Adding `safetensors` variant of this model

model-00001-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cde250d0fb50e7b015bd34fe131b3b53d9d80216b252d90174421db8e0c61a42
+size 843121636

model-00002-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:080b2c9c7b746b00661afafe3f8f2fdd0ce937a0693751661c326fbc35ebff4d
+size 822298396

model-00003-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a79a9b47ccbdd7bc02d528fc8265929f7e697315164cd50e64c1e24a3f610bd3
+size 822298396

model-00004-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c53825aa6fb2e080c277ac7744e07009f4a88a489bc4ff3666c14dd1f6323cf9
+size 822298396

model-00005-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc93e94316ed7830c8f7b77de1c72991ce6235df047c6fcf4c3a2a25cdbadfab
+size 822298396

model-00006-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:503216482a9e1a273441f7f63cab47f821e91511c9cad880bb1586748efb1ee4
+size 822298396

model-00007-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3adaa85c15d1d3b3e4bb841b998ca920668ad1df944ed485faed484f687e98cb
+size 822298396

model-00008-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0681ee8cc9f9543419951e3f4b073f3e79f0717c9033dbdde0b2fdbccf7bfb7
+size 822298396

model-00009-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f86c5e882d19efd2424713d085ad1842ee7449da30e4c9625fb4ab5709d1c761
+size 822298396

model-00010-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b122a7bf7eb7ad0587238dc7e50060e31b3c6b5b45af560d5ad7cca4673aa5f8
+size 822298396

model-00011-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11c33e0cbff34e767dcf28f86605d7ed4848786f9328477073d1883ae4d183ee
+size 822298340

model-00012-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31c96cd3262d8451b3c8610c331a8d1fe07af597daf6d6d8ae667bdefe0f3169
+size 822298412

model-00013-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:170a5f7a968f5111d734c1ffa8c6f25d1dcd29e7ecf48bb6489d57b4ba17b573
+size 822298412

model-00014-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3db140445495db01d82bcea3f62d4c4fa729eaf0347f8ea0ad64e6225ca00c1a
+size 822298412

model-00015-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce1d98356ba5777c648cc5509a9de60c95696f9e59c373deb61edb7c94d039f7
+size 822298412

model-00016-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:970920e0f42cf577c86715f29aa24505ea4a436540768084f5bd8737ab12eafe
+size 822298412

model-00017-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b265c6298e104f04a894f26e09f7cf1aa6db79424435209177c9f12801cea18c
+size 822298412

model-00018-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38836c04550a20bac833b9e35bba3ac5a43d68c5d3be433242bd0b1dbd71398d
+size 822298412

model-00019-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd0ed792a61a110caeb7e06a1110dd643dd3269ccd9d60cc66d181ad5a46fd21
+size 822298412

model-00020-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa7d2e69af0f911244c18898218657ef6bdaab161b9c289787e8ba623741325f
+size 822298412

model-00021-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2f4bb971ff73ea8bc6cf2fdf7913d8ad892e4aad6aaf00c67e026b8361a54e8
+size 822298412

model-00022-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ea17e64face53b935bdf3285237b796617a5c796fe1d64481e8525a6c99a74f
+size 822298412

model-00023-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffeff8257daf413a27221d7690fb1a277298ceacb14578262717c4e271b5235d
+size 822298412

model-00024-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ee509e53147f4e02b887fb791d0544ffe1029d927f202b092eb81674c3f3b71
+size 822298412

model-00025-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf0729849389082482d193682e4a9585e7e52ebabb9a1c158cfbf52fd8101c5c
+size 822298412

model-00026-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eb8c03d88a535a3a7c698456629f3cacc7eec432d8240b8725b504f58081e81
+size 822298412

model-00027-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d22a1c9aac479f5123942f223cd54093884a5fdd2e45413d1e544cd59fb6047
+size 822298412

model-00028-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0175dfa6d512c7760c8d21dc3f3264d2b4e76b6f954b89b691f068212f8f411a
+size 822298412

model-00029-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f455a2faf8e5a95232b6f733248a9802b920ba7c3097aabcd58a019bb234c1a0
+size 822298412

model-00030-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ff92163ab6120f1e54c3af75c14a68b5c894e1a192fa78b891c6da9d6d14f16
+size 822298412

model-00031-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcb57055f620788b486bd1ca5a67daf2dcbc14f92aa20f54fe46f4c05066e69f
+size 822298412

model-00032-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cb5ba2f2f706df7cb38e859a12793af5554efa15cbb1694705eec34c6a152d4
+size 822298412

model-00033-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37acb1c99a6ea41b7948bc22a05f122bbbe508366a02e2becb589973580481eb
+size 805487744

model-00034-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5c141e2b9214716b4f5b4f508e1d35ec22c4ec8208fc1b3273f09a3c5817e10
+size 826278016

