upload model files

README.md

@@ -1,3 +1,28 @@
 ---
+language:
+  - zh
+thumbnail: https://ckip.iis.sinica.edu.tw/files/ckip_logo.png
+tags:
+  - pytorch
+  - token-classification
+  - bert
+  - zh
 license: gpl-3.0
 ---
+
+# CKIP BERT Base Han Chinese POS
+
+This model provides part-of-speech (POS) tagging for the ancient Chinese language. Our training dataset covers four eras of the Chinese language.
+
+## Homepage
+* [ckiplab/han-transformers](https://github.com/ckiplab/han-transformers)
+
+## Training Datasets
+The copyright of the datasets belongs to the Institute of Linguistics, Academia Sinica.
+* [中央研究院上古漢語標記語料庫](http://lingcorpus.iis.sinica.edu.tw/cgi-bin/kiwi/akiwi/kiwi.sh)
+* [中央研究院中古漢語語料庫](http://lingcorpus.iis.sinica.edu.tw/cgi-bin/kiwi/dkiwi/kiwi.sh)
+* [中央研究院近代漢語語料庫](http://lingcorpus.iis.sinica.edu.tw/cgi-bin/kiwi/pkiwi/kiwi.sh)
+* [中央研究院現代漢語語料庫](http://asbc.iis.sinica.edu.tw)
+
+## Contributors
+* Chin-Tung Lin at [CKIP](https://ckip.iis.sinica.edu.tw/)

