Add sharded safetensors

model-00001-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b903093cb215236f2eb919777c3077978f1b29789ae10a20b1f18af45b54068e
+size 926101004

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc8ac893a4214c38b252172e966d7e6ead864f5f80c1bb11c0b154df98779941
+size 952365814

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39baaf4eeccbb0e1e75f2298bbbd1324b4738e4efb6855fb02383d88c87c7de1
+size 948162644

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eccaf367d55dde1989398b718e418acba475f6c4d3166f409093f1d65be85518
+size 948162412

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e3f339ee79d130296caac6a577b951d1da9acaabde01c2bdae586ac7fd6a66c
+size 952365830

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:187689223c1eb4a7dc5b94aa451996b53e41c4f75075de71887333cd55455692
+size 948162676

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a95347403712ca4f02c8cbd955942b00c78f6033416804c17e1e730a2b8acefc
+size 948162444

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac396358e0d568a909a6541d437cb0c1a430cacabf4a7fb827d84b50eb970244
+size 952365854

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e53a6496517e3564f45bf37e6ffe7317cfb870630dd539b0a5399c33cb54462
+size 948162676

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f1cd6bb25be55ae89350542d18e21b9bcc43027aab705294105f6ae3ccec966
+size 948162444

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc36b2f2a579e2028a1127a9332d2b223472bb887e8537a094823887c70fc591
+size 952365854

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c863063fdd54705ffedc2d9ce1dc545ddecd8c02b10a947331971a7a74053661
+size 948162676

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b116a5ac222f7f2e819368ccb12bd61eaee7f21169a8493638d48af94c17c2a
+size 514908960

