.10.mlp.dense_4h_to_h.bias": "model-00005-of-00009.safetensors",
+        "transformer.h.10.mlp.dense_4h_to_h.weight": "model-00005-of-00009.safetensors",
+        "transformer.h.10.mlp.dense_h_to_4h.bias": "model-00005-of-00009.safetensors",
+        "transformer.h.10.mlp.dense_h_to_4h.weight": "model-00005-of-00009.safetensors",
+        "transformer.h.10.post_attention_layernorm.bias": "model-00005-of-00009.safetensors",
+        "transformer.h.10.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+        "transformer.h.10.self_attention.dense.bias": "model-00005-of-00009.safetensors",
+        "transformer.h.10.self_attention.dense.weight": "model-00005-of-00009.safetensors",
+        "transformer.h.10.self_attention.query_key_value.bias": "model-00005-of-00009.safetensors",
+        "transformer.h.10.self_attention.query_key_value.weight": "model-00005-of-00009.safetensors",
+        "transformer.h.11.input_layernorm.bias": "model-00005-of-00009.safetensors",
+        "transformer.h.11.input_layernorm.weight": "model-00005-of-00009.safetensors",
+        "transformer.h.11.mlp.dense_4h_to_h.bias": "model-00005-of-00009.safetensors",
+        "transformer.h.11.mlp.dense_4h_to_h.weight": "model-00005-of-00009.safetensors",
+        "transformer.h.11.mlp.dense_h_to_4h.bias": "model-00005-of-00009.safetensors",
+        "transformer.h.11.mlp.dense_h_to_4h.weight": "model-00005-of-00009.safetensors",
+        "transformer.h.11.post_attention_layernorm.bias": "model-00005-of-00009.safetensors",
+        "transformer.h.11.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+        "transformer.h.11.self_attention.dense.bias": "model-00005-of-00009.safetensors",
+        "transformer.h.11.self_attention.dense.weight": "model-00005-of-00009.safetensors",
+        "transformer.h.11.self_attention.query_key_value.bias": "model-00005-of-00009.safetensors",
+        "transformer.h.11.self_attention.query_key_value.weight": "model-00005-of-00009.safetensors",
+        "transformer.h.12.input_layernorm.bias": "model-00005-of-00009.safetensors",
+        "transformer.h.12.input_layernorm.weight": "model-00005-of-00009.safetensors",
+        "transformer.h.12.mlp.dense_4h_to_h.bias": "model-00005-of-00009.safetensors",
+        "transformer.h.12.mlp.dense_4h_to_h.weight": "model-00005-of-00009.safetensors",
+        "transformer.h.12.mlp.dense_h_to_4h.bias": "model-00005-of-00009.safetensors",
+        "transformer.h.12.mlp.dense_h_to_4h.weight": "model-00005-of-00009.safetensors",
+        "transformer.h.12.post_attention_layernorm.bias": "model-00005-of-00009.safetensors",
+        "transformer.h.12.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+        "transformer.h.12.self_attention.dense.bias": "model-00005-of-00009.safetensors",
+        "transformer.h.12.self_attention.dense.weight": "model-00005-of-00009.safetensors",
+        "transformer.h.12.self_attention.query_key_value.bias": "model-00005-of-00009.safetensors",
+        "transformer.h.12.self_attention.query_key_value.weight": "model-00005-of-00009.safetensors",
+        "transformer.h.13.input_layernorm.bias": "model-00005-of-00009.safetensors",
+        "transformer.h.13.input_layernorm.weight": "model-00005-of-00009.safetensors",
+        "transformer.h.13.mlp.dense_4h_to_h.bias": "model-00005-of-00009.safetensors",
+        "transformer.h.13.mlp.dense_4h_to_h.weight": "model-00005-of-00009.safetensors",
+        "transformer.h.13.mlp.dense_h_to_4h.bias": "model-00005-of-00009.safetensors",
+        "transformer.h.13.mlp.dense_h_to_4h.weight": "model-00005-of-00009.safetensors",
+        "transformer.h.13.post_attention_layernorm.bias": "model-00005-of-00009.safetensors",
+        "transformer.h.13.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+        "transformer.h.13.self_attention.dense.bias": "model-00005-of-00009.safetensors",
