Update model checkpoint and configs

Files changed (7) hide show

.gitattributes +1 -0
README.md +55 -3
config.json +425 -0
label_map.json +198 -0
model.safetensors +3 -0
tokenizer.json +0 -0
用法示例.jpg +3 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+用法示例.jpg filter=lfs diff=lfs merge=lfs -text

README.md CHANGED Viewed

@@ -1,3 +1,55 @@
----
-license: cc-by-nc-sa-4.0
----

+---
+license: cc-by-nc-sa-4.0
+---
+# 明实录与清实录多标签分类推理模型
+本模型用于对《明实录》和《清实录》文本进行多标签分类推理。基于[Jihuai/bert-ancient-chinese](https://huggingface.co/Jihuai/bert-ancient-chinese)进行任务微调，利用公开语料进行预训练，得到适合实录类型的预训练模型[shiluBERT](https://huggingface.co/bztxb/shiluBERT)。
+## 中文说明
+### 模型与数据来源
+- 训练数据来源：[《朝鲜王朝实录》](https://sillok.history.go.kr)；
+- 任务类型：多标签文本分类；
+- 训练样本数：约27万。
+### 评估指标
+| 指标 | 数值 |
+|---|---|
+| Sample F1 | 0.7246 |
+| Sample Precision | 0.7594 |
+| Sample Recall | 0.7321 |
+| LRAP | 0.8074 |
+| Hamming Loss | 0.0069 |
+### 示例使用方法
+- 在线体验 Space： [bztxb/shiluInfer](https://huggingface.co/spaces/bztxb/shiluInfer)
+![Space 使用示例](用法示例.jpg)
+## English Version
+This model performs multi-label classification inference on texts of VERITABLE RECORDS of the Ming/Qing DYNASTY. It is fine-tuned from [Jihuai/bert-ancient-chinese](https://huggingface.co/Jihuai/bert-ancient-chinese), and further benefits from pretraining on public corpora to obtain a Shilu-oriented pretrained model, [shiluBERT](https://huggingface.co/bztxb/shiluBERT).
+### Model and Data Sources
+- Training data source: [VERITABLE RECORDS of the JOSEON DYNASTY](https://sillok.history.go.kr).
+- Task type: multi-label text classification.
+- Number of training samples: approximately 0.27 million.
+### Evaluation Metrics
+| Metric | Value |
+|---|---|
+| Sample F1 | 0.7246 |
+| Sample Precision | 0.7594 |
+| Sample Recall | 0.7321 |
+| LRAP | 0.8074 |
+| Hamming Loss | 0.0069 |
+### Example Usage
+- Try the online Space: [bztxb/shiluInfer](https://huggingface.co/spaces/bztxb/shiluInfer)
+![Space Usage Example](用法示例.jpg)