model.safetensors.index.json

@@ -0,0 +1,491 @@
+{
+    "metadata": {
+        "total_size": 27496319104.0
+    },
+    "weight_map": {
+        "embed_out.weight": "model-00034-of-00034.safetensors",
+        "gpt_neox.embed_in.weight": "model-00001-of-00034.safetensors",
+        "gpt_neox.final_layer_norm.bias": "model-00033-of-00034.safetensors",
+        "gpt_neox.final_layer_norm.weight": "model-00033-of-00034.safetensors",
+        "gpt_neox.layers.0.attention.bias": "model-00001-of-00034.safetensors",
+        "gpt_neox.layers.0.attention.dense.bias": "model-00002-of-00034.safetensors",
+        "gpt_neox.layers.0.attention.dense.weight": "model-00002-of-00034.safetensors",
+        "gpt_neox.layers.0.attention.masked_bias": "model-00001-of-00034.safetensors",
+        "gpt_neox.layers.0.attention.query_key_value.bias": "model-00002-of-00034.safetensors",
+        "gpt_neox.layers.0.attention.query_key_value.weight": "model-00002-of-00034.safetensors",
+        "gpt_neox.layers.0.attention.rotary_emb.inv_freq": "model-00001-of-00034.safetensors",
+        "gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00034.safetensors",
+        "gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00034.safetensors",
+        "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00002-of-00034.safetensors",
+        "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00002-of-00034.safetensors",
+        "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00002-of-00034.safetensors",
+        "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00002-of-00034.safetensors",
+        "gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00034.safetensors",
+        "gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00034.safetensors",
+        "gpt_neox.layers.1.attention.bias": "model-00002-of-00034.safetensors",
+        "gpt_neox.layers.1.attention.dense.bias": "model-00003-of-00034.safetensors",
+        "gpt_neox.layers.1.attention.dense.weight": "model-00003-of-00034.safetensors",
+        "gpt_neox.layers.1.attention.masked_bias": "model-00002-of-00034.safetensors",
+        "gpt_neox.layers.1.attention.query_key_value.bias": "model-00003-of-00034.safetensors",
+        "gpt_neox.layers.1.attention.query_key_value.weight": "model-00003-of-00034.safetensors",
+        "gpt_neox.layers.1.attention.rotary_emb.inv_freq": "model-00002-of-00034.safetensors",
+        "gpt_neox.layers.1.input_layernorm.bias": "model-00002-of-00034.safetensors",
+        "gpt_neox.layers.1.input_layernorm.weight": "model-00002-of-00034.safetensors",
+        "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00003-of-00034.safetensors",
+        "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00003-of-00034.safetensors",
+        "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00003-of-00034.safetensors",
+        "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00003-of-00034.safetensors",
+        "gpt_neox.layers.1.post_attention_layernorm.bias": "model-00002-of-00034.safetensors",
+        "gpt_neox.layers.1.post_attention_layernorm.weight": "model-00002-of-00034.safetensors",
+        "gpt_neox.layers.10.attention.bias": "model-00011-of-00034.safetensors",
+        "gpt_neox.layers.10.attention.dense.bias": "model-00012-of-00034.safetensors",
+        "gpt_neox.layers.10.attention.dense.weight": "model-00012-of-00034.safetensors",
+        "gpt_neox.layers.10.attention.masked_bias": "model-00011-of-00034.safetensors",
+        "gpt_neox.layers.10.attention.query_key_value.bias": "model-00012-of-00034.safetensors",
+        "gpt_neox.layers.10.attention.query_key_value.weight": "model-00012-of-00034.safetensors",
+        "gpt_neox.layers.10.attention.rotary_emb.inv_freq": "model-00011-of-00034.safetensors",
+        "gpt_neox.layers.10.input_layernorm.bias": "model-00011-of-00034.safetensors",
+        "gpt_neox.layers.10.input_layernorm.weight": "model-00011-of-00034.safetensors",
+        "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00012-of-00034.safetensors",
+        "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00012-of-00034.safetensors",
+        "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00012-of-00034.safetensors",
+        "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00012-of-00034.safetensors",
+        "gpt_neox.layers.10.post_attention_layernorm.bias": "model-00011-of-00034.safetensors",
+        "gpt_neox.layers.10.post_attention_layernorm.weight": "model-00011-of-00034.safetensors",
+        "gpt_neox.layers.11.attention.bias": "model-00012-of-00034.safetensors",
+        "gpt_neox.layers.11.attention.dense.bias": "model-00013-of-00034.safetensors",
+        "gpt_neox.layers.11.attention.dense.weight": "model-00013-of-00034.safetensors",
+        "gpt_neox.layers.11.attention.masked_bias": "model-00012-of-00034.safetensors",
+        "gpt_neox.layers.11.attention.query_key_value.bias": "model-00013-of-00034.safetensors",
+        "gpt_neox.layers.11.attention.query_key_value.weight": "model-00013-of-00034.safetensors",
+        "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "model-00012-of-00034.safetensors",
+        "gpt_neox.layers.11.input_layernorm.bias": "model-00012-of-00034.safetensors",
+        "gpt_neox.layers.11.input_layernorm.weight": "model-00012-of-00034.safetensors",
+        "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00013-of-00034.safetensors",
+        "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00013-of-00034.safetensors",
+        "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00013-of-00034.safetensors",
+        "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00013-of-00034.safetensors",
+        "gpt_neox.layers.11.post_attention_layernorm.bias": "model-00012-of-00034.safetensors",
+        "gpt_neox.layers.11.post_attention_layernorm.weight": "model-00012-of-00034.safetensors",
+        "gpt_neox.layers.12.attention.bias": "model-00013-of-00034.safetensors",
+        "gpt_neox.layers.12.attention.dense.bias": "model-00014-of-00034.safetensors",
+        "gpt_neox.layers.12.attention.dense.weight": "model-00014-of-00034.safetensors",
+        "gpt_neox.layers.12.attention.masked_bias": "model-00013-of-00034.safetensors",
+        "gpt_neox.layers.12.attention.query_key_value.bias": "model-00014-of-00034.safetensors",
+        "gpt_neox.layers.12.attention.query_key_value.weight": "model-00014-of-00034.safetensors",
