Upload GPTNeoXForCausalLM

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "./train_model/koquality-polyglot-ko-12.8b-inst",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 2,
+  "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": "float32",
+  "transformers_version": "4.35.0",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 30003
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "transformers_version": "4.35.0"
+}

model-00001-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91ea800baea1e52f5c16a369d7b738a8f9603fdad0ba2356aff546824da8af52
+size 4809733320

model-00002-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5b445d3e8609260c7aa12a6618678abb9235bfa1f2131b66fa4ef8bb5c9a6ea
+size 4929357120

model-00003-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:645e45e63d202454a2226b338c7d052c44b316b8748332071dea47efc1559170
+size 4719600952

model-00004-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c5c22add1ebfa29c48a3aab8d32d9d45d9cbe02f966aec4833abdcc902207f8
+size 4614701976

model-00005-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef027a47210991516e1e3bb19fffc3d978180dc1449cf7ce4fa225c62ac7fd8f
+size 4614722920

model-00006-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:186403053d11ad4c4e3cf7b67d2d06bee884e3a5bab67d7ca880a100cfed15f0
+size 4929357168

model-00007-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0aaabcb7ba533d411cdcfb517a53d312b8b2db60a345d731012923d9614be46
+size 4719600984

model-00008-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69fbb262d26f3de5e3f241a2d6c41342c2b6b89eb53ba10aad4489644b32b778
+size 4614701976

model-00009-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2235e24444b5e279c10a75fbeec203d91a6de92bc96f9c8ff19d1e9b67a1ddb2
+size 4614722920

model-00010-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f75ebd9af92b16960ff13b28e12a4e9af295f221dbbfb9fd9f2060eaec822cb4
+size 4929357168

model-00011-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:107f55b6529d232150050d726258fed0b2e60aedfa487dfd27e94fdbf3197669
+size 4075462440

