Adding `safetensors` variant of this model

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c172a612366f619af4e0f2f837070a61f5c17bd6a347b5c12ca5c1c239f0e31
+size 1859714244

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:183e6596d8a9346d0e0b09af9f397ff9ee94715a2ab2084560b7b364b9b53587
+size 1845816868

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:575224c1ede808df13c5fd846fdfd3fae9914387c039932a9f3ffce42d099a9a
+size 1845816868

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea2e3ac4604485e57e39ec9b1e3fb9da1632d92d1a61fa355d637ecc30e59f27
+size 1845816868

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d94d2a78e5e91695e1f2e26b6c96014e0c7e89cc1eb74ef1bc8c343fa9bd010
+size 1845816868

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30ef7eb6b12e1f24bf41bf19ac683b68c9a6c06049c44976021332c2d5402281
+size 1845816876

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bf51c3e3199a79100236ea8fcedb7ee19afbd85c732021e58cfa5ab9e336023
+size 1845816892

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c03c97791e159523ed3de8f26a28c592e673f2d7bd9fdcd236b825a2b4d590f0
+size 1845816892

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d15d4e59ad28395bf0e2bebb0bfb5d60e8327e9785bf9034ec810093e962b76
+size 1222005536

model.safetensors.index.json

@@ -0,0 +1,251 @@
+{
+    "metadata": {
+        "total_size": 15767528480.0
+    },
+    "weight_map": {
+        "embed_out.weight": "model-00009-of-00009.safetensors",
+        "gpt_neox.embed_in.weight": "model-00001-of-00009.safetensors",
+        "gpt_neox.final_layer_norm.bias": "model-00009-of-00009.safetensors",
+        "gpt_neox.final_layer_norm.weight": "model-00009-of-00009.safetensors",
+        "gpt_neox.layers.0.attention.bias": "model-00001-of-00009.safetensors",
+        "gpt_neox.layers.0.attention.dense.bias": "model-00001-of-00009.safetensors",
+        "gpt_neox.layers.0.attention.dense.weight": "model-00001-of-00009.safetensors",
+        "gpt_neox.layers.0.attention.masked_bias": "model-00001-of-00009.safetensors",
+        "gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-00009.safetensors",
+        "gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-00009.safetensors",
+        "gpt_neox.layers.0.attention.rotary_emb.inv_freq": "model-00001-of-00009.safetensors",
+        "gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00009.safetensors",
+        "gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors",
+        "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00009.safetensors",
+        "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00009.safetensors",
+        "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00009.safetensors",
+        "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00009.safetensors",
+        "gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00009.safetensors",
+        "gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+        "gpt_neox.layers.1.attention.bias": "model-00001-of-00009.safetensors",
+        "gpt_neox.layers.1.attention.dense.bias": "model-00001-of-00009.safetensors",
+        "gpt_neox.layers.1.attention.dense.weight": "model-00001-of-00009.safetensors",
+        "gpt_neox.layers.1.attention.masked_bias": "model-00001-of-00009.safetensors",
+        "gpt_neox.layers.1.attention.query_key_value.bias": "model-00001-of-00009.safetensors",
+        "gpt_neox.layers.1.attention.query_key_value.weight": "model-00001-of-00009.safetensors",
+        "gpt_neox.layers.1.attention.rotary_emb.inv_freq": "model-00001-of-00009.safetensors",
+        "gpt_neox.layers.1.input_layernorm.bias": "model-00001-of-00009.safetensors",
+        "gpt_neox.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors",
+        "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00002-of-00009.safetensors",
+        "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00002-of-00009.safetensors",
+        "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00002-of-00009.safetensors",
+        "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00002-of-00009.safetensors",
+        "gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00009.safetensors",
+        "gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+        "gpt_neox.layers.10.attention.bias": "model-00006-of-00009.safetensors",
+        "gpt_neox.layers.10.attention.dense.bias": "model-00006-of-00009.safetensors",
+        "gpt_neox.layers.10.attention.dense.weight": "model-00006-of-00009.safetensors",
+        "gpt_neox.layers.10.attention.masked_bias": "model-00006-of-00009.safetensors",
+        "gpt_neox.layers.10.attention.query_key_value.bias": "model-00006-of-00009.safetensors",