model.safetensors.index.json

@@ -0,0 +1,431 @@
+{
+  "metadata": {
+    "total_size": 11784801848.0
+  },
+  "weight_map": {
+    "embed_out.weight": "model-00013-of-00013.safetensors",
+    "gpt_neox.embed_in.weight": "model-00001-of-00013.safetensors",
+    "gpt_neox.final_layer_norm.bias": "model-00013-of-00013.safetensors",
+    "gpt_neox.final_layer_norm.weight": "model-00013-of-00013.safetensors",
+    "gpt_neox.layers.0.attention.bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.attention.dense.bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.attention.dense.weight": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.attention.masked_bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.attention.rotary_emb.inv_freq": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.1.attention.bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.1.attention.dense.bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.1.attention.dense.weight": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.1.attention.masked_bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.1.attention.query_key_value.bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.1.attention.query_key_value.weight": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.1.attention.rotary_emb.inv_freq": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.1.input_layernorm.bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.1.input_layernorm.weight": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.10.attention.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.attention.dense.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.attention.dense.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.attention.masked_bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.attention.query_key_value.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.attention.query_key_value.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.attention.rotary_emb.inv_freq": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.input_layernorm.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.input_layernorm.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.post_attention_layernorm.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.11.attention.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.11.attention.dense.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.11.attention.dense.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.11.attention.masked_bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.11.attention.query_key_value.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.11.attention.query_key_value.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.11.input_layernorm.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.11.input_layernorm.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.11.post_attention_layernorm.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.11.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.12.attention.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.attention.dense.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.attention.dense.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.attention.masked_bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.attention.query_key_value.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.attention.query_key_value.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.input_layernorm.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.input_layernorm.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.post_attention_layernorm.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.13.attention.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.13.attention.dense.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.13.attention.dense.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.13.attention.masked_bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.13.attention.query_key_value.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.13.attention.query_key_value.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.13.input_layernorm.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.13.input_layernorm.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.13.post_attention_layernorm.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.13.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.14.attention.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.attention.dense.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.attention.dense.weight": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.attention.masked_bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.attention.query_key_value.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.attention.query_key_value.weight": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.input_layernorm.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.input_layernorm.weight": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.post_attention_layernorm.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.15.attention.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.15.attention.dense.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.15.attention.dense.weight": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.15.attention.masked_bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.15.attention.query_key_value.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.15.attention.query_key_value.weight": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.15.input_layernorm.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.15.input_layernorm.weight": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.15.post_attention_layernorm.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.15.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.16.attention.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.attention.dense.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.attention.dense.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.attention.masked_bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.attention.query_key_value.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.attention.query_key_value.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.attention.rotary_emb.inv_freq": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.input_layernorm.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.input_layernorm.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.post_attention_layernorm.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.attention.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.attention.dense.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.attention.dense.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.attention.masked_bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.attention.query_key_value.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.attention.query_key_value.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.attention.rotary_emb.inv_freq": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.input_layernorm.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.input_layernorm.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.post_attention_layernorm.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.18.attention.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.18.attention.dense.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.18.attention.dense.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.18.attention.masked_bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.18.attention.query_key_value.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.18.attention.query_key_value.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.18.attention.rotary_emb.inv_freq": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.18.input_layernorm.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.18.input_layernorm.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.18.post_attention_layernorm.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.18.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.19.attention.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.attention.dense.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.attention.dense.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.attention.masked_bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.attention.query_key_value.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.attention.query_key_value.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.attention.rotary_emb.inv_freq": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.input_layernorm.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.input_layernorm.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.post_attention_layernorm.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.2.attention.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.attention.dense.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.attention.dense.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.attention.masked_bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.attention.query_key_value.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.attention.query_key_value.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.attention.rotary_emb.inv_freq": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.input_layernorm.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.input_layernorm.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.post_attention_layernorm.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.20.attention.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.20.attention.dense.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.20.attention.dense.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.20.attention.masked_bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.20.attention.query_key_value.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.20.attention.query_key_value.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.20.attention.rotary_emb.inv_freq": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.20.input_layernorm.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.20.input_layernorm.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.20.post_attention_layernorm.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.20.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.21.attention.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.attention.dense.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.attention.dense.weight": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.attention.masked_bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.attention.query_key_value.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.attention.query_key_value.weight": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.attention.rotary_emb.inv_freq": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.input_layernorm.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.input_layernorm.weight": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.post_attention_layernorm.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.22.attention.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.22.attention.dense.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.22.attention.dense.weight": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.22.attention.masked_bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.22.attention.query_key_value.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.22.attention.query_key_value.weight": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.22.attention.rotary_emb.inv_freq": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.22.input_layernorm.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.22.input_layernorm.weight": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.22.post_attention_layernorm.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.22.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.23.attention.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.attention.dense.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.attention.dense.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.attention.masked_bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.attention.query_key_value.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.attention.query_key_value.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.attention.rotary_emb.inv_freq": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.input_layernorm.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.input_layernorm.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.post_attention_layernorm.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.attention.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.attention.dense.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.attention.dense.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.attention.masked_bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.attention.query_key_value.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.attention.query_key_value.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.attention.rotary_emb.inv_freq": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.input_layernorm.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.input_layernorm.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.post_attention_layernorm.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.25.attention.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.25.attention.dense.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.25.attention.dense.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.25.attention.masked_bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.25.attention.query_key_value.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.25.attention.query_key_value.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.25.attention.rotary_emb.inv_freq": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.25.input_layernorm.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.25.input_layernorm.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.25.post_attention_layernorm.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.25.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.26.attention.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.attention.dense.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.attention.dense.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.attention.masked_bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.attention.query_key_value.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.attention.query_key_value.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.attention.rotary_emb.inv_freq": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.input_layernorm.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.input_layernorm.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.post_attention_layernorm.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.27.attention.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.27.attention.dense.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.27.attention.dense.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.27.attention.masked_bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.27.attention.query_key_value.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.27.attention.query_key_value.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.27.attention.rotary_emb.inv_freq": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.27.input_layernorm.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.27.input_layernorm.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "model-00013-of-00013.safetensors",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "model-00013-of-00013.safetensors",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "model-00013-of-00013.safetensors",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "model-00013-of-00013.safetensors",
+    "gpt_neox.layers.27.post_attention_layernorm.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.27.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.3.attention.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.attention.dense.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.attention.dense.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.attention.masked_bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.attention.query_key_value.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.attention.query_key_value.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.attention.rotary_emb.inv_freq": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.input_layernorm.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.input_layernorm.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.post_attention_layernorm.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.4.attention.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.4.attention.dense.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.4.attention.dense.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.4.attention.masked_bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.4.attention.query_key_value.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.4.attention.query_key_value.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.4.attention.rotary_emb.inv_freq": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.4.input_layernorm.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.4.input_layernorm.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.4.post_attention_layernorm.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.4.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.5.attention.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.attention.dense.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.attention.dense.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.attention.masked_bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.attention.query_key_value.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.attention.query_key_value.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.attention.rotary_emb.inv_freq": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.input_layernorm.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.input_layernorm.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.post_attention_layernorm.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.6.attention.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.6.attention.dense.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.6.attention.dense.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.6.attention.masked_bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.6.attention.query_key_value.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.6.attention.query_key_value.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.6.attention.rotary_emb.inv_freq": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.6.input_layernorm.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.6.input_layernorm.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.6.post_attention_layernorm.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.6.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.7.attention.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.attention.dense.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.attention.dense.weight": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.attention.masked_bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.attention.query_key_value.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.attention.query_key_value.weight": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.attention.rotary_emb.inv_freq": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.input_layernorm.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.input_layernorm.weight": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.post_attention_layernorm.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.8.attention.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.8.attention.dense.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.8.attention.dense.weight": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.8.attention.masked_bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.8.attention.query_key_value.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.8.attention.query_key_value.weight": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.8.attention.rotary_emb.inv_freq": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.8.input_layernorm.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.8.input_layernorm.weight": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.8.post_attention_layernorm.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.8.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.9.attention.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.attention.dense.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.attention.dense.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.attention.masked_bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.attention.query_key_value.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.attention.query_key_value.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.attention.rotary_emb.inv_freq": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.input_layernorm.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.input_layernorm.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.post_attention_layernorm.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.post_attention_layernorm.weight": "model-00005-of-00013.safetensors"
+  }
+}