config.json ADDED Viewed

	@@ -0,0 +1,425 @@

+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19",
+    "20": "LABEL_20",
+    "21": "LABEL_21",
+    "22": "LABEL_22",
+    "23": "LABEL_23",
+    "24": "LABEL_24",
+    "25": "LABEL_25",
+    "26": "LABEL_26",
+    "27": "LABEL_27",
+    "28": "LABEL_28",
+    "29": "LABEL_29",
+    "30": "LABEL_30",
+    "31": "LABEL_31",
+    "32": "LABEL_32",
+    "33": "LABEL_33",
+    "34": "LABEL_34",
+    "35": "LABEL_35",
+    "36": "LABEL_36",
+    "37": "LABEL_37",
+    "38": "LABEL_38",
+    "39": "LABEL_39",
+    "40": "LABEL_40",
+    "41": "LABEL_41",
+    "42": "LABEL_42",
+    "43": "LABEL_43",
+    "44": "LABEL_44",
+    "45": "LABEL_45",
+    "46": "LABEL_46",
+    "47": "LABEL_47",
+    "48": "LABEL_48",
+    "49": "LABEL_49",
+    "50": "LABEL_50",
+    "51": "LABEL_51",
+    "52": "LABEL_52",
+    "53": "LABEL_53",
+    "54": "LABEL_54",
+    "55": "LABEL_55",
+    "56": "LABEL_56",
+    "57": "LABEL_57",
+    "58": "LABEL_58",
+    "59": "LABEL_59",
+    "60": "LABEL_60",
+    "61": "LABEL_61",
+    "62": "LABEL_62",
+    "63": "LABEL_63",
+    "64": "LABEL_64",
+    "65": "LABEL_65",
+    "66": "LABEL_66",
+    "67": "LABEL_67",
+    "68": "LABEL_68",
+    "69": "LABEL_69",
+    "70": "LABEL_70",
+    "71": "LABEL_71",
+    "72": "LABEL_72",
+    "73": "LABEL_73",
+    "74": "LABEL_74",
+    "75": "LABEL_75",
+    "76": "LABEL_76",
+    "77": "LABEL_77",
+    "78": "LABEL_78",
+    "79": "LABEL_79",
+    "80": "LABEL_80",
+    "81": "LABEL_81",
+    "82": "LABEL_82",
+    "83": "LABEL_83",
+    "84": "LABEL_84",
+    "85": "LABEL_85",
+    "86": "LABEL_86",
+    "87": "LABEL_87",
+    "88": "LABEL_88",
+    "89": "LABEL_89",
+    "90": "LABEL_90",
+    "91": "LABEL_91",
+    "92": "LABEL_92",
+    "93": "LABEL_93",
+    "94": "LABEL_94",
+    "95": "LABEL_95",
+    "96": "LABEL_96",
+    "97": "LABEL_97",
+    "98": "LABEL_98",
+    "99": "LABEL_99",
+    "100": "LABEL_100",
+    "101": "LABEL_101",
+    "102": "LABEL_102",
+    "103": "LABEL_103",
+    "104": "LABEL_104",
+    "105": "LABEL_105",
+    "106": "LABEL_106",
+    "107": "LABEL_107",
+    "108": "LABEL_108",
+    "109": "LABEL_109",
+    "110": "LABEL_110",
+    "111": "LABEL_111",
+    "112": "LABEL_112",
+    "113": "LABEL_113",
+    "114": "LABEL_114",
+    "115": "LABEL_115",
+    "116": "LABEL_116",
+    "117": "LABEL_117",
+    "118": "LABEL_118",
+    "119": "LABEL_119",
+    "120": "LABEL_120",
+    "121": "LABEL_121",
+    "122": "LABEL_122",
+    "123": "LABEL_123",
+    "124": "LABEL_124",
+    "125": "LABEL_125",
+    "126": "LABEL_126",
+    "127": "LABEL_127",
+    "128": "LABEL_128",
+    "129": "LABEL_129",
+    "130": "LABEL_130",
+    "131": "LABEL_131",
+    "132": "LABEL_132",
+    "133": "LABEL_133",
+    "134": "LABEL_134",
+    "135": "LABEL_135",
+    "136": "LABEL_136",
+    "137": "LABEL_137",
