ko-electra-base-ner with naver ner dataset

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,68 @@
+{
+  "_name_or_path": "monologg/koelectra-base-v3-discriminator",
+  "architectures": [
+    "ElectraForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 768,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "-",
+    "1": "PER_B",
+    "2": "PER_I",
+    "3": "LFD_B",
+    "4": "LFD_I",
+    "5": "ORG_B",
+    "6": "ORG_I",
+    "7": "LOC_B",
+    "8": "LOC_I",
+    "9": "DAT_B",
+    "10": "DAT_I",
+    "11": "TIM_B",
+    "12": "TIM_I",
+    "13": "NUM_B",
+    "14": "NUM_I",
+    "15": "EVT_B",
+    "16": "EVT_I"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "-": 0,
+    "DAT_B": 9,
+    "DAT_I": 10,
+    "EVT_B": 15,
+    "EVT_I": 16,
+    "LFD_B": 3,
+    "LFD_I": 4,
+    "LOC_B": 7,
+    "LOC_I": 8,
+    "NUM_B": 13,
+    "NUM_I": 14,
+    "ORG_B": 5,
+    "ORG_I": 6,
+    "PER_B": 1,
+    "PER_I": 2,
+    "TIM_B": 11,
+    "TIM_I": 12
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 35000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2220710599231c6b8e61ce18cf921bf48ef494951edb0e1f4d2332773d4b6375
+size 449444777

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "ElectraTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:271d881b3f9244803a1307ba66e5c739fe1e82f28e57aeb5b9cd2de0eed37864
+size 3963