add safetensors weights

.gitattributes

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

config.json

@@ -1,10 +1,11 @@
 {
-  "_name_or_path": "EleutherAI/polyglot-ko-1.3b",
+  "_name_or_path": "./polyglot-ko-1.3b/",
   "architectures": [
     "GPTNeoXForCausalLM"
   ],
   "bos_token_id": 0,
-  "eos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_size": 2048,
   "initializer_range": 0.02,
@@ -17,8 +18,9 @@
   "rotary_emb_base": 10000,
   "rotary_pct": 0.5,
   "tie_word_embeddings": false,
-  "transformers_version": "4.22.0",
-  "torch_dtype": "float32",
+  "torch_dtype": "float16",
+  "transformers_version": "4.29.2",
   "use_cache": true,
+  "use_parallel_residual": true,
   "vocab_size": 30080
 }

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "transformers_version": "4.29.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc6dcf159c11ab442b1ce00c85124a4e13d735c1540661e90b273cac0b438c4a
+size 1000292202

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd1929594672146d268055fa2c322e312c883bab7fb8c1bc33efb9878d541dae
+size 1015555724

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75f223f820f5ba69867063bd4e0b6c5277e5bc3e0313a26f686e31d355179a6e
+size 748480810

model.safetensors.index.json

@@ -0,0 +1,371 @@
+{
+  "metadata": {
+    "total_size": 2676206640.0
+  },
+  "weight_map": {
+    "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.bias": "model-00001-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.masked_bias": "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.attention.rotary_emb.inv_freq": "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.bias": "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.masked_bias": "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.attention.rotary_emb.inv_freq": "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.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.10.attention.dense.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.10.attention.dense.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.10.attention.masked_bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.10.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.10.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.10.attention.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.10.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.10.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.11.attention.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.11.attention.dense.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.11.attention.dense.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.11.attention.masked_bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.11.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.11.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.11.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.11.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.12.attention.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.12.attention.dense.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.12.attention.dense.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.12.attention.masked_bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.12.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.12.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.12.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.12.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.13.attention.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.13.attention.dense.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.13.attention.dense.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.13.attention.masked_bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.13.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.13.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.13.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.13.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.14.attention.bias": "model-00002-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.masked_bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.14.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.14.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.14.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.14.input_layernorm.weight": "model-00002-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-00002-of-00003.safetensors",
+    "gpt_neox.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.15.attention.bias": "model-00002-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.masked_bias": "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.attention.rotary_emb.inv_freq": "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.bias": "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.masked_bias": "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.attention.rotary_emb.inv_freq": "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.bias": "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.masked_bias": "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.attention.rotary_emb.inv_freq": "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.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.18.attention.dense.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.18.attention.dense.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.18.attention.masked_bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.18.attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.18.attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.18.attention.rotary_emb.inv_freq": "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-00003-of-00003.safetensors",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "model-00003-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.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.19.attention.dense.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.19.attention.dense.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.19.attention.masked_bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.19.attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.19.attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.19.attention.rotary_emb.inv_freq": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.19.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.19.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.19.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.19.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.2.attention.bias": "model-00001-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.masked_bias": "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.attention.rotary_emb.inv_freq": "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.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.20.attention.dense.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.20.attention.dense.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.20.attention.masked_bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.20.attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.20.attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.20.attention.rotary_emb.inv_freq": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.20.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.20.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.20.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.21.attention.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.21.attention.dense.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.21.attention.dense.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.21.attention.masked_bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.21.attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.21.attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.21.attention.rotary_emb.inv_freq": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.21.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.21.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.21.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.22.attention.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.22.attention.dense.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.22.attention.dense.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.22.attention.masked_bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.22.attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.22.attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.22.attention.rotary_emb.inv_freq": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.22.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.22.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.23.attention.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.23.attention.dense.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.23.attention.dense.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.23.attention.masked_bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.23.attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.23.attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.23.attention.rotary_emb.inv_freq": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.23.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.23.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "gpt_neox.layers.3.attention.bias": "model-00001-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.masked_bias": "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.attention.rotary_emb.inv_freq": "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.4.attention.bias": "model-00001-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.masked_bias": "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.attention.rotary_emb.inv_freq": "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.bias": "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.masked_bias": "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.attention.rotary_emb.inv_freq": "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.bias": "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.masked_bias": "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.attention.rotary_emb.inv_freq": "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.bias": "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.masked_bias": "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.attention.rotary_emb.inv_freq": "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.bias": "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.masked_bias": "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.attention.rotary_emb.inv_freq": "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-00002-of-00003.safetensors",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00002-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.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.9.attention.dense.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.9.attention.dense.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.9.attention.masked_bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.9.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.9.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.9.attention.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.9.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.9.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "gpt_neox.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors"
+  }
+}