Upload folder using huggingface_hub

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "nlpai-lab/kullm-polyglot-12.8b-v2",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 20480,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_steps": "global_step301000",
+  "rope_scaling": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.5,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.35.0",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 30080
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.35.0"
+}

model-00001-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82895ee71e5378276721a1ca48a467ddab7c451b6ed169804344a7348f57bae1
+size 937340864

model-00002-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dc7f113a81852671bb7adff30a3d3497b579d3b77a93d7b1a3961f0096505c1
+size 839036768

model-00003-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c660947931b333d99b4e38ed68be14d95f6d8edd9d28e7a3b9c1a312360ea014
+size 839036528

model-00004-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ffed23048a160533a2d1af8f1767f2820b260d1075c6eb4a3d7ee1c2d912f6e
+size 996364592

model-00005-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d50e6b9f0da2ed3e041c31091a2fc54757940de042155ce271c244e38f392951
+size 891475792

model-00006-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6db1897e5cec4fe552131fa33120e6ac560050195b696823ae1b1f28e5604f3
+size 996364592

model-00007-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bcca3fc210c55a87b958b3c0fc90038e28b5ffe0dcd4aa8f7cf384d5587f627
+size 891475792

model-00008-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73466a70e3e12b64ba42bcd05891c030c25941ca29d2ff84c604b6e07124edf7
+size 996364608

model-00009-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b6327e9546b181f6c018dbb25eb0ba2e77e2203e95097121058a0e017ee9fad
+size 891475808

model-00010-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:923f71f79d8338730fd7eb1c56eab93b52f523f9cb5e4fe783f0097f39c88878
+size 996364616

model-00011-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98d14e7d6b3e89a3aa2fcb94d0cadd202fc9fd5f03f7e8f21e26192987ac42d7
+size 891475808

model-00012-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3fdce2f3de310ba6a8338608aff86c0a936a53e4e570af7e342718a611ad931
+size 996364616

model-00013-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55468d70140b81e2f8334a72975ecb2b16ebca7123b112adf328c3f19b26a782
+size 891475808

model-00014-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b4707a6274e74706d8914db0226523772d12d49e0b6901358ce081157ea0373
+size 996364616

model-00015-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f676ee0bbd5026c2f8ddeb4da9e920e95df16eb86a42c8855bfea8c452dbc8ff
+size 891475808

model-00016-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02f47f3b1a9fab50bb7b0b644bb55ae8621a75c07feae20cbd29c9b38b67ab36
+size 996364616

model-00017-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b96418413a8303988d4e1575c128841b93e0d2f0f13e68be0f962fcc56e0f9bb
+size 891475808

model-00018-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:723603811172a758cc09d728996bbfa85dfa8b9a20ed54c6af2955fb1ac2858a
+size 996364616

model-00019-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b166f5f49dd38962d89d1081392a7dd1b574b2d7a1ba8ee9dc7801a754a520e
+size 891475808

model-00020-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78c2097737bba7e3a5d102676ff8bc63113858945aac4c16cbd23fb64ade0bfb
+size 996364616

model-00021-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72602a8a6b11b64906ec886cc92efa0574bb639081db2d30064e47cdb5e3e1a9
+size 891475808

model-00022-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52c30ac27cc0d07968219bed4cfe0fa5b3face0d2cc33e6d0ea50610e4820e60
+size 996364616

model-00023-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:882110d3fa57d523b25d59ba7f5b435b3e3eabad23ee6d382ebf9dbaa37427dd
+size 891475808

model-00024-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5224d02d105a7a70d8383a8747723463fcfe322968a7cd46934c46242c1e36a9
+size 996364616

model-00025-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ed578c619e9f8a5791d0e9bb6dbcc1787fadcdbc5583ed542ecc37c0805261e
+size 891475808

model-00026-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d8cd97acf36dbab55641c36888af1085828fb8ca43e7de1880b3f3c72250c85
+size 996364616

model-00027-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4340b64a4748de82d78dbb1e85082fce4af400fbdd52ea712c0b858d344ea45
+size 891475808

model-00028-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7ea0188f126c4cd893bfdf40fbb5fb222da030f321ce595dfcf855887d72ead
+size 517765688

