Pushing model and tokenizer to hub

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "EleutherAI/pythia-12b",
+  "architectures": [
+    "GPTNeoXForSequenceClassification"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 20480,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 36,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "rope_scaling": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "use_cache": false,
+  "use_parallel_residual": true,
+  "vocab_size": 50688
+}

pytorch_model-00001-of-00010.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386ce231843b72b4989a1507ea9c6e65055825fab3e24db8fa126a34e6ecec8c
+size 4813859652

pytorch_model-00002-of-00010.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c92caf9f6d427502946639cc0b08c3179f40c390e0db457691de6b1ccf686405
+size 4614712546

pytorch_model-00003-of-00010.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fca1503dd3b29726f47b597fcc097dcf81e1ace21e590d712dc4869bcdbb896
+size 4614734506

pytorch_model-00004-of-00010.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:743248751159440629bde9f718c628030c97f66100540e88a3f04c39eebddd3a
+size 4929368866

pytorch_model-00005-of-00010.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8385282d9be0a28421254d35701ff1d7d723a9e3fcd9885045c0a11b4b99cb54
+size 4719612682

pytorch_model-00006-of-00010.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3b726f238fce027682ce7997f30e989cde49f4dabb2e2992080d0792b5e051d
+size 4614712610

pytorch_model-00007-of-00010.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e16fa13b731a63ca1ebab36d8f3e4fdbff9b89cb4a6d0214cbce592f01e97f98
+size 4614734506

pytorch_model-00008-of-00010.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c919c07fb9ea0f57b180fb7c520e91a94fe2edcd7800328bed58cc7a2790b2a
+size 4929368866

pytorch_model-00009-of-00010.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:133b6bca491a6c23fe59df0eb9e222a0cf775189cdb4f2bf82c3f4510e102da4
+size 4719612682

pytorch_model-00010-of-00010.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e548c20c1f55291b98feaeb2b440c00b6d9f53ce4dbe11cd2922f1208c2f65b
+size 3775685280

pytorch_model.bin.index.json

@@ -0,0 +1,443 @@
+{
+  "metadata": {
+    "total_size": 46346240000
+  },
+  "weight_map": {
+    "gpt_neox.embed_in.weight": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.final_layer_norm.bias": "pytorch_model-00010-of-00010.bin",
+    "gpt_neox.final_layer_norm.weight": "pytorch_model-00010-of-00010.bin",
+    "gpt_neox.layers.0.attention.dense.bias": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.0.attention.dense.weight": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.1.attention.dense.bias": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.1.attention.dense.weight": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.1.attention.query_key_value.bias": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.10.attention.dense.bias": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.10.attention.dense.weight": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.10.attention.query_key_value.bias": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.10.attention.query_key_value.weight": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.10.input_layernorm.bias": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.10.input_layernorm.weight": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.10.post_attention_layernorm.bias": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.11.attention.dense.bias": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.11.attention.dense.weight": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.11.attention.query_key_value.bias": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.11.attention.query_key_value.weight": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.11.input_layernorm.bias": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.11.input_layernorm.weight": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.11.post_attention_layernorm.bias": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.11.post_attention_layernorm.weight": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.12.attention.dense.bias": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.12.attention.dense.weight": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.12.attention.query_key_value.bias": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.12.attention.query_key_value.weight": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.12.input_layernorm.bias": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.12.input_layernorm.weight": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.12.post_attention_layernorm.bias": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.12.post_attention_layernorm.weight": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.13.attention.dense.bias": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.13.attention.dense.weight": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.13.attention.query_key_value.bias": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.13.attention.query_key_value.weight": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.13.input_layernorm.bias": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.13.input_layernorm.weight": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.13.post_attention_layernorm.bias": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.13.post_attention_layernorm.weight": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.14.attention.dense.bias": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.14.attention.dense.weight": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.14.attention.query_key_value.bias": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.14.attention.query_key_value.weight": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.14.input_layernorm.bias": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.14.input_layernorm.weight": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.14.post_attention_layernorm.bias": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.14.post_attention_layernorm.weight": "pytorch_model-00004-of-00010.bin",
+    "gpt_neox.layers.15.attention.dense.bias": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.15.attention.dense.weight": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.15.attention.query_key_value.bias": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.15.attention.query_key_value.weight": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.15.input_layernorm.bias": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.15.input_layernorm.weight": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.15.post_attention_layernorm.bias": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.15.post_attention_layernorm.weight": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.16.attention.dense.bias": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.16.attention.dense.weight": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.16.attention.query_key_value.bias": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.16.attention.query_key_value.weight": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.16.input_layernorm.bias": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.16.input_layernorm.weight": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.16.post_attention_layernorm.bias": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.16.post_attention_layernorm.weight": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.17.attention.dense.bias": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.17.attention.dense.weight": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.17.attention.query_key_value.bias": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.17.attention.query_key_value.weight": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.17.input_layernorm.bias": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.17.input_layernorm.weight": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.17.post_attention_layernorm.bias": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.17.post_attention_layernorm.weight": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.18.attention.dense.bias": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.18.attention.dense.weight": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.18.attention.query_key_value.bias": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.18.attention.query_key_value.weight": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.18.input_layernorm.bias": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.18.input_layernorm.weight": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.18.post_attention_layernorm.bias": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.18.post_attention_layernorm.weight": "pytorch_model-00005-of-00010.bin",
+    "gpt_neox.layers.19.attention.dense.bias": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.19.attention.dense.weight": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.19.attention.query_key_value.bias": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.19.attention.query_key_value.weight": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.19.input_layernorm.bias": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.19.input_layernorm.weight": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.19.post_attention_layernorm.bias": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.19.post_attention_layernorm.weight": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.2.attention.dense.bias": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.2.attention.dense.weight": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.2.attention.query_key_value.bias": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.2.attention.query_key_value.weight": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.20.attention.dense.bias": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.20.attention.dense.weight": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.20.attention.query_key_value.bias": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.20.attention.query_key_value.weight": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.20.input_layernorm.bias": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.20.input_layernorm.weight": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.20.post_attention_layernorm.bias": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.20.post_attention_layernorm.weight": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.21.attention.dense.bias": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.21.attention.dense.weight": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.21.attention.query_key_value.bias": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.21.attention.query_key_value.weight": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.21.input_layernorm.bias": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.21.input_layernorm.weight": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.21.post_attention_layernorm.bias": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.21.post_attention_layernorm.weight": "pytorch_model-00006-of-00010.bin",
