xeko56/html-generator

1{
2  "added_tokens_decoder": {
3    "0": {
4      "content": "<s>",
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>",
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    "57521": {
36      "content": "<mask>",
37      "lstrip": true,
38      "normalized": true,
39      "rstrip": false,
40      "single_word": false,
41      "special": true
42    },
43    "57522": {
44      "content": "<sep/>",
45      "lstrip": false,
46      "normalized": true,
47      "rstrip": false,
48      "single_word": false,
49      "special": false
50    },
51    "57523": {
52      "content": "<s_iitcdip>",
53      "lstrip": false,
54      "normalized": false,
55      "rstrip": false,
56      "single_word": false,
57      "special": true
58    },
59    "57524": {
60      "content": "<s_synthdog>",
61      "lstrip": false,
62      "normalized": false,
63      "rstrip": false,
64      "single_word": false,
65      "special": true
66    },
67    "57525": {
68      "content": "<html_table>",
69      "lstrip": false,
70      "normalized": true,
71      "rstrip": false,
72      "single_word": false,
73      "special": false
74    }
75  },
76  "additional_special_tokens": [
77    "<s_iitcdip>",
78    "<s_synthdog>"
79  ],
80  "bos_token": "<s>",
81  "clean_up_tokenization_spaces": true,
82  "cls_token": "<s>",
83  "eos_token": "</s>",
84  "mask_token": "<mask>",
85  "model_max_length": 1000000000000000019884624838656,
86  "pad_token": "<pad>",
87  "processor_class": "DonutProcessor",
88  "sep_token": "</s>",
89  "sp_model_kwargs": {},
90  "tokenizer_class": "XLMRobertaTokenizer",
91  "unk_token": "<unk>"
92}
93