+        "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "model-00013-of-00034.safetensors",
+        "gpt_neox.layers.12.input_layernorm.bias": "model-00013-of-00034.safetensors",
+        "gpt_neox.layers.12.input_layernorm.weight": "model-00013-of-00034.safetensors",
+        "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00014-of-00034.safetensors",
+        "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00014-of-00034.safetensors",
+        "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00014-of-00034.safetensors",
+        "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00014-of-00034.safetensors",
+        "gpt_neox.layers.12.post_attention_layernorm.bias": "model-00013-of-00034.safetensors",
+        "gpt_neox.layers.12.post_attention_layernorm.weight": "model-00013-of-00034.safetensors",
+        "gpt_neox.layers.13.attention.bias": "model-00014-of-00034.safetensors",
+        "gpt_neox.layers.13.attention.dense.bias": "model-00015-of-00034.safetensors",
+        "gpt_neox.layers.13.attention.dense.weight": "model-00015-of-00034.safetensors",
+        "gpt_neox.layers.13.attention.masked_bias": "model-00014-of-00034.safetensors",
+        "gpt_neox.layers.13.attention.query_key_value.bias": "model-00015-of-00034.safetensors",
+        "gpt_neox.layers.13.attention.query_key_value.weight": "model-00015-of-00034.safetensors",
+        "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "model-00014-of-00034.safetensors",
+        "gpt_neox.layers.13.input_layernorm.bias": "model-00014-of-00034.safetensors",
+        "gpt_neox.layers.13.input_layernorm.weight": "model-00014-of-00034.safetensors",
+        "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00015-of-00034.safetensors",
+        "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00015-of-00034.safetensors",
+        "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00015-of-00034.safetensors",
+        "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00015-of-00034.safetensors",
+        "gpt_neox.layers.13.post_attention_layernorm.bias": "model-00014-of-00034.safetensors",
+        "gpt_neox.layers.13.post_attention_layernorm.weight": "model-00014-of-00034.safetensors",
+        "gpt_neox.layers.14.attention.bias": "model-00015-of-00034.safetensors",
+        "gpt_neox.layers.14.attention.dense.bias": "model-00016-of-00034.safetensors",
+        "gpt_neox.layers.14.attention.dense.weight": "model-00016-of-00034.safetensors",
+        "gpt_neox.layers.14.attention.masked_bias": "model-00015-of-00034.safetensors",
+        "gpt_neox.layers.14.attention.query_key_value.bias": "model-00016-of-00034.safetensors",
+        "gpt_neox.layers.14.attention.query_key_value.weight": "model-00016-of-00034.safetensors",
+        "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "model-00015-of-00034.safetensors",
+        "gpt_neox.layers.14.input_layernorm.bias": "model-00015-of-00034.safetensors",
+        "gpt_neox.layers.14.input_layernorm.weight": "model-00015-of-00034.safetensors",
+        "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00016-of-00034.safetensors",
+        "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00016-of-00034.safetensors",
+        "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00016-of-00034.safetensors",
+        "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00016-of-00034.safetensors",
+        "gpt_neox.layers.14.post_attention_layernorm.bias": "model-00015-of-00034.safetensors",
+        "gpt_neox.layers.14.post_attention_layernorm.weight": "model-00015-of-00034.safetensors",
+        "gpt_neox.layers.15.attention.bias": "model-00016-of-00034.safetensors",
+        "gpt_neox.layers.15.attention.dense.bias": "model-00017-of-00034.safetensors",
+        "gpt_neox.layers.15.attention.dense.weight": "model-00017-of-00034.safetensors",
+        "gpt_neox.layers.15.attention.masked_bias": "model-00016-of-00034.safetensors",
+        "gpt_neox.layers.15.attention.query_key_value.bias": "model-00017-of-00034.safetensors",
+        "gpt_neox.layers.15.attention.query_key_value.weight": "model-00017-of-00034.safetensors",
+        "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "model-00016-of-00034.safetensors",
+        "gpt_neox.layers.15.input_layernorm.bias": "model-00016-of-00034.safetensors",
+        "gpt_neox.layers.15.input_layernorm.weight": "model-00016-of-00034.safetensors",
+        "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00017-of-00034.safetensors",
+        "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00017-of-00034.safetensors",
+        "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00017-of-00034.safetensors",
+        "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00017-of-00034.safetensors",
+        "gpt_neox.layers.15.post_attention_layernorm.bias": "model-00016-of-00034.safetensors",
+        "gpt_neox.layers.15.post_attention_layernorm.weight": "model-00016-of-00034.safetensors",
+        "gpt_neox.layers.16.attention.bias": "model-00017-of-00034.safetensors",
+        "gpt_neox.layers.16.attention.dense.bias": "model-00018-of-00034.safetensors",
+        "gpt_neox.layers.16.attention.dense.weight": "model-00018-of-00034.safetensors",
+        "gpt_neox.layers.16.attention.masked_bias": "model-00017-of-00034.safetensors",
+        "gpt_neox.layers.16.attention.query_key_value.bias": "model-00018-of-00034.safetensors",
+        "gpt_neox.layers.16.attention.query_key_value.weight": "model-00018-of-00034.safetensors",
+        "gpt_neox.layers.16.attention.rotary_emb.inv_freq": "model-00017-of-00034.safetensors",
+        "gpt_neox.layers.16.input_layernorm.bias": "model-00017-of-00034.safetensors",
+        "gpt_neox.layers.16.input_layernorm.weight": "model-00017-of-00034.safetensors",
+        "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "model-00018-of-00034.safetensors",
+        "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "model-00018-of-00034.safetensors",
+        "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "model-00018-of-00034.safetensors",
+        "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "model-00018-of-00034.safetensors",
+        "gpt_neox.layers.16.post_attention_layernorm.bias": "model-00017-of-00034.safetensors",
+        "gpt_neox.layers.16.post_attention_layernorm.weight": "model-00017-of-00034.safetensors",