+    "138": "LABEL_138",
+    "139": "LABEL_139",
+    "140": "LABEL_140",
+    "141": "LABEL_141",
+    "142": "LABEL_142",
+    "143": "LABEL_143",
+    "144": "LABEL_144",
+    "145": "LABEL_145",
+    "146": "LABEL_146",
+    "147": "LABEL_147",
+    "148": "LABEL_148",
+    "149": "LABEL_149",
+    "150": "LABEL_150",
+    "151": "LABEL_151",
+    "152": "LABEL_152",
+    "153": "LABEL_153",
+    "154": "LABEL_154",
+    "155": "LABEL_155",
+    "156": "LABEL_156",
+    "157": "LABEL_157",
+    "158": "LABEL_158",
+    "159": "LABEL_159",
+    "160": "LABEL_160",
+    "161": "LABEL_161",
+    "162": "LABEL_162",
+    "163": "LABEL_163",
+    "164": "LABEL_164",
+    "165": "LABEL_165",
+    "166": "LABEL_166",
+    "167": "LABEL_167",
+    "168": "LABEL_168",
+    "169": "LABEL_169",
+    "170": "LABEL_170",
+    "171": "LABEL_171",
+    "172": "LABEL_172",
+    "173": "LABEL_173",
+    "174": "LABEL_174",
+    "175": "LABEL_175",
+    "176": "LABEL_176",
+    "177": "LABEL_177",
+    "178": "LABEL_178",
+    "179": "LABEL_179",
+    "180": "LABEL_180",
+    "181": "LABEL_181",
+    "182": "LABEL_182",
+    "183": "LABEL_183",
+    "184": "LABEL_184",
+    "185": "LABEL_185",
+    "186": "LABEL_186",
+    "187": "LABEL_187",
+    "188": "LABEL_188",
+    "189": "LABEL_189",
+    "190": "LABEL_190",
+    "191": "LABEL_191",
+    "192": "LABEL_192",
+    "193": "LABEL_193"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_100": 100,
+    "LABEL_101": 101,
+    "LABEL_102": 102,
+    "LABEL_103": 103,
+    "LABEL_104": 104,
+    "LABEL_105": 105,
+    "LABEL_106": 106,
+    "LABEL_107": 107,
+    "LABEL_108": 108,
+    "LABEL_109": 109,
+    "LABEL_11": 11,
+    "LABEL_110": 110,
+    "LABEL_111": 111,
+    "LABEL_112": 112,
+    "LABEL_113": 113,
+    "LABEL_114": 114,
+    "LABEL_115": 115,
+    "LABEL_116": 116,
+    "LABEL_117": 117,
+    "LABEL_118": 118,
+    "LABEL_119": 119,
+    "LABEL_12": 12,
+    "LABEL_120": 120,
+    "LABEL_121": 121,
+    "LABEL_122": 122,
+    "LABEL_123": 123,
+    "LABEL_124": 124,
+    "LABEL_125": 125,
+    "LABEL_126": 126,
+    "LABEL_127": 127,
+    "LABEL_128": 128,
+    "LABEL_129": 129,
+    "LABEL_13": 13,
+    "LABEL_130": 130,
+    "LABEL_131": 131,
+    "LABEL_132": 132,
+    "LABEL_133": 133,
+    "LABEL_134": 134,
+    "LABEL_135": 135,
+    "LABEL_136": 136,
+    "LABEL_137": 137,
+    "LABEL_138": 138,
+    "LABEL_139": 139,
+    "LABEL_14": 14,
+    "LABEL_140": 140,
+    "LABEL_141": 141,
+    "LABEL_142": 142,
+    "LABEL_143": 143,
+    "LABEL_144": 144,
+    "LABEL_145": 145,
+    "LABEL_146": 146,
+    "LABEL_147": 147,
+    "LABEL_148": 148,
+    "LABEL_149": 149,
+    "LABEL_15": 15,
+    "LABEL_150": 150,
+    "LABEL_151": 151,
+    "LABEL_152": 152,
+    "LABEL_153": 153,
+    "LABEL_154": 154,
+    "LABEL_155": 155,
+    "LABEL_156": 156,
+    "LABEL_157": 157,