+        "transformer.h.13.self_attention.dense.weight": "model-00005-of-00009.safetensors",
+        "transformer.h.13.self_attention.query_key_value.bias": "model-00005-of-00009.safetensors",
+        "transformer.h.13.self_attention.query_key_value.weight": "model-00005-of-00009.safetensors",
+        "transformer.h.14.input_layernorm.bias": "model-00005-of-00009.safetensors",
+        "transformer.h.14.input_layernorm.weight": "model-00005-of-00009.safetensors",
+        "transformer.h.14.mlp.dense_4h_to_h.bias": "model-00006-of-00009.safetensors",
+        "transformer.h.14.mlp.dense_4h_to_h.weight": "model-00006-of-00009.safetensors",
+        "transformer.h.14.mlp.dense_h_to_4h.bias": "model-00006-of-00009.safetensors",
+        "transformer.h.14.mlp.dense_h_to_4h.weight": "model-00006-of-00009.safetensors",
+        "transformer.h.14.post_attention_layernorm.bias": "model-00006-of-00009.safetensors",
+        "transformer.h.14.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+        "transformer.h.14.self_attention.dense.bias": "model-00006-of-00009.safetensors",
+        "transformer.h.14.self_attention.dense.weight": "model-00006-of-00009.safetensors",
+        "transformer.h.14.self_attention.query_key_value.bias": "model-00005-of-00009.safetensors",
+        "transformer.h.14.self_attention.query_key_value.weight": "model-00005-of-00009.safetensors",
+        "transformer.h.15.input_layernorm.bias": "model-00006-of-00009.safetensors",
+        "transformer.h.15.input_layernorm.weight": "model-00006-of-00009.safetensors",
+        "transformer.h.15.mlp.dense_4h_to_h.bias": "model-00006-of-00009.safetensors",
+        "transformer.h.15.mlp.dense_4h_to_h.weight": "model-00006-of-00009.safetensors",
+        "transformer.h.15.mlp.dense_h_to_4h.bias": "model-00006-of-00009.safetensors",
+        "transformer.h.15.mlp.dense_h_to_4h.weight": "model-00006-of-00009.safetensors",
+        "transformer.h.15.post_attention_layernorm.bias": "model-00006-of-00009.safetensors",
+        "transformer.h.15.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+        "transformer.h.15.self_attention.dense.bias": "model-00006-of-00009.safetensors",
+        "transformer.h.15.self_attention.dense.weight": "model-00006-of-00009.safetensors",
+        "transformer.h.15.self_attention.query_key_value.bias": "model-00006-of-00009.safetensors",
+        "transformer.h.15.self_attention.query_key_value.weight": "model-00006-of-00009.safetensors",
+        "transformer.h.16.input_layernorm.bias": "model-00006-of-00009.safetensors",
+        "transformer.h.16.input_layernorm.weight": "model-00006-of-00009.safetensors",
+        "transformer.h.16.mlp.dense_4h_to_h.bias": "model-00006-of-00009.safetensors",
+        "transformer.h.16.mlp.dense_4h_to_h.weight": "model-00006-of-00009.safetensors",
+        "transformer.h.16.mlp.dense_h_to_4h.bias": "model-00006-of-00009.safetensors",
+        "transformer.h.16.mlp.dense_h_to_4h.weight": "model-00006-of-00009.safetensors",
+        "transformer.h.16.post_attention_layernorm.bias": "model-00006-of-00009.safetensors",
+        "transformer.h.16.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+        "transformer.h.16.self_attention.dense.bias": "model-00006-of-00009.safetensors",
+        "transformer.h.16.self_attention.dense.weight": "model-00006-of-00009.safetensors",
+        "transformer.h.16.self_attention.query_key_value.bias": "model-00006-of-00009.safetensors",
+        "transformer.h.16.self_attention.query_key_value.weight": "model-00006-of-00009.safetensors",
+        "transformer.h.17.input_layernorm.bias": "model-00006-of-00009.safetensors",
+        "transformer.h.17.input_layernorm.weight": "model-00006-of-00009.safetensors",
+        "transformer.h.17.mlp.dense_4h_to_h.bias": "model-00006-of-00009.safetensors",
