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-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac794a96269060d7deafd0bc9d6af9266fb8fa28590246ecf56059b1001a9ee4
+size 9780601660

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfc0e676760f8b035e1a55f49192dc85d4fd48622f9474735937d70beea7190a
+size 9766070208

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5746e89ca6296c87fa7e9776c63aeda716ae8f8b4a5c560a730e3faf8923dc50
+size 9749267932

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46c362b2aa27420049002a1ca2224f4a58fb40190f87eeabdf765a0c1b773045
+size 2447549224

model.safetensors.index.json

@@ -0,0 +1,251 @@
+{
+    "metadata": {
+        "total_size": 31508579392.0
+    },
+    "weight_map": {
+        "embed_out.weight": "model-00004-of-00004.safetensors",
+        "gpt_neox.embed_in.weight": "model-00001-of-00004.safetensors",
+        "gpt_neox.final_layer_norm.bias": "model-00004-of-00004.safetensors",
+        "gpt_neox.final_layer_norm.weight": "model-00004-of-00004.safetensors",
+        "gpt_neox.layers.0.attention.bias": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.0.attention.dense.bias": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.0.attention.dense.weight": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.0.attention.masked_bias": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.0.attention.rotary_emb.inv_freq": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.1.attention.bias": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.1.attention.dense.bias": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.1.attention.dense.weight": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.1.attention.masked_bias": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.1.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.1.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.1.attention.rotary_emb.inv_freq": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.1.input_layernorm.bias": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.10.attention.bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.10.attention.dense.bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.10.attention.dense.weight": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.10.attention.masked_bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.10.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.10.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.10.attention.rotary_emb.inv_freq": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.10.input_layernorm.bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.10.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.11.attention.bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.11.attention.dense.bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.11.attention.dense.weight": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.11.attention.masked_bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.11.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.11.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.11.input_layernorm.bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.11.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.12.attention.bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.12.attention.dense.bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.12.attention.dense.weight": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.12.attention.masked_bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.12.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.12.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.12.input_layernorm.bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.12.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.13.attention.bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.13.attention.dense.bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.13.attention.dense.weight": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.13.attention.masked_bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.13.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.13.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.13.input_layernorm.bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.13.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.14.attention.bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.14.attention.dense.bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.14.attention.dense.weight": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.14.attention.masked_bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.14.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.14.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.14.input_layernorm.bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.14.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.15.attention.bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.15.attention.dense.bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.15.attention.dense.weight": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.15.attention.masked_bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.15.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.15.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.15.input_layernorm.bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00004-of-00004.safetensors",
+        "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
+        "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00004-of-00004.safetensors",
+        "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
+        "gpt_neox.layers.15.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "gpt_neox.layers.2.attention.bias": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.2.attention.dense.bias": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.2.attention.dense.weight": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.2.attention.masked_bias": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.2.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.2.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.2.attention.rotary_emb.inv_freq": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.2.input_layernorm.bias": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.2.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.3.attention.bias": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.3.attention.dense.bias": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.3.attention.dense.weight": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.3.attention.masked_bias": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.3.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.3.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.3.attention.rotary_emb.inv_freq": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.3.input_layernorm.bias": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.3.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.4.attention.bias": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.4.attention.dense.bias": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.4.attention.dense.weight": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.4.attention.masked_bias": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.4.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.4.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.4.attention.rotary_emb.inv_freq": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.4.input_layernorm.bias": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.4.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "gpt_neox.layers.5.attention.bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.5.attention.dense.bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.5.attention.dense.weight": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.5.attention.masked_bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.5.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.5.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.5.attention.rotary_emb.inv_freq": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.5.input_layernorm.bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.5.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.6.attention.bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.6.attention.dense.bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.6.attention.dense.weight": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.6.attention.masked_bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.6.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.6.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.6.attention.rotary_emb.inv_freq": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.6.input_layernorm.bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.6.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.7.attention.bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.7.attention.dense.bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.7.attention.dense.weight": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.7.attention.masked_bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.7.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.7.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.7.attention.rotary_emb.inv_freq": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.7.input_layernorm.bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.7.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.8.attention.bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.8.attention.dense.bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.8.attention.dense.weight": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.8.attention.masked_bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.8.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.8.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.8.attention.rotary_emb.inv_freq": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.8.input_layernorm.bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.8.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.9.attention.bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.9.attention.dense.bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.9.attention.dense.weight": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.9.attention.masked_bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.9.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.9.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.9.attention.rotary_emb.inv_freq": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.9.input_layernorm.bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.9.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+        "gpt_neox.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors"
+    }
+}