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-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fb07c96dce8c80b13605720f09f12c79545f017ca9e5c3e29c25a6c0d8d4a24
+size 3796687888

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e100cd82dc15f21429983315bf8610b256c0af17507115af4adfd26aee0809ec
+size 3780076204

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:500818803a15e1d567d67b27d14289b18bc0acaf03c446f94701fc8eefe48695
+size 3981451988

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:293b0a7a8d32b54d6367034304a7a24158fd11d81c2dcaaf093ab5442da4608d
+size 3847201500

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bc652a69a3e708fb0fc196f6c14c5e7232dd18b51ea28c54a99be177cb21422
+size 3775864704

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a88f9cb4128e66b2a3a9d8d905b1fcb87798244c8d713ed22d278c0adfe3af3f
+size 3780076276

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdd4490b07dadcdf8a3afa83239af2a5d385b9edd097aaa9bdc0b76637738eff
+size 3775848264

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fadfd2e65a6e79cc6124872d4b4f34b07860b0bac2c754d4aa397f2f799bd5be
+size 826278016

model.safetensors.index.json

@@ -0,0 +1,491 @@
+{
+    "metadata": {
+        "total_size": 27563427968
+    },
+    "weight_map": {
+        "embed_out.weight": "model-00008-of-00008.safetensors",
+        "gpt_neox.embed_in.weight": "model-00001-of-00008.safetensors",
+        "gpt_neox.final_layer_norm.bias": "model-00007-of-00008.safetensors",
+        "gpt_neox.final_layer_norm.weight": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.0.attention.bias": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.0.attention.dense.bias": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.0.attention.dense.weight": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.0.attention.masked_bias": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.0.attention.rotary_emb.inv_freq": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.1.attention.bias": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.1.attention.dense.bias": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.1.attention.dense.weight": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.1.attention.masked_bias": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.1.attention.query_key_value.bias": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.1.attention.query_key_value.weight": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.1.attention.rotary_emb.inv_freq": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.1.input_layernorm.bias": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.10.attention.bias": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.10.attention.dense.bias": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.10.attention.dense.weight": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.10.attention.masked_bias": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.10.attention.query_key_value.bias": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.10.attention.query_key_value.weight": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.10.attention.rotary_emb.inv_freq": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.10.input_layernorm.bias": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.10.input_layernorm.weight": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.10.post_attention_layernorm.bias": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.10.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.11.attention.bias": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.11.attention.dense.bias": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.11.attention.dense.weight": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.11.attention.masked_bias": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.11.attention.query_key_value.bias": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.11.attention.query_key_value.weight": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.11.input_layernorm.bias": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.11.input_layernorm.weight": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.11.post_attention_layernorm.bias": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.11.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.12.attention.bias": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.12.attention.dense.bias": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.12.attention.dense.weight": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.12.attention.masked_bias": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.12.attention.query_key_value.bias": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.12.attention.query_key_value.weight": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.12.input_layernorm.bias": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.12.input_layernorm.weight": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.12.post_attention_layernorm.bias": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.12.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.13.attention.bias": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.13.attention.dense.bias": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.13.attention.dense.weight": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.13.attention.masked_bias": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.13.attention.query_key_value.bias": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.13.attention.query_key_value.weight": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.13.input_layernorm.bias": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.13.input_layernorm.weight": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.13.post_attention_layernorm.bias": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.13.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.14.attention.bias": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.14.attention.dense.bias": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.14.attention.dense.weight": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.14.attention.masked_bias": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.14.attention.query_key_value.bias": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.14.attention.query_key_value.weight": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.14.input_layernorm.bias": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.14.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.14.post_attention_layernorm.bias": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.14.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.15.attention.bias": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.15.attention.dense.bias": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.15.attention.dense.weight": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.15.attention.masked_bias": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.15.attention.query_key_value.bias": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.15.attention.query_key_value.weight": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.15.input_layernorm.bias": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.15.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.15.post_attention_layernorm.bias": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.15.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.16.attention.bias": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.16.attention.dense.bias": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.16.attention.dense.weight": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.16.attention.masked_bias": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.16.attention.query_key_value.bias": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.16.attention.query_key_value.weight": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.16.attention.rotary_emb.inv_freq": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.16.input_layernorm.bias": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.16.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.16.post_attention_layernorm.bias": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.16.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.17.attention.bias": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.17.attention.dense.bias": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.17.attention.dense.weight": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.17.attention.masked_bias": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.17.attention.query_key_value.bias": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.17.attention.query_key_value.weight": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.17.attention.rotary_emb.inv_freq": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.17.input_layernorm.bias": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.17.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.17.post_attention_layernorm.bias": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.17.