Commit
•
22ede2d
1
Parent(s):
3e10344
Upload tokenizer
Browse files- special_tokens_map.json +5 -35
- tokenizer_config.json +2 -50
special_tokens_map.json
CHANGED
@@ -1,37 +1,7 @@
|
|
1 |
{
|
2 |
-
"cls_token":
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"mask_token": {
|
10 |
-
"content": "[MASK]",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"pad_token": {
|
17 |
-
"content": "[PAD]",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": false,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
},
|
23 |
-
"sep_token": {
|
24 |
-
"content": "[SEP]",
|
25 |
-
"lstrip": false,
|
26 |
-
"normalized": false,
|
27 |
-
"rstrip": false,
|
28 |
-
"single_word": false
|
29 |
-
},
|
30 |
-
"unk_token": {
|
31 |
-
"content": "[UNK]",
|
32 |
-
"lstrip": false,
|
33 |
-
"normalized": false,
|
34 |
-
"rstrip": false,
|
35 |
-
"single_word": false
|
36 |
-
}
|
37 |
}
|
|
|
1 |
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
}
|
tokenizer_config.json
CHANGED
@@ -1,64 +1,16 @@
|
|
1 |
{
|
2 |
-
"added_tokens_decoder": {
|
3 |
-
"0": {
|
4 |
-
"content": "[PAD]",
|
5 |
-
"lstrip": false,
|
6 |
-
"normalized": false,
|
7 |
-
"rstrip": false,
|
8 |
-
"single_word": false,
|
9 |
-
"special": true
|
10 |
-
},
|
11 |
-
"100": {
|
12 |
-
"content": "[UNK]",
|
13 |
-
"lstrip": false,
|
14 |
-
"normalized": false,
|
15 |
-
"rstrip": false,
|
16 |
-
"single_word": false,
|
17 |
-
"special": true
|
18 |
-
},
|
19 |
-
"101": {
|
20 |
-
"content": "[CLS]",
|
21 |
-
"lstrip": false,
|
22 |
-
"normalized": false,
|
23 |
-
"rstrip": false,
|
24 |
-
"single_word": false,
|
25 |
-
"special": true
|
26 |
-
},
|
27 |
-
"102": {
|
28 |
-
"content": "[SEP]",
|
29 |
-
"lstrip": false,
|
30 |
-
"normalized": false,
|
31 |
-
"rstrip": false,
|
32 |
-
"single_word": false,
|
33 |
-
"special": true
|
34 |
-
},
|
35 |
-
"103": {
|
36 |
-
"content": "[MASK]",
|
37 |
-
"lstrip": false,
|
38 |
-
"normalized": false,
|
39 |
-
"rstrip": false,
|
40 |
-
"single_word": false,
|
41 |
-
"special": true
|
42 |
-
}
|
43 |
-
},
|
44 |
-
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
46 |
"do_basic_tokenize": true,
|
47 |
"do_lower_case": false,
|
48 |
"mask_token": "[MASK]",
|
49 |
-
"max_length": 150,
|
50 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
51 |
"never_split": null,
|
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 |
-
"
|
58 |
"strip_accents": null,
|
59 |
"tokenize_chinese_chars": true,
|
60 |
"tokenizer_class": "BertTokenizer",
|
61 |
-
"truncation_side": "right",
|
62 |
-
"truncation_strategy": "longest_first",
|
63 |
"unk_token": "[UNK]"
|
64 |
}
|
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"cls_token": "[CLS]",
|
3 |
"do_basic_tokenize": true,
|
4 |
"do_lower_case": false,
|
5 |
"mask_token": "[MASK]",
|
|
|
6 |
"model_max_length": 1000000000000000019884624838656,
|
7 |
+
"name_or_path": "google-play-sentiment-analysis/checkpoint-48424",
|
8 |
"never_split": null,
|
|
|
9 |
"pad_token": "[PAD]",
|
|
|
|
|
10 |
"sep_token": "[SEP]",
|
11 |
+
"special_tokens_map_file": "/mnt/hdd/bryan/huggingface/eecc45187d085a1169eed91017d358cc0e9cbdd5dc236bcd710059dbf0a2f816.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d",
|
12 |
"strip_accents": null,
|
13 |
"tokenize_chinese_chars": true,
|
14 |
"tokenizer_class": "BertTokenizer",
|
|
|
|
|
15 |
"unk_token": "[UNK]"
|
16 |
}
|