Upload tokenizer
Browse files- special_tokens_map.json +1 -30
- tokenizer.json +0 -36
- tokenizer_config.json +1 -40
special_tokens_map.json
CHANGED
@@ -1,30 +1 @@
|
|
1 |
-
{
|
2 |
-
"mask_token": {
|
3 |
-
"content": "[MASK]",
|
4 |
-
"lstrip": false,
|
5 |
-
"normalized": false,
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"pad_token": {
|
10 |
-
"content": "[PAD]",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"sep_token": {
|
17 |
-
"content": "[SEP]",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": false,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
},
|
23 |
-
"unk_token": {
|
24 |
-
"content": "[UNK]",
|
25 |
-
"lstrip": false,
|
26 |
-
"normalized": false,
|
27 |
-
"rstrip": false,
|
28 |
-
"single_word": false
|
29 |
-
}
|
30 |
-
}
|
|
|
1 |
+
{}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer.json
CHANGED
@@ -29,42 +29,6 @@
|
|
29 |
"rstrip": false,
|
30 |
"normalized": false,
|
31 |
"special": true
|
32 |
-
},
|
33 |
-
{
|
34 |
-
"id": 425,
|
35 |
-
"content": "[UNK]",
|
36 |
-
"single_word": false,
|
37 |
-
"lstrip": false,
|
38 |
-
"rstrip": false,
|
39 |
-
"normalized": false,
|
40 |
-
"special": true
|
41 |
-
},
|
42 |
-
{
|
43 |
-
"id": 426,
|
44 |
-
"content": "[SEP]",
|
45 |
-
"single_word": false,
|
46 |
-
"lstrip": false,
|
47 |
-
"rstrip": false,
|
48 |
-
"normalized": false,
|
49 |
-
"special": true
|
50 |
-
},
|
51 |
-
{
|
52 |
-
"id": 427,
|
53 |
-
"content": "[PAD]",
|
54 |
-
"single_word": false,
|
55 |
-
"lstrip": false,
|
56 |
-
"rstrip": false,
|
57 |
-
"normalized": false,
|
58 |
-
"special": true
|
59 |
-
},
|
60 |
-
{
|
61 |
-
"id": 428,
|
62 |
-
"content": "[MASK]",
|
63 |
-
"single_word": false,
|
64 |
-
"lstrip": false,
|
65 |
-
"rstrip": false,
|
66 |
-
"normalized": false,
|
67 |
-
"special": true
|
68 |
}
|
69 |
],
|
70 |
"normalizer": null,
|
|
|
29 |
"rstrip": false,
|
30 |
"normalized": false,
|
31 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
}
|
33 |
],
|
34 |
"normalizer": null,
|
tokenizer_config.json
CHANGED
@@ -23,48 +23,9 @@
|
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
-
},
|
27 |
-
"425": {
|
28 |
-
"content": "[UNK]",
|
29 |
-
"lstrip": false,
|
30 |
-
"normalized": false,
|
31 |
-
"rstrip": false,
|
32 |
-
"single_word": false,
|
33 |
-
"special": true
|
34 |
-
},
|
35 |
-
"426": {
|
36 |
-
"content": "[SEP]",
|
37 |
-
"lstrip": false,
|
38 |
-
"normalized": false,
|
39 |
-
"rstrip": false,
|
40 |
-
"single_word": false,
|
41 |
-
"special": true
|
42 |
-
},
|
43 |
-
"427": {
|
44 |
-
"content": "[PAD]",
|
45 |
-
"lstrip": false,
|
46 |
-
"normalized": false,
|
47 |
-
"rstrip": false,
|
48 |
-
"single_word": false,
|
49 |
-
"special": true
|
50 |
-
},
|
51 |
-
"428": {
|
52 |
-
"content": "[MASK]",
|
53 |
-
"lstrip": false,
|
54 |
-
"normalized": false,
|
55 |
-
"rstrip": false,
|
56 |
-
"single_word": false,
|
57 |
-
"special": true
|
58 |
}
|
59 |
},
|
60 |
"clean_up_tokenization_spaces": true,
|
61 |
-
"mask_token": "[MASK]",
|
62 |
-
"model_input_names": [
|
63 |
-
"input_ids"
|
64 |
-
],
|
65 |
"model_max_length": 1000000000000000019884624838656,
|
66 |
-
"
|
67 |
-
"sep_token": "[SEP]",
|
68 |
-
"tokenizer_class": "PreTrainedTokenizerFast",
|
69 |
-
"unk_token": "[UNK]"
|
70 |
}
|
|
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
}
|
27 |
},
|
28 |
"clean_up_tokenization_spaces": true,
|
|
|
|
|
|
|
|
|
29 |
"model_max_length": 1000000000000000019884624838656,
|
30 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
|
|
|
|
|
|
31 |
}
|