CoolFace
Modelpublic

putthaimastan/wangchanberta_thai_sms_content_classification

sourceHugging Faceupdated 1y agoView on Hugging Face
1likes4downloads
tokenizer_config.json86 linesDownload Raw Back to root
1{
2  "added_tokens_decoder": {
3    "0": {
4      "content": "<s>NOTUSED",
5      "lstrip": false,
6      "normalized": false,
7      "rstrip": false,
8      "single_word": false,
9      "special": true
10    },
11    "1": {
12      "content": "<pad>",
13      "lstrip": false,
14      "normalized": false,
15      "rstrip": false,
16      "single_word": false,
17      "special": true
18    },
19    "2": {
20      "content": "</s>NOTUSED",
21      "lstrip": false,
22      "normalized": false,
23      "rstrip": false,
24      "single_word": false,
25      "special": true
26    },
27    "3": {
28      "content": "<unk>",
29      "lstrip": false,
30      "normalized": false,
31      "rstrip": false,
32      "single_word": false,
33      "special": true
34    },
35    "5": {
36      "content": "<s>",
37      "lstrip": false,
38      "normalized": false,
39      "rstrip": false,
40      "single_word": false,
41      "special": true
42    },
43    "6": {
44      "content": "</s>",
45      "lstrip": false,
46      "normalized": false,
47      "rstrip": false,
48      "single_word": false,
49      "special": true
50    },
51    "8": {
52      "content": "<_>",
53      "lstrip": false,
54      "normalized": false,
55      "rstrip": false,
56      "single_word": false,
57      "special": false
58    },
59    "25004": {
60      "content": "<mask>",
61      "lstrip": true,
62      "normalized": false,
63      "rstrip": false,
64      "single_word": false,
65      "special": true
66    }
67  },
68  "additional_special_tokens": [
69    "<s>NOTUSED",
70    "</s>NOTUSED",
71    "<_>"
72  ],
73  "bos_token": "<s>",
74  "clean_up_tokenization_spaces": false,
75  "cls_token": "<s>",
76  "eos_token": "</s>",
77  "extra_special_tokens": {},
78  "mask_token": "<mask>",
79  "model_max_length": 1000000000000000019884624838656,
80  "pad_token": "<pad>",
81  "sep_token": "</s>",
82  "sp_model_kwargs": {},
83  "tokenizer_class": "CamembertTokenizer",
84  "unk_token": "<unk>"
85}
86