init

added_tokens.json

@@ -0,0 +1 @@
+{"[-Q]": 30524, "[-Query]": 30522, "[-,]": 30525, "[-R]": 30523, "[-Text]": 30526}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.15.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30527
+}

notremovedname.json

@@ -0,0 +1 @@
+["entity", "object", "abstract object", "concrete object", "agent", "unit", "structure", "system", "subject", "physical system", "physical object", "group", "spatial entity", "geographical object", "geographic location", "geographic region", "individual", "living thing group", "location", "artificial entity", "person", "temporal entity", "territorial entity", "occurrence", "community", "concept", "quality", "property", "representation", "mental representation", "category", "legal person", "juridical person", "product", "work", "creator", "activity", "series", "artificial physical object", "phenomenon", "information", "logical consequence", "result", "goods and services", "goods", "intellectual work", "item", "creative work", "worker", "class", "behavior", "change", "inconstancy", "professional", "process", "human behaviour", "position", "manifestation", "communication medium", "occupation", "production", "industry", "knowledge", "performer", "interaction", "power", "authority", "organ", "mass media", "mathematical concept", "mathematical object", "geographic entity", "artificial geographic entity", "geographic object", "construction", "real property", "architectural structure", "administrative territorial entity", "condition", "competition", "regularity", "rule", "requirement", "public body", "erudite", "natural object", "natural physical object", "intangible good", "sign", "absence", "abstract being", "recurring event", "constituency", "fictional entity", "social system", "political system", "transport infrastructure", "audiovisual work", "building", "relation", "fictional character", "democracy", "specialty", "depiction", "ruler", "image", "source", "agreement", "accord", "symbol", "resource", "geomorphological unit", "landform", "field", "rights", "asset", "intangible asset", "intellectual property", "trademark", "quantity", "physical property", "physical quantity", "sports figure", "animal behavior", "former entity", "emic unit", "executive", "constituent", "gifting", "meaning", "semantic unit", "sentence", "proposition", "statement", "historical fact", "historical administrative division", "exchange", "former administrative territorial entity", "social organism behavior", "employee", "information exchange", "communication", "social space", "public space", "lyricist", "name", "human action", "body", "human communication", "venue", "interpersonal communication", "metaclass", "recurrent event edition", "thoroughfare", "serial", "combatant", "landmass", "taxon", "people", "warrior", "profession", "mental process", "recurring", "periodical literature", "realm", "military personnel", "principle", "converter", "tool", "broadcaster", "value", "monetary value", "cost", "expenditure", "stimulus", "grant", "incentive", "bounty", "part", "release", "military unit", "list", "aptitude", "title", "perceptible object", "document", "skill", "jurist", "planning", "military operation plan"]

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-uncased", "tokenizer_class": "BertTokenizer"}