+        "transformer.h.17.mlp.dense_4h_to_h.weight": "model-00006-of-00009.safetensors",
+        "transformer.h.17.mlp.dense_h_to_4h.bias": "model-00006-of-00009.safetensors",
+        "transformer.h.17.mlp.dense_h_to_4h.weight": "model-00006-of-00009.safetensors",
+        "transformer.h.17.post_attention_layernorm.bias": "model-00006-of-00009.safetensors",
+        "transformer.h.17.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+        "transformer.h.17.self_attention.dense.bias": "model-00006-of-00009.safetensors",
+        "transformer.h.17.self_attention.dense.weight": "model-00006-of-00009.safetensors",
+        "transformer.h.17.self_attention.query_key_value.bias": "model-00006-of-00009.safetensors",
+        "transformer.h.17.self_attention.query_key_value.weight": "model-00006-of-00009.safetensors",
+        "transformer.h.18.input_layernorm.bias": "model-00006-of-00009.safetensors",
+        "transformer.h.18.input_layernorm.weight": "model-00006-of-00009.safetensors",
+        "transformer.h.18.mlp.dense_4h_to_h.bias": "model-00006-of-00009.safetensors",
+        "transformer.h.18.mlp.dense_4h_to_h.weight": "model-00006-of-00009.safetensors",
+        "transformer.h.18.mlp.dense_h_to_4h.bias": "model-00006-of-00009.safetensors",
+        "transformer.h.18.mlp.dense_h_to_4h.weight": "model-00006-of-00009.safetensors",
+        "transformer.h.18.post_attention_layernorm.bias": "model-00006-of-00009.safetensors",
+        "transformer.h.18.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+        "transformer.h.18.self_attention.dense.bias": "model-00006-of-00009.safetensors",
+        "transformer.h.18.self_attention.dense.weight": "model-00006-of-00009.safetensors",
+        "transformer.h.18.self_attention.query_key_value.bias": "model-00006-of-00009.safetensors",
+        "transformer.h.18.self_attention.query_key_value.weight": "model-00006-of-00009.safetensors",
+        "transformer.h.19.input_layernorm.bias": "model-00006-of-00009.safetensors",
+        "transformer.h.19.input_layernorm.weight": "model-00006-of-00009.safetensors",
+        "transformer.h.19.mlp.dense_4h_to_h.bias": "model-00007-of-00009.safetensors",
+        "transformer.h.19.mlp.dense_4h_to_h.weight": "model-00007-of-00009.safetensors",
+        "transformer.h.19.mlp.dense_h_to_4h.bias": "model-00007-of-00009.safetensors",
+        "transformer.h.19.mlp.dense_h_to_4h.weight": "model-00007-of-00009.safetensors",
+        "transformer.h.19.post_attention_layernorm.bias": "model-00007-of-00009.safetensors",
+        "transformer.h.19.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+        "transformer.h.19.self_attention.dense.bias": "model-00007-of-00009.safetensors",
+        "transformer.h.19.self_attention.dense.weight": "model-00007-of-00009.safetensors",
+        "transformer.h.19.self_attention.query_key_value.bias": "model-00007-of-00009.safetensors",
+        "transformer.h.19.self_attention.query_key_value.weight": "model-00007-of-00009.safetensors",
+        "transformer.h.2.input_layernorm.bias": "model-00003-of-00009.safetensors",
+        "transformer.h.2.input_layernorm.weight": "model-00003-of-00009.safetensors",
+        "transformer.h.2.mlp.dense_4h_to_h.bias": "model-00003-of-00009.safetensors",
+        "transformer.h.2.mlp.dense_4h_to_h.weight": "model-00003-of-00009.safetensors",
+        "transformer.h.2.mlp.dense_h_to_4h.bias": "model-00003-of-00009.safetensors",
+        "transformer.h.2.mlp.dense_h_to_4h.weight": "model-00003-of-00009.safetensors",
+        "transformer.h.2.post_attention_layernorm.bias": "model-00003-of-00009.safetensors",
+        "transformer.h.2.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+        "transformer.h.2.self_attention.dense.bias": "model-00003-of-00009.safetensors",
