add safetensors weights

.gitattributes

@@ -30,3 +30,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text

config.json

@@ -1 +1,27 @@
-{"hidden_act": "gelu", "architectures": ["GPTNeoXForCausalLM"], "bos_token_id": 0, "eos_token_id": 0, "initializer_range": 0.02, "layer_norm_eps": 1e-05, "model_type": "gpt_neox", "hidden_size": 4096, "intermediate_size": 16384, "num_attention_heads": 16, "num_hidden_layers": 28, "max_position_embeddings": 2048, "rotary_pct": 0.25, "rotary_emb_base": 10000, "torch_dtype": "float16", "use_cache": true, "vocab_size": 30080, "num_steps": "global_step320000"}
+{
+  "_name_or_path": "./polyglot-ko-5.8b/",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_steps": "global_step320000",
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.29.2",
+  "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": 2,
+  "transformers_version": "4.29.2"
+}

model-00001-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9525253224c8c49f441d63f85b4e41b042865dd15309c9f75c6522b502b951f5
+size 926101004

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4faf44378eac1c02c3d569c74d9d95c2fe230aa0cc2a1901417e92f870f21e89
+size 952365814

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:389cd21e9d44efd6952a3ba127a704538ff895163c7d303a120988d290543ac2
+size 948162644

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9a7391a3a23ee3d11d4ae2b97b0d5f6be18c2e3a7507f19a8645be8e9014495
+size 948162412

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:377e2ea5aa0f07e1d7cd7a55b67656123fe47fc9b88873b76a9315c71c111066
+size 952365830

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24f189ce457820612a49e88b536db63c4b132f37a850ca1f47728392ae3f436c
+size 948162676

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1a04027c907c186cddecb4779fa3d2b0adc9757dab6e51ce1b0603135176454
+size 948162444

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:081aff38df82775822de25a7c9382735a82d4e24acb3fb4dc275ae29a5a74b88
+size 952365854

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:039fff3bb0d4e39cae9f0c5a0dda8c4b1dfbff00bf7036041f5f453fb4047663
+size 948162676

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4628cac9f442d663d7ea8d4535341fb6bbc446e76394c82eab97b0d89140c6f5
+size 948162444

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc08f6c4e98e71f106cc236c45f60f4f94845c106c26c760e0b3635b2e387a26
+size 952365854

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:047fb3056bff118af349fe554aa3fb165f389632ac0e44722ea5c7aef9e00b51
+size 948162676

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6865c608008eba473353904c4f4b8d23a413617f9a0c3b22257c7380cdbfcbca
+size 514908960

