Thacio Garcia Scandaroli commited on
Commit
18ef259
1 Parent(s): ed9deac

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|NLG|>": 50260,
3
+ "<|NLU|>": 50259,
4
+ "<|beginoftext|>": 50257,
5
+ "<|extra_id_0|>": 50261,
6
+ "<|extra_id_10|>": 50271,
7
+ "<|extra_id_11|>": 50272,
8
+ "<|extra_id_12|>": 50273,
9
+ "<|extra_id_13|>": 50274,
10
+ "<|extra_id_14|>": 50275,
11
+ "<|extra_id_15|>": 50276,
12
+ "<|extra_id_16|>": 50277,
13
+ "<|extra_id_17|>": 50278,
14
+ "<|extra_id_18|>": 50279,
15
+ "<|extra_id_19|>": 50280,
16
+ "<|extra_id_1|>": 50262,
17
+ "<|extra_id_20|>": 50281,
18
+ "<|extra_id_21|>": 50282,
19
+ "<|extra_id_22|>": 50283,
20
+ "<|extra_id_23|>": 50284,
21
+ "<|extra_id_24|>": 50285,
22
+ "<|extra_id_25|>": 50286,
23
+ "<|extra_id_26|>": 50287,
24
+ "<|extra_id_27|>": 50288,
25
+ "<|extra_id_28|>": 50289,
26
+ "<|extra_id_29|>": 50290,
27
+ "<|extra_id_2|>": 50263,
28
+ "<|extra_id_30|>": 50291,
29
+ "<|extra_id_31|>": 50292,
30
+ "<|extra_id_32|>": 50293,
31
+ "<|extra_id_33|>": 50294,
32
+ "<|extra_id_34|>": 50295,
33
+ "<|extra_id_35|>": 50296,
34
+ "<|extra_id_36|>": 50297,
35
+ "<|extra_id_37|>": 50298,
36
+ "<|extra_id_38|>": 50299,
37
+ "<|extra_id_39|>": 50300,
38
+ "<|extra_id_3|>": 50264,
39
+ "<|extra_id_40|>": 50301,
40
+ "<|extra_id_41|>": 50302,
41
+ "<|extra_id_42|>": 50303,
42
+ "<|extra_id_43|>": 50304,
43
+ "<|extra_id_44|>": 50305,
44
+ "<|extra_id_45|>": 50306,
45
+ "<|extra_id_46|>": 50307,
46
+ "<|extra_id_47|>": 50308,
47
+ "<|extra_id_48|>": 50309,
48
+ "<|extra_id_49|>": 50310,
49
+ "<|extra_id_4|>": 50265,
50
+ "<|extra_id_50|>": 50311,
51
+ "<|extra_id_51|>": 50312,
52
+ "<|extra_id_52|>": 50313,
53
+ "<|extra_id_53|>": 50314,
54
+ "<|extra_id_54|>": 50315,
55
+ "<|extra_id_55|>": 50316,
56
+ "<|extra_id_56|>": 50317,
57
+ "<|extra_id_57|>": 50318,
58
+ "<|extra_id_58|>": 50319,
59
+ "<|extra_id_59|>": 50320,
60
+ "<|extra_id_5|>": 50266,
61
+ "<|extra_id_60|>": 50321,
62
+ "<|extra_id_61|>": 50322,
63
+ "<|extra_id_62|>": 50323,
64
+ "<|extra_id_63|>": 50324,
65
+ "<|extra_id_64|>": 50325,
66
+ "<|extra_id_65|>": 50326,
67
+ "<|extra_id_66|>": 50327,
68
+ "<|extra_id_67|>": 50328,
69
+ "<|extra_id_68|>": 50329,
70
+ "<|extra_id_69|>": 50330,
71
+ "<|extra_id_6|>": 50267,
72
+ "<|extra_id_70|>": 50331,
73
+ "<|extra_id_71|>": 50332,
74
+ "<|extra_id_72|>": 50333,
75
+ "<|extra_id_73|>": 50334,
76
+ "<|extra_id_74|>": 50335,
77
+ "<|extra_id_75|>": 50336,
78
+ "<|extra_id_76|>": 50337,
79
+ "<|extra_id_77|>": 50338,
80
+ "<|extra_id_78|>": 50339,
81
+ "<|extra_id_79|>": 50340,
82
+ "<|extra_id_7|>": 50268,
83
+ "<|extra_id_80|>": 50341,
84
+ "<|extra_id_81|>": 50342,
85
+ "<|extra_id_82|>": 50343,
86
+ "<|extra_id_83|>": 50344,
87
+ "<|extra_id_84|>": 50345,
88
+ "<|extra_id_85|>": 50346,
89
+ "<|extra_id_86|>": 50347,
90
+ "<|extra_id_87|>": 50348,
91
+ "<|extra_id_88|>": 50349,
92
+ "<|extra_id_89|>": 50350,
93
+ "<|extra_id_8|>": 50269,
94
+ "<|extra_id_90|>": 50351,
95
+ "<|extra_id_91|>": 50352,
96
+ "<|extra_id_92|>": 50353,
97
+ "<|extra_id_93|>": 50354,
98
+ "<|extra_id_94|>": 50355,
99
+ "<|extra_id_95|>": 50356,
100
+ "<|extra_id_96|>": 50357,
101