+        "gpt_neox.layers.10.attention.query_key_value.weight": "model-00006-of-00009.safetensors",
+        "gpt_neox.layers.10.attention.rotary_emb.inv_freq": "model-00006-of-00009.safetensors",
+        "gpt_neox.layers.10.input_layernorm.bias": "model-00006-of-00009.safetensors",
+        "gpt_neox.layers.10.input_layernorm.weight": "model-00006-of-00009.safetensors",
+        "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00006-of-00009.safetensors",
+        "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00006-of-00009.safetensors",
+        "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00006-of-00009.safetensors",
+        "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00006-of-00009.safetensors",
+        "gpt_neox.layers.10.post_attention_layernorm.bias": "model-00006-of-00009.safetensors",
+        "gpt_neox.layers.10.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+        "gpt_neox.layers.11.attention.bias": "model-00006-of-00009.safetensors",
+        "gpt_neox.layers.11.attention.dense.bias": "model-00006-of-00009.safetensors",
+        "gpt_neox.layers.11.attention.dense.weight": "model-00006-of-00009.safetensors",
+        "gpt_neox.layers.11.attention.masked_bias": "model-00006-of-00009.safetensors",
+        "gpt_neox.layers.11.attention.query_key_value.bias": "model-00006-of-00009.safetensors",
+        "gpt_neox.layers.11.attention.query_key_value.weight": "model-00006-of-00009.safetensors",
+        "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "model-00006-of-00009.safetensors",
+        "gpt_neox.layers.11.input_layernorm.bias": "model-00006-of-00009.safetensors",
+        "gpt_neox.layers.11.input_layernorm.weight": "model-00006-of-00009.safetensors",
+        "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00007-of-00009.safetensors",
+        "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00007-of-00009.safetensors",
+        "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00007-of-00009.safetensors",
+        "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00007-of-00009.safetensors",
+        "gpt_neox.layers.11.post_attention_layernorm.bias": "model-00006-of-00009.safetensors",
+        "gpt_neox.layers.11.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+        "gpt_neox.layers.12.attention.bias": "model-00007-of-00009.safetensors",
+        "gpt_neox.layers.12.attention.dense.bias": "model-00007-of-00009.safetensors",
+        "gpt_neox.layers.12.attention.dense.weight": "model-00007-of-00009.safetensors",
+        "gpt_neox.layers.12.attention.masked_bias": "model-00007-of-00009.safetensors",
+        "gpt_neox.layers.12.attention.query_key_value.bias": "model-00007-of-00009.safetensors",
+        "gpt_neox.layers.12.attention.query_key_value.weight": "model-00007-of-00009.safetensors",
+        "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "model-00007-of-00009.safetensors",
+        "gpt_neox.layers.12.input_layernorm.bias": "model-00007-of-00009.safetensors",
+        "gpt_neox.layers.12.input_layernorm.weight": "model-00007-of-00009.safetensors",
+        "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00007-of-00009.safetensors",
+        "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00007-of-00009.safetensors",
+        "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00007-of-00009.safetensors",
+        "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00007-of-00009.safetensors",
+        "gpt_neox.layers.12.post_attention_layernorm.bias": "model-00007-of-00009.safetensors",
+        "gpt_neox.layers.12.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+        "gpt_neox.layers.13.attention.bias": "model-00007-of-00009.safetensors",
+        "gpt_neox.layers.13.attention.dense.bias": "model-00007-of-00009.safetensors",
+        "gpt_neox.layers.13.attention.dense.weight": "model-00007-of-00009.safetensors",
+        "gpt_neox.layers.13.attention.masked_bias": "model-00007-of-00009.safetensors",
+        "gpt_neox.layers.13.attention.query_key_value.bias": "model-00007-of-00009.safetensors",
+        "gpt_neox.layers.13.attention.query_key_value.weight": "model-00007-of-00009.safetensors",
+        "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "model-00007-of-00009.safetensors",
+        "gpt_neox.layers.13.input_layernorm.bias": "model-00007-of-00009.safetensors",
+        "gpt_neox.layers.13.input_layernorm.weight": "model-00007-of-00009.safetensors",
+        "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00008-of-00009.safetensors",
+        "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00008-of-00009.safetensors",
