Adding `safetensors` variant of this model (#51)

- Adding `safetensors` variant of this model (7002f454fc2c08736dc9bd075cff2c2fa9c0eeba)


Co-authored-by: Safetensors convertbot <SFconvertbot@users.noreply.huggingface.co>

.gitattributes

@@ -26,3 +26,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10df3a160ea5352261e667073a5a896fc0c5253a3ea31b78f7940fcff83ede07
+size 9976218536

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1ae1c8a2e7b30795c7741b8c1bedd1093ad87dd95e95614a1d78ad1c75f6d03
+size 4161852232

model.safetensors.index.json

@@ -0,0 +1,372 @@
+{
+    "metadata": {
+        "total_size": 14138032128
+    },
+    "weight_map": {
+        "h.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.0.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "h.0.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.0.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.0.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.0.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.0.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.0.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "h.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.1.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "h.1.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "h.1.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.1.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.1.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.1.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.1.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.1.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.1.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "h.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.10.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "h.10.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "h.10.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.10.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.10.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.10.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.10.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.10.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.10.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "h.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.11.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "h.11.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "h.11.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.11.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.11.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.11.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.11.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.11.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.11.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "h.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.12.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "h.12.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "h.12.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.12.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.12.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.12.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.12.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.12.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.12.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "h.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.13.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "h.13.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "h.13.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.13.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.13.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.13.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.13.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.13.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.13.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "h.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.14.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "h.14.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "h.14.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.14.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.14.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.14.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.14.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.14.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.14.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "h.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.15.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "h.15.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "h.15.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.15.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.15.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.15.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.15.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.15.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.15.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "h.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.16.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "h.16.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "h.16.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.16.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.16.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.16.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.16.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.16.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.16.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "h.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.17.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "h.17.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "h.17.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.17.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.17.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.17.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.17.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.17.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.17.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "h.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.18.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "h.18.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "h.18.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.18.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.18.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.18.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.18.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.18.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.18.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "h.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.19.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+        "h.19.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+        "h.19.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.19.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.19.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.19.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.19.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.19.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.19.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "h.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.2.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "h.2.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "h.2.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.2.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.2.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.2.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.2.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.2.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.2.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "h.20.input_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.20.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+        "h.20.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+        "h.20.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
+        "h.20.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+        "h.20.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.20.self_attention.dense.bias": "model-00002-of-00002.safetensors",
+        "h.20.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+        "h.20.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+        "h.20.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+        "h.21.input_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.21.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+        "h.21.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+        "h.21.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
+        "h.21.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+        "h.21.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.21.self_attention.dense.bias": "model-00002-of-00002.safetensors",
+        "h.21.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+        "h.21.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+        "h.21.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+        "h.22.input_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.22.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+        "h.22.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+        "h.22.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
+        "h.22.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+        "h.22.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.22.self_attention.dense.bias": "model-00002-of-00002.safetensors",
+        "h.22.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+        "h.22.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+        "h.22.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+        "h.23.input_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.23.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+        "h.23.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+        "h.23.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
+        "h.23.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+        "h.23.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.23.self_attention.dense.bias": "model-00002-of-00002.safetensors",
+        "h.23.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+        "h.23.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+        "h.23.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+        "h.24.input_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.24.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+        "h.24.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+        "h.24.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
+        "h.24.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+        "h.24.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.24.self_attention.dense.bias": "model-00002-of-00002.safetensors",
+        "h.24.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+        "h.24.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+        "h.24.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+        "h.25.input_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.25.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+        "h.25.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+        "h.25.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
+        "h.25.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+        "h.25.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.25.self_attention.dense.bias": "model-00002-of-00002.safetensors",
+        "h.25.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+        "h.25.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+        "h.25.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+        "h.26.input_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.26.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+        "h.26.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+        "h.26.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
+        "h.26.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+        "h.26.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.26.self_attention.dense.bias": "model-00002-of-00002.safetensors",
+        "h.26.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+        "h.26.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+        "h.26.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+        "h.27.input_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.27.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+        "h.27.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+        "h.27.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
+        "h.27.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+        "h.27.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.27.self_attention.dense.bias": "model-00002-of-00002.safetensors",
+        "h.27.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+        "h.27.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+        "h.27.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+        "h.28.input_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.28.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+        "h.28.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+        "h.28.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
+        "h.28.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+        "h.28.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.28.self_attention.dense.bias": "model-00002-of-00002.safetensors",
+        "h.28.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+        "h.28.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+        "h.28.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+        "h.29.input_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.29.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+        "h.29.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+        "h.29.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
+        "h.29.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+        "h.29.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.29.self_attention.dense.bias": "model-00002-of-00002.safetensors",
+        "h.29.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+        "h.29.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+        "h.29.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+        "h.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.3.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "h.3.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "h.3.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.3.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.3.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.3.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.3.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.3.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.3.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "h.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.4.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "h.4.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "h.4.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.4.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.4.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.4.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.4.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.4.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.4.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "h.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.5.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "h.5.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "h.5.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.5.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.5.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.5.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.5.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.5.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.5.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "h.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.6.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "h.6.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "h.6.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.6.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.6.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.6.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.6.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.6.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.6.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "h.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.7.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "h.7.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "h.7.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.7.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.7.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.7.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.7.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.7.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.7.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "h.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.8.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "h.8.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "h.8.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.8.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.8.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.8.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.8.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.8.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.8.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "h.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.9.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "h.9.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "h.9.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.9.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.9.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.9.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.9.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.9.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.9.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "ln_f.bias": "model-00002-of-00002.safetensors",
+        "ln_f.weight": "model-00002-of-00002.safetensors",
+        "word_embeddings.weight": "model-00001-of-00002.safetensors",
+        "word_embeddings_layernorm.bias": "model-00001-of-00002.safetensors",
+        "word_embeddings_layernorm.weight": "model-00001-of-00002.safetensors"
+    }
+}