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 sha256:58758c68d2145d9aa422babfd993679353bf03a9cd225b541b0bfd8ad8fb7ade
+size 937340864

model-00002-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bb309d182a168b94dc17ccb55cd035525b5e3f6fd060a8654630ae5d2097c71
+size 839036768

model-00003-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c4440a265eb9d6ac6c982a19a2c835feb5568eb105901057eab9e189c565e3e
+size 839036528

model-00004-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21260cfc6b465cc27f03c015dde0a4f44e91342bd84bfad8db52482f0d2fb89d
+size 996364592

model-00005-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:676d67908cf5349d858686524ff71923a56939a581116e7b9c21ef76add62009
+size 891475792

model-00006-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b73d73b64431d16d78d3bb8e0282ae709590c7d46c503b12300a1bb5225e249c
+size 996364592

model-00007-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8929ff7b77a40308a79bb1fca1ae594fcb859b0f03b2bb64e08cea5dad10a62f
+size 891475792

model-00008-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ac4172f6e4e386d509d12fa2e23c20649181f2635f3f17c3811d64c376ca1cf
+size 996364608

model-00009-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:817ba7bcde2a8b428a051409bdad9056241c652620ab6e240f0fa7a9fa03dbad
+size 891475808

model-00010-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:048bb9f9731a466126c506b47ec99a3695a855458474043f024987bd2533a0bd
+size 996364616

model-00011-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dd66c42eb2fcb8716069962441a3ab0713820542cdf072c214d88afd716c73c
+size 891475808

model-00012-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8d99b4b8ef958183c4d7dfc18b8204ebdd3d7f93a7bab5265f64ee0fc448021
+size 996364616

model-00013-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f695527d11b08f073b6bd6b45aea9ee8102a49c4849e30ba4e89802cb1c22b4c
+size 891475808

model-00014-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f69c09e43d697bd4f3c7d909309122f93a632d6180cf8ec987f820c3a4bdfe9
+size 996364616

model-00015-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49ea289eb1edd84696b830cc35dcc6681ff8c6b80ac83beec00286fbcb25e1df
+size 891475808

model-00016-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59cdb9da1eab874a6c1f42539f72a18613a0cd125fe6b13e846828db26e043d4
+size 996364616

model-00017-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0246923475c643efd65e9f24cbc74678b1492a2b09f96ecb8137f6ab5520d30d
+size 891475808

model-00018-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b94b3848d5c0a7bbcd604de076f2035114e188be9d230f76cd1b1543b5ce4b8c
+size 996364616

model-00019-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc36c91c422ab13420dddfbdf589cab1f56bdbcbfba1273823fccf1d9b5b7d56
+size 891475808

model-00020-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30aa038da70a1ea9194f7ffaaf5692511d66c9ac250abbc993b595b60bf31305
+size 996364616

model-00021-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e49607534ab450d81ef0ae981a1ba343d72480b0a907a662f6610a9d2483f43
+size 891475808

model-00022-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37e304d71d11d0c83506437c5d4f9fbdde267d6db5b87a6bee4eac11238fba25
+size 996364616

model-00023-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c709ccd8c6cfec624b95a403046d04b194340d582278229f8ae633743de2c1b8
+size 891475808

model-00024-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f8bcadf00c761bd98fe42d643c76ac45d6b6f147b30f0fe7efa1de825343482
+size 996364616

model-00025-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4282442a70dc2655d135bc4ee8c5329fca19a4e3d90901f87e45d44a5c8035d
+size 891475808

model-00026-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f164722917e29449538a0cac3b9fd8866bfea153ee606782e1597a71c83975b
+size 996364616

model-00027-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3a42487f15523ca7debaa544c85b6bdab55b607cdd9a3af08a7211c12f94d06
+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"
+}