File size: 4,035 Bytes
8f01022
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
{
    "version": "1.0",
    "truncation": null,
    "padding": null,
    "added_tokens": [
        {
            "id": 0,
            "special": true,
            "content": "<|startoftext|>",
            "single_word": false,
            "lstrip": false,
            "rstrip": false,
            "normalized": true
        },
        {
            "id": 1,
            "special": true,
            "content": "<|endoftext|>",
            "single_word": false,
            "lstrip": false,
            "rstrip": false,
            "normalized": false
        }
    ],
    "normalizer": {
        "type": "Sequence",
        "normalizers": [
            {
                "type": "NFC"
            },
            {
                "type": "Replace",
                "pattern": {
                    "Regex": "\\s+"
                },
                "content": " "
            },
            {
                "type": "Lowercase"
            }
        ]
    },
    "pre_tokenizer": {
        "type": "Sequence",
        "pretokenizers": [
            {
                "type": "Split",
                "pattern": {
                    "Regex": "'s|'t|'re|'ve|'m|'ll|'d|[\\p{L}]+|[\\p{N}]|[^\\s\\p{L}\\p{N}]+"
                },
                "behavior": "Removed",
                "invert": true
            },
            {
                "type": "ByteLevel",
                "add_prefix_space": false,
                "trim_offsets": true
            }
        ]
    },
    "post_processor": {
        "type": "RobertaProcessing",
        "sep": ["<|endoftext|>", 1],
        "cls": ["<|startoftext|>", 0],
        "trim_offsets": false,
        "add_prefix_space": false
    },
    "decoder": {
        "type": "ByteLevel",
        "add_prefix_space": true,
        "trim_offsets": true
    },
    "model": {
        "type": "BPE",
        "dropout": null,
        "unk_token": "<|endoftext|>",
        "continuing_subword_prefix": "",
        "end_of_word_suffix": "</w>",
        "fuse_unk": false,
        "vocab": {
            "<|startoftext|>": 0,
            "<|endoftext|>": 1,
            "!": 2,
            "\"": 3,
            "#": 4,
            "$": 5,
            "%": 6,
            "&": 7,
            "'": 8,
            "(": 9,
            ")": 10,
            "*": 11,
            "+": 12,
            ",": 13,
            "-": 14,
            ".": 15,
            "/": 16,
            "0": 17,
            "1": 18,
            "2": 19,
            "3": 20,
            "4": 21,
            "5": 22,
            "6": 23,
            "7": 24,
            "8": 25,
            "9": 26,
            ":": 27,
            ";": 28,
            "<": 29,
            "=": 30,
            ">": 31,
            "?": 32,
            "@": 33,
            "A": 34,
            "B": 35,
            "C": 36,
            "D": 37,
            "E": 38,
            "F": 39,
            "G": 40,
            "H": 41,
            "I": 42,
            "J": 43,
            "K": 44,
            "L": 45,
            "M": 46,
            "N": 47,
            "O": 48,
            "P": 49,
            "Q": 50,
            "R": 51,
            "S": 52,
            "T": 53,
            "U": 54,
            "V": 55,
            "W": 56,
            "X": 57,
            "Y": 58,
            "Z": 59,
            "[": 60,
            "\\": 61,
            "]": 62,
            "^": 63,
            "_": 64,
            "`": 65,
            "a": 66,
            "b": 67,
            "c": 68,
            "d": 69,
            "e": 70,
            "f": 71,
            "g": 72,
            "h": 73,
            "i": 74,
            "j": 75,
            "k": 76,
            "l": 77,
            "m": 78,
            "n": 79,
            "o": 80,
            "p": 81,
            "q": 82,
            "r": 83,
            "s": 84,
            "t": 85,
            "u": 86,
            "v": 87,
            "w": 88,
            "x": 89,
            "y": 90,
            "z": 91,
            "|": 92
        },
        "merges": []
    }
}