+ "<|extra_id_97|>": 50358,
102
+ "<|extra_id_98|>": 50359,
103
+ "<|extra_id_99|>": 50360,
104
+ "<|extra_id_9|>": 50270,
105
+ "<|unk|>": 50258
106
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|NLU|>",
4
+ "<|NLG|>",
5
+ "<|extra_id_0|>",
6
+ "<|extra_id_1|>",
7
+ "<|extra_id_2|>",
8
+ "<|extra_id_3|>",
9
+ "<|extra_id_4|>",
10
+ "<|extra_id_5|>",
11
+ "<|extra_id_6|>",
12
+ "<|extra_id_7|>",
13
+ "<|extra_id_8|>",
14
+ "<|extra_id_9|>",
15
+ "<|extra_id_10|>",
16
+ "<|extra_id_11|>",
17
+ "<|extra_id_12|>",
18
+ "<|extra_id_13|>",
19
+ "<|extra_id_14|>",
20
+ "<|extra_id_15|>",
21
+ "<|extra_id_16|>",
22
+ "<|extra_id_17|>",
23
+ "<|extra_id_18|>",
24
+ "<|extra_id_19|>",
25
+ "<|extra_id_20|>",
26
+ "<|extra_id_21|>",
27
+ "<|extra_id_22|>",
28
+ "<|extra_id_23|>",
29
+ "<|extra_id_24|>",
30
+ "<|extra_id_25|>",
31
+ "<|extra_id_26|>",
32
+ "<|extra_id_27|>",
33
+ "<|extra_id_28|>",
34
+ "<|extra_id_29|>",
35
+ "<|extra_id_30|>",
36
+ "<|extra_id_31|>",
37
+ "<|extra_id_32|>",
38
+ "<|extra_id_33|>",
39
+ "<|extra_id_34|>",
40
+ "<|extra_id_35|>",
41
+ "<|extra_id_36|>",
42
+ "<|extra_id_37|>",
43
+ "<|extra_id_38|>",
44
+ "<|extra_id_39|>",
45
+ "<|extra_id_40|>",
46
+ "<|extra_id_41|>",
47
+ "<|extra_id_42|>",
48
+ "<|extra_id_43|>",
49
+ "<|extra_id_44|>",
50
+ "<|extra_id_45|>",
51
+ "<|extra_id_46|>",
52
+ "<|extra_id_47|>",
53
+ "<|extra_id_48|>",
54
+ "<|extra_id_49|>",
55
+ "<|extra_id_50|>",
56
+ "<|extra_id_51|>",
57
+ "<|extra_id_52|>",
58
+ "<|extra_id_53|>",
59
+ "<|extra_id_54|>",
60
+ "<|extra_id_55|>",
61
+ "<|extra_id_56|>",
62
+ "<|extra_id_57|>",
63
+ "<|extra_id_58|>",
64
+ "<|extra_id_59|>",
65
+ "<|extra_id_60|>",
66
+ "<|extra_id_61|>",
67
+ "<|extra_id_62|>",
68
+ "<|extra_id_63|>",
69
+ "<|extra_id_64|>",
70
+ "<|extra_id_65|>",
71
+ "<|extra_id_66|>",
72
+ "<|extra_id_67|>",
73
+ "<|extra_id_68|>",
74
+ "<|extra_id_69|>",
75
+ "<|extra_id_70|>",
76
+ "<|extra_id_71|>",
77
+ "<|extra_id_72|>",
78
+ "<|extra_id_73|>",
79
+ "<|extra_id_74|>",
80
+ "<|extra_id_75|>",
81
+ "<|extra_id_76|>",
82
+ "<|extra_id_77|>",
83
+ "<|extra_id_78|>",
84
+ "<|extra_id_79|>",
85
+ "<|extra_id_80|>",
86
+ "<|extra_id_81|>",
87
+ "<|extra_id_82|>",
88
+ "<|extra_id_83|>",
89
+ "<|extra_id_84|>",
90
+ "<|extra_id_85|>",
91
+ "<|extra_id_86|>",
92
+ "<|extra_id_87|>",
93
+ "<|extra_id_88|>",
94
+ "<|extra_id_89|>",
95
+ "<|extra_id_90|>",
96
+ "<|extra_id_91|>",
97
+ "<|extra_id_92|>",
98
+ "<|extra_id_93|>",
99
+ "<|extra_id_94|>",
100
+ "<|extra_id_95|>",
101
+ "<|extra_id_96|>",
102
+ "<|extra_id_97|>",
103
+ "<|extra_id_98|>",
104
+ "<|extra_id_99|>"
105
+ ],
106
+ "bos_token": "<|beginoftext|>",
107
+ "eos_token": "<|endoftext|>",
108
+ "pad_token": "<|pad|>",
109
+ "unk_token": "<|unk|>"
110
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "additional_special_tokens": [
4
+ "<|pad|>",
5
+ "<|endoftext|>"
6
+ ],
7
+ "bos_token": "<|pad|>",
8
+ "clean_up_tokenization_spaces": true,
9
+ "eos_token": "<|pad|>",
10
+ "model_max_length": 1024,
11
+ "special_tokens_map_file": null,
12
+ "tokenizer_class": "GPT2Tokenizer",
13
+ "unk_token": "<|pad|>"
14
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff