Shankhdhar
commited on
Commit
•
c0d25e3
1
Parent(s):
0ee6515
Upload tokenizer_config.json with huggingface_hub
Browse files- tokenizer_config.json +66 -0
tokenizer_config.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"104": {
|
28 |
+
"content": "[UNK]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"30526": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"bos_token": "<s>",
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "<s>",
|
47 |
+
"do_basic_tokenize": true,
|
48 |
+
"do_lower_case": true,
|
49 |
+
"eos_token": "</s>",
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"max_length": 512,
|
52 |
+
"model_max_length": 512,
|
53 |
+
"never_split": null,
|
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 |
+
"strip_accents": null,
|
61 |
+
"tokenize_chinese_chars": true,
|
62 |
+
"tokenizer_class": "MPNetTokenizer",
|
63 |
+
"truncation_side": "right",
|
64 |
+
"truncation_strategy": "longest_first",
|
65 |
+
"unk_token": "[UNK]"
|
66 |
+
}
|