+    "LABEL_158": 158,
+    "LABEL_159": 159,
+    "LABEL_16": 16,
+    "LABEL_160": 160,
+    "LABEL_161": 161,
+    "LABEL_162": 162,
+    "LABEL_163": 163,
+    "LABEL_164": 164,
+    "LABEL_165": 165,
+    "LABEL_166": 166,
+    "LABEL_167": 167,
+    "LABEL_168": 168,
+    "LABEL_169": 169,
+    "LABEL_17": 17,
+    "LABEL_170": 170,
+    "LABEL_171": 171,
+    "LABEL_172": 172,
+    "LABEL_173": 173,
+    "LABEL_174": 174,
+    "LABEL_175": 175,
+    "LABEL_176": 176,
+    "LABEL_177": 177,
+    "LABEL_178": 178,
+    "LABEL_179": 179,
+    "LABEL_18": 18,
+    "LABEL_180": 180,
+    "LABEL_181": 181,
+    "LABEL_182": 182,
+    "LABEL_183": 183,
+    "LABEL_184": 184,
+    "LABEL_185": 185,
+    "LABEL_186": 186,
+    "LABEL_187": 187,
+    "LABEL_188": 188,
+    "LABEL_189": 189,
+    "LABEL_19": 19,
+    "LABEL_190": 190,
+    "LABEL_191": 191,
+    "LABEL_192": 192,
+    "LABEL_193": 193,
+    "LABEL_2": 2,
+    "LABEL_20": 20,
+    "LABEL_21": 21,
+    "LABEL_22": 22,
+    "LABEL_23": 23,
+    "LABEL_24": 24,
+    "LABEL_25": 25,
+    "LABEL_26": 26,
+    "LABEL_27": 27,
+    "LABEL_28": 28,
+    "LABEL_29": 29,
+    "LABEL_3": 3,
+    "LABEL_30": 30,
+    "LABEL_31": 31,
+    "LABEL_32": 32,
+    "LABEL_33": 33,
+    "LABEL_34": 34,
+    "LABEL_35": 35,
+    "LABEL_36": 36,
+    "LABEL_37": 37,
+    "LABEL_38": 38,
+    "LABEL_39": 39,
+    "LABEL_4": 4,
+    "LABEL_40": 40,
+    "LABEL_41": 41,
+    "LABEL_42": 42,
+    "LABEL_43": 43,
+    "LABEL_44": 44,
+    "LABEL_45": 45,
+    "LABEL_46": 46,
+    "LABEL_47": 47,
+    "LABEL_48": 48,
+    "LABEL_49": 49,
+    "LABEL_5": 5,
+    "LABEL_50": 50,
+    "LABEL_51": 51,
+    "LABEL_52": 52,
+    "LABEL_53": 53,
+    "LABEL_54": 54,
+    "LABEL_55": 55,
+    "LABEL_56": 56,
+    "LABEL_57": 57,
+    "LABEL_58": 58,
+    "LABEL_59": 59,
+    "LABEL_6": 6,
+    "LABEL_60": 60,
+    "LABEL_61": 61,
+    "LABEL_62": 62,
+    "LABEL_63": 63,
+    "LABEL_64": 64,
+    "LABEL_65": 65,
+    "LABEL_66": 66,
+    "LABEL_67": 67,
+    "LABEL_68": 68,
+    "LABEL_69": 69,
+    "LABEL_7": 7,
+    "LABEL_70": 70,
+    "LABEL_71": 71,
+    "LABEL_72": 72,
+    "LABEL_73": 73,
+    "LABEL_74": 74,
+    "LABEL_75": 75,
+    "LABEL_76": 76,
+    "LABEL_77": 77,
+    "LABEL_78": 78,
+    "LABEL_79": 79,
+    "LABEL_8": 8,
+    "LABEL_80": 80,
+    "LABEL_81": 81,
+    "LABEL_82": 82,
+    "LABEL_83": 83,
+    "LABEL_84": 84,
+    "LABEL_85": 85,
+    "LABEL_86": 86,
+    "LABEL_87": 87,
+    "LABEL_88": 88,
+    "LABEL_89": 89,
+    "LABEL_9": 9,
+    "LABEL_90": 90,
+    "LABEL_91": 91,
+    "LABEL_92": 92,
+    "LABEL_93": 93,
+    "LABEL_94": 94,
+    "LABEL_95": 95,
+    "LABEL_96": 96,
+    "LABEL_97": 97,
+    "LABEL_98": 98,
+    "LABEL_99": 99
+  },
+  "layer_norm_eps": 1e-12,
+  "lstm_dropout_prob": 0.5,
+  "lstm_embedding_size": 768,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 38208
+}

