Upload GPTNeoXForCausalLM

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "togethercomputer/RedPajama-INCITE-7B-Base",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "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": 32,
+  "num_hidden_layers": 32,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 1.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.30.2",
+  "use_cache": true,
+  "use_parallel_residual": false,
+  "vocab_size": 50432
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.30.2"
+}

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11f3eb17ca015bd1b6961f1cef2fbf0d3f36a1fb381e0cbd5946a9dc1dc047ab
+size 1906736824

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d2f6d5f19187f1a9cdba626d651db18613585ecfb41a742f8d13d662fa25d05
+size 1900529154

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3d7b024702a1225c38259d3929666126b39acc86977b0af6ad70d9e8920ee84
+size 2001217074

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0adae6a5eda1f7fc2abd602a3ab1bcb57a49bc92bce1ebcdfe89777ec1f0720
+size 1934091834

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84b4bd4d7b76034fed1c3eb474a847835aa29cd2c8bc31960855c67989215229
+size 1896325672

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c5cf2fa53dd4f34f531560f9f5cf7fb10867a731edd1eab299f7c7927ba1412
+size 1900529226

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:663de5a3095f813d076243ed15e86c50ae2394d99afc455e22ae774ecead1b33
+size 1896317432

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d9587f89cacd957d182fd5f973f389613601ce634dc0f15d5ada40e8c1653f6
+size 413139072

