Upload GPTNeoXForCausalLM

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "eunbinni/ola_polyglot_5.8B_lora2_8bit_merge",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_steps": "global_step320000",
+  "rope_scaling": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 30003
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "transformers_version": "4.35.2"
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4a53ca6d0f0e3613e795d2c413b10f5e343623da66f30bb043664d7a00472e3
+size 4787740624

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc55589dbfb9896bf7695b20eefeac062ca5ee8ad94bfb2e0bfaec8cd699125b
+size 4833124664

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0a2e5ec41524534f8890cdd097973cdfd1ed8adb20e7ba570f8e773e760006b
+size 4833124728

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ce89364a71b98b5d87cc40eeed46d2b149afa5bff733c3fe91919a3858c9eef
+size 4833124728

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71a69d1f7fb10b71d7e033506b191190c4c45984ac0b68227901c6dcaaf13560
+size 4250638696

model.safetensors.index.json

@@ -0,0 +1,347 @@
+{
+  "metadata": {
+    "total_size": 23537713152
+  },
+  "weight_map": {
+    "embed_out.weight": "model-00005-of-00005.safetensors",
+    "gpt_neox.embed_in.weight": "model-00001-of-00005.safetensors",
+    "gpt_neox.final_layer_norm.bias": "model-00005-of-00005.safetensors",
+    "gpt_neox.final_layer_norm.weight": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.0.attention.dense.bias": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.0.attention.dense.weight": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.1.attention.dense.bias": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.1.attention.dense.weight": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.1.attention.query_key_value.bias": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.1.attention.query_key_value.weight": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.1.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.10.attention.dense.bias": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.10.attention.dense.weight": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.10.attention.query_key_value.bias": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.10.attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.10.input_layernorm.bias": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.10.post_attention_layernorm.bias": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.11.attention.dense.bias": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.11.attention.dense.weight": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.11.attention.query_key_value.bias": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.11.attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.11.input_layernorm.bias": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.11.post_attention_layernorm.bias": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.12.attention.dense.bias": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.12.attention.dense.weight": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.12.attention.query_key_value.bias": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.12.attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.12.input_layernorm.bias": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.12.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.12.post_attention_layernorm.bias": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.12.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.13.attention.dense.bias": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.13.attention.dense.weight": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.13.attention.query_key_value.bias": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.13.attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.13.input_layernorm.bias": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.13.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.13.post_attention_layernorm.bias": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.13.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.14.attention.dense.bias": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.14.attention.dense.weight": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.14.attention.query_key_value.bias": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.14.attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.14.input_layernorm.bias": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.14.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.14.post_attention_layernorm.bias": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.14.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.15.attention.dense.bias": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.15.attention.dense.weight": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.15.attention.query_key_value.bias": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.15.attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.15.input_layernorm.bias": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.15.post_attention_layernorm.bias": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.16.attention.dense.bias": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.16.attention.dense.weight": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.16.attention.query_key_value.bias": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.16.attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.16.input_layernorm.bias": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.16.post_attention_layernorm.bias": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.17.attention.dense.bias": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.17.attention.dense.weight": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.17.attention.query_key_value.bias": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.17.attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.17.input_layernorm.bias": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.17.post_attention_layernorm.bias": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "gpt_neox.layers.18.attention.dense.bias": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.18.attention.dense.weight": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.18.attention.query_key_value.bias": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.18.attention.query_key_value.weight": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.18.input_layernorm.bias": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.18.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.18.post_attention_layernorm.bias": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.18.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.19.attention.dense.bias": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.19.attention.dense.weight": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.19.attention.query_key_value.bias": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.19.attention.query_key_value.weight": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.19.input_layernorm.bias": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.19.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.19.post_attention_layernorm.bias": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.19.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.2.attention.dense.bias": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.2.attention.dense.weight": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.2.attention.query_key_value.bias": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.2.attention.query_key_value.weight": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.2.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.2.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.20.attention.dense.bias": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.20.attention.dense.weight": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.20.attention.query_key_value.bias": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.20.attention.query_key_value.weight": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.20.input_layernorm.bias": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.20.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.20.post_attention_layernorm.bias": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.20.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.21.attention.dense.bias": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.21.attention.dense.weight": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.21.attention.query_key_value.bias": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.21.attention.query_key_value.weight": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.21.input_layernorm.bias": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.21.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.21.post_attention_layernorm.bias": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.21.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.22.attention.dense.bias": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.22.attention.dense.weight": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.22.attention.query_key_value.bias": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.22.attention.query_key_value.weight": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.22.input_layernorm.bias": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.22.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.22.post_attention_layernorm.bias": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.22.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.23.attention.dense.bias": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.23.attention.dense.weight": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.23.attention.query_key_value.bias": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.23.attention.query_key_value.weight": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.23.input_layernorm.bias": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.23.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.23.post_attention_layernorm.bias": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.23.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "gpt_neox.layers.24.attention.dense.bias": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.24.attention.dense.weight": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.24.attention.query_key_value.bias": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.24.attention.query_key_value.weight": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.24.input_layernorm.bias": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.24.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.24.post_attention_layernorm.bias": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.24.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.25.attention.dense.bias": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.25.attention.dense.weight": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.25.attention.query_key_value.bias": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.25.attention.query_key_value.weight": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.25.input_layernorm.bias": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.25.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.25.post_attention_layernorm.bias": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.25.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.26.attention.dense.bias": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.26.attention.dense.weight": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.26.attention.query_key_value.bias": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.26.attention.query_key_value.weight": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.26.input_layernorm.bias": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.26.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.26.post_attention_layernorm.bias": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.26.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.27.attention.dense.bias": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.27.attention.dense.weight": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.27.attention.query_key_value.bias": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.27.attention.query_key_value.weight": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.27.input_layernorm.bias": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.27.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.27.post_attention_layernorm.bias": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.27.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "gpt_neox.layers.3.attention.dense.bias": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.3.attention.dense.weight": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.3.attention.query_key_value.bias": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.3.attention.query_key_value.weight": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.3.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.3.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.4.attention.dense.bias": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.4.attention.dense.weight": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.4.attention.query_key_value.bias": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.4.attention.query_key_value.weight": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.4.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.4.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.5.attention.dense.bias": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.5.attention.dense.weight": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.5.attention.query_key_value.bias": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.5.attention.query_key_value.weight": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.5.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.5.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "gpt_neox.layers.6.attention.dense.bias": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.6.attention.dense.weight": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.6.attention.query_key_value.bias": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.6.attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.6.input_layernorm.bias": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.6.post_attention_layernorm.bias": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.7.attention.dense.bias": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.7.attention.dense.weight": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.7.attention.query_key_value.bias": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.7.attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.7.input_layernorm.bias": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.7.post_attention_layernorm.bias": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.8.attention.dense.bias": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.8.attention.dense.weight": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.8.attention.query_key_value.bias": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.8.attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.8.input_layernorm.bias": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.8.post_attention_layernorm.bias": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.9.attention.dense.bias": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.9.attention.dense.weight": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.9.attention.query_key_value.bias": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.9.attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.9.input_layernorm.bias": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.9.post_attention_layernorm.bias": "model-00002-of-00005.safetensors",
+    "gpt_neox.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors"
+  }
+}