Upload tokenizer
Browse files- special_tokens_map.json +6 -42
- tokenizer.json +0 -0
- tokenizer_config.json +0 -7
special_tokens_map.json
CHANGED
@@ -1,46 +1,10 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
},
|
9 |
-
"cls_token": {
|
10 |
-
"content": "[CLS]",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"eos_token": {
|
17 |
-
"content": "[SEP]",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": false,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
},
|
23 |
-
"mask_token": {
|
24 |
-
"content": "[MASK]",
|
25 |
-
"lstrip": false,
|
26 |
-
"normalized": false,
|
27 |
-
"rstrip": false,
|
28 |
-
"single_word": false
|
29 |
-
},
|
30 |
-
"pad_token": {
|
31 |
-
"content": "[PAD]",
|
32 |
-
"lstrip": false,
|
33 |
-
"normalized": false,
|
34 |
-
"rstrip": false,
|
35 |
-
"single_word": false
|
36 |
-
},
|
37 |
-
"sep_token": {
|
38 |
-
"content": "[SEP]",
|
39 |
-
"lstrip": false,
|
40 |
-
"normalized": false,
|
41 |
-
"rstrip": false,
|
42 |
-
"single_word": false
|
43 |
-
},
|
44 |
"unk_token": {
|
45 |
"content": "[UNK]",
|
46 |
"lstrip": false,
|
|
|
1 |
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"eos_token": "[SEP]",
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"pad_token": "[PAD]",
|
7 |
+
"sep_token": "[SEP]",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
"unk_token": {
|
9 |
"content": "[UNK]",
|
10 |
"lstrip": false,
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -47,19 +47,12 @@
|
|
47 |
"do_lower_case": false,
|
48 |
"eos_token": "[SEP]",
|
49 |
"mask_token": "[MASK]",
|
50 |
-
"max_length": 256,
|
51 |
"model_max_length": 1000000000000000019884624838656,
|
52 |
-
"pad_to_multiple_of": null,
|
53 |
"pad_token": "[PAD]",
|
54 |
-
"pad_token_type_id": 0,
|
55 |
-
"padding_side": "right",
|
56 |
"sep_token": "[SEP]",
|
57 |
"sp_model_kwargs": {},
|
58 |
"split_by_punct": false,
|
59 |
-
"stride": 0,
|
60 |
"tokenizer_class": "DebertaV2Tokenizer",
|
61 |
-
"truncation_side": "right",
|
62 |
-
"truncation_strategy": "longest_first",
|
63 |
"unk_token": "[UNK]",
|
64 |
"vocab_type": "spm"
|
65 |
}
|
|
|
47 |
"do_lower_case": false,
|
48 |
"eos_token": "[SEP]",
|
49 |
"mask_token": "[MASK]",
|
|
|
50 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
51 |
"pad_token": "[PAD]",
|
|
|
|
|
52 |
"sep_token": "[SEP]",
|
53 |
"sp_model_kwargs": {},
|
54 |
"split_by_punct": false,
|
|
|
55 |
"tokenizer_class": "DebertaV2Tokenizer",
|
|
|
|
|
56 |
"unk_token": "[UNK]",
|
57 |
"vocab_type": "spm"
|
58 |
}
|