model.safetensors.index.json

@@ -0,0 +1,491 @@
+{
+  "metadata": {
+    "total_size": 51571261440
+  },
+  "weight_map": {
+    "embed_out.weight": "model-00011-of-00011.safetensors",
+    "gpt_neox.embed_in.weight": "model-00001-of-00011.safetensors",
+    "gpt_neox.final_layer_norm.bias": "model-00011-of-00011.safetensors",
+    "gpt_neox.final_layer_norm.weight": "model-00011-of-00011.safetensors",
+    "gpt_neox.layers.0.attention.dense.bias": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.0.attention.dense.weight": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.1.attention.dense.bias": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.1.attention.dense.weight": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.1.attention.query_key_value.bias": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.1.attention.query_key_value.weight": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.1.input_layernorm.bias": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.1.input_layernorm.weight": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.10.attention.dense.bias": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.10.attention.dense.weight": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.10.attention.query_key_value.bias": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.10.attention.query_key_value.weight": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.10.input_layernorm.bias": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.10.input_layernorm.weight": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.10.post_attention_layernorm.bias": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.10.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.11.attention.dense.bias": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.11.attention.dense.weight": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.11.attention.query_key_value.bias": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.11.attention.query_key_value.weight": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.11.input_layernorm.bias": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.11.input_layernorm.weight": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.11.post_attention_layernorm.bias": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.11.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.12.attention.dense.bias": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.12.attention.dense.weight": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.12.attention.query_key_value.bias": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.12.attention.query_key_value.weight": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.12.input_layernorm.bias": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.12.input_layernorm.weight": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.12.post_attention_layernorm.bias": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.12.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.13.attention.dense.bias": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.13.attention.dense.weight": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.13.attention.query_key_value.bias": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.13.attention.query_key_value.weight": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.13.input_layernorm.bias": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.13.input_layernorm.weight": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.13.post_attention_layernorm.bias": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.13.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.14.attention.dense.bias": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.14.attention.dense.weight": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.14.attention.query_key_value.bias": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.14.attention.query_key_value.weight": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.14.input_layernorm.bias": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.14.input_layernorm.weight": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.14.post_attention_layernorm.bias": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.14.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+    "gpt_neox.layers.15.attention.dense.bias": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.15.attention.dense.weight": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.15.attention.query_key_value.bias": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.15.attention.query_key_value.weight": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.15.input_layernorm.bias": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.15.input_layernorm.weight": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.15.post_attention_layernorm.bias": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.15.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.16.attention.dense.bias": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.16.attention.dense.weight": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.16.attention.query_key_value.bias": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.16.attention.query_key_value.weight": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.16.input_layernorm.bias": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.16.input_layernorm.weight": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.16.post_attention_layernorm.bias": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.16.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.17.attention.dense.bias": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.17.attention.dense.weight": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.17.attention.query_key_value.bias": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.17.attention.query_key_value.weight": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.17.input_layernorm.bias": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.17.input_layernorm.weight": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.17.post_attention_layernorm.bias": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.17.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.18.attention.dense.bias": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.18.attention.dense.weight": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.18.attention.query_key_value.bias": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.18.attention.query_key_value.weight": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.18.input_layernorm.bias": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.18.input_layernorm.weight": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.18.post_attention_layernorm.bias": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.18.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+    "gpt_neox.layers.19.attention.dense.bias": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.19.attention.dense.weight": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.19.attention.query_key_value.bias": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.19.attention.query_key_value.weight": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.19.input_layernorm.bias": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.19.input_layernorm.weight": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.19.post_attention_layernorm.bias": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.19.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.2.attention.dense.bias": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.2.attention.dense.weight": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.2.attention.query_key_value.bias": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.2.attention.query_key_value.weight": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.2.input_layernorm.bias": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.2.input_layernorm.weight": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.2.post_attention_layernorm.bias": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.2.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.20.attention.dense.bias": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.20.attention.dense.weight": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.20.attention.query_key_value.bias": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.20.attention.query_key_value.weight": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.20.input_layernorm.bias": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.20.input_layernorm.weight": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.20.post_attention_layernorm.bias": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.20.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.21.attention.dense.bias": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.21.attention.dense.weight": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.21.attention.query_key_value.bias": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.21.attention.query_key_value.weight": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.21.input_layernorm.bias": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.21.input_layernorm.weight": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.21.post_attention_layernorm.bias": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.21.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.22.attention.dense.bias": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.22.attention.dense.weight": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.22.attention.query_key_value.bias": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.22.attention.query_key_value.weight": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.22.input_layernorm.bias": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.22.input_layernorm.weight": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.22.post_attention_layernorm.bias": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.22.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
+    "gpt_neox.layers.23.attention.dense.bias": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.23.attention.dense.weight": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.23.attention.query_key_value.bias": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.23.attention.query_key_value.weight": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.23.input_layernorm.bias": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.23.input_layernorm.weight": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.23.post_attention_layernorm.bias": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.23.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.24.attention.dense.bias": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.24.attention.dense.weight": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.24.attention.query_key_value.bias": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.24.attention.query_key_value.weight": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.24.input_layernorm.bias": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.24.input_layernorm.weight": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.24.post_attention_layernorm.bias": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.24.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.25.attention.dense.bias": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.25.attention.dense.weight": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.25.attention.query_key_value.bias": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.25.attention.query_key_value.weight": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.25.input_layernorm.bias": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.25.input_layernorm.weight": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.25.post_attention_layernorm.bias": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.25.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.26.attention.dense.bias": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.26.attention.dense.weight": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.26.attention.query_key_value.bias": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.26.attention.query_key_value.weight": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.26.input_layernorm.bias": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.26.input_layernorm.weight": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.26.post_attention_layernorm.bias": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.26.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+    "gpt_neox.layers.27.attention.dense.bias": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.27.attention.dense.weight": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.27.attention.query_key_value.bias": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.27.attention.query_key_value.weight": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.27.input_layernorm.bias": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.27.input_layernorm.weight": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.27.post_attention_layernorm.bias": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.27.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.28.attention.dense.bias": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.28.attention.dense.weight": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.28.attention.query_key_value.bias": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.28.attention.query_key_value.weight": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.28.input_layernorm.bias": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.28.input_layernorm.weight": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.28.post_attention_layernorm.bias": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.28.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.29.attention.dense.bias": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.29.attention.dense.weight": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.29.attention.query_key_value.bias": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.29.attention.query_key_value.weight": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.29.input_layernorm.bias": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.29.input_layernorm.weight": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.29.post_attention_layernorm.bias": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.29.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+    "gpt_neox.layers.3.attention.dense.bias": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.3.attention.dense.weight": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.3.attention.query_key_value.bias": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.3.attention.query_key_value.weight": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.3.input_layernorm.bias": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.3.input_layernorm.weight": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.3.post_attention_layernorm.bias": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.3.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
+    "gpt_neox.layers.30.attention.dense.bias": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.30.attention.dense.weight": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.30.attention.query_key_value.bias": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.30.attention.query_key_value.weight": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.30.input_layernorm.bias": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.30.input_layernorm.weight": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.30.post_attention_layernorm.bias": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.30.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.31.attention.dense.bias": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.31.attention.dense.weight": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.31.attention.query_key_value.bias": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.31.attention.query_key_value.weight": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.31.input_layernorm.bias": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.31.input_layernorm.weight": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.31.post_attention_layernorm.bias": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.31.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.32.attention.dense.bias": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.32.attention.dense.weight": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.32.attention.query_key_value.bias": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.32.attention.query_key_value.weight": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.32.input_layernorm.bias": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.32.input_layernorm.weight": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.32.mlp.dense_4h_to_h.bias": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.32.mlp.dense_4h_to_h.weight": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.32.mlp.dense_h_to_4h.bias": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.32.mlp.dense_h_to_4h.weight": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.32.post_attention_layernorm.bias": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.32.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.33.attention.dense.bias": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.33.attention.dense.weight": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.33.attention.query_key_value.bias": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.33.attention.query_key_value.weight": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.33.input_layernorm.bias": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.33.input_layernorm.weight": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.33.mlp.dense_4h_to_h.bias": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.33.mlp.dense_4h_to_h.weight": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.33.mlp.dense_h_to_4h.bias": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.33.mlp.dense_h_to_4h.weight": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.33.post_attention_layernorm.bias": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.33.