model.safetensors.index.json

@@ -0,0 +1,491 @@
+{
+  "metadata": {
+    "total_size": 25787207680
+  },
+  "weight_map": {
+    "embed_out.weight": "model-00028-of-00028.safetensors",
+    "gpt_neox.embed_in.weight": "model-00001-of-00028.safetensors",
+    "gpt_neox.final_layer_norm.bias": "model-00028-of-00028.safetensors",
+    "gpt_neox.final_layer_norm.weight": "model-00028-of-00028.safetensors",
+    "gpt_neox.layers.0.attention.dense.bias": "model-00001-of-00028.safetensors",
+    "gpt_neox.layers.0.attention.dense.weight": "model-00001-of-00028.safetensors",
+    "gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-00028.safetensors",
+    "gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-00028.safetensors",
+    "gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00028.safetensors",
+    "gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00028.safetensors",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00028.safetensors",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00028.safetensors",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00028.safetensors",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00028.safetensors",
+    "gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00028.safetensors",
+    "gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00028.safetensors",
+    "gpt_neox.layers.1.attention.dense.bias": "model-00002-of-00028.safetensors",
+    "gpt_neox.layers.1.attention.dense.weight": "model-00002-of-00028.safetensors",
+    "gpt_neox.layers.1.attention.query_key_value.bias": "model-00002-of-00028.safetensors",
+    "gpt_neox.layers.1.attention.query_key_value.weight": "model-00002-of-00028.safetensors",
+    "gpt_neox.layers.1.input_layernorm.bias": "model-00001-of-00028.safetensors",
+    "gpt_neox.layers.1.input_layernorm.weight": "model-00001-of-00028.safetensors",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00002-of-00028.safetensors",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00002-of-00028.safetensors",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00002-of-00028.safetensors",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00002-of-00028.safetensors",
+    "gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00028.safetensors",
+    "gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00028.safetensors",
+    "gpt_neox.layers.10.attention.dense.bias": "model-00008-of-00028.safetensors",
+    "gpt_neox.layers.10.attention.dense.weight": "model-00008-of-00028.safetensors",
+    "gpt_neox.layers.10.attention.query_key_value.bias": "model-00008-of-00028.safetensors",
+    "gpt_neox.layers.10.attention.query_key_value.weight": "model-00008-of-00028.safetensors",
+    "gpt_neox.layers.10.input_layernorm.bias": "model-00008-of-00028.safetensors",
+    "gpt_neox.layers.10.input_layernorm.weight": "model-00008-of-00028.safetensors",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00008-of-00028.safetensors",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00008-of-00028.safetensors",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00008-of-00028.safetensors",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00008-of-00028.safetensors",
+    "gpt_neox.layers.10.post_attention_layernorm.bias": "model-00008-of-00028.safetensors",
+    "gpt_neox.layers.10.post_attention_layernorm.weight": "model-00008-of-00028.safetensors",
+    "gpt_neox.layers.11.attention.dense.bias": "model-00009-of-00028.safetensors",
+    "gpt_neox.layers.11.attention.dense.weight": "model-00009-of-00028.safetensors",
+    "gpt_neox.layers.11.attention.query_key_value.bias": "model-00008-of-00028.safetensors",
+    "gpt_neox.layers.11.attention.query_key_value.weight": "model-00008-of-00028.safetensors",
+    "gpt_neox.layers.11.input_layernorm.bias": "model-00008-of-00028.safetensors",
+    "gpt_neox.layers.11.input_layernorm.weight": "model-00008-of-00028.safetensors",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00009-of-00028.safetensors",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00009-of-00028.safetensors",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00009-of-00028.safetensors",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00009-of-00028.safetensors",
+    "gpt_neox.layers.11.post_attention_layernorm.bias": "model-00008-of-00028.safetensors",
+    "gpt_neox.layers.11.post_attention_layernorm.weight": "model-00008-of-00028.safetensors",
+    "gpt_neox.layers.12.attention.dense.bias": "model-00009-of-00028.safetensors",
+    "gpt_neox.layers.12.attention.dense.weight": "model-00009-of-00028.safetensors",
+    "gpt_neox.layers.12.attention.query_key_value.bias": "model-00009-of-00028.safetensors",
+    "gpt_neox.layers.12.attention.query_key_value.weight": "model-00009-of-00028.safetensors",
+    "gpt_neox.layers.12.input_layernorm.bias": "model-00009-of-00028.safetensors",
+    "gpt_neox.layers.12.input_layernorm.weight": "model-00009-of-00028.safetensors",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00010-of-00028.safetensors",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00010-of-00028.safetensors",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00009-of-00028.safetensors",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00009-of-00028.safetensors",
+    "gpt_neox.layers.12.post_attention_layernorm.bias": "model-00009-of-00028.safetensors",
+    "gpt_neox.layers.12.post_attention_layernorm.weight": "model-00009-of-00028.safetensors",
+    "gpt_neox.layers.13.attention.dense.bias": "model-00010-of-00028.safetensors",
+    "gpt_neox.layers.13.attention.dense.weight": "model-00010-of-00028.safetensors",
+    "gpt_neox.layers.13.attention.query_key_value.bias": "model-00010-of-00028.safetensors",
+    "gpt_neox.layers.13.attention.query_key_value.weight": "model-00010-of-00028.safetensors",
+    "gpt_neox.layers.13.input_layernorm.bias": "model-00010-of-00028.safetensors",
+    "gpt_neox.layers.13.input_layernorm.weight": "model-00010-of-00028.safetensors",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00010-of-00028.safetensors",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00010-of-00028.safetensors",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00010-of-00028.safetensors",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00010-of-00028.safetensors",