model.safetensors.index.json

@@ -0,0 +1,431 @@
+{
+  "metadata": {
+    "total_size": 11784801848.0
+  },
+  "weight_map": {
+    "embed_out.weight": "model-00013-of-00013.safetensors",
+    "gpt_neox.embed_in.weight": "model-00001-of-00013.safetensors",
+    "gpt_neox.final_layer_norm.bias": "model-00013-of-00013.safetensors",
+    "gpt_neox.final_layer_norm.weight": "model-00013-of-00013.safetensors",
+    "gpt_neox.layers.0.attention.bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.attention.dense.bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.attention.dense.weight": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.attention.masked_bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.attention.rotary_emb.inv_freq": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.1.attention.bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.1.attention.dense.bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.1.attention.dense.weight": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.1.attention.masked_bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.1.attention.query_key_value.bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.1.attention.query_key_value.weight": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.1.attention.rotary_emb.inv_freq": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.1.input_layernorm.bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.1.input_layernorm.weight": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.10.attention.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.attention.dense.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.attention.dense.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.attention.masked_bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.attention.query_key_value.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.attention.query_key_value.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.attention.rotary_emb.inv_freq": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.input_layernorm.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.input_layernorm.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.post_attention_layernorm.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.11.attention.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.11.attention.dense.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.11.attention.dense.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.11.attention.masked_bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.11.attention.query_key_value.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.11.attention.query_key_value.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.11.input_layernorm.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.11.input_layernorm.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.11.post_attention_layernorm.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.11.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.12.attention.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.attention.dense.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.attention.dense.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.attention.masked_bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.attention.query_key_value.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.attention.query_key_value.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.input_layernorm.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.input_layernorm.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.post_attention_layernorm.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.13.attention.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.13.attention.dense.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.13.attention.dense.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.13.attention.masked_bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.13.attention.query_key_value.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.13.attention.query_key_value.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.13.input_layernorm.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.13.input_layernorm.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.13.post_attention_layernorm.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.13.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.14.attention.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.attention.dense.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.attention.dense.weight": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.attention.masked_bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.attention.query_key_value.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.attention.query_key_value.weight": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.input_layernorm.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.input_layernorm.weight": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.post_attention_layernorm.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.15.attention.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.15.attention.dense.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.15.attention.dense.weight": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.15.attention.masked_bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.15.attention.query_key_value.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.15.attention.query_key_value.weight": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.15.input_layernorm.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.15.input_layernorm.weight": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.15.post_attention_layernorm.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.15.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.16.attention.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.attention.dense.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.attention.dense.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.attention.masked_bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.attention.query_key_value.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.attention.query_key_value.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.attention.rotary_emb.inv_freq": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.input_layernorm.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.input_layernorm.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.post_attention_layernorm.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.attention.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.attention.dense.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.attention.dense.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.attention.masked_bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.attention.query_key_value.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.attention.query_key_value.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.attention.rotary_emb.inv_freq": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.input_layernorm.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.input_layernorm.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.post_attention_layernorm.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.18.attention.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.18.attention.dense.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.18.attention.dense.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.18.attention.masked_bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.18.attention.query_key_value.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.18.attention.query_key_value.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.18.attention.rotary_emb.inv_freq": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.18.input_layernorm.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.18.input_layernorm.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.18.post_attention_layernorm.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.18.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.19.attention.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.attention.dense.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.attention.dense.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.attention.masked_bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.attention.query_key_value.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.attention.query_key_value.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.attention.rotary_emb.inv_freq": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.input_layernorm.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.input_layernorm.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.post_attention_layernorm.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.2.attention.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.attention.dense.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.attention.dense.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.attention.masked_bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.attention.query_key_value.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.attention.query_key_value.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.attention.rotary_emb.inv_freq": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.input_layernorm.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.input_layernorm.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.post_attention_layernorm.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.20.attention.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.20.attention.dense.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.20.attention.dense.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.20.attention.masked_bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.20.attention.query_key_value.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.20.attention.query_key_value.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.20.attention.rotary_emb.inv_freq": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.20.input_layernorm.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.20.input_layernorm.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.20.post_attention_layernorm.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.20.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.21.attention.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.attention.dense.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.attention.dense.weight": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.attention.masked_bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.attention.query_key_value.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.attention.query_key_value.weight": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.attention.rotary_emb.inv_freq": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.input_layernorm.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.input_layernorm.weight": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.post_attention_layernorm.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.22.attention.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.22.attention.dense.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.22.attention.dense.weight": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.22.attention.masked_bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.22.attention.query_key_value.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.22.attention.query_key_value.weight": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.22.attention.rotary_emb.inv_freq": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.22.input_layernorm.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.22.input_layernorm.weight": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.22.post_attention_layernorm.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.22.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.23.attention.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.attention.dense.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.attention.dense.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.attention.masked_bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.attention.query_key_value.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.attention.query_key_value.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.attention.rotary_emb.inv_freq": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.input_layernorm.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.input_layernorm.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.post_attention_layernorm.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.attention.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.attention.dense.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.attention.dense.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.attention.masked_bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.attention.query_key_value.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.attention.query_key_value.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.attention.rotary_emb.inv_freq": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.input_layernorm.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.input_layernorm.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.post_attention_layernorm.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.25.attention.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.25.attention.dense.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.25.attention.dense.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.25.attention.masked_bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.25.attention.query_key_value.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.25.attention.query_key_value.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.25.attention.rotary_emb.inv_freq": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.25.input_layernorm.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.25.input_layernorm.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.25.post_attention_layernorm.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.25.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.26.attention.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.attention.dense.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.attention.dense.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.attention.masked_bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.attention.query_key_value.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.attention.query_key_value.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.attention.rotary_emb.inv_freq": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.input_layernorm.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.input_layernorm.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.post_attention_layernorm.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.27.attention.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.27.attention.dense.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.27.attention.dense.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.27.attention.masked_bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.27.attention.query_key_value.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.27.attention.query_key_value.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.27.attention.rotary_emb.inv_freq": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.27.input_layernorm.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.27.input_layernorm.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "model-00013-of-00013.safetensors",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "model-00013-of-00013.safetensors",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "model-00013-of-00013.safetensors",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "model-00013-of-00013.safetensors",
+    "gpt_neox.layers.27.post_attention_layernorm.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.27.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.3.attention.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.attention.dense.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.attention.dense.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.attention.masked_bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.attention.query_key_value.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.attention.query_key_value.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.attention.rotary_emb.inv_freq": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.input_layernorm.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.input_layernorm.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.post_attention_layernorm.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.4.attention.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.4.attention.dense.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.4.attention.dense.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.4.attention.masked_bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.4.attention.query_key_value.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.4.attention.query_key_value.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.4.attention.rotary_emb.inv_freq": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.4.input_layernorm.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.4.input_layernorm.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.4.post_attention_layernorm.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.4.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.5.attention.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.attention.dense.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.attention.dense.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.attention.masked_bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.attention.query_key_value.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.attention.query_key_value.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.attention.rotary_emb.inv_freq": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.input_layernorm.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.input_layernorm.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.post_attention_layernorm.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.6.attention.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.6.attention.dense.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.6.attention.dense.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.6.attention.masked_bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.6.attention.query_key_value.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.6.attention.query_key_value.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.6.attention.rotary_emb.inv_freq": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.6.input_layernorm.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.6.input_layernorm.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.6.post_attention_layernorm.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.6.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.7.attention.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.attention.dense.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.attention.dense.weight": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.attention.masked_bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.attention.query_key_value.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.attention.query_key_value.weight": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.attention.rotary_emb.inv_freq": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.input_layernorm.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.input_layernorm.weight": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.post_attention_layernorm.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.8.attention.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.8.attention.dense.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.8.attention.dense.weight": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.8.attention.masked_bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.8.attention.query_key_value.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.8.attention.query_key_value.weight": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.8.attention.rotary_emb.inv_freq": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.8.input_layernorm.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.8.input_layernorm.weight": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.8.post_attention_layernorm.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.8.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.9.attention.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.attention.dense.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.attention.dense.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.attention.masked_bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.attention.query_key_value.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.attention.query_key_value.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.attention.rotary_emb.inv_freq": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.input_layernorm.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.input_layernorm.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.post_attention_layernorm.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.post_attention_layernorm.weight": "model-00005-of-00013.safetensors"
+  }
+}