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+    "gpt_neox.layers.34.attention.dense.bias": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.34.attention.dense.weight": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.34.attention.query_key_value.bias": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.34.attention.query_key_value.weight": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.34.input_layernorm.bias": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.34.input_layernorm.weight": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.34.mlp.dense_4h_to_h.bias": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.34.mlp.dense_4h_to_h.weight": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.34.mlp.dense_h_to_4h.bias": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.34.mlp.dense_h_to_4h.weight": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.34.post_attention_layernorm.bias": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.34.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.35.attention.dense.bias": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.35.attention.dense.weight": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.35.attention.query_key_value.bias": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.35.attention.query_key_value.weight": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.35.input_layernorm.bias": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.35.input_layernorm.weight": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.35.mlp.dense_4h_to_h.bias": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.35.mlp.dense_4h_to_h.weight": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.35.mlp.dense_h_to_4h.bias": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.35.mlp.dense_h_to_4h.weight": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.35.post_attention_layernorm.bias": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.35.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.36.attention.dense.bias": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.36.attention.dense.weight": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.36.attention.query_key_value.bias": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.36.attention.query_key_value.weight": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.36.input_layernorm.bias": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.36.input_layernorm.weight": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.36.mlp.dense_4h_to_h.bias": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.36.mlp.dense_4h_to_h.weight": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.36.mlp.dense_h_to_4h.bias": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.36.mlp.dense_h_to_4h.weight": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.36.post_attention_layernorm.bias": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.36.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.37.attention.dense.bias": "model-00011-of-00011.safetensors",
+    "gpt_neox.layers.37.attention.dense.weight": "model-00011-of-00011.safetensors",
+    "gpt_neox.layers.37.attention.query_key_value.bias": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.37.attention.query_key_value.weight": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.37.input_layernorm.bias": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.37.input_layernorm.weight": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.37.mlp.dense_4h_to_h.bias": "model-00011-of-00011.safetensors",
+    "gpt_neox.layers.37.mlp.dense_4h_to_h.weight": "model-00011-of-00011.safetensors",
+    "gpt_neox.layers.37.mlp.dense_h_to_4h.bias": "model-00011-of-00011.safetensors",
+    "gpt_neox.layers.37.mlp.dense_h_to_4h.weight": "model-00011-of-00011.safetensors",
+    "gpt_neox.layers.37.post_attention_layernorm.bias": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.37.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
+    "gpt_neox.layers.38.attention.dense.bias": "model-00011-of-00011.safetensors",
+    "gpt_neox.layers.38.attention.dense.weight": "model-00011-of-00011.safetensors",
+    "gpt_neox.layers.38.attention.query_key_value.bias": "model-00011-of-00011.safetensors",
+    "gpt_neox.layers.38.attention.query_key_value.weight": "model-00011-of-00011.safetensors",
+    "gpt_neox.layers.38.input_layernorm.bias": "model-00011-of-00011.safetensors",
+    "gpt_neox.layers.38.input_layernorm.weight": "model-00011-of-00011.safetensors",
+    "gpt_neox.layers.38.mlp.dense_4h_to_h.bias": "model-00011-of-00011.safetensors",
+    "gpt_neox.layers.38.mlp.dense_4h_to_h.weight": "model-00011-of-00011.safetensors",
+    "gpt_neox.layers.38.mlp.dense_h_to_4h.bias": "model-00011-of-00011.safetensors",
+    "gpt_neox.layers.38.mlp.dense_h_to_4h.weight": "model-00011-of-00011.safetensors",
+    "gpt_neox.layers.38.post_attention_layernorm.bias": "model-00011-of-00011.safetensors",
+    "gpt_neox.layers.38.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
+    "gpt_neox.layers.39.attention.dense.bias": "model-00011-of-00011.safetensors",
+    "gpt_neox.layers.39.attention.dense.weight": "model-00011-of-00011.safetensors",
+    "gpt_neox.layers.39.attention.query_key_value.bias": "model-00011-of-00011.safetensors",
+    "gpt_neox.layers.39.attention.query_key_value.weight": "model-00011-of-00011.safetensors",
+    "gpt_neox.layers.39.input_layernorm.bias": "model-00011-of-00011.safetensors",
+    "gpt_neox.layers.39.input_layernorm.weight": "model-00011-of-00011.safetensors",
+    "gpt_neox.layers.39.mlp.dense_4h_to_h.bias": "model-00011-of-00011.safetensors",
+    "gpt_neox.layers.39.mlp.dense_4h_to_h.weight": "model-00011-of-00011.safetensors",
+    "gpt_neox.layers.39.mlp.dense_h_to_4h.bias": "model-00011-of-00011.safetensors",
+    "gpt_neox.layers.39.mlp.dense_h_to_4h.weight": "model-00011-of-00011.safetensors",
+    "gpt_neox.layers.39.post_attention_layernorm.bias": "model-00011-of-00011.safetensors",
+    "gpt_neox.layers.39.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
+    "gpt_neox.layers.4.attention.dense.bias": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.4.attention.dense.weight": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.4.attention.query_key_value.bias": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.4.attention.query_key_value.weight": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.4.input_layernorm.bias": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.4.input_layernorm.weight": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.4.post_attention_layernorm.bias": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.4.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.5.attention.dense.bias": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.5.attention.dense.weight": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.5.attention.query_key_value.bias": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.5.attention.query_key_value.weight": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.5.input_layernorm.bias": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.5.input_layernorm.weight": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.5.post_attention_layernorm.bias": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.5.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.6.attention.dense.bias": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.6.attention.dense.weight": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.6.attention.query_key_value.bias": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.6.attention.query_key_value.weight": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.6.input_layernorm.bias": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.6.input_layernorm.weight": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.6.post_attention_layernorm.bias": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.6.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.7.attention.dense.bias": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.7.attention.dense.weight": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.7.attention.query_key_value.bias": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.7.attention.query_key_value.weight": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.7.input_layernorm.bias": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.7.input_layernorm.weight": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.7.post_attention_layernorm.bias": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.7.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
+    "gpt_neox.layers.8.attention.dense.bias": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.8.attention.dense.weight": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.8.attention.query_key_value.bias": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.8.attention.query_key_value.weight": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.8.input_layernorm.bias": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.8.input_layernorm.weight": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.8.post_attention_layernorm.bias": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.8.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.9.attention.dense.bias": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.9.attention.dense.weight": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.9.attention.query_key_value.bias": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.9.attention.query_key_value.weight": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.9.input_layernorm.bias": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.9.input_layernorm.weight": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.9.post_attention_layernorm.bias": "model-00003-of-00011.safetensors",
+    "gpt_neox.layers.9.post_attention_layernorm.weight": "model-00003-of-00011.safetensors"
+  }
+}