Team Ai
Modelpublic

GunMan0410/Text_Profanity

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes5downloads
tokenizer_config.json66 linesDownload Raw Back to root
1{
2  "add_prefix_space": false,
3  "added_tokens_decoder": {
4    "0": {
5      "content": "<s>",
6      "lstrip": false,
7      "normalized": true,
8      "rstrip": false,
9      "single_word": false,
10      "special": true
11    },
12    "1": {
13      "content": "<pad>",
14      "lstrip": false,
15      "normalized": true,
16      "rstrip": false,
17      "single_word": false,
18      "special": true
19    },
20    "2": {
21      "content": "</s>",
22      "lstrip": false,
23      "normalized": true,
24      "rstrip": false,
25      "single_word": false,
26      "special": true
27    },
28    "3": {
29      "content": "<unk>",
30      "lstrip": false,
31      "normalized": true,
32      "rstrip": false,
33      "single_word": false,
34      "special": true
35    },
36    "50264": {
37      "content": "<mask>",
38      "lstrip": true,
39      "normalized": false,
40      "rstrip": false,
41      "single_word": false,
42      "special": true
43    }
44  },
45  "bos_token": "<s>",
46  "clean_up_tokenization_spaces": true,
47  "cls_token": "<s>",
48  "do_lower_case": false,
49  "eos_token": "</s>",
50  "errors": "replace",
51  "mask_token": "<mask>",
52  "max_length": 512,
53  "model_max_length": 512,
54  "pad_to_multiple_of": null,
55  "pad_token": "<pad>",
56  "pad_token_type_id": 0,
57  "padding_side": "right",
58  "sep_token": "</s>",
59  "stride": 0,
60  "tokenizer_class": "RobertaTokenizer",
61  "trim_offsets": true,
62  "truncation_side": "right",
63  "truncation_strategy": "longest_first",
64  "unk_token": "<unk>"
65}
66