model.safetensors.index.json

@@ -0,0 +1,491 @@
+{
+  "metadata": {
+    "total_size": 13731389504.0
+  },
+  "weight_map": {
+    "embed_out.weight": "model-00008-of-00008.safetensors",
+    "gpt_neox.embed_in.weight": "model-00001-of-00008.safetensors",
+    "gpt_neox.final_layer_norm.bias": "model-00007-of-00008.safetensors",
+    "gpt_neox.final_layer_norm.weight": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.0.attention.bias": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.0.attention.dense.bias": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.0.attention.dense.weight": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.0.attention.masked_bias": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.0.attention.rotary_emb.inv_freq": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.1.attention.bias": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.1.attention.dense.bias": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.1.attention.dense.weight": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.1.attention.masked_bias": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.1.attention.query_key_value.bias": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.1.attention.query_key_value.weight": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.1.attention.rotary_emb.inv_freq": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.1.input_layernorm.bias": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.10.attention.bias": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.10.attention.dense.bias": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.10.attention.dense.weight": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.10.attention.masked_bias": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.10.attention.query_key_value.bias": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.10.attention.query_key_value.weight": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.10.attention.rotary_emb.inv_freq": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.10.input_layernorm.bias": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.10.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.10.post_attention_layernorm.bias": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.10.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.11.attention.bias": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.11.attention.dense.bias": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.11.attention.dense.weight": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.11.attention.masked_bias": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.11.attention.query_key_value.bias": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.11.attention.query_key_value.weight": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.11.input_layernorm.bias": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.11.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.11.post_attention_layernorm.bias": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.11.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.12.attention.bias": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.12.attention.dense.bias": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.12.attention.dense.weight": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.12.attention.masked_bias": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.12.attention.query_key_value.bias": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.12.attention.query_key_value.weight": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.12.input_layernorm.bias": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.12.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.12.post_attention_layernorm.bias": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.12.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.13.attention.bias": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.13.attention.dense.bias": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.13.attention.dense.weight": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.13.attention.masked_bias": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.13.attention.query_key_value.bias": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.13.attention.query_key_value.weight": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.13.input_layernorm.bias": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.13.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.13.post_attention_layernorm.bias": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.13.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.14.attention.bias": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.14.attention.dense.bias": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.14.attention.dense.weight": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.14.attention.masked_bias": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.14.attention.query_key_value.bias": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.14.attention.query_key_value.weight": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.14.input_layernorm.bias": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.14.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.14.post_attention_layernorm.bias": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.14.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.15.attention.bias": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.15.attention.dense.bias": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.15.attention.dense.weight": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.15.attention.masked_bias": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.15.attention.query_key_value.bias": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.15.attention.query_key_value.weight": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.15.input_layernorm.bias": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.15.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.15.post_attention_layernorm.bias": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.15.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.16.attention.bias": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.16.attention.dense.bias": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.16.attention.dense.weight": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.16.attention.masked_bias": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.16.attention.query_key_value.bias": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.16.attention.query_key_value.weight": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.16.attention.rotary_emb.inv_freq": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.16.input_layernorm.bias": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.16.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.16.post_attention_layernorm.bias": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.16.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.17.attention.bias": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.17.attention.dense.bias": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.17.attention.dense.weight": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.17.attention.masked_bias": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.17.attention.query_key_value.bias": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.17.attention.query_key_value.weight": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.17.attention.rotary_emb.inv_freq": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.17.input_layernorm.bias": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.17.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.17.post_attention_layernorm.bias": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.17.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.18.attention.bias": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.18.attention.dense.bias": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.18.attention.dense.weight": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.18.attention.masked_bias": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.18.attention.query_key_value.bias": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.18.attention.query_key_value.weight": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.18.attention.rotary_emb.inv_freq": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.18.input_layernorm.bias": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.18.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.18.post_attention_layernorm.bias": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.18.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "gpt_neox.layers.19.attention.bias": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.19.attention.dense.bias": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.19.attention.dense.weight": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.19.attention.masked_bias": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.19.attention.query_key_value.bias": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.19.attention.query_key_value.weight": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.19.attention.rotary_emb.inv_freq": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.19.input_layernorm.bias": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.19.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.19.post_attention_layernorm.bias": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.19.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.2.attention.bias": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.2.attention.dense.bias": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.2.attention.dense.weight": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.2.attention.masked_bias": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.2.attention.query_key_value.bias": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.2.attention.query_key_value.weight": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.2.attention.rotary_emb.inv_freq": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.2.input_layernorm.bias": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.2.post_attention_layernorm.bias": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.2.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.20.attention.bias": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.20.attention.dense.bias": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.20.attention.dense.weight": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.20.attention.masked_bias": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.20.attention.query_key_value.bias": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.20.attention.query_key_value.weight": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.20.attention.rotary_emb.inv_freq": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.20.input_layernorm.bias": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.20.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.20.post_attention_layernorm.bias": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.20.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.21.attention.bias": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.21.attention.dense.bias": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.21.attention.dense.weight": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.21.attention.masked_bias": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.21.attention.query_key_value.bias": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.21.attention.query_key_value.weight": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.21.attention.rotary_emb.inv_freq": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.21.input_layernorm.bias": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.21.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.21.post_attention_layernorm.bias": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.21.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.22.attention.bias": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.22.attention.dense.bias": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.22.attention.dense.weight": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.22.attention.masked_bias": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.22.attention.query_key_value.bias": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.22.attention.query_key_value.weight": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.22.attention.rotary_emb.inv_freq": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.22.input_layernorm.bias": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.22.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.22.post_attention_layernorm.bias": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.22.