+    "gpt_neox.layers.22.attention.dense.bias": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.22.attention.dense.weight": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.22.attention.query_key_value.bias": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.22.attention.query_key_value.weight": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.22.input_layernorm.bias": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.22.input_layernorm.weight": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.22.post_attention_layernorm.bias": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.22.post_attention_layernorm.weight": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.23.attention.dense.bias": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.23.attention.dense.weight": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.23.attention.query_key_value.bias": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.23.attention.query_key_value.weight": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.23.input_layernorm.bias": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.23.input_layernorm.weight": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.23.post_attention_layernorm.bias": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.23.post_attention_layernorm.weight": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.24.attention.dense.bias": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.24.attention.dense.weight": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.24.attention.query_key_value.bias": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.24.attention.query_key_value.weight": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.24.input_layernorm.bias": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.24.input_layernorm.weight": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.24.post_attention_layernorm.bias": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.24.post_attention_layernorm.weight": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.25.attention.dense.bias": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.25.attention.dense.weight": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.25.attention.query_key_value.bias": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.25.attention.query_key_value.weight": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.25.input_layernorm.bias": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.25.input_layernorm.weight": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.25.post_attention_layernorm.bias": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.25.post_attention_layernorm.weight": "pytorch_model-00007-of-00010.bin",
+    "gpt_neox.layers.26.attention.dense.bias": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.26.attention.dense.weight": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.26.attention.query_key_value.bias": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.26.attention.query_key_value.weight": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.26.input_layernorm.bias": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.26.input_layernorm.weight": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.26.post_attention_layernorm.bias": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.26.post_attention_layernorm.weight": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.27.attention.dense.bias": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.27.attention.dense.weight": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.27.attention.query_key_value.bias": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.27.attention.query_key_value.weight": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.27.input_layernorm.bias": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.27.input_layernorm.weight": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.27.post_attention_layernorm.bias": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.27.post_attention_layernorm.weight": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.28.attention.dense.bias": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.28.attention.dense.weight": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.28.attention.query_key_value.bias": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.28.attention.query_key_value.weight": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.28.input_layernorm.bias": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.28.input_layernorm.weight": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.28.post_attention_layernorm.bias": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.28.post_attention_layernorm.weight": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.29.attention.dense.bias": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.29.attention.dense.weight": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.29.attention.query_key_value.bias": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.29.attention.query_key_value.weight": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.29.input_layernorm.bias": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.29.input_layernorm.weight": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.29.post_attention_layernorm.bias": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.29.post_attention_layernorm.weight": "pytorch_model-00008-of-00010.bin",
+    "gpt_neox.layers.3.attention.dense.bias": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.3.attention.dense.weight": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.3.attention.query_key_value.bias": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.3.attention.query_key_value.weight": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00010.bin",
+    "gpt_neox.layers.30.attention.dense.bias": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.30.attention.dense.weight": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.30.attention.query_key_value.bias": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.30.attention.query_key_value.weight": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.30.input_layernorm.bias": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.30.input_layernorm.weight": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.30.post_attention_layernorm.bias": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.30.post_attention_layernorm.weight": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.31.attention.dense.bias": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.31.attention.dense.weight": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.31.attention.query_key_value.bias": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.31.attention.query_key_value.weight": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.31.input_layernorm.bias": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.31.input_layernorm.weight": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.31.post_attention_layernorm.bias": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.31.post_attention_layernorm.weight": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.32.attention.dense.bias": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.32.attention.dense.weight": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.32.attention.query_key_value.bias": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.32.attention.query_key_value.weight": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.32.input_layernorm.bias": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.32.input_layernorm.weight": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.32.mlp.dense_4h_to_h.bias": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.32.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.32.mlp.dense_h_to_4h.bias": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.32.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.32.post_attention_layernorm.bias": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.32.post_attention_layernorm.weight": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.33.attention.dense.bias": "pytorch_model-00010-of-00010.bin",