+        "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00008-of-00009.safetensors",
+        "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00008-of-00009.safetensors",
+        "gpt_neox.layers.13.post_attention_layernorm.bias": "model-00007-of-00009.safetensors",
+        "gpt_neox.layers.13.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+        "gpt_neox.layers.14.attention.bias": "model-00008-of-00009.safetensors",
+        "gpt_neox.layers.14.attention.dense.bias": "model-00008-of-00009.safetensors",
+        "gpt_neox.layers.14.attention.dense.weight": "model-00008-of-00009.safetensors",
+        "gpt_neox.layers.14.attention.masked_bias": "model-00008-of-00009.safetensors",
+        "gpt_neox.layers.14.attention.query_key_value.bias": "model-00008-of-00009.safetensors",
+        "gpt_neox.layers.14.attention.query_key_value.weight": "model-00008-of-00009.safetensors",
+        "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "model-00008-of-00009.safetensors",
+        "gpt_neox.layers.14.input_layernorm.bias": "model-00008-of-00009.safetensors",
+        "gpt_neox.layers.14.input_layernorm.weight": "model-00008-of-00009.safetensors",
+        "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00008-of-00009.safetensors",
+        "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00008-of-00009.safetensors",
+        "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00008-of-00009.safetensors",
+        "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00008-of-00009.safetensors",
+        "gpt_neox.layers.14.post_attention_layernorm.bias": "model-00008-of-00009.safetensors",
+        "gpt_neox.layers.14.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+        "gpt_neox.layers.15.attention.bias": "model-00008-of-00009.safetensors",
+        "gpt_neox.layers.15.attention.dense.bias": "model-00008-of-00009.safetensors",
+        "gpt_neox.layers.15.attention.dense.weight": "model-00008-of-00009.safetensors",
+        "gpt_neox.layers.15.attention.masked_bias": "model-00008-of-00009.safetensors",
+        "gpt_neox.layers.15.attention.query_key_value.bias": "model-00008-of-00009.safetensors",
+        "gpt_neox.layers.15.attention.query_key_value.weight": "model-00008-of-00009.safetensors",
+        "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "model-00008-of-00009.safetensors",
+        "gpt_neox.layers.15.input_layernorm.bias": "model-00008-of-00009.safetensors",
+        "gpt_neox.layers.15.input_layernorm.weight": "model-00008-of-00009.safetensors",
+        "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00009-of-00009.safetensors",
+        "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00009-of-00009.safetensors",
+        "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00009-of-00009.safetensors",
+        "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00009-of-00009.safetensors",
+        "gpt_neox.layers.15.post_attention_layernorm.bias": "model-00008-of-00009.safetensors",
+        "gpt_neox.layers.15.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+        "gpt_neox.layers.2.attention.bias": "model-00002-of-00009.safetensors",
+        "gpt_neox.layers.2.attention.dense.bias": "model-00002-of-00009.safetensors",
+        "gpt_neox.layers.2.attention.dense.weight": "model-00002-of-00009.safetensors",
+        "gpt_neox.layers.2.attention.masked_bias": "model-00002-of-00009.safetensors",
+        "gpt_neox.layers.2.attention.query_key_value.bias": "model-00002-of-00009.safetensors",
+        "gpt_neox.layers.2.attention.query_key_value.weight": "model-00002-of-00009.safetensors",
+        "gpt_neox.layers.2.attention.rotary_emb.inv_freq": "model-00002-of-00009.safetensors",
+        "gpt_neox.layers.2.input_layernorm.bias": "model-00002-of-00009.safetensors",
+        "gpt_neox.layers.2.input_layernorm.weight": "model-00002-of-00009.safetensors",
+        "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00002-of-00009.safetensors",
+        "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00002-of-00009.safetensors",
+        "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00002-of-00009.safetensors",
+        "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00002-of-00009.safetensors",
+        "gpt_neox.layers.2.post_attention_layernorm.bias": "model-00002-of-00009.safetensors",
+        "gpt_neox.layers.2.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+        "gpt_neox.layers.3.attention.bias": "model-00002-of-00009.safetensors",
+        "gpt_neox.layers.3.attention.dense.bias": "model-00002-of-00009.safetensors",
