Upload folder using huggingface_hub

10_shot.json

@@ -0,0 +1,47 @@
+{
+  "results": {
+    "kobest_boolq": {
+      "acc": 0.594017094017094,
+      "acc_stderr": 0.013110658638863893,
+      "macro_f1": 0.5766968517264726,
+      "macro_f1_stderr": 0.013321751352234396
+    },
+    "kobest_copa": {
+      "acc": 0.796,
+      "acc_stderr": 0.012749374359024387,
+      "macro_f1": 0.7956042899052566,
+      "macro_f1_stderr": 0.012768263930194495
+    },
+    "kobest_hellaswag": {
+      "acc": 0.494,
+      "acc_stderr": 0.022381462412439324,
+      "acc_norm": 0.586,
+      "acc_norm_stderr": 0.02204949796982787,
+      "macro_f1": 0.49215887000493286,
+      "macro_f1_stderr": 0.02237097469536285
+    },
+    "kobest_sentineg": {
+      "acc": 0.9395465994962217,
+      "acc_stderr": 0.01197627988893257,
+      "macro_f1": 0.9393430099312452,
+      "macro_f1_stderr": 0.012043294700994262
+    }
+  },
+  "versions": {
+    "kobest_boolq": 0,
+    "kobest_copa": 0,
+    "kobest_hellaswag": 0,
+    "kobest_sentineg": 0
+  },
+  "config": {
+    "model": "gpt2",
+    "model_args": "pretrained=./output",
+    "num_fewshot": 10,
+    "batch_size": "4",
+    "device": "cuda:0",
+    "no_cache": true,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "description_dict": {}
+  }
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "EleutherAI/polyglot-ko-5.8b",
+  "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": "float16",
+  "transformers_version": "4.32.1",
+  "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": "4.32.1"
+}

model-00001-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d9e5eb37024dd15b03d1ccbb97dd5288cee42fdca1ac45404f0db80e6ca893f
+size 917711952

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f98d9eae67276e70da8085725c6b336fdc266b476bc65d82c48a962c262291e1
+size 939782240

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d91cfb12623435c6992b68f6e19d71746a96a4e902074b87793f20f3cfa5fde
+size 939773592

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:856fbc1bd3d481f0f3c04d846cf91564291385fc99b15e0cb6b792c590e4b20b
+size 939773360

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0261e880f1a15bb0cca75a410244918939364574f2b4710e31d73924a43c9c12
+size 939782256

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deec79a9b8e2fc7db9c63622557f79d46104de9b3d5bb076678736d556b22c50
+size 939773624

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea0139d45016c261f3c6fce1804cc8fe480f093be9873ef72387e70818516af7
+size 939773384

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7894a7bc1a09a183d69052468415c5dbaa57690f1230d754aedd253681602721
+size 939782272

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f39d7e578525b74fe4fb52ae25bdc3e171d9f5b0d24b789b92b48afbc722b73
+size 939773624

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:758cd431d7b731265ce0072012832f30efdc87d997ea1952145f340d6f279d67
+size 939773384

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4aa67714f77e66b2478d36fa98e71a70d1c0d830c9691a3fa8bc1125de1fe50
+size 939782272

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f19c5671eb6d79bcd266103972c9e0d8d6564ed4b8b1a52c0c2dcc7288fad24
+size 939773624

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6865c608008eba473353904c4f4b8d23a413617f9a0c3b22257c7380cdbfcbca
+size 514908960