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.18.attention.bias": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.18.attention.dense.bias": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.18.attention.dense.weight": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.18.attention.masked_bias": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.18.attention.query_key_value.bias": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.18.attention.query_key_value.weight": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.18.attention.rotary_emb.inv_freq": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.18.input_layernorm.bias": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.18.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.18.post_attention_layernorm.bias": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.18.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+        "gpt_neox.layers.19.attention.bias": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.19.attention.dense.bias": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.19.attention.dense.weight": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.19.attention.masked_bias": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.19.attention.query_key_value.bias": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.19.attention.query_key_value.weight": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.19.attention.rotary_emb.inv_freq": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.19.input_layernorm.bias": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.19.input_layernorm.weight": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.19.post_attention_layernorm.bias": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.19.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.2.attention.bias": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.2.attention.dense.bias": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.2.attention.dense.weight": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.2.attention.masked_bias": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.2.attention.query_key_value.bias": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.2.attention.query_key_value.weight": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.2.attention.rotary_emb.inv_freq": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.2.input_layernorm.bias": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.2.post_attention_layernorm.bias": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.2.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.20.attention.bias": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.20.attention.dense.bias": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.20.attention.dense.weight": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.20.attention.masked_bias": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.20.attention.query_key_value.bias": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.20.attention.query_key_value.weight": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.20.attention.rotary_emb.inv_freq": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.20.input_layernorm.bias": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.20.input_layernorm.weight": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.20.post_attention_layernorm.bias": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.20.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.21.attention.bias": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.21.attention.dense.bias": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.21.attention.dense.weight": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.21.attention.masked_bias": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.21.attention.query_key_value.bias": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.21.attention.query_key_value.weight": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.21.attention.rotary_emb.inv_freq": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.21.input_layernorm.bias": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.21.input_layernorm.weight": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.21.post_attention_layernorm.bias": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.21.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.22.attention.bias": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.22.attention.dense.bias": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.22.attention.dense.weight": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.22.attention.masked_bias": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.22.attention.query_key_value.bias": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.22.attention.query_key_value.weight": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.22.attention.rotary_emb.inv_freq": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.22.input_layernorm.bias": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.22.input_layernorm.weight": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.22.post_attention_layernorm.bias": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.22.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+        "gpt_neox.layers.23.attention.bias": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.23.attention.dense.bias": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.23.attention.dense.weight": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.23.attention.masked_bias": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.23.attention.query_key_value.bias": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.23.attention.query_key_value.weight": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.23.attention.rotary_emb.inv_freq": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.23.input_layernorm.bias": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.23.input_layernorm.weight": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.23.post_attention_layernorm.bias": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.23.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.24.attention.bias": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.24.attention.dense.bias": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.24.attention.dense.weight": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.24.attention.masked_bias": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.24.attention.query_key_value.bias": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.24.attention.query_key_value.weight": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.24.attention.rotary_emb.inv_freq": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.24.input_layernorm.bias": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.24.input_layernorm.weight": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.24.post_attention_layernorm.bias": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.24.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.25.attention.bias": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.25.attention.dense.bias": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.25.attention.dense.weight": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.25.attention.masked_bias": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.25.attention.query_key_value.bias": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.25.attention.query_key_value.weight": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.25.attention.rotary_emb.inv_freq": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.25.input_layernorm.bias": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.25.input_layernorm.weight": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.25.post_attention_layernorm.bias": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.25.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.26.attention.bias": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.26.attention.dense.bias": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.26.attention.dense.weight": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.26.attention.masked_bias": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.26.attention.query_key_value.bias": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.26.attention.query_key_value.weight": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.26.attention.rotary_emb.inv_freq": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.26.input_layernorm.bias": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.26.input_layernorm.weight": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.26.post_attention_layernorm.bias": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.26.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.27.attention.bias": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.27.attention.dense.bias": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.27.attention.dense.weight": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.27.attention.masked_bias": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.27.attention.query_key_value.bias": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.27.attention.query_key_value.weight": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.27.attention.rotary_emb.inv_freq": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.27.input_layernorm.bias": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.27.input_layernorm.weight": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.27.post_attention_layernorm.bias": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.27.