+        "transformer.h.2.self_attention.dense.weight": "model-00003-of-00009.safetensors",
+        "transformer.h.2.self_attention.query_key_value.bias": "model-00003-of-00009.safetensors",
+        "transformer.h.2.self_attention.query_key_value.weight": "model-00003-of-00009.safetensors",
+        "transformer.h.20.input_layernorm.bias": "model-00007-of-00009.safetensors",
+        "transformer.h.20.input_layernorm.weight": "model-00007-of-00009.safetensors",
+        "transformer.h.20.mlp.dense_4h_to_h.bias": "model-00007-of-00009.safetensors",
+        "transformer.h.20.mlp.dense_4h_to_h.weight": "model-00007-of-00009.safetensors",
+        "transformer.h.20.mlp.dense_h_to_4h.bias": "model-00007-of-00009.safetensors",
+        "transformer.h.20.mlp.dense_h_to_4h.weight": "model-00007-of-00009.safetensors",
+        "transformer.h.20.post_attention_layernorm.bias": "model-00007-of-00009.safetensors",
+        "transformer.h.20.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+        "transformer.h.20.self_attention.dense.bias": "model-00007-of-00009.safetensors",
+        "transformer.h.20.self_attention.dense.weight": "model-00007-of-00009.safetensors",
+        "transformer.h.20.self_attention.query_key_value.bias": "model-00007-of-00009.safetensors",
+        "transformer.h.20.self_attention.query_key_value.weight": "model-00007-of-00009.safetensors",
+        "transformer.h.21.input_layernorm.bias": "model-00007-of-00009.safetensors",
+        "transformer.h.21.input_layernorm.weight": "model-00007-of-00009.safetensors",
+        "transformer.h.21.mlp.dense_4h_to_h.bias": "model-00007-of-00009.safetensors",
+        "transformer.h.21.mlp.dense_4h_to_h.weight": "model-00007-of-00009.safetensors",
+        "transformer.h.21.mlp.dense_h_to_4h.bias": "model-00007-of-00009.safetensors",
+        "transformer.h.21.mlp.dense_h_to_4h.weight": "model-00007-of-00009.safetensors",
+        "transformer.h.21.post_attention_layernorm.bias": "model-00007-of-00009.safetensors",
+        "transformer.h.21.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+        "transformer.h.21.self_attention.dense.bias": "model-00007-of-00009.safetensors",
+        "transformer.h.21.self_attention.dense.weight": "model-00007-of-00009.safetensors",
+        "transformer.h.21.self_attention.query_key_value.bias": "model-00007-of-00009.safetensors",
+        "transformer.h.21.self_attention.query_key_value.weight": "model-00007-of-00009.safetensors",
+        "transformer.h.22.input_layernorm.bias": "model-00007-of-00009.safetensors",
+        "transformer.h.22.input_layernorm.weight": "model-00007-of-00009.safetensors",
+        "transformer.h.22.mlp.dense_4h_to_h.bias": "model-00007-of-00009.safetensors",
+        "transformer.h.22.mlp.dense_4h_to_h.weight": "model-00007-of-00009.safetensors",
+        "transformer.h.22.mlp.dense_h_to_4h.bias": "model-00007-of-00009.safetensors",
+        "transformer.h.22.mlp.dense_h_to_4h.weight": "model-00007-of-00009.safetensors",
+        "transformer.h.22.post_attention_layernorm.bias": "model-00007-of-00009.safetensors",
+        "transformer.h.22.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+        "transformer.h.22.self_attention.dense.bias": "model-00007-of-00009.safetensors",
+        "transformer.h.22.self_attention.dense.weight": "model-00007-of-00009.safetensors",
+        "transformer.h.22.self_attention.query_key_value.bias": "model-00007-of-00009.safetensors",
+        "transformer.h.22.self_attention.query_key_value.weight": "model-00007-of-00009.safetensors",
+        "transformer.h.23.input_layernorm.bias": "model-00007-of-00009.safetensors",
+        "transformer.h.23.input_layernorm.weight": "model-00007-of-00009.safetensors",
+        "transformer.h.23.mlp.dense_4h_to_h.bias": "model-00008-of-00009.safetensors",