+    "gpt_neox.layers.13.post_attention_layernorm.bias": "model-00010-of-00028.safetensors",
+    "gpt_neox.layers.13.post_attention_layernorm.weight": "model-00010-of-00028.safetensors",
+    "gpt_neox.layers.14.attention.dense.bias": "model-00011-of-00028.safetensors",
+    "gpt_neox.layers.14.attention.dense.weight": "model-00011-of-00028.safetensors",
+    "gpt_neox.layers.14.attention.query_key_value.bias": "model-00010-of-00028.safetensors",
+    "gpt_neox.layers.14.attention.query_key_value.weight": "model-00010-of-00028.safetensors",
+    "gpt_neox.layers.14.input_layernorm.bias": "model-00010-of-00028.safetensors",
+    "gpt_neox.layers.14.input_layernorm.weight": "model-00010-of-00028.safetensors",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00011-of-00028.safetensors",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00011-of-00028.safetensors",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00011-of-00028.safetensors",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00011-of-00028.safetensors",
+    "gpt_neox.layers.14.post_attention_layernorm.bias": "model-00010-of-00028.safetensors",
+    "gpt_neox.layers.14.post_attention_layernorm.weight": "model-00010-of-00028.safetensors",
+    "gpt_neox.layers.15.attention.dense.bias": "model-00011-of-00028.safetensors",
+    "gpt_neox.layers.15.attention.dense.weight": "model-00011-of-00028.safetensors",
+    "gpt_neox.layers.15.attention.query_key_value.bias": "model-00011-of-00028.safetensors",
+    "gpt_neox.layers.15.attention.query_key_value.weight": "model-00011-of-00028.safetensors",
+    "gpt_neox.layers.15.input_layernorm.bias": "model-00011-of-00028.safetensors",
+    "gpt_neox.layers.15.input_layernorm.weight": "model-00011-of-00028.safetensors",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00012-of-00028.safetensors",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00012-of-00028.safetensors",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00011-of-00028.safetensors",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00011-of-00028.safetensors",
+    "gpt_neox.layers.15.post_attention_layernorm.bias": "model-00011-of-00028.safetensors",
+    "gpt_neox.layers.15.post_attention_layernorm.weight": "model-00011-of-00028.safetensors",
+    "gpt_neox.layers.16.attention.dense.bias": "model-00012-of-00028.safetensors",
+    "gpt_neox.layers.16.attention.dense.weight": "model-00012-of-00028.safetensors",
+    "gpt_neox.layers.16.attention.query_key_value.bias": "model-00012-of-00028.safetensors",
+    "gpt_neox.layers.16.attention.query_key_value.weight": "model-00012-of-00028.safetensors",
+    "gpt_neox.layers.16.input_layernorm.bias": "model-00012-of-00028.safetensors",
+    "gpt_neox.layers.16.input_layernorm.weight": "model-00012-of-00028.safetensors",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "model-00012-of-00028.safetensors",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "model-00012-of-00028.safetensors",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "model-00012-of-00028.safetensors",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "model-00012-of-00028.safetensors",
+    "gpt_neox.layers.16.post_attention_layernorm.bias": "model-00012-of-00028.safetensors",
+    "gpt_neox.layers.16.post_attention_layernorm.weight": "model-00012-of-00028.safetensors",
+    "gpt_neox.layers.17.attention.dense.bias": "model-00013-of-00028.safetensors",
+    "gpt_neox.layers.17.attention.dense.weight": "model-00013-of-00028.safetensors",
+    "gpt_neox.layers.17.attention.query_key_value.bias": "model-00012-of-00028.safetensors",
+    "gpt_neox.layers.17.attention.query_key_value.weight": "model-00012-of-00028.safetensors",
+    "gpt_neox.layers.17.input_layernorm.bias": "model-00012-of-00028.safetensors",
+    "gpt_neox.layers.17.input_layernorm.weight": "model-00012-of-00028.safetensors",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "model-00013-of-00028.safetensors",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "model-00013-of-00028.safetensors",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "model-00013-of-00028.safetensors",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "model-00013-of-00028.safetensors",
+    "gpt_neox.layers.17.post_attention_layernorm.bias": "model-00012-of-00028.safetensors",
+    "gpt_neox.layers.17.post_attention_layernorm.weight": "model-00012-of-00028.safetensors",
+    "gpt_neox.layers.18.attention.dense.bias": "model-00013-of-00028.safetensors",
+    "gpt_neox.layers.18.attention.dense.weight": "model-00013-of-00028.safetensors",
+    "gpt_neox.layers.18.attention.query_key_value.bias": "model-00013-of-00028.safetensors",
+    "gpt_neox.layers.18.attention.query_key_value.weight": "model-00013-of-00028.safetensors",
+    "gpt_neox.layers.18.input_layernorm.bias": "model-00013-of-00028.safetensors",
+    "gpt_neox.layers.18.input_layernorm.weight": "model-00013-of-00028.safetensors",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "model-00014-of-00028.safetensors",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "model-00014-of-00028.safetensors",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "model-00013-of-00028.safetensors",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "model-00013-of-00028.safetensors",
+    "gpt_neox.layers.18.post_attention_layernorm.bias": "model-00013-of-00028.safetensors",
+    "gpt_neox.layers.18.post_attention_layernorm.weight": "model-00013-of-00028.safetensors",
+    "gpt_neox.layers.19.attention.dense.bias": "model-00014-of-00028.safetensors",
+    "gpt_neox.layers.19.attention.dense.weight": "model-00014-of-00028.safetensors",
+    "gpt_neox.layers.19.attention.query_key_value.bias": "model-00014-of-00028.safetensors",
+    "gpt_neox.layers.19.attention.query_key_value.weight": "model-00014-of-00028.safetensors",
+    "gpt_neox.layers.19.input_layernorm.bias": "model-00014-of-00028.safetensors",