+        "gpt_neox.layers.17.attention.bias": "model-00018-of-00034.safetensors",
+        "gpt_neox.layers.17.attention.dense.bias": "model-00019-of-00034.safetensors",
+        "gpt_neox.layers.17.attention.dense.weight": "model-00019-of-00034.safetensors",
+        "gpt_neox.layers.17.attention.masked_bias": "model-00018-of-00034.safetensors",
+        "gpt_neox.layers.17.attention.query_key_value.bias": "model-00019-of-00034.safetensors",
+        "gpt_neox.layers.17.attention.query_key_value.weight": "model-00019-of-00034.safetensors",
+        "gpt_neox.layers.17.attention.rotary_emb.inv_freq": "model-00018-of-00034.safetensors",
+        "gpt_neox.layers.17.input_layernorm.bias": "model-00018-of-00034.safetensors",
+        "gpt_neox.layers.17.input_layernorm.weight": "model-00018-of-00034.safetensors",
+        "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "model-00019-of-00034.safetensors",
+        "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "model-00019-of-00034.safetensors",
+        "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "model-00019-of-00034.safetensors",
+        "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "model-00019-of-00034.safetensors",
+        "gpt_neox.layers.17.post_attention_layernorm.bias": "model-00018-of-00034.safetensors",
+        "gpt_neox.layers.17.post_attention_layernorm.weight": "model-00018-of-00034.safetensors",
+        "gpt_neox.layers.18.attention.bias": "model-00019-of-00034.safetensors",
+        "gpt_neox.layers.18.attention.dense.bias": "model-00020-of-00034.safetensors",
+        "gpt_neox.layers.18.attention.dense.weight": "model-00020-of-00034.safetensors",
+        "gpt_neox.layers.18.attention.masked_bias": "model-00019-of-00034.safetensors",
+        "gpt_neox.layers.18.attention.query_key_value.bias": "model-00020-of-00034.safetensors",
+        "gpt_neox.layers.18.attention.query_key_value.weight": "model-00020-of-00034.safetensors",
+        "gpt_neox.layers.18.attention.rotary_emb.inv_freq": "model-00019-of-00034.safetensors",
+        "gpt_neox.layers.18.input_layernorm.bias": "model-00019-of-00034.safetensors",
+        "gpt_neox.layers.18.input_layernorm.weight": "model-00019-of-00034.safetensors",
+        "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "model-00020-of-00034.safetensors",
+        "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "model-00020-of-00034.safetensors",
+        "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "model-00020-of-00034.safetensors",
+        "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "model-00020-of-00034.safetensors",
+        "gpt_neox.layers.18.post_attention_layernorm.bias": "model-00019-of-00034.safetensors",
+        "gpt_neox.layers.18.post_attention_layernorm.weight": "model-00019-of-00034.safetensors",
+        "gpt_neox.layers.19.attention.bias": "model-00020-of-00034.safetensors",
+        "gpt_neox.layers.19.attention.dense.bias": "model-00021-of-00034.safetensors",
+        "gpt_neox.layers.19.attention.dense.weight": "model-00021-of-00034.safetensors",
+        "gpt_neox.layers.19.attention.masked_bias": "model-00020-of-00034.safetensors",
+        "gpt_neox.layers.19.attention.query_key_value.bias": "model-00021-of-00034.safetensors",
+        "gpt_neox.layers.19.attention.query_key_value.weight": "model-00021-of-00034.safetensors",
+        "gpt_neox.layers.19.attention.rotary_emb.inv_freq": "model-00020-of-00034.safetensors",
+        "gpt_neox.layers.19.input_layernorm.bias": "model-00020-of-00034.safetensors",
+        "gpt_neox.layers.19.input_layernorm.weight": "model-00020-of-00034.safetensors",
+        "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "model-00021-of-00034.safetensors",
+        "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "model-00021-of-00034.safetensors",
+        "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "model-00021-of-00034.safetensors",
+        "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "model-00021-of-00034.safetensors",
+        "gpt_neox.layers.19.post_attention_layernorm.bias": "model-00020-of-00034.safetensors",
+        "gpt_neox.layers.19.post_attention_layernorm.weight": "model-00020-of-00034.safetensors",
+        "gpt_neox.layers.2.attention.bias": "model-00003-of-00034.safetensors",
+        "gpt_neox.layers.2.attention.dense.bias": "model-00004-of-00034.safetensors",
+        "gpt_neox.layers.2.attention.dense.weight": "model-00004-of-00034.safetensors",
+        "gpt_neox.layers.2.attention.masked_bias": "model-00003-of-00034.safetensors",
+        "gpt_neox.layers.2.attention.query_key_value.bias": "model-00004-of-00034.safetensors",
+        "gpt_neox.layers.2.attention.query_key_value.weight": "model-00004-of-00034.safetensors",
+        "gpt_neox.layers.2.attention.rotary_emb.inv_freq": "model-00003-of-00034.safetensors",
+        "gpt_neox.layers.2.input_layernorm.bias": "model-00003-of-00034.safetensors",
+        "gpt_neox.layers.2.input_layernorm.weight": "model-00003-of-00034.safetensors",
+        "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00004-of-00034.safetensors",
+        "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00004-of-00034.safetensors",
+        "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00004-of-00034.safetensors",
+        "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00004-of-00034.safetensors",
+        "gpt_neox.layers.2.post_attention_layernorm.bias": "model-00003-of-00034.safetensors",
+        "gpt_neox.layers.2.post_attention_layernorm.weight": "model-00003-of-00034.safetensors",
+        "gpt_neox.layers.20.attention.bias": "model-00021-of-00034.safetensors",
+        "gpt_neox.layers.20.attention.dense.bias": "model-00022-of-00034.safetensors",
+        "gpt_neox.layers.20.attention.dense.weight": "model-00022-of-00034.safetensors",
+        "gpt_neox.layers.20.attention.masked_bias": "model-00021-of-00034.safetensors",
+        "gpt_neox.layers.20.attention.query_key_value.bias": "model-00022-of-00034.safetensors",
+        "gpt_neox.layers.20.attention.query_key_value.weight": "model-00022-of-00034.safetensors",
+        "gpt_neox.layers.20.attention.rotary_emb.inv_freq": "model-00021-of-00034.safetensors",
+        "gpt_neox.layers.20.input_layernorm.bias": "model-00021-of-00034.safetensors",
+        "gpt_neox.layers.20.input_layernorm.weight": "model-00021-of-00034.safetensors",