+        "transformer.h.23.mlp.dense_4h_to_h.weight": "model-00008-of-00009.safetensors",
+        "transformer.h.23.mlp.dense_h_to_4h.bias": "model-00007-of-00009.safetensors",
+        "transformer.h.23.mlp.dense_h_to_4h.weight": "model-00007-of-00009.safetensors",
+        "transformer.h.23.post_attention_layernorm.bias": "model-00007-of-00009.safetensors",
+        "transformer.h.23.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+        "transformer.h.23.self_attention.dense.bias": "model-00007-of-00009.safetensors",
+        "transformer.h.23.self_attention.dense.weight": "model-00007-of-00009.safetensors",
+        "transformer.h.23.self_attention.query_key_value.bias": "model-00007-of-00009.safetensors",
+        "transformer.h.23.self_attention.query_key_value.weight": "model-00007-of-00009.safetensors",
+        "transformer.h.24.input_layernorm.bias": "model-00008-of-00009.safetensors",
+        "transformer.h.24.input_layernorm.weight": "model-00008-of-00009.safetensors",
+        "transformer.h.24.mlp.dense_4h_to_h.bias": "model-00008-of-00009.safetensors",
+        "transformer.h.24.mlp.dense_4h_to_h.weight": "model-00008-of-00009.safetensors",
+        "transformer.h.24.mlp.dense_h_to_4h.bias": "model-00008-of-00009.safetensors",
+        "transformer.h.24.mlp.dense_h_to_4h.weight": "model-00008-of-00009.safetensors",
+        "transformer.h.24.post_attention_layernorm.bias": "model-00008-of-00009.safetensors",
+        "transformer.h.24.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+        "transformer.h.24.self_attention.dense.bias": "model-00008-of-00009.safetensors",
+        "transformer.h.24.self_attention.dense.weight": "model-00008-of-00009.safetensors",
+        "transformer.h.24.self_attention.query_key_value.bias": "model-00008-of-00009.safetensors",
+        "transformer.h.24.self_attention.query_key_value.weight": "model-00008-of-00009.safetensors",
+        "transformer.h.25.input_layernorm.bias": "model-00008-of-00009.safetensors",
+        "transformer.h.25.input_layernorm.weight": "model-00008-of-00009.safetensors",
+        "transformer.h.25.mlp.dense_4h_to_h.bias": "model-00008-of-00009.safetensors",
+        "transformer.h.25.mlp.dense_4h_to_h.weight": "model-00008-of-00009.safetensors",
+        "transformer.h.25.mlp.dense_h_to_4h.bias": "model-00008-of-00009.safetensors",
+        "transformer.h.25.mlp.dense_h_to_4h.weight": "model-00008-of-00009.safetensors",
+        "transformer.h.25.post_attention_layernorm.bias": "model-00008-of-00009.safetensors",
+        "transformer.h.25.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+        "transformer.h.25.self_attention.dense.bias": "model-00008-of-00009.safetensors",
+        "transformer.h.25.self_attention.dense.weight": "model-00008-of-00009.safetensors",
+        "transformer.h.25.self_attention.query_key_value.bias": "model-00008-of-00009.safetensors",
+        "transformer.h.25.self_attention.query_key_value.weight": "model-00008-of-00009.safetensors",
+        "transformer.h.26.input_layernorm.bias": "model-00008-of-00009.safetensors",
+        "transformer.h.26.input_layernorm.weight": "model-00008-of-00009.safetensors",
+        "transformer.h.26.mlp.dense_4h_to_h.bias": "model-00008-of-00009.safetensors",
+        "transformer.h.26.mlp.dense_4h_to_h.weight": "model-00008-of-00009.safetensors",
+        "transformer.h.26.mlp.dense_h_to_4h.bias": "model-00008-of-00009.safetensors",
+        "transformer.h.26.mlp.dense_h_to_4h.weight": "model-00008-of-00009.safetensors",
+        "transformer.h.26.post_attention_layernorm.bias": "model-00008-of-00009.safetensors",
+        "transformer.h.26.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+        "transformer.h.26.self_attention.dense.bias": "model-00008-of-00009.safetensors",