config.json

@@ -0,0 +1,232 @@
+{
+  "_name_or_path": "hub/ckiplab/bert-base-chinese-20210817-001848",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "directionality": "bidi",
+  "finetuning_task": "ner",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "label2id": {
+    "/Na": 88,
+    "3": 72,
+    "A": 46,
+    "CE": 82,
+    "COLONCATEGORY": 11,
+    "COMMACATEGORY": 0,
+    "Caa": 56,
+    "Cbb": 33,
+    "D": 96,
+    "DASHCATEGORY": 63,
+    "DE": 24,
+    "Daa": 38,
+    "Dab": 39,
+    "Dba": 54,
+    "Dbb": 35,
+    "Dc": 18,
+    "Dd": 22,
+    "Df": 95,
+    "Dfa": 48,
+    "Dfb": 65,
+    "Dg": 67,
+    "Dh": 32,
+    "Dha": 94,
+    "Di": 21,
+    "Dj": 43,
+    "Dk": 60,
+    "Dl": 14,
+    "ETCCATEGORY": 62,
+    "EXCLAMATIONCATEGORY": 58,
+    "EXCLANATIONCATEGORY": 28,
+    "FW": 52,
+    "I": 64,
+    "N": 80,
+    "NA": 81,
+    "Na": 1,
+    "Nb": 7,
+    "Nc": 10,
+    "Nd": 19,
+    "Neqa": 40,
+    "Nes": 41,
+    "Neu": 12,
+    "Nf": 15,
+    "Ng": 17,
+    "Nh": 4,
+    "Nha": 87,
+    "P": 16,
+    "PARENTHESISCATEGOR": 74,
+    "PARENTHESISCATEGORY": 8,
+    "PAUSECATEGORY": 42,
+    "PERIODCATEGORY": 2,
+    "Q": 70,
+    "QUESTIONCATEGORY": 26,
+    "R": 66,
+    "SEMICOLONCATEGORY": 44,
+    "SHI": 25,
+    "T": 23,
+    "T3": 45,
+    "T4": 49,
+    "T5": 55,
+    "T6": 50,
+    "T7": 57,
+    "T8": 51,
+    "U": 53,
+    "V": 77,
+    "V-2": 76,
+    "VA": 20,
+    "VAC": 47,
+    "VAL": 89,
+    "VB": 61,
+    "VC": 3,
+    "VCL": 9,
+    "VCl": 79,
+    "VD": 37,
+    "VE": 5,
+    "VF": 30,
+    "VG": 36,
+    "VH": 6,
+    "VHC": 29,
+    "VHL": 71,
+    "VI": 68,
+    "VJ": 27,
+    "VK": 13,
+    "VL": 31,
+    "VU": 97,
+    "V_": 90,
+    "V_2": 34,
+    "Va": 91,
+    "Vf": 78,
+    "Vh": 83,
+    "Vk": 93,
+    "X": 75,
+    "b": 59,
+    "cr": 92,
+    "q": 73,
+    "u": 84,
+    "x": 69,
+    "\u5750": 85,
+    "\u7c59": 86
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "id2label": {
+    "0": "COMMACATEGORY",
+    "1": "Na",
+    "2": "PERIODCATEGORY",
+    "3": "VC",
+    "4": "Nh",
+    "5": "VE",
+    "6": "VH",
+    "7": "Nb",
+    "8": "PARENTHESISCATEGORY",
+    "9": "VCL",
+    "10": "Nc",
+    "11": "COLONCATEGORY",
+    "12": "Neu",
+    "13": "VK",
+    "14": "Dl",
+    "15": "Nf",
+    "16": "P",
+    "17": "Ng",
+    "18": "Dc",
+    "19": "Nd",
+    "20": "VA",
+    "21": "Di",
+    "22": "Dd",
+    "23": "T",
+    "24": "DE",
+    "25": "SHI",
+    "26": "QUESTIONCATEGORY",
+    "27": "VJ",
+    "28": "EXCLANATIONCATEGORY",
+    "29": "VHC",
+    "30": "VF",
+    "31": "VL",
+    "32": "Dh",
+    "33": "Cbb",
+    "34": "V_2",
+    "35": "Dbb",
+    "36": "VG",
+    "37": "VD",
+    "38": "Daa",
+    "39": "Dab",
+    "40": "Neqa",
+    "41": "Nes",
+    "42": "PAUSECATEGORY",
+    "43": "Dj",
+    "44": "SEMICOLONCATEGORY",
+    "45": "T3",
+    "46": "A",
+    "47": "VAC",
+    "48": "Dfa",
+    "49": "T4",
+    "50": "T6",
+    "51": "T8",
+    "52": "FW",
+    "53": "U",
+    "54": "Dba",
+    "55": "T5",
+    "56": "Caa",
+    "57": "T7",
+    "58": "EXCLAMATIONCATEGORY",
+    "59": "b",
+    "60": "Dk",
+    "61": "VB",
+    "62": "ETCCATEGORY",
+    "63": "DASHCATEGORY",
+    "64": "I",
+    "65": "Dfb",
+    "66": "R",
+    "67": "Dg",
+    "68": "VI",
+    "69": "x",
+    "70": "Q",
+    "71": "VHL",
+    "72": "3",
+    "73": "q",
+    "74": "PARENTHESISCATEGOR",
+    "75": "X",
+    "76": "V-2",
+    "77": "V",
+    "78": "Vf",
+    "79": "VCl",
+    "80": "N",
+    "81": "NA",
+    "82": "CE",
+    "83": "Vh",
+    "84": "u",
+    "85": "\u5750",
+    "86": "\u7c59",
+    "87": "Nha",
+    "88": "/Na",
+    "89": "VAL",
+    "90": "V_",
+    "91": "Va",
+    "92": "cr",
+    "93": "Vk",
+    "94": "Dha",
+    "95": "Df",
+    "96": "D",
+    "97": "VU"
+  },
+  "layer_norm_eps": 1e-12,
+  "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",
+  "tokenizer_class": "BertTokenizerFast",
+  "transformers_version": "4.7.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 26140
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c18e15377f8c615c95b2c095f5d064e5ae8ab2a30d996dca100b7644b3a44c70
+size 422458643

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, "name_or_path": "hub/ckiplab/bert-base-chinese-20210817-001848", "special_tokens_map_file": "/home/cindy666/.cache/huggingface/transformers/d8a1a1b7a3de221ae53bf9d55154b9df9c4cda18409b393ee0fda4bce4ca7818.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "do_basic_tokenize": true, "never_split": null}