Upload GPTNeoXForCausalLM

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "EleutherAI/pythia-2.8b",
+  "_name_or_path": "./sft-models/pythia-2.8b-squaring-first-ft/checkpoint-16384",
   "architectures": [
     "GPTNeoXForCausalLM"
   ],
@@ -22,7 +22,7 @@
   "rotary_emb_base": 10000,
   "rotary_pct": 0.25,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
+  "torch_dtype": "float32",
   "transformers_version": "4.37.2",
   "use_cache": true,
   "use_parallel_residual": true,

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:621a41097e4e07b439dc84eaf22813f80351316b4af8138d708107da1e00e52f
+size 4999731368

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9332ccf48cc00f86dd6dd473de918d8481bab1537289ad184a17b52d141ac6f9
+size 4956643296

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74d436c83cce985cc55d13c8e6ab3c1cbef7e80bdd4565101c7c7fd2a7be2e17
+size 1144507000

model.safetensors.index.json

@@ -1,395 +1,395 @@
 {
   "metadata": {
-    "total_size": 5550417920
+    "total_size": 11100835840
   },
   "weight_map": {
-    "embed_out.weight": "model-00002-of-00002.safetensors",
-    "gpt_neox.embed_in.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.final_layer_norm.bias": "model-00002-of-00002.safetensors",
-    "gpt_neox.final_layer_norm.weight": "model-00002-of-00002.safetensors",
-    "gpt_neox.layers.0.attention.dense.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.0.attention.dense.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.1.attention.dense.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.1.attention.dense.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.1.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.1.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.10.attention.dense.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.10.attention.dense.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.10.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.10.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.10.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.11.attention.dense.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.11.attention.dense.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.11.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.11.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.11.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.12.attention.dense.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.12.attention.dense.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.12.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.12.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.12.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.13.attention.dense.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.13.attention.dense.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.13.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.13.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.13.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.14.attention.dense.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.14.attention.dense.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.14.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.14.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.14.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.15.attention.dense.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.15.attention.dense.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.15.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.15.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.15.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.16.attention.dense.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.16.attention.dense.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.16.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.16.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.16.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.17.attention.dense.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.17.attention.dense.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.17.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.17.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.17.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.18.attention.dense.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.18.attention.dense.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.18.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.18.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.18.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.19.attention.dense.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.19.attention.dense.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.19.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.19.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.19.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.2.attention.dense.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.2.attention.dense.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.2.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.2.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.2.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.20.attention.dense.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.20.attention.dense.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.20.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.20.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.20.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.21.attention.dense.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.21.attention.dense.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.21.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.21.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.21.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.22.attention.dense.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.22.attention.dense.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.22.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.22.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.22.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.22.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.23.attention.dense.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.23.attention.dense.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.23.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.23.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.23.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.23.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.24.attention.dense.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.24.attention.dense.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.24.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.24.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.24.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.24.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.25.attention.dense.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.25.attention.dense.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.25.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.25.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.25.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.25.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.26.attention.dense.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.26.attention.dense.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.26.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.26.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.26.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.26.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.27.attention.dense.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.27.attention.dense.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.27.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.27.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.27.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.27.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.28.attention.dense.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.28.attention.dense.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.28.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.28.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.28.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.28.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.29.attention.dense.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.29.attention.dense.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.29.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.29.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.29.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.29.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.3.attention.dense.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.3.attention.dense.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.3.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.3.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.3.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.30.attention.dense.bias": "model-00002-of-00002.safetensors",
-    "gpt_neox.layers.30.attention.dense.weight": "model-00002-of-00002.safetensors",
-    "gpt_neox.layers.30.attention.query_key_value.bias": "model-00002-of-00002.safetensors",
-    "gpt_neox.layers.30.attention.query_key_value.weight": "model-00002-of-00002.safetensors",
-    "gpt_neox.layers.30.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
-    "gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
-    "gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
-    "gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
-    "gpt_neox.layers.30.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.31.attention.dense.bias": "model-00002-of-00002.safetensors",
-    "gpt_neox.layers.31.attention.dense.weight": "model-00002-of-00002.safetensors",
-    "gpt_neox.layers.31.attention.query_key_value.bias": "model-00002-of-00002.safetensors",
-    "gpt_neox.layers.31.attention.query_key_value.weight": "model-00002-of-00002.safetensors",
-    "gpt_neox.layers.31.input_layernorm.bias": "model-00002-of-00002.safetensors",
-    "gpt_neox.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
-    "gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
-    "gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
-    "gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
-    "gpt_neox.layers.31.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
-    "gpt_neox.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "gpt_neox.layers.4.attention.dense.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.4.attention.dense.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.4.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.4.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.4.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.5.attention.dense.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.5.attention.dense.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.5.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.5.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.5.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.6.attention.dense.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.6.attention.dense.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.6.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.6.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.6.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.7.attention.dense.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.7.attention.dense.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.7.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.7.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.7.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.8.attention.dense.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.8.attention.dense.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.8.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.8.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.8.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.9.attention.dense.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.9.attention.dense.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.9.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.9.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.9.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors"