+        "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "model-00022-of-00034.safetensors",
+        "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "model-00022-of-00034.safetensors",
+        "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "model-00022-of-00034.safetensors",
+        "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "model-00022-of-00034.safetensors",
+        "gpt_neox.layers.20.post_attention_layernorm.bias": "model-00021-of-00034.safetensors",
+        "gpt_neox.layers.20.post_attention_layernorm.weight": "model-00021-of-00034.safetensors",
+        "gpt_neox.layers.21.attention.bias": "model-00022-of-00034.safetensors",
+        "gpt_neox.layers.21.attention.dense.bias": "model-00023-of-00034.safetensors",
+        "gpt_neox.layers.21.attention.dense.weight": "model-00023-of-00034.safetensors",
+        "gpt_neox.layers.21.attention.masked_bias": "model-00022-of-00034.safetensors",
+        "gpt_neox.layers.21.attention.query_key_value.bias": "model-00023-of-00034.safetensors",
+        "gpt_neox.layers.21.attention.query_key_value.weight": "model-00023-of-00034.safetensors",
+        "gpt_neox.layers.21.attention.rotary_emb.inv_freq": "model-00022-of-00034.safetensors",
+        "gpt_neox.layers.21.input_layernorm.bias": "model-00022-of-00034.safetensors",
+        "gpt_neox.layers.21.input_layernorm.weight": "model-00022-of-00034.safetensors",
+        "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "model-00023-of-00034.safetensors",
+        "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "model-00023-of-00034.safetensors",
+        "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "model-00023-of-00034.safetensors",
+        "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "model-00023-of-00034.safetensors",
+        "gpt_neox.layers.21.post_attention_layernorm.bias": "model-00022-of-00034.safetensors",
+        "gpt_neox.layers.21.post_attention_layernorm.weight": "model-00022-of-00034.safetensors",
+        "gpt_neox.layers.22.attention.bias": "model-00023-of-00034.safetensors",
+        "gpt_neox.layers.22.attention.dense.bias": "model-00024-of-00034.safetensors",
+        "gpt_neox.layers.22.attention.dense.weight": "model-00024-of-00034.safetensors",
+        "gpt_neox.layers.22.attention.masked_bias": "model-00023-of-00034.safetensors",
+        "gpt_neox.layers.22.attention.query_key_value.bias": "model-00024-of-00034.safetensors",
+        "gpt_neox.layers.22.attention.query_key_value.weight": "model-00024-of-00034.safetensors",
+        "gpt_neox.layers.22.attention.rotary_emb.inv_freq": "model-00023-of-00034.safetensors",
+        "gpt_neox.layers.22.input_layernorm.bias": "model-00023-of-00034.safetensors",
+        "gpt_neox.layers.22.input_layernorm.weight": "model-00023-of-00034.safetensors",
+        "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "model-00024-of-00034.safetensors",
+        "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "model-00024-of-00034.safetensors",
+        "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "model-00024-of-00034.safetensors",
+        "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "model-00024-of-00034.safetensors",
+        "gpt_neox.layers.22.post_attention_layernorm.bias": "model-00023-of-00034.safetensors",
+        "gpt_neox.layers.22.post_attention_layernorm.weight": "model-00023-of-00034.safetensors",
+        "gpt_neox.layers.23.attention.bias": "model-00024-of-00034.safetensors",
+        "gpt_neox.layers.23.attention.dense.bias": "model-00025-of-00034.safetensors",
+        "gpt_neox.layers.23.attention.dense.weight": "model-00025-of-00034.safetensors",
+        "gpt_neox.layers.23.attention.masked_bias": "model-00024-of-00034.safetensors",
+        "gpt_neox.layers.23.attention.query_key_value.bias": "model-00025-of-00034.safetensors",
+        "gpt_neox.layers.23.attention.query_key_value.weight": "model-00025-of-00034.safetensors",
+        "gpt_neox.layers.23.attention.rotary_emb.inv_freq": "model-00024-of-00034.safetensors",
+        "gpt_neox.layers.23.input_layernorm.bias": "model-00024-of-00034.safetensors",
+        "gpt_neox.layers.23.input_layernorm.weight": "model-00024-of-00034.safetensors",
+        "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "model-00025-of-00034.safetensors",
+        "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "model-00025-of-00034.safetensors",
+        "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "model-00025-of-00034.safetensors",
+        "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "model-00025-of-00034.safetensors",
+        "gpt_neox.layers.23.post_attention_layernorm.bias": "model-00024-of-00034.safetensors",
+        "gpt_neox.layers.23.post_attention_layernorm.weight": "model-00024-of-00034.safetensors",
+        "gpt_neox.layers.24.attention.bias": "model-00025-of-00034.safetensors",
+        "gpt_neox.layers.24.attention.dense.bias": "model-00026-of-00034.safetensors",
+        "gpt_neox.layers.24.attention.dense.weight": "model-00026-of-00034.safetensors",
+        "gpt_neox.layers.24.attention.masked_bias": "model-00025-of-00034.safetensors",
+        "gpt_neox.layers.24.attention.query_key_value.bias": "model-00026-of-00034.safetensors",
+        "gpt_neox.layers.24.attention.query_key_value.weight": "model-00026-of-00034.safetensors",
+        "gpt_neox.layers.24.attention.rotary_emb.inv_freq": "model-00025-of-00034.safetensors",
+        "gpt_neox.layers.24.input_layernorm.bias": "model-00025-of-00034.safetensors",
+        "gpt_neox.layers.24.input_layernorm.weight": "model-00025-of-00034.safetensors",
+        "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "model-00026-of-00034.safetensors",
+        "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "model-00026-of-00034.safetensors",
+        "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "model-00026-of-00034.safetensors",
+        "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "model-00026-of-00034.safetensors",
+        "gpt_neox.layers.24.post_attention_layernorm.bias": "model-00025-of-00034.safetensors",
+        "gpt_neox.layers.24.post_attention_layernorm.weight": "model-00025-of-00034.safetensors",
+        "gpt_neox.layers.25.attention.bias": "model-00026-of-00034.safetensors",
+        "gpt_neox.layers.25.attention.dense.bias": "model-00027-of-00034.safetensors",