+        "gpt_neox.layers.3.attention.dense.weight": "model-00002-of-00009.safetensors",
+        "gpt_neox.layers.3.attention.masked_bias": "model-00002-of-00009.safetensors",
+        "gpt_neox.layers.3.attention.query_key_value.bias": "model-00002-of-00009.safetensors",
+        "gpt_neox.layers.3.attention.query_key_value.weight": "model-00002-of-00009.safetensors",
+        "gpt_neox.layers.3.attention.rotary_emb.inv_freq": "model-00002-of-00009.safetensors",
+        "gpt_neox.layers.3.input_layernorm.bias": "model-00002-of-00009.safetensors",
+        "gpt_neox.layers.3.input_layernorm.weight": "model-00002-of-00009.safetensors",
+        "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00003-of-00009.safetensors",
+        "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00003-of-00009.safetensors",
+        "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00003-of-00009.safetensors",
+        "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00003-of-00009.safetensors",
+        "gpt_neox.layers.3.post_attention_layernorm.bias": "model-00002-of-00009.safetensors",
+        "gpt_neox.layers.3.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+        "gpt_neox.layers.4.attention.bias": "model-00003-of-00009.safetensors",
+        "gpt_neox.layers.4.attention.dense.bias": "model-00003-of-00009.safetensors",
+        "gpt_neox.layers.4.attention.dense.weight": "model-00003-of-00009.safetensors",
+        "gpt_neox.layers.4.attention.masked_bias": "model-00003-of-00009.safetensors",
+        "gpt_neox.layers.4.attention.query_key_value.bias": "model-00003-of-00009.safetensors",
+        "gpt_neox.layers.4.attention.query_key_value.weight": "model-00003-of-00009.safetensors",
+        "gpt_neox.layers.4.attention.rotary_emb.inv_freq": "model-00003-of-00009.safetensors",
+        "gpt_neox.layers.4.input_layernorm.bias": "model-00003-of-00009.safetensors",
+        "gpt_neox.layers.4.input_layernorm.weight": "model-00003-of-00009.safetensors",
+        "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00003-of-00009.safetensors",
+        "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00003-of-00009.safetensors",
+        "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00003-of-00009.safetensors",
+        "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00003-of-00009.safetensors",
+        "gpt_neox.layers.4.post_attention_layernorm.bias": "model-00003-of-00009.safetensors",
+        "gpt_neox.layers.4.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+        "gpt_neox.layers.5.attention.bias": "model-00003-of-00009.safetensors",
+        "gpt_neox.layers.5.attention.dense.bias": "model-00003-of-00009.safetensors",
+        "gpt_neox.layers.5.attention.dense.weight": "model-00003-of-00009.safetensors",
+        "gpt_neox.layers.5.attention.masked_bias": "model-00003-of-00009.safetensors",
+        "gpt_neox.layers.5.attention.query_key_value.bias": "model-00003-of-00009.safetensors",
+        "gpt_neox.layers.5.attention.query_key_value.weight": "model-00003-of-00009.safetensors",
+        "gpt_neox.layers.5.attention.rotary_emb.inv_freq": "model-00003-of-00009.safetensors",
+        "gpt_neox.layers.5.input_layernorm.bias": "model-00003-of-00009.safetensors",
+        "gpt_neox.layers.5.input_layernorm.weight": "model-00003-of-00009.safetensors",
+        "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00004-of-00009.safetensors",
+        "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00004-of-00009.safetensors",
+        "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00004-of-00009.safetensors",
+        "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00004-of-00009.safetensors",
+        "gpt_neox.layers.5.post_attention_layernorm.bias": "model-00003-of-00009.safetensors",
+        "gpt_neox.layers.5.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+        "gpt_neox.layers.6.attention.bias": "model-00004-of-00009.safetensors",
+        "gpt_neox.layers.6.attention.dense.bias": "model-00004-of-00009.safetensors",
+        "gpt_neox.layers.6.attention.dense.weight": "model-00004-of-00009.safetensors",
+        "gpt_neox.layers.6.attention.masked_bias": "model-00004-of-00009.safetensors",
+        "gpt_neox.layers.6.attention.query_key_value.bias": "model-00004-of-00009.safetensors",
+        "gpt_neox.layers.6.attention.query_key_value.weight": "model-00004-of-00009.safetensors",
+        "gpt_neox.layers.6.attention.rotary_emb.inv_freq": "model-00004-of-00009.safetensors",
+        "gpt_neox.layers.6.input_layernorm.bias": "model-00004-of-00009.safetensors",
+        "gpt_neox.layers.6.input_layernorm.weight": "model-00004-of-00009.safetensors",