+    "gpt_neox.layers.33.attention.dense.weight": "pytorch_model-00010-of-00010.bin",
+    "gpt_neox.layers.33.attention.query_key_value.bias": "pytorch_model-00010-of-00010.bin",
+    "gpt_neox.layers.33.attention.query_key_value.weight": "pytorch_model-00010-of-00010.bin",
+    "gpt_neox.layers.33.input_layernorm.bias": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.33.input_layernorm.weight": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.33.mlp.dense_4h_to_h.bias": "pytorch_model-00010-of-00010.bin",
+    "gpt_neox.layers.33.mlp.dense_4h_to_h.weight": "pytorch_model-00010-of-00010.bin",
+    "gpt_neox.layers.33.mlp.dense_h_to_4h.bias": "pytorch_model-00010-of-00010.bin",
+    "gpt_neox.layers.33.mlp.dense_h_to_4h.weight": "pytorch_model-00010-of-00010.bin",
+    "gpt_neox.layers.33.post_attention_layernorm.bias": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.33.post_attention_layernorm.weight": "pytorch_model-00009-of-00010.bin",
+    "gpt_neox.layers.34.attention.dense.bias": "pytorch_model-00010-of-00010.bin",
+    "gpt_neox.layers.34.attention.dense.weight": "pytorch_model-00010-of-00010.bin",
+    "gpt_neox.layers.34.attention.query_key_value.bias": "pytorch_model-00010-of-00010.bin",
+    "gpt_neox.layers.34.attention.query_key_value.weight": "pytorch_model-00010-of-00010.bin",
+    "gpt_neox.layers.34.input_layernorm.bias": "pytorch_model-00010-of-00010.bin",
+    "gpt_neox.layers.34.input_layernorm.weight": "pytorch_model-00010-of-00010.bin",
+    "gpt_neox.layers.34.mlp.dense_4h_to_h.bias": "pytorch_model-00010-of-00010.bin",
+    "gpt_neox.layers.34.mlp.dense_4h_to_h.weight": "pytorch_model-00010-of-00010.bin",
+    "gpt_neox.layers.34.mlp.dense_h_to_4h.bias": "pytorch_model-00010-of-00010.bin",
+    "gpt_neox.layers.34.mlp.dense_h_to_4h.weight": "pytorch_model-00010-of-00010.bin",
+    "gpt_neox.layers.34.post_attention_layernorm.bias": "pytorch_model-00010-of-00010.bin",
+    "gpt_neox.layers.34.post_attention_layernorm.weight": "pytorch_model-00010-of-00010.bin",
+    "gpt_neox.layers.35.attention.dense.bias": "pytorch_model-00010-of-00010.bin",
+    "gpt_neox.layers.35.attention.dense.weight": "pytorch_model-00010-of-00010.bin",
+    "gpt_neox.layers.35.attention.query_key_value.bias": "pytorch_model-00010-of-00010.bin",
+    "gpt_neox.layers.35.attention.query_key_value.weight": "pytorch_model-00010-of-00010.bin",
+    "gpt_neox.layers.35.input_layernorm.bias": "pytorch_model-00010-of-00010.bin",
+    "gpt_neox.layers.35.input_layernorm.weight": "pytorch_model-00010-of-00010.bin",
+    "gpt_neox.layers.35.mlp.dense_4h_to_h.bias": "pytorch_model-00010-of-00010.bin",
+    "gpt_neox.layers.35.mlp.dense_4h_to_h.weight": "pytorch_model-00010-of-00010.bin",
+    "gpt_neox.layers.35.mlp.dense_h_to_4h.bias": "pytorch_model-00010-of-00010.bin",
+    "gpt_neox.layers.35.mlp.dense_h_to_4h.weight": "pytorch_model-00010-of-00010.bin",
+    "gpt_neox.layers.35.post_attention_layernorm.bias": "pytorch_model-00010-of-00010.bin",
+    "gpt_neox.layers.35.post_attention_layernorm.weight": "pytorch_model-00010-of-00010.bin",
+    "gpt_neox.layers.4.attention.dense.bias": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.4.attention.dense.weight": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.4.attention.query_key_value.bias": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.4.attention.query_key_value.weight": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.4.input_layernorm.bias": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.4.post_attention_layernorm.bias": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.5.attention.dense.bias": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.5.attention.dense.weight": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.5.attention.query_key_value.bias": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.5.attention.query_key_value.weight": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.5.input_layernorm.bias": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.5.post_attention_layernorm.bias": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.6.attention.dense.bias": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.6.attention.dense.weight": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.6.attention.query_key_value.bias": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.6.attention.query_key_value.weight": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.6.input_layernorm.bias": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.6.post_attention_layernorm.bias": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00010.bin",
+    "gpt_neox.layers.7.attention.dense.bias": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.7.attention.dense.weight": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.7.attention.query_key_value.bias": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.7.attention.query_key_value.weight": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.7.input_layernorm.bias": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.7.input_layernorm.weight": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.7.post_attention_layernorm.bias": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.7.post_attention_layernorm.weight": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.8.attention.dense.bias": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.8.attention.dense.weight": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.8.attention.query_key_value.bias": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.8.attention.query_key_value.weight": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.8.input_layernorm.bias": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.8.input_layernorm.weight": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.8.post_attention_layernorm.bias": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.9.attention.dense.bias": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.9.attention.dense.weight": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.9.attention.query_key_value.bias": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.9.attention.query_key_value.weight": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.9.input_layernorm.bias": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.9.input_layernorm.weight": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.9.post_attention_layernorm.bias": "pytorch_model-00003-of-00010.bin",
+    "gpt_neox.layers.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00010.bin",
+    "score.weight": "pytorch_model-00010-of-00010.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,215 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50254": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50255": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50256": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50257": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}