Upload model files.
Browse files- README.md +22 -0
- config.json +153 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- zh
|
4 |
+
thumbnail: https://ckip.iis.sinica.edu.tw/files/ckip_logo.png
|
5 |
+
tags:
|
6 |
+
- pytorch
|
7 |
+
- token-classification
|
8 |
+
- albert
|
9 |
+
- zh
|
10 |
+
license: gpl-3.0
|
11 |
+
datasets:
|
12 |
+
metrics:
|
13 |
+
---
|
14 |
+
|
15 |
+
# CKIP ALBERT Tiny Chinese β Part-of-Speech Tagging
|
16 |
+
|
17 |
+
## Contributers
|
18 |
+
|
19 |
+
* [Mu Yang](https://muyang.pro) at [CKIP](https://ckip.iis.sinica.edu.tw) (Author & Maintainer)
|
20 |
+
|
21 |
+
## Attention
|
22 |
+
Please Use `BertTokenizer` instead of `AutoTokenizer`!!!
|
config.json
ADDED
@@ -0,0 +1,153 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"AlbertForTokenClassification"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.0,
|
6 |
+
"bos_token_id": 2,
|
7 |
+
"classifier_dropout_prob": 0.1,
|
8 |
+
"down_scale_factor": 1,
|
9 |
+
"embedding_size": 128,
|
10 |
+
"eos_token_id": 3,
|
11 |
+
"gap_size": 0,
|
12 |
+
"hidden_act": "gelu",
|
13 |
+
"hidden_dropout_prob": 0.0,
|
14 |
+
"hidden_size": 312,
|
15 |
+
"id2label": {
|
16 |
+
"0": "A",
|
17 |
+
"1": "Caa",
|
18 |
+
"2": "Cab",
|
19 |
+
"3": "Cba",
|
20 |
+
"4": "Cbb",
|
21 |
+
"5": "D",
|
22 |
+
"6": "Da",
|
23 |
+
"7": "Dfa",
|
24 |
+
"8": "Dfb",
|
25 |
+
"9": "Di",
|
26 |
+
"10": "Dk",
|
27 |
+
"11": "DM",
|
28 |
+
"12": "I",
|
29 |
+
"13": "Na",
|
30 |
+
"14": "Nb",
|
31 |
+
"15": "Nc",
|
32 |
+
"16": "Ncd",
|
33 |
+
"17": "Nd",
|
34 |
+
"18": "Nep",
|
35 |
+
"19": "Neqa",
|
36 |
+
"20": "Neqb",
|
37 |
+
"21": "Nes",
|
38 |
+
"22": "Neu",
|
39 |
+
"23": "Nf",
|
40 |
+
"24": "Ng",
|
41 |
+
"25": "Nh",
|
42 |
+
"26": "Nv",
|
43 |
+
"27": "P",
|
44 |
+
"28": "T",
|
45 |
+
"29": "VA",
|
46 |
+
"30": "VAC",
|
47 |
+
"31": "VB",
|
48 |
+
"32": "VC",
|
49 |
+
"33": "VCL",
|
50 |
+
"34": "VD",
|
51 |
+
"35": "VF",
|
52 |
+
"36": "VE",
|
53 |
+
"37": "VG",
|
54 |
+
"38": "VH",
|
55 |
+
"39": "VHC",
|
56 |
+
"40": "VI",
|
57 |
+
"41": "VJ",
|
58 |
+
"42": "VK",
|
59 |
+
"43": "VL",
|
60 |
+
"44": "V_2",
|
61 |
+
"45": "DE",
|
62 |
+
"46": "SHI",
|
63 |
+
"47": "FW",
|
64 |
+
"48": "COLONCATEGORY",
|
65 |
+
"49": "COMMACATEGORY",
|
66 |
+
"50": "DASHCATEGORY",
|
67 |
+
"51": "DOTCATEGORY",
|
68 |
+
"52": "ETCCATEGORY",
|
69 |
+
"53": "EXCLAMATIONCATEGORY",
|
70 |
+
"54": "PARENTHESISCATEGORY",
|