+    "gpt_neox.layers.19.input_layernorm.weight": "model-00014-of-00028.safetensors",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "model-00014-of-00028.safetensors",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "model-00014-of-00028.safetensors",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "model-00014-of-00028.safetensors",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "model-00014-of-00028.safetensors",
+    "gpt_neox.layers.19.post_attention_layernorm.bias": "model-00014-of-00028.safetensors",
+    "gpt_neox.layers.19.post_attention_layernorm.weight": "model-00014-of-00028.safetensors",
+    "gpt_neox.layers.2.attention.dense.bias": "model-00002-of-00028.safetensors",
+    "gpt_neox.layers.2.attention.dense.weight": "model-00002-of-00028.safetensors",
+    "gpt_neox.layers.2.attention.query_key_value.bias": "model-00002-of-00028.safetensors",
+    "gpt_neox.layers.2.attention.query_key_value.weight": "model-00002-of-00028.safetensors",
+    "gpt_neox.layers.2.input_layernorm.bias": "model-00002-of-00028.safetensors",
+    "gpt_neox.layers.2.input_layernorm.weight": "model-00002-of-00028.safetensors",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00003-of-00028.safetensors",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00003-of-00028.safetensors",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00003-of-00028.safetensors",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00003-of-00028.safetensors",
+    "gpt_neox.layers.2.post_attention_layernorm.bias": "model-00002-of-00028.safetensors",
+    "gpt_neox.layers.2.post_attention_layernorm.weight": "model-00002-of-00028.safetensors",
+    "gpt_neox.layers.20.attention.dense.bias": "model-00015-of-00028.safetensors",
+    "gpt_neox.layers.20.attention.dense.weight": "model-00015-of-00028.safetensors",
+    "gpt_neox.layers.20.attention.query_key_value.bias": "model-00014-of-00028.safetensors",
+    "gpt_neox.layers.20.attention.query_key_value.weight": "model-00014-of-00028.safetensors",
+    "gpt_neox.layers.20.input_layernorm.bias": "model-00014-of-00028.safetensors",
+    "gpt_neox.layers.20.input_layernorm.weight": "model-00014-of-00028.safetensors",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "model-00015-of-00028.safetensors",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "model-00015-of-00028.safetensors",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "model-00015-of-00028.safetensors",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "model-00015-of-00028.safetensors",
+    "gpt_neox.layers.20.post_attention_layernorm.bias": "model-00014-of-00028.safetensors",
+    "gpt_neox.layers.20.post_attention_layernorm.weight": "model-00014-of-00028.safetensors",
+    "gpt_neox.layers.21.attention.dense.bias": "model-00015-of-00028.safetensors",
+    "gpt_neox.layers.21.attention.dense.weight": "model-00015-of-00028.safetensors",
+    "gpt_neox.layers.21.attention.query_key_value.bias": "model-00015-of-00028.safetensors",
+    "gpt_neox.layers.21.attention.query_key_value.weight": "model-00015-of-00028.safetensors",
+    "gpt_neox.layers.21.input_layernorm.bias": "model-00015-of-00028.safetensors",
+    "gpt_neox.layers.21.input_layernorm.weight": "model-00015-of-00028.safetensors",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "model-00016-of-00028.safetensors",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "model-00016-of-00028.safetensors",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "model-00015-of-00028.safetensors",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "model-00015-of-00028.safetensors",
+    "gpt_neox.layers.21.post_attention_layernorm.bias": "model-00015-of-00028.safetensors",
+    "gpt_neox.layers.21.post_attention_layernorm.weight": "model-00015-of-00028.safetensors",
+    "gpt_neox.layers.22.attention.dense.bias": "model-00016-of-00028.safetensors",
+    "gpt_neox.layers.22.attention.dense.weight": "model-00016-of-00028.safetensors",
+    "gpt_neox.layers.22.attention.query_key_value.bias": "model-00016-of-00028.safetensors",
+    "gpt_neox.layers.22.attention.query_key_value.weight": "model-00016-of-00028.safetensors",
+    "gpt_neox.layers.22.input_layernorm.bias": "model-00016-of-00028.safetensors",
+    "gpt_neox.layers.22.input_layernorm.weight": "model-00016-of-00028.safetensors",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "model-00016-of-00028.safetensors",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "model-00016-of-00028.safetensors",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "model-00016-of-00028.safetensors",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "model-00016-of-00028.safetensors",
+    "gpt_neox.layers.22.post_attention_layernorm.bias": "model-00016-of-00028.safetensors",
+    "gpt_neox.layers.22.post_attention_layernorm.weight": "model-00016-of-00028.safetensors",
+    "gpt_neox.layers.23.attention.dense.bias": "model-00017-of-00028.safetensors",
+    "gpt_neox.layers.23.attention.dense.weight": "model-00017-of-00028.safetensors",
+    "gpt_neox.layers.23.attention.query_key_value.bias": "model-00016-of-00028.safetensors",
+    "gpt_neox.layers.23.attention.query_key_value.weight": "model-00016-of-00028.safetensors",
+    "gpt_neox.layers.23.input_layernorm.bias": "model-00016-of-00028.safetensors",
+    "gpt_neox.layers.23.input_layernorm.weight": "model-00016-of-00028.safetensors",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "model-00017-of-00028.safetensors",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "model-00017-of-00028.safetensors",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "model-00017-of-00028.safetensors",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "model-00017-of-00028.safetensors",
+    "gpt_neox.layers.23.post_attention_layernorm.bias": "model-00016-of-00028.safetensors",
+    "gpt_neox.layers.23.post_attention_layernorm.weight": "model-00016-of-00028.safetensors",
+    "gpt_neox.layers.24.attention.dense.bias": "model-00017-of-00028.safetensors",
+    "gpt_neox.layers.24.attention.dense.weight": "model-00017-of-00028.safetensors",
+    "gpt_neox.layers.24.attention.query_key_value.bias": "model-00017-of-00028.safetensors",
+    "gpt_neox.layers.24.attention.query_key_value.weight": "model-00017-of-00028.safetensors",