+        "gpt_neox.layers.25.attention.dense.weight": "model-00027-of-00034.safetensors",
+        "gpt_neox.layers.25.attention.masked_bias": "model-00026-of-00034.safetensors",
+        "gpt_neox.layers.25.attention.query_key_value.bias": "model-00027-of-00034.safetensors",
+        "gpt_neox.layers.25.attention.query_key_value.weight": "model-00027-of-00034.safetensors",
+        "gpt_neox.layers.25.attention.rotary_emb.inv_freq": "model-00026-of-00034.safetensors",
+        "gpt_neox.layers.25.input_layernorm.bias": "model-00026-of-00034.safetensors",
+        "gpt_neox.layers.25.input_layernorm.weight": "model-00026-of-00034.safetensors",
+        "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "model-00027-of-00034.safetensors",
+        "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "model-00027-of-00034.safetensors",
+        "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "model-00027-of-00034.safetensors",
+        "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "model-00027-of-00034.safetensors",
+        "gpt_neox.layers.25.post_attention_layernorm.bias": "model-00026-of-00034.safetensors",
+        "gpt_neox.layers.25.post_attention_layernorm.weight": "model-00026-of-00034.safetensors",
+        "gpt_neox.layers.26.attention.bias": "model-00027-of-00034.safetensors",
+        "gpt_neox.layers.26.attention.dense.bias": "model-00028-of-00034.safetensors",
+        "gpt_neox.layers.26.attention.dense.weight": "model-00028-of-00034.safetensors",
+        "gpt_neox.layers.26.attention.masked_bias": "model-00027-of-00034.safetensors",
+        "gpt_neox.layers.26.attention.query_key_value.bias": "model-00028-of-00034.safetensors",
+        "gpt_neox.layers.26.attention.query_key_value.weight": "model-00028-of-00034.safetensors",
+        "gpt_neox.layers.26.attention.rotary_emb.inv_freq": "model-00027-of-00034.safetensors",
+        "gpt_neox.layers.26.input_layernorm.bias": "model-00027-of-00034.safetensors",
+        "gpt_neox.layers.26.input_layernorm.weight": "model-00027-of-00034.safetensors",
+        "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "model-00028-of-00034.safetensors",
+        "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "model-00028-of-00034.safetensors",
+        "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "model-00028-of-00034.safetensors",
+        "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "model-00028-of-00034.safetensors",
+        "gpt_neox.layers.26.post_attention_layernorm.bias": "model-00027-of-00034.safetensors",
+        "gpt_neox.layers.26.post_attention_layernorm.weight": "model-00027-of-00034.safetensors",
+        "gpt_neox.layers.27.attention.bias": "model-00028-of-00034.safetensors",
+        "gpt_neox.layers.27.attention.dense.bias": "model-00029-of-00034.safetensors",
+        "gpt_neox.layers.27.attention.dense.weight": "model-00029-of-00034.safetensors",
+        "gpt_neox.layers.27.attention.masked_bias": "model-00028-of-00034.safetensors",
+        "gpt_neox.layers.27.attention.query_key_value.bias": "model-00029-of-00034.safetensors",
+        "gpt_neox.layers.27.attention.query_key_value.weight": "model-00029-of-00034.safetensors",
+        "gpt_neox.layers.27.attention.rotary_emb.inv_freq": "model-00028-of-00034.safetensors",
+        "gpt_neox.layers.27.input_layernorm.bias": "model-00028-of-00034.safetensors",
+        "gpt_neox.layers.27.input_layernorm.weight": "model-00028-of-00034.safetensors",
+        "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "model-00029-of-00034.safetensors",
+        "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "model-00029-of-00034.safetensors",
+        "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "model-00029-of-00034.safetensors",
+        "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "model-00029-of-00034.safetensors",
+        "gpt_neox.layers.27.post_attention_layernorm.bias": "model-00028-of-00034.safetensors",
+        "gpt_neox.layers.27.post_attention_layernorm.weight": "model-00028-of-00034.safetensors",
+        "gpt_neox.layers.28.attention.bias": "model-00029-of-00034.safetensors",
+        "gpt_neox.layers.28.attention.dense.bias": "model-00030-of-00034.safetensors",
+        "gpt_neox.layers.28.attention.dense.weight": "model-00030-of-00034.safetensors",
+        "gpt_neox.layers.28.attention.masked_bias": "model-00029-of-00034.safetensors",
+        "gpt_neox.layers.28.attention.query_key_value.bias": "model-00030-of-00034.safetensors",
+        "gpt_neox.layers.28.attention.query_key_value.weight": "model-00030-of-00034.safetensors",
+        "gpt_neox.layers.28.attention.rotary_emb.inv_freq": "model-00029-of-00034.safetensors",
+        "gpt_neox.layers.28.input_layernorm.bias": "model-00029-of-00034.safetensors",
+        "gpt_neox.layers.28.input_layernorm.weight": "model-00029-of-00034.safetensors",
+        "gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "model-00030-of-00034.safetensors",
+        "gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "model-00030-of-00034.safetensors",
+        "gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "model-00030-of-00034.safetensors",
+        "gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "model-00030-of-00034.safetensors",
+        "gpt_neox.layers.28.post_attention_layernorm.bias": "model-00029-of-00034.safetensors",
+        "gpt_neox.layers.28.post_attention_layernorm.weight": "model-00029-of-00034.safetensors",
+        "gpt_neox.layers.29.attention.bias": "model-00030-of-00034.safetensors",
+        "gpt_neox.layers.29.attention.dense.bias": "model-00031-of-00034.safetensors",
+        "gpt_neox.layers.29.attention.dense.weight": "model-00031-of-00034.safetensors",
+        "gpt_neox.layers.29.attention.masked_bias": "model-00030-of-00034.safetensors",
+        "gpt_neox.layers.29.attention.query_key_value.bias": "model-00031-of-00034.safetensors",
+        "gpt_neox.layers.29.attention.query_key_value.weight": "model-00031-of-00034.safetensors",
+        "gpt_neox.layers.29.attention.rotary_emb.inv_freq": "model-00030-of-00034.safetensors",
+        "gpt_neox.layers.29.input_layernorm.bias": "model-00030-of-00034.safetensors",
+        "gpt_neox.layers.29.input_layernorm.weight": "model-00030-of-00034.safetensors",
+        "gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "model-00031-of-00034.safetensors",
+        "gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "model-00031-of-00034.safetensors",
