Adding `safetensors` variant of this model

This is an automated PR created with https://huggingface.co/spaces/safetensors/convert

This new file is equivalent to `pytorch_model.bin` but safe in the sense that
no arbitrary code can be put into it.

These files also happen to load much faster than their pytorch counterpart:
https://colab.research.google.com/github/huggingface/notebooks/blob/main/safetensors_doc/en/speed.ipynb

The widgets on your model page will run using this model even if this is not merged
making sure the file actually works.

If you find any issues: please report here: https://huggingface.co/spaces/safetensors/convert/discussions

Feel free to ignore this PR.

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fefb78ce18280024551f2491fe3b6a9615d7ea21f884cbb09485d66123f6599
+size 9931091640

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:900cda90af195ffe802592b4314a4f49684d75eec370a3519529fda87986274e
+size 9753839408

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19fce3252b009816b3d3f8c014fe2a6b9ec21e63f1cddc400bf5fdddc8825437
+size 9648940064

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a47207cf15a80b61fbcd7416cffce9beb49b02e1e7baa705f38df7c4e71800f
+size 9648961384

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4755c150b03e72eac83aefea880651f1037b2a357091d691bc0a5b2de1d28d61
+size 9963595640

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe35d4bda45f4922919a268f83b8234395a19627fbacb41f6610164cef4ea1e6
+size 5526020648