+    "gpt_neox.layers.24.input_layernorm.bias": "model-00017-of-00028.safetensors",
+    "gpt_neox.layers.24.input_layernorm.weight": "model-00017-of-00028.safetensors",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "model-00018-of-00028.safetensors",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "model-00018-of-00028.safetensors",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "model-00017-of-00028.safetensors",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "model-00017-of-00028.safetensors",
+    "gpt_neox.layers.24.post_attention_layernorm.bias": "model-00017-of-00028.safetensors",
+    "gpt_neox.layers.24.post_attention_layernorm.weight": "model-00017-of-00028.safetensors",
+    "gpt_neox.layers.25.attention.dense.bias": "model-00018-of-00028.safetensors",
+    "gpt_neox.layers.25.attention.dense.weight": "model-00018-of-00028.safetensors",
+    "gpt_neox.layers.25.attention.query_key_value.bias": "model-00018-of-00028.safetensors",
+    "gpt_neox.layers.25.attention.query_key_value.weight": "model-00018-of-00028.safetensors",
+    "gpt_neox.layers.25.input_layernorm.bias": "model-00018-of-00028.safetensors",
+    "gpt_neox.layers.25.input_layernorm.weight": "model-00018-of-00028.safetensors",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "model-00018-of-00028.safetensors",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "model-00018-of-00028.safetensors",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "model-00018-of-00028.safetensors",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "model-00018-of-00028.safetensors",
+    "gpt_neox.layers.25.post_attention_layernorm.bias": "model-00018-of-00028.safetensors",
+    "gpt_neox.layers.25.post_attention_layernorm.weight": "model-00018-of-00028.safetensors",
+    "gpt_neox.layers.26.attention.dense.bias": "model-00019-of-00028.safetensors",
+    "gpt_neox.layers.26.attention.dense.weight": "model-00019-of-00028.safetensors",
+    "gpt_neox.layers.26.attention.query_key_value.bias": "model-00018-of-00028.safetensors",
+    "gpt_neox.layers.26.attention.query_key_value.weight": "model-00018-of-00028.safetensors",
+    "gpt_neox.layers.26.input_layernorm.bias": "model-00018-of-00028.safetensors",
+    "gpt_neox.layers.26.input_layernorm.weight": "model-00018-of-00028.safetensors",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "model-00019-of-00028.safetensors",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "model-00019-of-00028.safetensors",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "model-00019-of-00028.safetensors",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "model-00019-of-00028.safetensors",
+    "gpt_neox.layers.26.post_attention_layernorm.bias": "model-00018-of-00028.safetensors",
+    "gpt_neox.layers.26.post_attention_layernorm.weight": "model-00018-of-00028.safetensors",
+    "gpt_neox.layers.27.attention.dense.bias": "model-00019-of-00028.safetensors",
+    "gpt_neox.layers.27.attention.dense.weight": "model-00019-of-00028.safetensors",
+    "gpt_neox.layers.27.attention.query_key_value.bias": "model-00019-of-00028.safetensors",
+    "gpt_neox.layers.27.attention.query_key_value.weight": "model-00019-of-00028.safetensors",
+    "gpt_neox.layers.27.input_layernorm.bias": "model-00019-of-00028.safetensors",
+    "gpt_neox.layers.27.input_layernorm.weight": "model-00019-of-00028.safetensors",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "model-00020-of-00028.safetensors",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "model-00020-of-00028.safetensors",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "model-00019-of-00028.safetensors",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "model-00019-of-00028.safetensors",
+    "gpt_neox.layers.27.post_attention_layernorm.bias": "model-00019-of-00028.safetensors",
+    "gpt_neox.layers.27.post_attention_layernorm.weight": "model-00019-of-00028.safetensors",
+    "gpt_neox.layers.28.attention.dense.bias": "model-00020-of-00028.safetensors",
+    "gpt_neox.layers.28.attention.dense.weight": "model-00020-of-00028.safetensors",
+    "gpt_neox.layers.28.attention.query_key_value.bias": "model-00020-of-00028.safetensors",
+    "gpt_neox.layers.28.attention.query_key_value.weight": "model-00020-of-00028.safetensors",
+    "gpt_neox.layers.28.input_layernorm.bias": "model-00020-of-00028.safetensors",
+    "gpt_neox.layers.28.input_layernorm.weight": "model-00020-of-00028.safetensors",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "model-00020-of-00028.safetensors",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "model-00020-of-00028.safetensors",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "model-00020-of-00028.safetensors",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "model-00020-of-00028.safetensors",
+    "gpt_neox.layers.28.post_attention_layernorm.bias": "model-00020-of-00028.safetensors",
+    "gpt_neox.layers.28.post_attention_layernorm.weight": "model-00020-of-00028.safetensors",
+    "gpt_neox.layers.29.attention.dense.bias": "model-00021-of-00028.safetensors",
+    "gpt_neox.layers.29.attention.dense.weight": "model-00021-of-00028.safetensors",
+    "gpt_neox.layers.29.attention.query_key_value.bias": "model-00020-of-00028.safetensors",
+    "gpt_neox.layers.29.attention.query_key_value.weight": "model-00020-of-00028.safetensors",
+    "gpt_neox.layers.29.input_layernorm.bias": "model-00020-of-00028.safetensors",
+    "gpt_neox.layers.29.input_layernorm.weight": "model-00020-of-00028.safetensors",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "model-00021-of-00028.safetensors",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "model-00021-of-00028.safetensors",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "model-00021-of-00028.safetensors",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "model-00021-of-00028.safetensors",
+    "gpt_neox.layers.29.post_attention_layernorm.bias": "model-00020-of-00028.safetensors",
+    "gpt_neox.layers.29.post_attention_layernorm.weight": "model-00020-of-00028.safetensors",
+    "gpt_neox.layers.3.attention.dense.bias": "model-00003-of-00028.safetensors",
+    "gpt_neox.layers.3.attention.dense.weight": "model-00003-of-00028.safetensors",
