Upload 26 files

.gitattributes

@@ -25,7 +25,6 @@
 *.safetensors filter=lfs diff=lfs merge=lfs -text
 saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
 *.wasm filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,46 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+- polyglot-ko
+- gpt-neox
+- KoAlpaca
+model-index:
+- name: KoAlpaca-Polyglot-5.8B
+  results: []
+language:
+- ko
+datasets:
+- KoAlpaca-v1.1b
+pipeline_tag: text-generation
+---
+
+Update @ 2023.06.01
+
+- Add Safetensor sharded model weight (max shard = 1GB)
+
+# KoAlpaca-Polyglot-5.8B (v1.1b)
+
+This model is a fine-tuned version of [EleutherAI/polyglot-ko-5.8b](https://huggingface.co/EleutherAI/polyglot-ko-5.8b) on a KoAlpaca Dataset v1.1b
+
+Detail Codes are available at [KoAlpaca Github Repository](https://github.com/Beomi/KoAlpaca)
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 2
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2.0
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- Transformers 4.29.0.dev0
+- Pytorch 2.0.0+cu117
+- Datasets 2.10.1
+- Tokenizers 0.13.2

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "beomi/KoAlpaca-Polyglot-5.8B",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "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": "4.29.0.dev0",
+  "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": "4.29.0.dev0"
+}

model-00001-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8a1f356a59d738bcb97e3c3aa5f89f584da7cab0063db73b95eb056f8049398
+size 134

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:450875c20ff67f7931aabff2df6dc0dcc3ce40ad07f520c60defa9d042dc0f82
+size 134

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f51e22b62abbd4d82b13718b23d604929d3791aefcd1c0886406634997233b5
+size 134

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5730115f2923b236955f0092560bec728b90e772c5d29f0cd160ed9813e47297
+size 134

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaead070d919596a22cebbb53f70e000c6d733ef1a8c3eadd0c69f53383033b9
+size 134

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9558092e24ced045ef96cfe45d81a87184ebabf8d208e9eb303e4a50d09f154a
+size 134

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83e260b2ece13b9faa00f1e9c0b480228637bced5a3e9200cad9db48f3468faf
+size 134

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79a745f96edf1ae8706c4ed3b1922c7f6163687e3b1a2a3ee1fee489370ebb65
+size 134

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a13236131e610ae7fa1e8a187feeb0c12d8b3b1d9aa0f74451454ece1100b9b2
+size 134

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81251eb4e4fd3a808a03ded7e545c486c633649e640fde58724ae7f9385f2730
+size 134

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e736dc83893c65628454dd2865508af017a5d0e9a5c8a6297e3419b4691596a9
+size 134

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:956229ad6417bad15cdc9555f862adefdff50ff589af7be3f670cc8e15ca8576
+size 134

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25f114c522c0416ed191c309f811029ad62ea1f6815203962452996adeeb61b8
+size 134

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"
+  }
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b2815dba3f8bee8100a4d8dadfd9c5f933194aa2c4c5c920c25328ddc90c7fa
+size 136

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e9d4ba770d05659dc80271e6c6e9e0752041ec0a9ac66f5c47555183ac60080
+size 135

pytorch_model.bin.index.json

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

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 +1,7 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

trainer_state.json

@@ -0,0 +1,64 @@
+{
+  "best_metric": 0.2509765625,
+  "best_model_checkpoint": "./models/2023-03-16_1edc4008-e54e/checkpoint-2534",
+  "epoch": 3.0,
+  "global_step": 7602,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.9997369113391214e-05,
+      "loss": 9.8984,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.2605,
+      "step": 2534
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.2509765625,
+      "eval_runtime": 191.3685,
+      "eval_samples_per_second": 23.536,
+      "eval_steps_per_second": 2.942,
+      "step": 2534
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.1598,
+      "step": 5068
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.258544921875,
+      "eval_runtime": 159.499,
+      "eval_samples_per_second": 28.238,
+      "eval_steps_per_second": 3.53,
+      "step": 5068
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.0753,
+      "step": 7602
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.3056640625,
+      "eval_runtime": 159.3863,
+      "eval_samples_per_second": 28.258,
+      "eval_steps_per_second": 3.532,
+      "step": 7602
+    }
+  ],
+  "max_steps": 7602,
+  "num_train_epochs": 3,
+  "total_flos": 2.1525111523686482e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f53bd7e65a8586258c34de78ab2c36d4059b27f4ef1a568022363ceda2a21bd
+size 129