Commit
•
cf529ad
1
Parent(s):
6d82fb2
Upload tokenizer
Browse files- special_tokens_map.json +1 -0
- tokenizer.json +118 -0
- tokenizer_config.json +5 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,118 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
| 5 |
+
"added_tokens": [],
|
| 6 |
+
"normalizer": null,
|
| 7 |
+
"pre_tokenizer": null,
|
| 8 |
+
"post_processor": null,
|
| 9 |
+
"decoder": null,
|
| 10 |
+
"model": {
|
| 11 |
+
"type": "BPE",
|
| 12 |
+
"dropout": null,
|
| 13 |
+
"unk_token": null,
|
| 14 |
+
"continuing_subword_prefix": null,
|
| 15 |
+
"end_of_word_suffix": null,
|
| 16 |
+
"fuse_unk": false,
|
| 17 |
+
"byte_fallback": false,
|
| 18 |
+
"vocab": {
|
| 19 |
+
"\n": 0,
|
| 20 |
+
" ": 1,
|
| 21 |
+
"!": 2,
|
| 22 |
+
"\"": 3,
|
| 23 |
+
"#": 4,
|
| 24 |
+
"$": 5,
|
| 25 |
+
"%": 6,
|
| 26 |
+
"&": 7,
|
| 27 |
+
"'": 8,
|
| 28 |
+
"(": 9,
|
| 29 |
+
")": 10,
|
| 30 |
+
"*": 11,
|
| 31 |
+
"+": 12,
|
| 32 |
+
",": 13,
|
| 33 |
+
"-": 14,
|
| 34 |
+
".": 15,
|
| 35 |
+
"/": 16,
|
| 36 |
+
"0": 17,
|
| 37 |
+
"1": 18,
|
| 38 |
+
"2": 19,
|
| 39 |
+
"3": 20,
|
| 40 |
+
"4": 21,
|
| 41 |
+
"5": 22,
|
| 42 |
+
"6": 23,
|
| 43 |
+
"7": 24,
|
| 44 |
+
"8": 25,
|
| 45 |
+
"9": 26,
|
| 46 |
+
":": 27,
|
| 47 |
+
";": 28,
|
| 48 |
+
"<": 29,
|
| 49 |
+
"=": 30,
|
| 50 |
+
">": 31,
|
| 51 |
+
"?": 32,
|
| 52 |
+
"@": 33,
|
| 53 |
+
"A": 34,
|
| 54 |
+
"B": 35,
|
| 55 |
+
"C": 36,
|
| 56 |
+
"D": 37,
|
| 57 |
+
"E": 38,
|
| 58 |
+
"F": 39,
|
| 59 |
+
"G": 40,
|
| 60 |
+
"H": 41,
|
| 61 |
+
"I": 42,
|
| 62 |
+
"J": 43,
|
| 63 |
+
"K": 44,
|
| 64 |
+
"L": 45,
|
| 65 |
+
"M": 46,
|
| 66 |
+
"N": 47,
|
| 67 |
+
"O": 48,
|
| 68 |
+
"P": 49,
|
| 69 |
+
"Q": 50,
|
| 70 |
+
"R": 51,
|
| 71 |
+
"S": 52,
|
| 72 |
+
"T": 53,
|
| 73 |
+
"U": 54,
|
| 74 |
+
"V": 55,
|
| 75 |
+
"W": 56,
|
| 76 |
+
"X": 57,
|
| 77 |
+
"Y": 58,
|
| 78 |
+
"Z": 59,
|
| 79 |
+
"[": 60,
|
| 80 |
+
"\\": 61,
|
| 81 |
+
"]": 62,
|
| 82 |
+
"^": 63,
|
| 83 |
+
"_": 64,
|
| 84 |
+
"`": 65,
|
| 85 |
+
"a": 66,
|
| 86 |
+
"b": 67,
|
| 87 |
+
"c": 68,
|
| 88 |
+
"d": 69,
|
| 89 |
+
"e": 70,
|
| 90 |
+
"f": 71,
|
| 91 |
+
"g": 72,
|
| 92 |
+
"h": 73,
|
| 93 |
+
"i": 74,
|
| 94 |
+
"j": 75,
|
| 95 |
+
"k": 76,
|
| 96 |
+
"l": 77,
|
| 97 |
+
"m": 78,
|
| 98 |
+
"n": 79,
|
| 99 |
+
"o": 80,
|
| 100 |
+
"p": 81,
|
| 101 |
+
"q": 82,
|
| 102 |
+
"r": 83,
|
| 103 |
+
"s": 84,
|
| 104 |
+
"t": 85,
|
| 105 |
+
"u": 86,
|
| 106 |
+
"v": 87,
|
| 107 |
+
"w": 88,
|
| 108 |
+
"x": 89,
|
| 109 |
+
"y": 90,
|
| 110 |
+
"z": 91,
|
| 111 |
+
"{": 92,
|
| 112 |
+
"|": 93,
|
| 113 |
+
"}": 94,
|
| 114 |
+
"~": 95
|
| 115 |
+
},
|
| 116 |
+
"merges": []
|
| 117 |
+
}
|
| 118 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"clean_up_tokenization_spaces": true,
|
| 3 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 4 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 5 |
+
}
|