+        "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00004-of-00009.safetensors",
+        "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00004-of-00009.safetensors",
+        "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00004-of-00009.safetensors",
+        "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00004-of-00009.safetensors",
+        "gpt_neox.layers.6.post_attention_layernorm.bias": "model-00004-of-00009.safetensors",
+        "gpt_neox.layers.6.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+        "gpt_neox.layers.7.attention.bias": "model-00004-of-00009.safetensors",
+        "gpt_neox.layers.7.attention.dense.bias": "model-00004-of-00009.safetensors",
+        "gpt_neox.layers.7.attention.dense.weight": "model-00004-of-00009.safetensors",
+        "gpt_neox.layers.7.attention.masked_bias": "model-00004-of-00009.safetensors",
+        "gpt_neox.layers.7.attention.query_key_value.bias": "model-00004-of-00009.safetensors",
+        "gpt_neox.layers.7.attention.query_key_value.weight": "model-00004-of-00009.safetensors",
+        "gpt_neox.layers.7.attention.rotary_emb.inv_freq": "model-00004-of-00009.safetensors",
+        "gpt_neox.layers.7.input_layernorm.bias": "model-00004-of-00009.safetensors",
+        "gpt_neox.layers.7.input_layernorm.weight": "model-00004-of-00009.safetensors",
+        "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00005-of-00009.safetensors",
+        "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00005-of-00009.safetensors",
+        "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00005-of-00009.safetensors",
+        "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00005-of-00009.safetensors",
+        "gpt_neox.layers.7.post_attention_layernorm.bias": "model-00004-of-00009.safetensors",
+        "gpt_neox.layers.7.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+        "gpt_neox.layers.8.attention.bias": "model-00005-of-00009.safetensors",
+        "gpt_neox.layers.8.attention.dense.bias": "model-00005-of-00009.safetensors",
+        "gpt_neox.layers.8.attention.dense.weight": "model-00005-of-00009.safetensors",
+        "gpt_neox.layers.8.attention.masked_bias": "model-00005-of-00009.safetensors",
+        "gpt_neox.layers.8.attention.query_key_value.bias": "model-00005-of-00009.safetensors",
+        "gpt_neox.layers.8.attention.query_key_value.weight": "model-00005-of-00009.safetensors",
+        "gpt_neox.layers.8.attention.rotary_emb.inv_freq": "model-00005-of-00009.safetensors",
+        "gpt_neox.layers.8.input_layernorm.bias": "model-00005-of-00009.safetensors",
+        "gpt_neox.layers.8.input_layernorm.weight": "model-00005-of-00009.safetensors",
+        "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00005-of-00009.safetensors",
+        "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00005-of-00009.safetensors",
+        "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00005-of-00009.safetensors",
+        "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00005-of-00009.safetensors",
+        "gpt_neox.layers.8.post_attention_layernorm.bias": "model-00005-of-00009.safetensors",
+        "gpt_neox.layers.8.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+        "gpt_neox.layers.9.attention.bias": "model-00005-of-00009.safetensors",
+        "gpt_neox.layers.9.attention.dense.bias": "model-00005-of-00009.safetensors",
+        "gpt_neox.layers.9.attention.dense.weight": "model-00005-of-00009.safetensors",
+        "gpt_neox.layers.9.attention.masked_bias": "model-00005-of-00009.safetensors",
+        "gpt_neox.layers.9.attention.query_key_value.bias": "model-00005-of-00009.safetensors",
+        "gpt_neox.layers.9.attention.query_key_value.weight": "model-00005-of-00009.safetensors",
+        "gpt_neox.layers.9.attention.rotary_emb.inv_freq": "model-00005-of-00009.safetensors",
+        "gpt_neox.layers.9.input_layernorm.bias": "model-00005-of-00009.safetensors",
+        "gpt_neox.layers.9.input_layernorm.weight": "model-00005-of-00009.safetensors",
+        "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00006-of-00009.safetensors",
+        "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00006-of-00009.safetensors",
+        "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00006-of-00009.safetensors",
+        "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00006-of-00009.safetensors",
+        "gpt_neox.layers.9.post_attention_layernorm.bias": "model-00005-of-00009.safetensors",
+        "gpt_neox.layers.9.post_attention_layernorm.weight": "model-00005-of-00009.safetensors"
+    }
+}