+        "gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "model-00031-of-00034.safetensors",
+        "gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "model-00031-of-00034.safetensors",
+        "gpt_neox.layers.29.post_attention_layernorm.bias": "model-00030-of-00034.safetensors",
+        "gpt_neox.layers.29.post_attention_layernorm.weight": "model-00030-of-00034.safetensors",
+        "gpt_neox.layers.3.attention.bias": "model-00004-of-00034.safetensors",
+        "gpt_neox.layers.3.attention.dense.bias": "model-00005-of-00034.safetensors",
+        "gpt_neox.layers.3.attention.dense.weight": "model-00005-of-00034.safetensors",
+        "gpt_neox.layers.3.attention.masked_bias": "model-00004-of-00034.safetensors",
+        "gpt_neox.layers.3.attention.query_key_value.bias": "model-00005-of-00034.safetensors",
+        "gpt_neox.layers.3.attention.query_key_value.weight": "model-00005-of-00034.safetensors",
+        "gpt_neox.layers.3.attention.rotary_emb.inv_freq": "model-00004-of-00034.safetensors",
+        "gpt_neox.layers.3.input_layernorm.bias": "model-00004-of-00034.safetensors",
+        "gpt_neox.layers.3.input_layernorm.weight": "model-00004-of-00034.safetensors",
+        "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00005-of-00034.safetensors",
+        "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00005-of-00034.safetensors",
+        "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00005-of-00034.safetensors",
+        "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00005-of-00034.safetensors",
+        "gpt_neox.layers.3.post_attention_layernorm.bias": "model-00004-of-00034.safetensors",
+        "gpt_neox.layers.3.post_attention_layernorm.weight": "model-00004-of-00034.safetensors",
+        "gpt_neox.layers.30.attention.bias": "model-00031-of-00034.safetensors",
+        "gpt_neox.layers.30.attention.dense.bias": "model-00032-of-00034.safetensors",
+        "gpt_neox.layers.30.attention.dense.weight": "model-00032-of-00034.safetensors",
+        "gpt_neox.layers.30.attention.masked_bias": "model-00031-of-00034.safetensors",
+        "gpt_neox.layers.30.attention.query_key_value.bias": "model-00032-of-00034.safetensors",
+        "gpt_neox.layers.30.attention.query_key_value.weight": "model-00032-of-00034.safetensors",
+        "gpt_neox.layers.30.attention.rotary_emb.inv_freq": "model-00031-of-00034.safetensors",
+        "gpt_neox.layers.30.input_layernorm.bias": "model-00031-of-00034.safetensors",
+        "gpt_neox.layers.30.input_layernorm.weight": "model-00031-of-00034.safetensors",
+        "gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "model-00032-of-00034.safetensors",
+        "gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "model-00032-of-00034.safetensors",
+        "gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "model-00032-of-00034.safetensors",
+        "gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "model-00032-of-00034.safetensors",
+        "gpt_neox.layers.30.post_attention_layernorm.bias": "model-00031-of-00034.safetensors",
+        "gpt_neox.layers.30.post_attention_layernorm.weight": "model-00031-of-00034.safetensors",
+        "gpt_neox.layers.31.attention.bias": "model-00032-of-00034.safetensors",
+        "gpt_neox.layers.31.attention.dense.bias": "model-00033-of-00034.safetensors",
+        "gpt_neox.layers.31.attention.dense.weight": "model-00033-of-00034.safetensors",
+        "gpt_neox.layers.31.attention.masked_bias": "model-00032-of-00034.safetensors",
+        "gpt_neox.layers.31.attention.query_key_value.bias": "model-00033-of-00034.safetensors",
+        "gpt_neox.layers.31.attention.query_key_value.weight": "model-00033-of-00034.safetensors",
+        "gpt_neox.layers.31.attention.rotary_emb.inv_freq": "model-00032-of-00034.safetensors",
+        "gpt_neox.layers.31.input_layernorm.bias": "model-00032-of-00034.safetensors",
+        "gpt_neox.layers.31.input_layernorm.weight": "model-00032-of-00034.safetensors",
+        "gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "model-00033-of-00034.safetensors",
+        "gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "model-00033-of-00034.safetensors",
+        "gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "model-00033-of-00034.safetensors",
+        "gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "model-00033-of-00034.safetensors",
+        "gpt_neox.layers.31.post_attention_layernorm.bias": "model-00032-of-00034.safetensors",
+        "gpt_neox.layers.31.post_attention_layernorm.weight": "model-00032-of-00034.safetensors",
+        "gpt_neox.layers.4.attention.bias": "model-00005-of-00034.safetensors",
+        "gpt_neox.layers.4.attention.dense.bias": "model-00006-of-00034.safetensors",
+        "gpt_neox.layers.4.attention.dense.weight": "model-00006-of-00034.safetensors",
+        "gpt_neox.layers.4.attention.masked_bias": "model-00005-of-00034.safetensors",
+        "gpt_neox.layers.4.attention.query_key_value.bias": "model-00006-of-00034.safetensors",
+        "gpt_neox.layers.4.attention.query_key_value.weight": "model-00006-of-00034.safetensors",
+        "gpt_neox.layers.4.attention.rotary_emb.inv_freq": "model-00005-of-00034.safetensors",
+        "gpt_neox.layers.4.input_layernorm.bias": "model-00005-of-00034.safetensors",
+        "gpt_neox.layers.4.input_layernorm.weight": "model-00005-of-00034.safetensors",
+        "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00006-of-00034.safetensors",
+        "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00006-of-00034.safetensors",
+        "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00006-of-00034.safetensors",
+        "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00006-of-00034.safetensors",
+        "gpt_neox.layers.4.post_attention_layernorm.bias": "model-00005-of-00034.safetensors",
+        "gpt_neox.layers.4.post_attention_layernorm.weight": "model-00005-of-00034.safetensors",
+        "gpt_neox.layers.5.attention.bias": "model-00006-of-00034.safetensors",
+        "gpt_neox.layers.5.attention.dense.bias": "model-00007-of-00034.safetensors",
+        "gpt_neox.layers.5.attention.dense.weight": "model-00007-of-00034.safetensors",
+        "gpt_neox.layers.5.attention.masked_bias": "model-00006-of-00034.safetensors",
+        "gpt_neox.layers.5.attention.query_key_value.bias": "model-00007-of-00034.safetensors",