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+        "gpt_neox.layers.28.attention.bias": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.28.attention.dense.bias": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.28.attention.dense.weight": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.28.attention.masked_bias": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.28.attention.query_key_value.bias": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.28.attention.query_key_value.weight": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.28.attention.rotary_emb.inv_freq": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.28.input_layernorm.bias": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.28.input_layernorm.weight": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.28.post_attention_layernorm.bias": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.28.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.29.attention.bias": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.29.attention.dense.bias": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.29.attention.dense.weight": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.29.attention.masked_bias": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.29.attention.query_key_value.bias": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.29.attention.query_key_value.weight": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.29.attention.rotary_emb.inv_freq": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.29.input_layernorm.bias": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.29.input_layernorm.weight": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.29.post_attention_layernorm.bias": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.29.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.3.attention.bias": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.3.attention.dense.bias": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.3.attention.dense.weight": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.3.attention.masked_bias": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.3.attention.query_key_value.bias": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.3.attention.query_key_value.weight": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.3.attention.rotary_emb.inv_freq": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.3.input_layernorm.bias": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.3.input_layernorm.weight": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.3.post_attention_layernorm.bias": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.3.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+        "gpt_neox.layers.30.attention.bias": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.30.attention.dense.bias": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.30.attention.dense.weight": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.30.attention.masked_bias": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.30.attention.query_key_value.bias": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.30.attention.query_key_value.weight": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.30.attention.rotary_emb.inv_freq": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.30.input_layernorm.bias": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.30.input_layernorm.weight": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.30.post_attention_layernorm.bias": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.30.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.31.attention.bias": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.31.attention.dense.bias": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.31.attention.dense.weight": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.31.attention.masked_bias": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.31.attention.query_key_value.bias": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.31.attention.query_key_value.weight": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.31.attention.rotary_emb.inv_freq": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.31.input_layernorm.bias": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.31.input_layernorm.weight": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.31.post_attention_layernorm.bias": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.31.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+        "gpt_neox.layers.4.attention.bias": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.4.attention.dense.bias": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.4.attention.dense.weight": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.4.attention.masked_bias": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.4.attention.query_key_value.bias": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.4.attention.query_key_value.weight": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.4.attention.rotary_emb.inv_freq": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.4.input_layernorm.bias": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.4.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.4.post_attention_layernorm.bias": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.4.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.5.attention.bias": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.5.attention.dense.bias": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.5.attention.dense.weight": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.5.attention.masked_bias": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.5.attention.query_key_value.bias": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.5.attention.query_key_value.weight": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.5.attention.rotary_emb.inv_freq": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.5.input_layernorm.bias": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.5.post_attention_layernorm.bias": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.6.attention.bias": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.6.attention.dense.bias": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.6.attention.dense.weight": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.6.attention.masked_bias": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.6.attention.query_key_value.bias": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.6.attention.query_key_value.weight": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.6.attention.rotary_emb.inv_freq": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.6.input_layernorm.bias": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.6.post_attention_layernorm.bias": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.7.attention.bias": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.7.attention.dense.bias": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.7.attention.dense.weight": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.7.attention.masked_bias": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.7.attention.query_key_value.bias": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.7.attention.query_key_value.weight": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.7.attention.rotary_emb.inv_freq": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.7.input_layernorm.bias": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.7.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.7.post_attention_layernorm.bias": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.7.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.8.attention.bias": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.8.attention.dense.bias": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.8.attention.dense.weight": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.8.attention.masked_bias": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.8.attention.query_key_value.bias": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.8.attention.query_key_value.weight": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.8.attention.rotary_emb.inv_freq": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.8.input_layernorm.bias": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.8.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.8.post_attention_layernorm.bias": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.8.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+        "gpt_neox.layers.9.attention.bias": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.9.attention.dense.bias": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.9.attention.dense.weight": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.9.attention.masked_bias": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.9.attention.query_key_value.bias": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.9.attention.query_key_value.weight": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.9.attention.rotary_emb.inv_freq": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.9.input_layernorm.bias": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.9.input_layernorm.weight": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.9.post_attention_layernorm.bias": "model-00003-of-00008.safetensors",
+        "gpt_neox.layers.9.post_attention_layernorm.weight": "model-00003-of-00008.safetensors"
+    }
+}