+    "gpt_neox.layers.3.attention.query_key_value.bias": "model-00003-of-00028.safetensors",
+    "gpt_neox.layers.3.attention.query_key_value.weight": "model-00003-of-00028.safetensors",
+    "gpt_neox.layers.3.input_layernorm.bias": "model-00003-of-00028.safetensors",
+    "gpt_neox.layers.3.input_layernorm.weight": "model-00003-of-00028.safetensors",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00004-of-00028.safetensors",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00004-of-00028.safetensors",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00003-of-00028.safetensors",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00003-of-00028.safetensors",
+    "gpt_neox.layers.3.post_attention_layernorm.bias": "model-00003-of-00028.safetensors",
+    "gpt_neox.layers.3.post_attention_layernorm.weight": "model-00003-of-00028.safetensors",
+    "gpt_neox.layers.30.attention.dense.bias": "model-00021-of-00028.safetensors",
+    "gpt_neox.layers.30.attention.dense.weight": "model-00021-of-00028.safetensors",
+    "gpt_neox.layers.30.attention.query_key_value.bias": "model-00021-of-00028.safetensors",
+    "gpt_neox.layers.30.attention.query_key_value.weight": "model-00021-of-00028.safetensors",
+    "gpt_neox.layers.30.input_layernorm.bias": "model-00021-of-00028.safetensors",
+    "gpt_neox.layers.30.input_layernorm.weight": "model-00021-of-00028.safetensors",
+    "gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "model-00022-of-00028.safetensors",
+    "gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "model-00022-of-00028.safetensors",
+    "gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "model-00021-of-00028.safetensors",
+    "gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "model-00021-of-00028.safetensors",
+    "gpt_neox.layers.30.post_attention_layernorm.bias": "model-00021-of-00028.safetensors",
+    "gpt_neox.layers.30.post_attention_layernorm.weight": "model-00021-of-00028.safetensors",
+    "gpt_neox.layers.31.attention.dense.bias": "model-00022-of-00028.safetensors",
+    "gpt_neox.layers.31.attention.dense.weight": "model-00022-of-00028.safetensors",
+    "gpt_neox.layers.31.attention.query_key_value.bias": "model-00022-of-00028.safetensors",
+    "gpt_neox.layers.31.attention.query_key_value.weight": "model-00022-of-00028.safetensors",
+    "gpt_neox.layers.31.input_layernorm.bias": "model-00022-of-00028.safetensors",
+    "gpt_neox.layers.31.input_layernorm.weight": "model-00022-of-00028.safetensors",
+    "gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "model-00022-of-00028.safetensors",
+    "gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "model-00022-of-00028.safetensors",
+    "gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "model-00022-of-00028.safetensors",
+    "gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "model-00022-of-00028.safetensors",
+    "gpt_neox.layers.31.post_attention_layernorm.bias": "model-00022-of-00028.safetensors",
+    "gpt_neox.layers.31.post_attention_layernorm.weight": "model-00022-of-00028.safetensors",
+    "gpt_neox.layers.32.attention.dense.bias": "model-00023-of-00028.safetensors",
+    "gpt_neox.layers.32.attention.dense.weight": "model-00023-of-00028.safetensors",
+    "gpt_neox.layers.32.attention.query_key_value.bias": "model-00022-of-00028.safetensors",
+    "gpt_neox.layers.32.attention.query_key_value.weight": "model-00022-of-00028.safetensors",
+    "gpt_neox.layers.32.input_layernorm.bias": "model-00022-of-00028.safetensors",
+    "gpt_neox.layers.32.input_layernorm.weight": "model-00022-of-00028.safetensors",
+    "gpt_neox.layers.32.mlp.dense_4h_to_h.bias": "model-00023-of-00028.safetensors",
+    "gpt_neox.layers.32.mlp.dense_4h_to_h.weight": "model-00023-of-00028.safetensors",
+    "gpt_neox.layers.32.mlp.dense_h_to_4h.bias": "model-00023-of-00028.safetensors",
+    "gpt_neox.layers.32.mlp.dense_h_to_4h.weight": "model-00023-of-00028.safetensors",
+    "gpt_neox.layers.32.post_attention_layernorm.bias": "model-00022-of-00028.safetensors",
+    "gpt_neox.layers.32.post_attention_layernorm.weight": "model-00022-of-00028.safetensors",
+    "gpt_neox.layers.33.attention.dense.bias": "model-00023-of-00028.safetensors",
+    "gpt_neox.layers.33.attention.dense.weight": "model-00023-of-00028.safetensors",
+    "gpt_neox.layers.33.attention.query_key_value.bias": "model-00023-of-00028.safetensors",
+    "gpt_neox.layers.33.attention.query_key_value.weight": "model-00023-of-00028.safetensors",
+    "gpt_neox.layers.33.input_layernorm.bias": "model-00023-of-00028.safetensors",
+    "gpt_neox.layers.33.input_layernorm.weight": "model-00023-of-00028.safetensors",
+    "gpt_neox.layers.33.mlp.dense_4h_to_h.bias": "model-00024-of-00028.safetensors",
+    "gpt_neox.layers.33.mlp.dense_4h_to_h.weight": "model-00024-of-00028.safetensors",
+    "gpt_neox.layers.33.mlp.dense_h_to_4h.bias": "model-00023-of-00028.safetensors",
+    "gpt_neox.layers.33.mlp.dense_h_to_4h.weight": "model-00023-of-00028.safetensors",
+    "gpt_neox.layers.33.post_attention_layernorm.bias": "model-00023-of-00028.safetensors",
+    "gpt_neox.layers.33.post_attention_layernorm.weight": "model-00023-of-00028.safetensors",
+    "gpt_neox.layers.34.attention.dense.bias": "model-00024-of-00028.safetensors",
+    "gpt_neox.layers.34.attention.dense.weight": "model-00024-of-00028.safetensors",
+    "gpt_neox.layers.34.attention.query_key_value.bias": "model-00024-of-00028.safetensors",
+    "gpt_neox.layers.34.attention.query_key_value.weight": "model-00024-of-00028.safetensors",
+    "gpt_neox.layers.34.input_layernorm.bias": "model-00024-of-00028.safetensors",
+    "gpt_neox.layers.34.input_layernorm.weight": "model-00024-of-00028.safetensors",
+    "gpt_neox.layers.34.mlp.dense_4h_to_h.bias": "model-00024-of-00028.safetensors",
+    "gpt_neox.layers.34.mlp.dense_4h_to_h.weight": "model-00024-of-00028.safetensors",
+    "gpt_neox.layers.34.mlp.dense_h_to_4h.bias": "model-00024-of-00028.safetensors",
+    "gpt_neox.layers.34.mlp.dense_h_to_4h.weight": "model-00024-of-00028.safetensors",
+    "gpt_neox.layers.34.post_attention_layernorm.bias": "model-00024-of-00028.safetensors",