model.safetensors.index.json

@@ -0,0 +1,531 @@
+{
+    "metadata": {
+        "total_size": 54472386560
+    },
+    "weight_map": {
+        "embed_out.weight": "model-00006-of-00006.safetensors",
+        "gpt_neox.embed_in.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.final_layer_norm.bias": "model-00006-of-00006.safetensors",
+        "gpt_neox.final_layer_norm.weight": "model-00006-of-00006.safetensors",
+        "gpt_neox.layers.0.attention.dense.bias": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.0.attention.dense.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.0.attention.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.1.attention.dense.bias": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.1.attention.dense.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.1.attention.query_key_value.bias": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.1.attention.query_key_value.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.1.attention.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.1.input_layernorm.bias": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.10.attention.dense.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.10.attention.dense.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.10.attention.query_key_value.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.10.attention.query_key_value.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.10.attention.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.10.input_layernorm.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.10.post_attention_layernorm.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.11.attention.dense.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.11.attention.dense.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.11.attention.query_key_value.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.11.attention.query_key_value.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.11.input_layernorm.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.11.post_attention_layernorm.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.12.attention.dense.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.12.attention.dense.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.12.attention.query_key_value.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.12.attention.query_key_value.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.12.input_layernorm.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.12.post_attention_layernorm.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.13.attention.dense.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.13.attention.dense.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.13.attention.query_key_value.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.13.attention.query_key_value.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.13.input_layernorm.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.13.post_attention_layernorm.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.14.attention.dense.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.14.attention.dense.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.14.attention.query_key_value.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.14.attention.query_key_value.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.14.input_layernorm.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.14.post_attention_layernorm.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.15.attention.dense.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.15.attention.dense.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.15.attention.query_key_value.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.15.attention.query_key_value.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.15.input_layernorm.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.15.post_attention_layernorm.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.16.attention.dense.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.16.attention.dense.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.16.attention.query_key_value.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.16.attention.query_key_value.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.16.attention.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.16.input_layernorm.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.16.post_attention_layernorm.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.17.attention.dense.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.17.attention.dense.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.17.attention.query_key_value.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.17.attention.query_key_value.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.17.attention.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.17.input_layernorm.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.17.post_attention_layernorm.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.18.attention.dense.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.18.attention.dense.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.18.attention.query_key_value.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.18.attention.query_key_value.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.18.attention.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.18.input_layernorm.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.18.post_attention_layernorm.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.19.attention.dense.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.19.attention.dense.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.19.attention.query_key_value.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.19.attention.query_key_value.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.19.attention.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.19.input_layernorm.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.19.post_attention_layernorm.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.2.attention.dense.bias": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.2.attention.dense.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.2.attention.query_key_value.bias": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.2.attention.query_key_value.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.2.attention.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.2.input_layernorm.bias": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.2.post_attention_layernorm.bias": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.20.attention.dense.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.20.attention.dense.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.20.attention.query_key_value.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.20.attention.query_key_value.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.20.attention.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.20.input_layernorm.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.20.post_attention_layernorm.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.21.attention.dense.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.21.attention.dense.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.21.attention.query_key_value.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.21.attention.query_key_value.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.21.attention.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.21.input_layernorm.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.21.post_attention_layernorm.bias": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "gpt_neox.layers.22.attention.dense.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.22.attention.dense.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.22.attention.query_key_value.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.22.attention.query_key_value.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.22.attention.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.22.input_layernorm.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.22.post_attention_layernorm.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.23.attention.dense.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.23.attention.dense.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.23.attention.query_key_value.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.23.attention.query_key_value.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.23.attention.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.23.input_layernorm.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.23.post_attention_layernorm.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.24.attention.dense.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.24.attention.dense.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.24.attention.query_key_value.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.24.attention.query_key_value.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.24.attention.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.24.input_layernorm.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.24.post_attention_layernorm.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.25.attention.dense.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.25.attention.dense.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.25.attention.query_key_value.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.25.attention.query_key_value.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.25.attention.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.25.input_layernorm.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.25.post_attention_layernorm.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.26.attention.dense.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.26.attention.dense.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.26.attention.query_key_value.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.26.attention.query_key_value.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.26.attention.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.26.input_layernorm.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.26.post_attention_layernorm.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.27.attention.dense.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.27.attention.dense.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.27.attention.query_key_value.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.27.attention.query_key_value.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.27.attention.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.27.input_layernorm.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.27.post_attention_layernorm.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.28.attention.dense.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.28.attention.dense.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.28.attention.query_key_value.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.28.attention.query_key_value.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.28.attention.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.28.input_layernorm.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.28.post_attention_layernorm.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.29.attention.dense.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.29.attention.dense.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.29.attention.query_key_value.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.29.attention.query_key_value.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.29.attention.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.29.input_layernorm.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.29.post_attention_layernorm.bias": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "gpt_neox.layers.3.attention.dense.bias": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.3.attention.dense.