+    "embed_out.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.embed_in.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.final_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.final_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.0.attention.dense.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.0.attention.dense.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.1.attention.dense.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.1.attention.dense.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.1.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.1.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.1.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.10.attention.dense.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.10.attention.dense.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.10.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.10.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.10.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.10.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.11.attention.dense.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.11.attention.dense.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.11.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.11.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.11.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.11.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.12.attention.dense.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.12.attention.dense.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.12.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.12.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.12.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.12.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.13.attention.dense.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.13.attention.dense.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.13.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.13.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.13.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.13.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.14.attention.dense.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.14.attention.dense.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.14.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.14.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.14.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.14.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.15.attention.dense.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.15.attention.dense.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.15.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.15.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.15.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.15.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.16.attention.dense.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.16.attention.dense.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.16.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.16.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.16.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.16.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.17.attention.dense.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.17.attention.dense.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.17.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.17.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.17.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.17.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.18.attention.dense.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.18.attention.dense.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.18.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.18.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.18.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.18.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.19.attention.dense.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.19.attention.dense.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.19.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.19.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.19.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.19.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.2.attention.dense.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.2.attention.dense.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.2.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.2.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.2.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.2.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.20.attention.dense.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.20.attention.dense.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.20.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.20.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.20.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.20.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.21.attention.dense.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.21.attention.dense.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.21.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.21.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.21.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.21.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.22.attention.dense.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.22.attention.dense.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.22.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.22.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.22.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.22.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.23.attention.dense.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.23.attention.dense.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.23.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.23.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.23.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.23.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.24.attention.dense.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.24.attention.dense.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.24.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.24.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.24.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.24.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.25.attention.dense.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.25.attention.dense.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.25.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.25.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.25.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.25.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.26.attention.dense.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.26.attention.dense.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.26.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.26.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.26.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.26.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.27.attention.dense.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.27.attention.dense.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.27.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.27.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.27.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.27.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.28.attention.dense.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.28.attention.dense.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.28.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.28.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.28.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.28.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.29.attention.dense.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.29.attention.dense.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.29.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.29.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.29.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.29.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.3.attention.dense.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.3.attention.dense.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.3.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.3.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.3.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.3.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.30.attention.dense.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.30.attention.dense.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.30.attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.30.attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.30.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.30.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.31.attention.dense.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.31.attention.dense.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.31.attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.31.attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.31.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.31.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.4.attention.dense.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.4.attention.dense.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.4.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.4.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.4.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.4.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.5.attention.dense.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.5.attention.dense.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.5.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.5.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.5.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.5.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.6.attention.dense.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.6.attention.dense.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.6.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.6.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.6.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.6.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.7.attention.dense.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.7.attention.dense.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.7.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.7.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.7.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.7.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.8.attention.dense.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.8.attention.dense.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.8.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.8.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.8.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.8.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.9.attention.dense.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.9.attention.dense.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.9.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.9.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.9.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.9.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "gpt_neox.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors"
   }
 }