init klue-ner

config.json

@@ -0,0 +1,59 @@
+{
+  "_name_or_path": "klue/roberta-base",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-DT",
+    "1": "I-DT",
+    "2": "B-LC",
+    "3": "I-LC",
+    "4": "B-OG",
+    "5": "I-OG",
+    "6": "B-PS",
+    "7": "I-PS",
+    "8": "B-QT",
+    "9": "I-QT",
+    "10": "B-TI",
+    "11": "I-TI",
+    "12": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-DT": 0,
+    "B-LC": 2,
+    "B-OG": 4,
+    "B-PS": 6,
+    "B-QT": 8,
+    "B-TI": 10,
+    "I-DT": 1,
+    "I-LC": 3,
+    "I-OG": 5,
+    "I-PS": 7,
+    "I-QT": 9,
+    "I-TI": 11,
+    "O": 12
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "BertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6337bf549fe8358b1f0fa1ca13beec133a88c5acc1436efa7e94930dc52a93c4
+size 440221105

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "add_prefix_space": true,
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "klue/roberta-base",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--klue--roberta-base/snapshots/67dd433d36ebc66a42c9aaa85abcf8d2620e41d9/special_tokens_map.json",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}