+        "gpt_neox.layers.5.attention.query_key_value.weight": "model-00007-of-00034.safetensors",
+        "gpt_neox.layers.5.attention.rotary_emb.inv_freq": "model-00006-of-00034.safetensors",
+        "gpt_neox.layers.5.input_layernorm.bias": "model-00006-of-00034.safetensors",
+        "gpt_neox.layers.5.input_layernorm.weight": "model-00006-of-00034.safetensors",
+        "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00007-of-00034.safetensors",
+        "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00007-of-00034.safetensors",
+        "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00007-of-00034.safetensors",
+        "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00007-of-00034.safetensors",
+        "gpt_neox.layers.5.post_attention_layernorm.bias": "model-00006-of-00034.safetensors",
+        "gpt_neox.layers.5.post_attention_layernorm.weight": "model-00006-of-00034.safetensors",
+        "gpt_neox.layers.6.attention.bias": "model-00007-of-00034.safetensors",
+        "gpt_neox.layers.6.attention.dense.bias": "model-00008-of-00034.safetensors",
+        "gpt_neox.layers.6.attention.dense.weight": "model-00008-of-00034.safetensors",
+        "gpt_neox.layers.6.attention.masked_bias": "model-00007-of-00034.safetensors",
+        "gpt_neox.layers.6.attention.query_key_value.bias": "model-00008-of-00034.safetensors",
+        "gpt_neox.layers.6.attention.query_key_value.weight": "model-00008-of-00034.safetensors",
+        "gpt_neox.layers.6.attention.rotary_emb.inv_freq": "model-00007-of-00034.safetensors",
+        "gpt_neox.layers.6.input_layernorm.bias": "model-00007-of-00034.safetensors",
+        "gpt_neox.layers.6.input_layernorm.weight": "model-00007-of-00034.safetensors",
+        "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00008-of-00034.safetensors",
+        "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00008-of-00034.safetensors",
+        "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00008-of-00034.safetensors",
+        "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00008-of-00034.safetensors",
+        "gpt_neox.layers.6.post_attention_layernorm.bias": "model-00007-of-00034.safetensors",
+        "gpt_neox.layers.6.post_attention_layernorm.weight": "model-00007-of-00034.safetensors",
+        "gpt_neox.layers.7.attention.bias": "model-00008-of-00034.safetensors",
+        "gpt_neox.layers.7.attention.dense.bias": "model-00009-of-00034.safetensors",
+        "gpt_neox.layers.7.attention.dense.weight": "model-00009-of-00034.safetensors",
+        "gpt_neox.layers.7.attention.masked_bias": "model-00008-of-00034.safetensors",
+        "gpt_neox.layers.7.attention.query_key_value.bias": "model-00009-of-00034.safetensors",
+        "gpt_neox.layers.7.attention.query_key_value.weight": "model-00009-of-00034.safetensors",
+        "gpt_neox.layers.7.attention.rotary_emb.inv_freq": "model-00008-of-00034.safetensors",
+        "gpt_neox.layers.7.input_layernorm.bias": "model-00008-of-00034.safetensors",
+        "gpt_neox.layers.7.input_layernorm.weight": "model-00008-of-00034.safetensors",
+        "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00009-of-00034.safetensors",
+        "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00009-of-00034.safetensors",
+        "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00009-of-00034.safetensors",
+        "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00009-of-00034.safetensors",
+        "gpt_neox.layers.7.post_attention_layernorm.bias": "model-00008-of-00034.safetensors",
+        "gpt_neox.layers.7.post_attention_layernorm.weight": "model-00008-of-00034.safetensors",
+        "gpt_neox.layers.8.attention.bias": "model-00009-of-00034.safetensors",
+        "gpt_neox.layers.8.attention.dense.bias": "model-00010-of-00034.safetensors",
+        "gpt_neox.layers.8.attention.dense.weight": "model-00010-of-00034.safetensors",
+        "gpt_neox.layers.8.attention.masked_bias": "model-00009-of-00034.safetensors",
+        "gpt_neox.layers.8.attention.query_key_value.bias": "model-00010-of-00034.safetensors",
+        "gpt_neox.layers.8.attention.query_key_value.weight": "model-00010-of-00034.safetensors",
+        "gpt_neox.layers.8.attention.rotary_emb.inv_freq": "model-00009-of-00034.safetensors",
+        "gpt_neox.layers.8.input_layernorm.bias": "model-00009-of-00034.safetensors",
+        "gpt_neox.layers.8.input_layernorm.weight": "model-00009-of-00034.safetensors",
+        "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00010-of-00034.safetensors",
+        "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00010-of-00034.safetensors",
+        "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00010-of-00034.safetensors",
+        "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00010-of-00034.safetensors",
+        "gpt_neox.layers.8.post_attention_layernorm.bias": "model-00009-of-00034.safetensors",
+        "gpt_neox.layers.8.post_attention_layernorm.weight": "model-00009-of-00034.safetensors",
+        "gpt_neox.layers.9.attention.bias": "model-00010-of-00034.safetensors",
+        "gpt_neox.layers.9.attention.dense.bias": "model-00011-of-00034.safetensors",
+        "gpt_neox.layers.9.attention.dense.weight": "model-00011-of-00034.safetensors",
+        "gpt_neox.layers.9.attention.masked_bias": "model-00010-of-00034.safetensors",
+        "gpt_neox.layers.9.attention.query_key_value.bias": "model-00011-of-00034.safetensors",
+        "gpt_neox.layers.9.attention.query_key_value.weight": "model-00011-of-00034.safetensors",
+        "gpt_neox.layers.9.attention.rotary_emb.inv_freq": "model-00010-of-00034.safetensors",
+        "gpt_neox.layers.9.input_layernorm.bias": "model-00010-of-00034.safetensors",
+        "gpt_neox.layers.9.input_layernorm.weight": "model-00010-of-00034.safetensors",
+        "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00011-of-00034.safetensors",
+        "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00011-of-00034.safetensors",
+        "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00011-of-00034.safetensors",
+        "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00011-of-00034.safetensors",
+        "gpt_neox.layers.9.post_attention_layernorm.bias": "model-00010-of-00034.safetensors",
+        "gpt_neox.layers.9.post_attention_layernorm.weight": "model-00010-of-00034.safetensors"
+    }
+}