+    "gpt_neox.layers.34.post_attention_layernorm.weight": "model-00024-of-00028.safetensors",
+    "gpt_neox.layers.35.attention.dense.bias": "model-00025-of-00028.safetensors",
+    "gpt_neox.layers.35.attention.dense.weight": "model-00025-of-00028.safetensors",
+    "gpt_neox.layers.35.attention.query_key_value.bias": "model-00024-of-00028.safetensors",
+    "gpt_neox.layers.35.attention.query_key_value.weight": "model-00024-of-00028.safetensors",
+    "gpt_neox.layers.35.input_layernorm.bias": "model-00024-of-00028.safetensors",
+    "gpt_neox.layers.35.input_layernorm.weight": "model-00024-of-00028.safetensors",
+    "gpt_neox.layers.35.mlp.dense_4h_to_h.bias": "model-00025-of-00028.safetensors",
+    "gpt_neox.layers.35.mlp.dense_4h_to_h.weight": "model-00025-of-00028.safetensors",
+    "gpt_neox.layers.35.mlp.dense_h_to_4h.bias": "model-00025-of-00028.safetensors",
+    "gpt_neox.layers.35.mlp.dense_h_to_4h.weight": "model-00025-of-00028.safetensors",
+    "gpt_neox.layers.35.post_attention_layernorm.bias": "model-00024-of-00028.safetensors",
+    "gpt_neox.layers.35.post_attention_layernorm.weight": "model-00024-of-00028.safetensors",
+    "gpt_neox.layers.36.attention.dense.bias": "model-00025-of-00028.safetensors",
+    "gpt_neox.layers.36.attention.dense.weight": "model-00025-of-00028.safetensors",
+    "gpt_neox.layers.36.attention.query_key_value.bias": "model-00025-of-00028.safetensors",
+    "gpt_neox.layers.36.attention.query_key_value.weight": "model-00025-of-00028.safetensors",
+    "gpt_neox.layers.36.input_layernorm.bias": "model-00025-of-00028.safetensors",
+    "gpt_neox.layers.36.input_layernorm.weight": "model-00025-of-00028.safetensors",
+    "gpt_neox.layers.36.mlp.dense_4h_to_h.bias": "model-00026-of-00028.safetensors",
+    "gpt_neox.layers.36.mlp.dense_4h_to_h.weight": "model-00026-of-00028.safetensors",
+    "gpt_neox.layers.36.mlp.dense_h_to_4h.bias": "model-00025-of-00028.safetensors",
+    "gpt_neox.layers.36.mlp.dense_h_to_4h.weight": "model-00025-of-00028.safetensors",
+    "gpt_neox.layers.36.post_attention_layernorm.bias": "model-00025-of-00028.safetensors",
+    "gpt_neox.layers.36.post_attention_layernorm.weight": "model-00025-of-00028.safetensors",
+    "gpt_neox.layers.37.attention.dense.bias": "model-00026-of-00028.safetensors",
+    "gpt_neox.layers.37.attention.dense.weight": "model-00026-of-00028.safetensors",
+    "gpt_neox.layers.37.attention.query_key_value.bias": "model-00026-of-00028.safetensors",
+    "gpt_neox.layers.37.attention.query_key_value.weight": "model-00026-of-00028.safetensors",
+    "gpt_neox.layers.37.input_layernorm.bias": "model-00026-of-00028.safetensors",
+    "gpt_neox.layers.37.input_layernorm.weight": "model-00026-of-00028.safetensors",
+    "gpt_neox.layers.37.mlp.dense_4h_to_h.bias": "model-00026-of-00028.safetensors",
+    "gpt_neox.layers.37.mlp.dense_4h_to_h.weight": "model-00026-of-00028.safetensors",
+    "gpt_neox.layers.37.mlp.dense_h_to_4h.bias": "model-00026-of-00028.safetensors",
+    "gpt_neox.layers.37.mlp.dense_h_to_4h.weight": "model-00026-of-00028.safetensors",
+    "gpt_neox.layers.37.post_attention_layernorm.bias": "model-00026-of-00028.safetensors",
+    "gpt_neox.layers.37.post_attention_layernorm.weight": "model-00026-of-00028.safetensors",
+    "gpt_neox.layers.38.attention.dense.bias": "model-00027-of-00028.safetensors",
+    "gpt_neox.layers.38.attention.dense.weight": "model-00027-of-00028.safetensors",
+    "gpt_neox.layers.38.attention.query_key_value.bias": "model-00026-of-00028.safetensors",
+    "gpt_neox.layers.38.attention.query_key_value.weight": "model-00026-of-00028.safetensors",
+    "gpt_neox.layers.38.input_layernorm.bias": "model-00026-of-00028.safetensors",
+    "gpt_neox.layers.38.input_layernorm.weight": "model-00026-of-00028.safetensors",
+    "gpt_neox.layers.38.mlp.dense_4h_to_h.bias": "model-00027-of-00028.safetensors",
+    "gpt_neox.layers.38.mlp.dense_4h_to_h.weight": "model-00027-of-00028.safetensors",
+    "gpt_neox.layers.38.mlp.dense_h_to_4h.bias": "model-00027-of-00028.safetensors",
+    "gpt_neox.layers.38.mlp.dense_h_to_4h.weight": "model-00027-of-00028.safetensors",
+    "gpt_neox.layers.38.post_attention_layernorm.bias": "model-00026-of-00028.safetensors",
+    "gpt_neox.layers.38.post_attention_layernorm.weight": "model-00026-of-00028.safetensors",
+    "gpt_neox.layers.39.attention.dense.bias": "model-00027-of-00028.safetensors",
+    "gpt_neox.layers.39.attention.dense.weight": "model-00027-of-00028.safetensors",
+    "gpt_neox.layers.39.attention.query_key_value.bias": "model-00027-of-00028.safetensors",
+    "gpt_neox.layers.39.attention.query_key_value.weight": "model-00027-of-00028.safetensors",
+    "gpt_neox.layers.39.input_layernorm.bias": "model-00027-of-00028.safetensors",
+    "gpt_neox.layers.39.input_layernorm.weight": "model-00027-of-00028.safetensors",
+    "gpt_neox.layers.39.mlp.dense_4h_to_h.bias": "model-00028-of-00028.safetensors",
+    "gpt_neox.layers.39.mlp.dense_4h_to_h.weight": "model-00028-of-00028.safetensors",
+    "gpt_neox.layers.39.mlp.dense_h_to_4h.bias": "model-00027-of-00028.safetensors",
+    "gpt_neox.layers.39.mlp.dense_h_to_4h.weight": "model-00027-of-00028.safetensors",
+    "gpt_neox.layers.39.post_attention_layernorm.bias": "model-00027-of-00028.safetensors",
+    "gpt_neox.layers.39.post_attention_layernorm.weight": "model-00027-of-00028.safetensors",
+    "gpt_neox.layers.4.attention.dense.bias": "model-00004-of-00028.safetensors",
+    "gpt_neox.layers.4.attention.dense.weight": "model-00004-of-00028.safetensors",
+    "gpt_neox.layers.4.attention.query_key_value.bias": "model-00004-of-00028.safetensors",
+    "gpt_neox.layers.4.attention.query_key_value.weight": "model-00004-of-00028.safetensors",
+    "gpt_neox.layers.4.input_layernorm.bias": "model-00004-of-00028.safetensors",
+    "gpt_neox.layers.4.input_layernorm.weight": "model-00004-of-00028.safetensors",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00004-of-00028.safetensors",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00004-of-00028.safetensors",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00004-of-00028.safetensors",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00004-of-00028.safetensors",