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.3.attention.query_key_value.bias": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.3.attention.query_key_value.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.3.attention.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.3.input_layernorm.bias": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.3.post_attention_layernorm.bias": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.30.attention.dense.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.30.attention.dense.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.30.attention.query_key_value.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.30.attention.query_key_value.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.30.attention.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.30.input_layernorm.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.30.post_attention_layernorm.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.31.attention.dense.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.31.attention.dense.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.31.attention.query_key_value.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.31.attention.query_key_value.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.31.attention.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.31.input_layernorm.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.31.post_attention_layernorm.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.32.attention.dense.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.32.attention.dense.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.32.attention.query_key_value.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.32.attention.query_key_value.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.32.attention.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.32.input_layernorm.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.32.mlp.dense_4h_to_h.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.32.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.32.mlp.dense_h_to_4h.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.32.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.32.post_attention_layernorm.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.33.attention.dense.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.33.attention.dense.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.33.attention.query_key_value.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.33.attention.query_key_value.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.33.attention.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.33.input_layernorm.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.33.mlp.dense_4h_to_h.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.33.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.33.mlp.dense_h_to_4h.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.33.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.33.post_attention_layernorm.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.34.attention.dense.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.34.attention.dense.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.34.attention.query_key_value.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.34.attention.query_key_value.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.34.attention.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.34.input_layernorm.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.34.mlp.dense_4h_to_h.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.34.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.34.mlp.dense_h_to_4h.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.34.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.34.post_attention_layernorm.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.35.attention.dense.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.35.attention.dense.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.35.attention.query_key_value.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.35.attention.query_key_value.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.35.attention.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.35.input_layernorm.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.35.mlp.dense_4h_to_h.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.35.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.35.mlp.dense_h_to_4h.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.35.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.35.post_attention_layernorm.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.36.attention.dense.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.36.attention.dense.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.36.attention.query_key_value.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.36.attention.query_key_value.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.36.attention.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.36.input_layernorm.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.36.mlp.dense_4h_to_h.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.36.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.36.mlp.dense_h_to_4h.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.36.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.36.post_attention_layernorm.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.37.attention.dense.bias": "model-00006-of-00006.safetensors",
+        "gpt_neox.layers.37.attention.dense.weight": "model-00006-of-00006.safetensors",
+        "gpt_neox.layers.37.attention.query_key_value.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.37.attention.query_key_value.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.37.attention.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.37.input_layernorm.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.37.mlp.dense_4h_to_h.bias": "model-00006-of-00006.safetensors",
+        "gpt_neox.layers.37.mlp.dense_4h_to_h.weight": "model-00006-of-00006.safetensors",
+        "gpt_neox.layers.37.mlp.dense_h_to_4h.bias": "model-00006-of-00006.safetensors",
+        "gpt_neox.layers.37.mlp.dense_h_to_4h.weight": "model-00006-of-00006.safetensors",
+        "gpt_neox.layers.37.post_attention_layernorm.bias": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "gpt_neox.layers.38.attention.dense.bias": "model-00006-of-00006.safetensors",
+        "gpt_neox.layers.38.attention.dense.weight": "model-00006-of-00006.safetensors",
+        "gpt_neox.layers.38.attention.query_key_value.bias": "model-00006-of-00006.safetensors",
+        "gpt_neox.layers.38.attention.query_key_value.weight": "model-00006-of-00006.safetensors",
+        "gpt_neox.layers.38.attention.rotary_emb.inv_freq": "model-00006-of-00006.safetensors",
+        "gpt_neox.layers.38.input_layernorm.bias": "model-00006-of-00006.safetensors",
+        "gpt_neox.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
+        "gpt_neox.layers.38.mlp.dense_4h_to_h.bias": "model-00006-of-00006.safetensors",
+        "gpt_neox.layers.38.mlp.dense_4h_to_h.weight": "model-00006-of-00006.safetensors",
+        "gpt_neox.layers.38.mlp.dense_h_to_4h.bias": "model-00006-of-00006.safetensors",
+        "gpt_neox.layers.38.mlp.dense_h_to_4h.weight": "model-00006-of-00006.safetensors",
+        "gpt_neox.layers.38.post_attention_layernorm.bias": "model-00006-of-00006.safetensors",
+        "gpt_neox.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+        "gpt_neox.layers.39.attention.dense.bias": "model-00006-of-00006.safetensors",
+        "gpt_neox.layers.39.attention.dense.weight": "model-00006-of-00006.safetensors",
+        "gpt_neox.layers.39.attention.query_key_value.bias": "model-00006-of-00006.safetensors",
+        "gpt_neox.layers.39.attention.query_key_value.weight": "model-00006-of-00006.safetensors",
+        "gpt_neox.layers.39.attention.rotary_emb.inv_freq": "model-00006-of-00006.safetensors",
+        "gpt_neox.layers.39.input_layernorm.bias": "model-00006-of-00006.safetensors",
+        "gpt_neox.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
+        "gpt_neox.layers.39.mlp.dense_4h_to_h.bias": "model-00006-of-00006.safetensors",
+        "gpt_neox.layers.39.mlp.dense_4h_to_h.weight": "model-00006-of-00006.safetensors",
+        "gpt_neox.layers.39.mlp.dense_h_to_4h.bias": "model-00006-of-00006.safetensors",
+        "gpt_neox.layers.39.mlp.dense_h_to_4h.weight": "model-00006-of-00006.safetensors",
+        "gpt_neox.layers.39.post_attention_layernorm.bias": "model-00006-of-00006.safetensors",
+        "gpt_neox.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+        "gpt_neox.layers.4.attention.dense.bias": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.4.attention.dense.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.4.attention.query_key_value.bias": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.4.attention.query_key_value.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.4.attention.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.4.input_layernorm.bias": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.4.post_attention_layernorm.bias": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.5.attention.dense.bias": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.5.attention.dense.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.5.attention.query_key_value.bias": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.5.attention.query_key_value.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.5.attention.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.5.input_layernorm.bias": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.5.post_attention_layernorm.bias": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.6.attention.dense.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.6.attention.dense.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.6.attention.query_key_value.bias": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.6.attention.query_key_value.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.6.attention.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.6.input_layernorm.bias": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.6.input_layernorm.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.6.post_attention_layernorm.bias": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.6.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+        "gpt_neox.layers.7.attention.dense.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.7.attention.dense.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.7.attention.query_key_value.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.7.attention.query_key_value.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.7.attention.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.7.input_layernorm.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.7.post_attention_layernorm.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.8.attention.dense.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.8.attention.dense.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.8.attention.query_key_value.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.8.attention.query_key_value.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.8.attention.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.8.input_layernorm.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.8.post_attention_layernorm.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.9.attention.dense.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.9.attention.dense.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.9.attention.query_key_value.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.9.attention.query_key_value.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.9.attention.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.9.input_layernorm.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.9.post_attention_layernorm.bias": "model-00002-of-00006.safetensors",
+        "gpt_neox.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors"
+    }
+}