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 +1,188 @@
+{
+  "_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": {
+    "A": 33,
+    "COLONCATEGORY": 40,
+    "COMMACATEGORY": 1,
+    "Caa": 21,
+    "Cab": 47,
+    "Cba": 57,
+    "Cbb": 13,
+    "D": 2,
+    "DASHCATEGORY": 53,
+    "DE": 3,
+    "DK": 64,
+    "DM": 59,
+    "DOTCATEGORY": 58,
+    "Da": 38,
+    "De": 63,
+    "Dfa": 27,
+    "Dfb": 55,
+    "Di": 26,
+    "Dk": 49,
+    "ETCCATEGORY": 51,
+    "EXCLAMATIONCATEGORY": 44,
+    "FW": 37,
+    "I": 52,
+    "N": 73,
+    "ND": 68,
+    "NG": 61,
+    "Na": 0,
+    "Nb": 15,
+    "Nc": 6,
+    "Ncd": 29,
+    "Nd": 17,
+    "Nep": 23,
+    "Neqa": 25,
+    "Neqb": 56,
+    "Nes": 35,
+    "Neu": 11,
+    "Nf": 10,
+    "Ng": 20,
+    "Nh": 9,
+    "Nv": 28,
+    "P": 7,
+    "PARENTHESISCATEGORY": 12,
+    "PAUSECATEGORY": 22,
+    "PERIODCATEGORY": 8,
+    "QUESTIONCATEGORY": 41,
+    "SEMICOLONCATEGORY": 46,
+    "SHI": 19,
+    "SPCHANGECATEGORY": 48,
+    "T": 32,
+    "V": 66,
+    "VA": 16,
+    "VAC": 54,
+    "VB": 45,
+    "VC": 4,
+    "VCL": 34,
+    "VD": 42,
+    "VE": 14,
+    "VF": 43,
+    "VG": 30,
+    "VH": 5,
+    "VHC": 39,
+    "VI": 50,
+    "VJ": 18,
+    "VK": 24,
+    "VL": 36,
+    "V_2": 31,
+    "Vc": 65,
+    "cbb": 67,
+    "dI": 75,
+    "na": 69,
+    "nf": 72,
+    "p": 71,
+    "sHI": 60,
+    "vA": 62,
+    "vC": 70,
+    "vH": 74
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "id2label": {
+    "0": "Na",
+    "1": "COMMACATEGORY",
+    "2": "D",
+    "3": "DE",
+    "4": "VC",
+    "5": "VH",
+    "6": "Nc",
+    "7": "P",
+    "8": "PERIODCATEGORY",
+    "9": "Nh",
+    "10": "Nf",
+    "11": "Neu",
+    "12": "PARENTHESISCATEGORY",
+    "13": "Cbb",
+    "14": "VE",
+    "15": "Nb",
+    "16": "VA",
+    "17": "Nd",
+    "18": "VJ",
+    "19": "SHI",
+    "20": "Ng",
+    "21": "Caa",
+    "22": "PAUSECATEGORY",
+    "23": "Nep",
+    "24": "VK",
+    "25": "Neqa",
+    "26": "Di",
+    "27": "Dfa",
+    "28": "Nv",
+    "29": "Ncd",
+    "30": "VG",
+    "31": "V_2",
+    "32": "T",
+    "33": "A",
+    "34": "VCL",
+    "35": "Nes",
+    "36": "VL",
+    "37": "FW",
+    "38": "Da",
+    "39": "VHC",
+    "40": "COLONCATEGORY",
+    "41": "QUESTIONCATEGORY",
+    "42": "VD",
+    "43": "VF",
+    "44": "EXCLAMATIONCATEGORY",
+    "45": "VB",
+    "46": "SEMICOLONCATEGORY",
+    "47": "Cab",
+    "48": "SPCHANGECATEGORY",
+    "49": "Dk",
+    "50": "VI",
+    "51": "ETCCATEGORY",
+    "52": "I",
+    "53": "DASHCATEGORY",
+    "54": "VAC",
+    "55": "Dfb",
+    "56": "Neqb",
+    "57": "Cba",
+    "58": "DOTCATEGORY",
+    "59": "DM",
+    "60": "sHI",
+    "61": "NG",
+    "62": "vA",
+    "63": "De",
+    "64": "DK",
+    "65": "Vc",
+    "66": "V",
+    "67": "cbb",
+    "68": "ND",
+    "69": "na",
+    "70": "vC",
+    "71": "p",
+    "72": "nf",
+    "73": "N",
+    "74": "vH",
+    "75": "dI"
+  },
+  "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:a64721b8cce84399ba6259e968d1629bec858d596ef6fcaa043b894faf8ac5a0
+size 422390967

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}