+        "transformer.h.26.self_attention.dense.weight": "model-00008-of-00009.safetensors",
+        "transformer.h.26.self_attention.query_key_value.bias": "model-00008-of-00009.safetensors",
+        "transformer.h.26.self_attention.query_key_value.weight": "model-00008-of-00009.safetensors",
+        "transformer.h.27.input_layernorm.bias": "model-00008-of-00009.safetensors",
+        "transformer.h.27.input_layernorm.weight": "model-00008-of-00009.safetensors",
+        "transformer.h.27.mlp.dense_4h_to_h.bias": "model-00008-of-00009.safetensors",
+        "transformer.h.27.mlp.dense_4h_to_h.weight": "model-00008-of-00009.safetensors",
+        "transformer.h.27.mlp.dense_h_to_4h.bias": "model-00008-of-00009.safetensors",
+        "transformer.h.27.mlp.dense_h_to_4h.weight": "model-00008-of-00009.safetensors",
+        "transformer.h.27.post_attention_layernorm.bias": "model-00008-of-00009.safetensors",
+        "transformer.h.27.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+        "transformer.h.27.self_attention.dense.bias": "model-00008-of-00009.safetensors",
+        "transformer.h.27.self_attention.dense.weight": "model-00008-of-00009.safetensors",
+        "transformer.h.27.self_attention.query_key_value.bias": "model-00008-of-00009.safetensors",
+        "transformer.h.27.self_attention.query_key_value.weight": "model-00008-of-00009.safetensors",
+        "transformer.h.28.input_layernorm.bias": "model-00008-of-00009.safetensors",
+        "transformer.h.28.input_layernorm.weight": "model-00008-of-00009.safetensors",
+        "transformer.h.28.mlp.dense_4h_to_h.bias": "model-00009-of-00009.safetensors",
+        "transformer.h.28.mlp.dense_4h_to_h.weight": "model-00009-of-00009.safetensors",
+        "transformer.h.28.mlp.dense_h_to_4h.bias": "model-00009-of-00009.safetensors",
+        "transformer.h.28.mlp.dense_h_to_4h.weight": "model-00009-of-00009.safetensors",
+        "transformer.h.28.post_attention_layernorm.bias": "model-00008-of-00009.safetensors",
+        "transformer.h.28.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+        "transformer.h.28.self_attention.dense.bias": "model-00008-of-00009.safetensors",
+        "transformer.h.28.self_attention.dense.weight": "model-00008-of-00009.safetensors",
+        "transformer.h.28.self_attention.query_key_value.bias": "model-00008-of-00009.safetensors",
+        "transformer.h.28.self_attention.query_key_value.weight": "model-00008-of-00009.safetensors",
+        "transformer.h.29.input_layernorm.bias": "model-00009-of-00009.safetensors",
+        "transformer.h.29.input_layernorm.weight": "model-00009-of-00009.safetensors",
+        "transformer.h.29.mlp.dense_4h_to_h.bias": "model-00009-of-00009.safetensors",
+        "transformer.h.29.mlp.dense_4h_to_h.weight": "model-00009-of-00009.safetensors",
+        "transformer.h.29.mlp.dense_h_to_4h.bias": "model-00009-of-00009.safetensors",
+        "transformer.h.29.mlp.dense_h_to_4h.weight": "model-00009-of-00009.safetensors",
+        "transformer.h.29.post_attention_layernorm.bias": "model-00009-of-00009.safetensors",
+        "transformer.h.29.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+        "transformer.h.29.self_attention.dense.bias": "model-00009-of-00009.safetensors",
+        "transformer.h.29.self_attention.dense.weight": "model-00009-of-00009.safetensors",
+        "transformer.h.29.self_attention.query_key_value.bias": "model-00009-of-00009.safetensors",
+        "transformer.h.29.self_attention.query_key_value.weight": "model-00009-of-00009.safetensors",
+        "transformer.h.3.input_layernorm.bias": "model-00003-of-00009.safetensors",
+        "transformer.h.3.input_layernorm.weight": "model-00003-of-00009.safetensors",
+        "transformer.h.3.mlp.dense_4h_to_h.bias": "model-00003-of-00009.safetensors",
