Upload tokenizer
Browse files- special_tokens_map.json +7 -0
- tokenizer.json +72 -0
- tokenizer_config.json +9 -0
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"version": "1.0",
|
3 |
+
"truncation": null,
|
4 |
+
"padding": null,
|
5 |
+
"added_tokens": [
|
6 |
+
{
|
7 |
+
"id": 0,
|
8 |
+
"content": "[PAD]",
|
9 |
+
"single_word": false,
|
10 |
+
"lstrip": false,
|
11 |
+
"rstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"special": true
|
14 |
+
},
|
15 |
+
{
|
16 |
+
"id": 1,
|
17 |
+
"content": "[MASK]",
|
18 |
+
"single_word": false,
|
19 |
+
"lstrip": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"normalized": false,
|
22 |
+
"special": true
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"id": 2,
|
26 |
+
"content": "[UNK]",
|
27 |
+
"single_word": false,
|
28 |
+
"lstrip": false,
|
29 |
+
"rstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"special": true
|
32 |
+
}
|
33 |
+
],
|
34 |
+
"normalizer": null,
|
35 |
+
"pre_tokenizer": null,
|
36 |
+
"post_processor": null,
|
37 |
+
"decoder": null,
|
38 |
+
"model": {
|
39 |
+
"type": "BPE",
|
40 |
+
"dropout": null,
|
41 |
+
"unk_token": "[UNK]",
|
42 |
+
"continuing_subword_prefix": null,
|
43 |
+
"end_of_word_suffix": null,
|
44 |
+
"fuse_unk": false,
|
45 |
+
"vocab": {
|
46 |
+
"[PAD]": 0,
|
47 |
+
"[MASK]": 1,
|
48 |
+
"[UNK]": 2,
|
49 |
+
"A": 3,
|
50 |
+
"C": 4,
|
51 |
+
"D": 5,
|
52 |
+
"E": 6,
|
53 |
+
"F": 7,
|
54 |
+
"G": 8,
|
55 |
+
"H": 9,
|
56 |
+
"I": 10,
|
57 |
+
"K": 11,
|
58 |
+
"L": 12,
|
59 |
+
"M": 13,
|
60 |
+
"N": 14,
|
61 |
+
"P": 15,
|
62 |
+
"Q": 16,
|
63 |
+
"R": 17,
|
64 |
+
"S": 18,
|
65 |
+
"T": 19,
|
66 |
+
"V": 20,
|
67 |
+
"W": 21,
|
68 |
+
"Y": 22
|
69 |
+
},
|
70 |
+
"merges": []
|
71 |
+
}
|
72 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"model_max_length": 1000000000000000019884624838656,
|
5 |
+
"pad_token": "[PAD]",
|
6 |
+
"sep_token": "[SEP]",
|
7 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
8 |
+
"unk_token": "[UNK]"
|
9 |
+
}
|