label_map.json ADDED Viewed

	@@ -0,0 +1,198 @@

+{
+  "labels": [
+    "上供",
+    "中人",
+    "中央亞",
+    "中央行政",
+    "中央軍",
+    "主副食",
+    "交通",
+    "人事",
+    "人文敎育",
+    "人物",
+    "任免",
+    "住生活",
+    "佛敎",
+    "保健",
+    "倉庫",
+    "倫理",
+    "倭",
+    "儀式",
+    "儒學",
+    "元",
+    "兩班",
+    "兵法",
+    "兵站",
+    "其他",
+    "出版",
+    "前史",
+    "勸農",
+    "化學",
+    "匠人",
+    "印刷",
+    "史學",
+    "司法",
+    "商人",
+    "商品",
+    "商業",
+    "嗜好食品",
+    "器皿祭物",
+    "國王",
+    "國用",
+    "土俗信仰",
+    "土地賣買",
+    "土木",
+    "地學",
+    "地方自治",
+    "地方行政",
+    "地方軍",
+    "外交",
+    "天氣",
+    "契",
+    "妃嬪",
+    "姓名",
+    "宅地",
+    "宗社",
+    "宗親",
+    "官廳手工",
+    "官服",
+    "宮官",
+    "宴會",
+    "家具",
+    "家屋",
+    "家族",
+    "家産",
+    "專賣",
+    "工業",
+    "市場",
+    "常服",
+    "常民",
+    "度量衡",
+    "建築",
+    "建設",
+    "彈劾",
+    "役",
+    "思想",
+    "恤兵",
+    "戰爭",
+    "戶口",
+    "戶籍",
+    "手工業品",
+    "手數料",
+    "技術敎育",
+    "採鑛",
+    "政論",
+    "政變",
+    "故事",
+    "敎育",
+    "救恤",
+    "數學",
+    "文學",
+    "明",
+    "曆法",
+    "書冊",
+    "東南亞",
+    "東學",
+    "林業",
+    "果樹園藝",
+    "歐美",
+    "歷史",
+    "殖利",
+    "民亂",
+    "水利",
+    "水産業",
+    "水運",
+    "治安",
+    "法制",
+    "漁業",
+    "演劇",
+    "物價",
+    "物理",
+    "特殊敎育",
+    "特殊軍",
+    "特用作物",
+    "獸醫學",
+    "王室",
+    "琉球",
+    "生物",
+    "田制",
+    "田稅",
+    "畜産",
+    "社會紀綱",
+    "禁火",
+    "禮俗",
+    "禮服",
+    "私營手工",
+    "科學",
+    "移動",
+    "管理",
+    "經營形態",
+    "經筵",
+    "綱常",
+    "綿作",
+    "編史",
+    "美術",
+    "聚落",
+    "舞踊",
+    "藝術",
+    "藥學",
+    "行刑",
+    "行幸",
+    "行政",
+    "衣生活",
+    "裁判",
+    "裝身具",
+    "製鍊",
+    "西學",
+    "親族",
+    "語學",
+    "語文學",
+    "諫諍",
+    "變亂",
+    "財政",
+    "貢物",
+    "貨幣",
+    "貿易",
+    "賃貸",
+    "賃金",
+    "賜給",
+    "賤人",
+    "赴防",
+    "身分",
+    "身分變動",
+    "身良役賤",
+    "軍事",
+    "軍器",
+    "軍役",
+    "軍政",
+    "軍資",
+    "農作",
+    "農村手工",
+    "農業",
+    "農業技術",
+    "通信",
+    "進上",
+    "運賃",
+    "道敎",
+    "選拔",
+    "鄕村",
+    "酒類",
+    "醫學",
+    "醫藥",
+    "野",
+    "量田",
+    "金融",
+    "鑛山",
+    "鑛業",
+    "開墾",
+    "關防",
+    "陸運",
+    "雜稅",
+    "音樂",
+    "風俗",
+    "食生活",
+    "養蠶",
+    "馬政",
+    "鹽業"
+  ]
+}

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f4ccff14c7aa1f762b804988d54ab7a2382853e1a96d91cc78286d734554618d
+size 462160648

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

用法示例.jpg ADDED Viewed

Git LFS Details

SHA256: 19e3e2a382dbf6b8a2c01933b28a3eae9ad5c63b907f41f47da7c2d97e91338d
Pointer size: 131 Bytes
Size of remote file: 221 kB