+        "transformer.h.3.mlp.dense_4h_to_h.weight": "model-00003-of-00009.safetensors",
+        "transformer.h.3.mlp.dense_h_to_4h.bias": "model-00003-of-00009.safetensors",
+        "transformer.h.3.mlp.dense_h_to_4h.weight": "model-00003-of-00009.safetensors",
+        "transformer.h.3.post_attention_layernorm.bias": "model-00003-of-00009.safetensors",
+        "transformer.h.3.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+        "transformer.h.3.self_attention.dense.bias": "model-00003-of-00009.safetensors",
+        "transformer.h.3.self_attention.dense.weight": "model-00003-of-00009.safetensors",
+        "transformer.h.3.self_attention.query_key_value.bias": "model-00003-of-00009.safetensors",
+        "transformer.h.3.self_attention.query_key_value.weight": "model-00003-of-00009.safetensors",
+        "transformer.h.4.input_layernorm.bias": "model-00003-of-00009.safetensors",
+        "transformer.h.4.input_layernorm.weight": "model-00003-of-00009.safetensors",
+        "transformer.h.4.mlp.dense_4h_to_h.bias": "model-00004-of-00009.safetensors",
+        "transformer.h.4.mlp.dense_4h_to_h.weight": "model-00004-of-00009.safetensors",
+        "transformer.h.4.mlp.dense_h_to_4h.bias": "model-00003-of-00009.safetensors",
+        "transformer.h.4.mlp.dense_h_to_4h.weight": "model-00003-of-00009.safetensors",
+        "transformer.h.4.post_attention_layernorm.bias": "model-00003-of-00009.safetensors",
+        "transformer.h.4.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+        "transformer.h.4.self_attention.dense.bias": "model-00003-of-00009.safetensors",
+        "transformer.h.4.self_attention.dense.weight": "model-00003-of-00009.safetensors",
+        "transformer.h.4.self_attention.query_key_value.bias": "model-00003-of-00009.safetensors",
+        "transformer.h.4.self_attention.query_key_value.weight": "model-00003-of-00009.safetensors",
+        "transformer.h.5.input_layernorm.bias": "model-00004-of-00009.safetensors",
+        "transformer.h.5.input_layernorm.weight": "model-00004-of-00009.safetensors",
+        "transformer.h.5.mlp.dense_4h_to_h.bias": "model-00004-of-00009.safetensors",
+        "transformer.h.5.mlp.dense_4h_to_h.weight": "model-00004-of-00009.safetensors",
+        "transformer.h.5.mlp.dense_h_to_4h.bias": "model-00004-of-00009.safetensors",
+        "transformer.h.5.mlp.dense_h_to_4h.weight": "model-00004-of-00009.safetensors",
+        "transformer.h.5.post_attention_layernorm.bias": "model-00004-of-00009.safetensors",
+        "transformer.h.5.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+        "transformer.h.5.self_attention.dense.bias": "model-00004-of-00009.safetensors",
+        "transformer.h.5.self_attention.dense.weight": "model-00004-of-00009.safetensors",
+        "transformer.h.5.self_attention.query_key_value.bias": "model-00004-of-00009.safetensors",
+        "transformer.h.5.self_attention.query_key_value.weight": "model-00004-of-00009.safetensors",
+        "transformer.h.6.input_layernorm.bias": "model-00004-of-00009.safetensors",
+        "transformer.h.6.input_layernorm.weight": "model-00004-of-00009.safetensors",
+        "transformer.h.6.mlp.dense_4h_to_h.bias": "model-00004-of-00009.safetensors",
+        "transformer.h.6.mlp.dense_4h_to_h.weight": "model-00004-of-00009.safetensors",
+        "transformer.h.6.mlp.dense_h_to_4h.bias": "model-00004-of-00009.safetensors",
+        "transformer.h.6.mlp.dense_h_to_4h.weight": "model-00004-of-00009.safetensors",
+        "transformer.h.6.post_attention_layernorm.bias": "model-00004-of-00009.safetensors",
+        "transformer.h.6.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+        "transformer.h.6.self_attention.dense.bias": "model-00004-of-00009.safetensors",
+        "transformer.h.6.self_attention.dense.weight": "model-00004-of-00009.safetensors",