+    "gpt_neox.layers.4.post_attention_layernorm.bias": "model-00004-of-00028.safetensors",
+    "gpt_neox.layers.4.post_attention_layernorm.weight": "model-00004-of-00028.safetensors",
+    "gpt_neox.layers.5.attention.dense.bias": "model-00005-of-00028.safetensors",
+    "gpt_neox.layers.5.attention.dense.weight": "model-00005-of-00028.safetensors",
+    "gpt_neox.layers.5.attention.query_key_value.bias": "model-00004-of-00028.safetensors",
+    "gpt_neox.layers.5.attention.query_key_value.weight": "model-00004-of-00028.safetensors",
+    "gpt_neox.layers.5.input_layernorm.bias": "model-00004-of-00028.safetensors",
+    "gpt_neox.layers.5.input_layernorm.weight": "model-00004-of-00028.safetensors",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00005-of-00028.safetensors",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00005-of-00028.safetensors",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00005-of-00028.safetensors",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00005-of-00028.safetensors",
+    "gpt_neox.layers.5.post_attention_layernorm.bias": "model-00004-of-00028.safetensors",
+    "gpt_neox.layers.5.post_attention_layernorm.weight": "model-00004-of-00028.safetensors",
+    "gpt_neox.layers.6.attention.dense.bias": "model-00005-of-00028.safetensors",
+    "gpt_neox.layers.6.attention.dense.weight": "model-00005-of-00028.safetensors",
+    "gpt_neox.layers.6.attention.query_key_value.bias": "model-00005-of-00028.safetensors",
+    "gpt_neox.layers.6.attention.query_key_value.weight": "model-00005-of-00028.safetensors",
+    "gpt_neox.layers.6.input_layernorm.bias": "model-00005-of-00028.safetensors",
+    "gpt_neox.layers.6.input_layernorm.weight": "model-00005-of-00028.safetensors",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00006-of-00028.safetensors",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00006-of-00028.safetensors",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00005-of-00028.safetensors",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00005-of-00028.safetensors",
+    "gpt_neox.layers.6.post_attention_layernorm.bias": "model-00005-of-00028.safetensors",
+    "gpt_neox.layers.6.post_attention_layernorm.weight": "model-00005-of-00028.safetensors",
+    "gpt_neox.layers.7.attention.dense.bias": "model-00006-of-00028.safetensors",
+    "gpt_neox.layers.7.attention.dense.weight": "model-00006-of-00028.safetensors",
+    "gpt_neox.layers.7.attention.query_key_value.bias": "model-00006-of-00028.safetensors",
+    "gpt_neox.layers.7.attention.query_key_value.weight": "model-00006-of-00028.safetensors",
+    "gpt_neox.layers.7.input_layernorm.bias": "model-00006-of-00028.safetensors",
+    "gpt_neox.layers.7.input_layernorm.weight": "model-00006-of-00028.safetensors",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00006-of-00028.safetensors",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00006-of-00028.safetensors",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00006-of-00028.safetensors",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00006-of-00028.safetensors",
+    "gpt_neox.layers.7.post_attention_layernorm.bias": "model-00006-of-00028.safetensors",
+    "gpt_neox.layers.7.post_attention_layernorm.weight": "model-00006-of-00028.safetensors",
+    "gpt_neox.layers.8.attention.dense.bias": "model-00007-of-00028.safetensors",
+    "gpt_neox.layers.8.attention.dense.weight": "model-00007-of-00028.safetensors",
+    "gpt_neox.layers.8.attention.query_key_value.bias": "model-00006-of-00028.safetensors",
+    "gpt_neox.layers.8.attention.query_key_value.weight": "model-00006-of-00028.safetensors",
+    "gpt_neox.layers.8.input_layernorm.bias": "model-00006-of-00028.safetensors",
+    "gpt_neox.layers.8.input_layernorm.weight": "model-00006-of-00028.safetensors",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00007-of-00028.safetensors",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00007-of-00028.safetensors",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00007-of-00028.safetensors",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00007-of-00028.safetensors",
+    "gpt_neox.layers.8.post_attention_layernorm.bias": "model-00006-of-00028.safetensors",
+    "gpt_neox.layers.8.post_attention_layernorm.weight": "model-00006-of-00028.safetensors",
+    "gpt_neox.layers.9.attention.dense.bias": "model-00007-of-00028.safetensors",
+    "gpt_neox.layers.9.attention.dense.weight": "model-00007-of-00028.safetensors",
+    "gpt_neox.layers.9.attention.query_key_value.bias": "model-00007-of-00028.safetensors",
+    "gpt_neox.layers.9.attention.query_key_value.weight": "model-00007-of-00028.safetensors",
+    "gpt_neox.layers.9.input_layernorm.bias": "model-00007-of-00028.safetensors",
+    "gpt_neox.layers.9.input_layernorm.weight": "model-00007-of-00028.safetensors",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00008-of-00028.safetensors",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00008-of-00028.safetensors",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00007-of-00028.safetensors",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00007-of-00028.safetensors",
+    "gpt_neox.layers.9.post_attention_layernorm.bias": "model-00007-of-00028.safetensors",
+    "gpt_neox.layers.9.post_attention_layernorm.weight": "model-00007-of-00028.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|sep|>",
+    "<|acc|>",
+    "<|tel|>",
+    "<|rrn|>"
+  ],
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,72 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|unused0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|unused1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<|sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30000": {
+      "content": "<|acc|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30001": {
+      "content": "<|tel|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30002": {
+      "content": "<|rrn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|sep|>",
+    "<|acc|>",
+    "<|tel|>",
+    "<|rrn|>"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}