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "gpt_neox.layers.23.attention.bias": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.23.attention.dense.bias": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.23.attention.dense.weight": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.23.attention.masked_bias": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.23.attention.query_key_value.bias": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.23.attention.query_key_value.weight": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.23.attention.rotary_emb.inv_freq": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.23.input_layernorm.bias": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.23.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.23.post_attention_layernorm.bias": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.23.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.24.attention.bias": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.24.attention.dense.bias": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.24.attention.dense.weight": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.24.attention.masked_bias": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.24.attention.query_key_value.bias": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.24.attention.query_key_value.weight": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.24.attention.rotary_emb.inv_freq": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.24.input_layernorm.bias": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.24.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.24.post_attention_layernorm.bias": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.24.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.25.attention.bias": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.25.attention.dense.bias": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.25.attention.dense.weight": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.25.attention.masked_bias": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.25.attention.query_key_value.bias": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.25.attention.query_key_value.weight": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.25.attention.rotary_emb.inv_freq": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.25.input_layernorm.bias": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.25.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.25.post_attention_layernorm.bias": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.25.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.26.attention.bias": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.26.attention.dense.bias": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.26.attention.dense.weight": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.26.attention.masked_bias": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.26.attention.query_key_value.bias": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.26.attention.query_key_value.weight": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.26.attention.rotary_emb.inv_freq": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.26.input_layernorm.bias": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.26.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.26.post_attention_layernorm.bias": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.26.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.27.attention.bias": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.27.attention.dense.bias": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.27.attention.dense.weight": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.27.attention.masked_bias": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.27.attention.query_key_value.bias": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.27.attention.query_key_value.weight": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.27.attention.rotary_emb.inv_freq": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.27.input_layernorm.bias": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.27.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.27.post_attention_layernorm.bias": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.27.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "gpt_neox.layers.28.attention.bias": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.28.attention.dense.bias": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.28.attention.dense.weight": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.28.attention.masked_bias": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.28.attention.query_key_value.bias": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.28.attention.query_key_value.weight": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.28.attention.rotary_emb.inv_freq": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.28.input_layernorm.bias": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.28.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.28.post_attention_layernorm.bias": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.28.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.29.attention.bias": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.29.attention.dense.bias": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.29.attention.dense.weight": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.29.attention.masked_bias": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.29.attention.query_key_value.bias": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.29.attention.query_key_value.weight": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.29.attention.rotary_emb.inv_freq": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.29.input_layernorm.bias": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.29.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.29.post_attention_layernorm.bias": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.29.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.3.attention.bias": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.3.attention.dense.bias": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.3.attention.dense.weight": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.3.attention.masked_bias": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.3.attention.query_key_value.bias": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.3.attention.query_key_value.weight": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.3.attention.rotary_emb.inv_freq": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.3.input_layernorm.bias": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.3.input_layernorm.weight": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.3.post_attention_layernorm.bias": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.3.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+    "gpt_neox.layers.30.attention.bias": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.30.attention.dense.bias": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.30.attention.dense.weight": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.30.attention.masked_bias": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.30.attention.query_key_value.bias": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.30.attention.query_key_value.weight": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.30.attention.rotary_emb.inv_freq": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.30.input_layernorm.bias": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.30.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.30.post_attention_layernorm.bias": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.30.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.31.attention.bias": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.31.attention.dense.bias": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.31.attention.dense.weight": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.31.attention.masked_bias": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.31.attention.query_key_value.bias": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.31.attention.query_key_value.weight": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.31.attention.rotary_emb.inv_freq": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.31.input_layernorm.bias": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.31.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.31.post_attention_layernorm.bias": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.31.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "gpt_neox.layers.4.attention.bias": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.4.attention.dense.bias": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.4.attention.dense.weight": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.4.attention.masked_bias": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.4.attention.query_key_value.bias": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.4.attention.query_key_value.weight": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.4.attention.rotary_emb.inv_freq": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.4.input_layernorm.bias": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.4.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.4.post_attention_layernorm.bias": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.4.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.5.attention.bias": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.5.attention.dense.bias": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.5.attention.dense.weight": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.5.attention.masked_bias": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.5.attention.query_key_value.bias": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.5.attention.query_key_value.weight": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.5.attention.rotary_emb.inv_freq": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.5.input_layernorm.bias": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.5.post_attention_layernorm.bias": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.6.attention.bias": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.6.attention.dense.bias": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.6.attention.dense.weight": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.6.attention.masked_bias": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.6.attention.query_key_value.bias": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.6.attention.query_key_value.weight": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.6.attention.rotary_emb.inv_freq": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.6.input_layernorm.bias": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.6.post_attention_layernorm.bias": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.7.attention.bias": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.7.attention.dense.bias": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.7.attention.dense.weight": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.7.attention.masked_bias": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.7.attention.query_key_value.bias": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.7.attention.query_key_value.weight": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.7.attention.rotary_emb.inv_freq": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.7.input_layernorm.bias": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.7.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.7.post_attention_layernorm.bias": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.7.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.8.attention.bias": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.8.attention.dense.bias": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.8.attention.dense.weight": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.8.attention.masked_bias": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.8.attention.query_key_value.bias": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.8.attention.query_key_value.weight": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.8.attention.rotary_emb.inv_freq": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.8.input_layernorm.bias": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.8.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.8.post_attention_layernorm.bias": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.8.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "gpt_neox.layers.9.attention.bias": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.9.attention.dense.bias": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.9.attention.dense.weight": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.9.attention.masked_bias": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.9.attention.query_key_value.bias": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.9.attention.query_key_value.weight": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.9.attention.rotary_emb.inv_freq": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.9.input_layernorm.bias": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.9.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.9.post_attention_layernorm.bias": "model-00003-of-00008.safetensors",
+    "gpt_neox.layers.9.post_attention_layernorm.weight": "model-00003-of-00008.safetensors"
+  }
+}