+        "transformer.h.6.self_attention.query_key_value.bias": "model-00004-of-00009.safetensors",
+        "transformer.h.6.self_attention.query_key_value.weight": "model-00004-of-00009.safetensors",
+        "transformer.h.7.input_layernorm.bias": "model-00004-of-00009.safetensors",
+        "transformer.h.7.input_layernorm.weight": "model-00004-of-00009.safetensors",
+        "transformer.h.7.mlp.dense_4h_to_h.bias": "model-00004-of-00009.safetensors",
+        "transformer.h.7.mlp.dense_4h_to_h.weight": "model-00004-of-00009.safetensors",
+        "transformer.h.7.mlp.dense_h_to_4h.bias": "model-00004-of-00009.safetensors",
+        "transformer.h.7.mlp.dense_h_to_4h.weight": "model-00004-of-00009.safetensors",
+        "transformer.h.7.post_attention_layernorm.bias": "model-00004-of-00009.safetensors",
+        "transformer.h.7.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+        "transformer.h.7.self_attention.dense.bias": "model-00004-of-00009.safetensors",
+        "transformer.h.7.self_attention.dense.weight": "model-00004-of-00009.safetensors",
+        "transformer.h.7.self_attention.query_key_value.bias": "model-00004-of-00009.safetensors",
+        "transformer.h.7.self_attention.query_key_value.weight": "model-00004-of-00009.safetensors",
+        "transformer.h.8.input_layernorm.bias": "model-00004-of-00009.safetensors",
+        "transformer.h.8.input_layernorm.weight": "model-00004-of-00009.safetensors",
+        "transformer.h.8.mlp.dense_4h_to_h.bias": "model-00004-of-00009.safetensors",
+        "transformer.h.8.mlp.dense_4h_to_h.weight": "model-00004-of-00009.safetensors",
+        "transformer.h.8.mlp.dense_h_to_4h.bias": "model-00004-of-00009.safetensors",
+        "transformer.h.8.mlp.dense_h_to_4h.weight": "model-00004-of-00009.safetensors",
+        "transformer.h.8.post_attention_layernorm.bias": "model-00004-of-00009.safetensors",
+        "transformer.h.8.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+        "transformer.h.8.self_attention.dense.bias": "model-00004-of-00009.safetensors",
+        "transformer.h.8.self_attention.dense.weight": "model-00004-of-00009.safetensors",
+        "transformer.h.8.self_attention.query_key_value.bias": "model-00004-of-00009.safetensors",
+        "transformer.h.8.self_attention.query_key_value.weight": "model-00004-of-00009.safetensors",
+        "transformer.h.9.input_layernorm.bias": "model-00004-of-00009.safetensors",
+        "transformer.h.9.input_layernorm.weight": "model-00004-of-00009.safetensors",
+        "transformer.h.9.mlp.dense_4h_to_h.bias": "model-00005-of-00009.safetensors",
+        "transformer.h.9.mlp.dense_4h_to_h.weight": "model-00005-of-00009.safetensors",
+        "transformer.h.9.mlp.dense_h_to_4h.bias": "model-00005-of-00009.safetensors",
+        "transformer.h.9.mlp.dense_h_to_4h.weight": "model-00005-of-00009.safetensors",
+        "transformer.h.9.post_attention_layernorm.bias": "model-00004-of-00009.safetensors",
+        "transformer.h.9.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+        "transformer.h.9.self_attention.dense.bias": "model-00004-of-00009.safetensors",
+        "transformer.h.9.self_attention.dense.weight": "model-00004-of-00009.safetensors",
+        "transformer.h.9.self_attention.query_key_value.bias": "model-00004-of-00009.safetensors",
+        "transformer.h.9.self_attention.query_key_value.weight": "model-00004-of-00009.safetensors",
+        "transformer.ln_f.bias": "model-00009-of-00009.safetensors",
+        "transformer.ln_f.weight": "model-00009-of-00009.safetensors",
+        "transformer.word_embeddings.weight": "model-00002-of-00009.safetensors",
+        "transformer.word_embeddings_layernorm.bias": "model-00003-of-00009.safetensors",
+        "transformer.word_embeddings_layernorm.weight": "model-00003-of-00009.safetensors"
+    }
+}