71 |
+
"55": "PAUSECATEGORY",
|
72 |
+
"56": "PERIODCATEGORY",
|
73 |
+
"57": "QUESTIONCATEGORY",
|
74 |
+
"58": "SEMICOLONCATEGORY",
|
75 |
+
"59": "SPCHANGECATEGORY"
|
76 |
+
},
|
77 |
+
"initializer_range": 0.02,
|
78 |
+
"inner_group_num": 1,
|
79 |
+
"intermediate_size": 1248,
|
80 |
+
"label2id": {
|
81 |
+
"A": 0,
|
82 |
+
"COLONCATEGORY": 48,
|
83 |
+
"COMMACATEGORY": 49,
|
84 |
+
"Caa": 1,
|
85 |
+
"Cab": 2,
|
86 |
+
"Cba": 3,
|
87 |
+
"Cbb": 4,
|
88 |
+
"D": 5,
|
89 |
+
"DASHCATEGORY": 50,
|
90 |
+
"DE": 45,
|
91 |
+
"DM": 11,
|
92 |
+
"DOTCATEGORY": 51,
|
93 |
+
"Da": 6,
|
94 |
+
"Dfa": 7,
|
95 |
+
"Dfb": 8,
|
96 |
+
"Di": 9,
|
97 |
+
"Dk": 10,
|
98 |
+
"ETCCATEGORY": 52,
|
99 |
+
"EXCLAMATIONCATEGORY": 53,
|
100 |
+
"FW": 47,
|
101 |
+
"I": 12,
|
102 |
+
"Na": 13,
|
103 |
+
"Nb": 14,
|
104 |
+
"Nc": 15,
|
105 |
+
"Ncd": 16,
|
106 |
+
"Nd": 17,
|
107 |
+
"Nep": 18,
|
108 |
+
"Neqa": 19,
|
109 |
+
"Neqb": 20,
|
110 |
+
"Nes": 21,
|
111 |
+
"Neu": 22,
|
112 |
+
"Nf": 23,
|
113 |
+
"Ng": 24,
|
114 |
+
"Nh": 25,
|
115 |
+
"Nv": 26,
|
116 |
+
"P": 27,
|
117 |
+
"PARENTHESISCATEGORY": 54,
|
118 |
+
"PAUSECATEGORY": 55,
|
119 |
+
"PERIODCATEGORY": 56,
|
120 |
+
"QUESTIONCATEGORY": 57,
|
121 |
+
"SEMICOLONCATEGORY": 58,
|
122 |
+
"SHI": 46,
|
123 |
+
"SPCHANGECATEGORY": 59,
|
124 |
+
"T": 28,
|
125 |
+
"VA": 29,
|
126 |
+
"VAC": 30,
|
127 |
+
"VB": 31,
|
128 |
+
"VC": 32,
|
129 |
+
"VCL": 33,
|
130 |
+
"VD": 34,
|
131 |
+
"VE": 36,
|
132 |
+
"VF": 35,
|
133 |
+
"VG": 37,
|
134 |
+
"VH": 38,
|
135 |
+
"VHC": 39,
|
136 |
+
"VI": 40,
|
137 |
+
"VJ": 41,
|
138 |
+
"VK": 42,
|
139 |
+
"VL": 43,
|
140 |
+
"V_2": 44
|
141 |
+
},
|
142 |
+
"layer_norm_eps": 1e-12,
|
143 |
+
"max_position_embeddings": 512,
|
144 |
+
"model_type": "albert",
|
145 |
+
"net_structure_type": 0,
|
146 |
+
"num_attention_heads": 12,
|
147 |
+
"num_hidden_groups": 1,
|
148 |
+
"num_hidden_layers": 4,
|
149 |
+
"num_memory_blocks": 0,
|
150 |
+
"pad_token_id": 0,
|
151 |
+
"type_vocab_size": 2,
|
152 |
+
"vocab_size": 21128
|
153 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad2531da210e17fef06b14ad9b5b056ccdcf4bd8952cdb13142d094a67f9c2c8
|
3 |
+
size 16021593
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "do_basic_tokenize": true, "never_split": null, "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": "bert-base-chinese"}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|