Upload tokenizer
Browse files- special_tokens_map.json +3 -0
- tokenizer.json +51 -0
- tokenizer_config.json +21 -0
special_tokens_map.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"pad_token": "[PAD]"
|
3 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"version": "1.0",
|
3 |
+
"truncation": null,
|
4 |
+
"padding": {
|
5 |
+
"strategy": "BatchLongest",
|
6 |
+
"direction": "Right",
|
7 |
+
"pad_to_multiple_of": null,
|
8 |
+
"pad_id": 1,
|
9 |
+
"pad_type_id": 0,
|
10 |
+
"pad_token": "[PAD]"
|
11 |
+
},
|
12 |
+
"added_tokens": [
|
13 |
+
{
|
14 |
+
"id": 11,
|
15 |
+
"content": "[PAD]",
|
16 |
+
"single_word": false,
|
17 |
+
"lstrip": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"special": true
|
21 |
+
}
|
22 |
+
],
|
23 |
+
"normalizer": null,
|
24 |
+
"pre_tokenizer": {
|
25 |
+
"type": "Split",
|
26 |
+
"pattern": {
|
27 |
+
"String": ""
|
28 |
+
},
|
29 |
+
"behavior": "Isolated",
|
30 |
+
"invert": false
|
31 |
+
},
|
32 |
+
"post_processor": null,
|
33 |
+
"decoder": null,
|
34 |
+
"model": {
|
35 |
+
"type": "WordLevel",
|
36 |
+
"vocab": {
|
37 |
+
"0": 0,
|
38 |
+
"1": 1,
|
39 |
+
"2": 2,
|
40 |
+
"3": 3,
|
41 |
+
"4": 4,
|
42 |
+
"5": 5,
|
43 |
+
"6": 6,
|
44 |
+
"7": 7,
|
45 |
+
"8": 8,
|
46 |
+
"9": 9,
|
47 |
+
"S": 10
|
48 |
+
},
|
49 |
+
"unk_token": "[UNK]"
|
50 |
+
}
|
51 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"11": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
}
|
11 |
+
},
|
12 |
+
"additional_special_tokens": [],
|
13 |
+
"clean_up_tokenization_spaces": true,
|
14 |
+
"max_length": null,
|
15 |
+
"model_max_length": 1000000000000000019884624838656,
|
16 |
+
"pad_to_multiple_of": null,
|
17 |
+
"pad_token": "[PAD]",
|
18 |
+
"pad_token_type_id": 0,
|
19 |
+
"padding_side": "right",
|
20 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
21 |
+
}
|