model.safetensors.index.json

@@ -0,0 +1,375 @@
+{
+  "metadata": {
+    "total_size": 11770121728
+  },
+  "weight_map": {
+    "embed_out.weight": "model-00013-of-00013.safetensors",
+    "gpt_neox.embed_in.weight": "model-00001-of-00013.safetensors",
+    "gpt_neox.final_layer_norm.bias": "model-00013-of-00013.safetensors",
+    "gpt_neox.final_layer_norm.weight": "model-00013-of-00013.safetensors",
+    "gpt_neox.layers.0.attention.dense.bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.attention.dense.weight": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.attention.rotary_emb.inv_freq": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.1.attention.dense.bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.1.attention.dense.weight": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.1.attention.query_key_value.bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.1.attention.query_key_value.weight": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.1.attention.rotary_emb.inv_freq": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.1.input_layernorm.bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.1.input_layernorm.weight": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
+    "gpt_neox.layers.10.attention.dense.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.attention.dense.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.attention.query_key_value.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.attention.query_key_value.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.attention.rotary_emb.inv_freq": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.input_layernorm.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.input_layernorm.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.post_attention_layernorm.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.10.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.11.attention.dense.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.11.attention.dense.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.11.attention.query_key_value.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.11.attention.query_key_value.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.11.input_layernorm.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.11.input_layernorm.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.11.post_attention_layernorm.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.11.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.12.attention.dense.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.attention.dense.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.attention.query_key_value.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.attention.query_key_value.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.input_layernorm.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.input_layernorm.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.post_attention_layernorm.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.12.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.13.attention.dense.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.13.attention.dense.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.13.attention.query_key_value.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.13.attention.query_key_value.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.13.input_layernorm.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.13.input_layernorm.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.13.post_attention_layernorm.bias": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.13.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+    "gpt_neox.layers.14.attention.dense.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.attention.dense.weight": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.attention.query_key_value.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.attention.query_key_value.weight": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.input_layernorm.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.input_layernorm.weight": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.post_attention_layernorm.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.14.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.15.attention.dense.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.15.attention.dense.weight": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.15.attention.query_key_value.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.15.attention.query_key_value.weight": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.15.input_layernorm.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.15.input_layernorm.weight": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.15.post_attention_layernorm.bias": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.15.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+    "gpt_neox.layers.16.attention.dense.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.attention.dense.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.attention.query_key_value.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.attention.query_key_value.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.attention.rotary_emb.inv_freq": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.input_layernorm.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.input_layernorm.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.post_attention_layernorm.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.16.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.attention.dense.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.attention.dense.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.attention.query_key_value.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.attention.query_key_value.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.attention.rotary_emb.inv_freq": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.input_layernorm.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.input_layernorm.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.post_attention_layernorm.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.17.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.18.attention.dense.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.18.attention.dense.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.18.attention.query_key_value.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.18.attention.query_key_value.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.18.attention.rotary_emb.inv_freq": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.18.input_layernorm.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.18.input_layernorm.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.18.post_attention_layernorm.bias": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.18.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+    "gpt_neox.layers.19.attention.dense.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.attention.dense.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.attention.query_key_value.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.attention.query_key_value.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.attention.rotary_emb.inv_freq": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.input_layernorm.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.input_layernorm.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.post_attention_layernorm.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.19.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.2.attention.dense.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.attention.dense.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.attention.query_key_value.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.attention.query_key_value.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.attention.rotary_emb.inv_freq": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.input_layernorm.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.input_layernorm.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.post_attention_layernorm.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.2.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.20.attention.dense.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.20.attention.dense.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.20.attention.query_key_value.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.20.attention.query_key_value.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.20.attention.rotary_emb.inv_freq": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.20.input_layernorm.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.20.input_layernorm.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.20.post_attention_layernorm.bias": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.20.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+    "gpt_neox.layers.21.attention.dense.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.attention.dense.weight": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.attention.query_key_value.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.attention.query_key_value.weight": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.attention.rotary_emb.inv_freq": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.input_layernorm.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.input_layernorm.weight": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.post_attention_layernorm.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.21.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.22.attention.dense.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.22.attention.dense.weight": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.22.attention.query_key_value.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.22.attention.query_key_value.weight": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.22.attention.rotary_emb.inv_freq": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.22.input_layernorm.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.22.input_layernorm.weight": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.22.post_attention_layernorm.bias": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.22.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+    "gpt_neox.layers.23.attention.dense.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.attention.dense.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.attention.query_key_value.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.attention.query_key_value.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.attention.rotary_emb.inv_freq": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.input_layernorm.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.input_layernorm.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.post_attention_layernorm.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.23.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.attention.dense.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.attention.dense.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.attention.query_key_value.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.attention.query_key_value.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.attention.rotary_emb.inv_freq": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.input_layernorm.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.input_layernorm.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.post_attention_layernorm.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.24.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.25.attention.dense.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.25.attention.dense.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.25.attention.query_key_value.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.25.attention.query_key_value.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.25.attention.rotary_emb.inv_freq": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.25.input_layernorm.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.25.input_layernorm.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.25.post_attention_layernorm.bias": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.25.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+    "gpt_neox.layers.26.attention.dense.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.attention.dense.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.attention.query_key_value.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.attention.query_key_value.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.attention.rotary_emb.inv_freq": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.input_layernorm.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.input_layernorm.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.post_attention_layernorm.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.26.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.27.attention.dense.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.27.attention.dense.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.27.attention.query_key_value.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.27.attention.query_key_value.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.27.attention.rotary_emb.inv_freq": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.27.input_layernorm.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.27.input_layernorm.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "model-00013-of-00013.safetensors",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "model-00013-of-00013.safetensors",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "model-00013-of-00013.safetensors",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "model-00013-of-00013.safetensors",
+    "gpt_neox.layers.27.post_attention_layernorm.bias": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.27.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+    "gpt_neox.layers.3.attention.dense.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.attention.dense.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.attention.query_key_value.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.attention.query_key_value.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.attention.rotary_emb.inv_freq": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.input_layernorm.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.input_layernorm.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.post_attention_layernorm.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.3.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.4.attention.dense.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.4.attention.dense.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.4.attention.query_key_value.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.4.attention.query_key_value.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.4.attention.rotary_emb.inv_freq": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.4.input_layernorm.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.4.input_layernorm.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.4.post_attention_layernorm.bias": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.4.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+    "gpt_neox.layers.5.attention.dense.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.attention.dense.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.attention.query_key_value.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.attention.query_key_value.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.attention.rotary_emb.inv_freq": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.input_layernorm.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.input_layernorm.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.post_attention_layernorm.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.5.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.6.attention.dense.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.6.attention.dense.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.6.attention.query_key_value.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.6.attention.query_key_value.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.6.attention.rotary_emb.inv_freq": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.6.input_layernorm.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.6.input_layernorm.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.6.post_attention_layernorm.bias": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.6.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+    "gpt_neox.layers.7.attention.dense.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.attention.dense.weight": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.attention.query_key_value.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.attention.query_key_value.weight": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.attention.rotary_emb.inv_freq": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.input_layernorm.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.input_layernorm.weight": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.post_attention_layernorm.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.7.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.8.attention.dense.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.8.attention.dense.weight": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.8.attention.query_key_value.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.8.attention.query_key_value.weight": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.8.attention.rotary_emb.inv_freq": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.8.input_layernorm.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.8.input_layernorm.weight": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.8.post_attention_layernorm.bias": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.8.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+    "gpt_neox.layers.9.attention.dense.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.attention.dense.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.attention.query_key_value.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.attention.query_key_value.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.attention.rotary_emb.inv_freq": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.input_layernorm.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.input_layernorm.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.post_attention_layernorm.bias": "model-00005-of-00013.safetensors",
+    "gpt_neox.layers.9.post_attention_layernorm.weight": "model-00005-of-00013.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|sep|>",
+    "<|acc|>",
+    "<|tel|>",
+    "<|rrn|>"
+  ],
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,7 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}