Upload folder using huggingface_hub
Browse files- README.md +1 -3
- tokenizer.json +578 -1
- tokenizer_config.json +74 -1
- vocab.json +91 -91
README.md
CHANGED
|
@@ -1,14 +1,12 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
language:
|
| 4 |
-
- und
|
| 5 |
tags:
|
| 6 |
- tokenizer
|
| 7 |
- bpe
|
| 8 |
- flexitok
|
| 9 |
- fineweb2
|
| 10 |
-
datasets:
|
| 11 |
-
- flexitok/mod-arithmetic
|
| 12 |
---
|
| 13 |
|
| 14 |
# Byte-Level BPE Tokenizer: numeric (0K)
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
language:
|
| 4 |
+
- und # ISO 639-3 code or "und" if not identifiable
|
| 5 |
tags:
|
| 6 |
- tokenizer
|
| 7 |
- bpe
|
| 8 |
- flexitok
|
| 9 |
- fineweb2
|
|
|
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
# Byte-Level BPE Tokenizer: numeric (0K)
|
tokenizer.json
CHANGED
|
@@ -1 +1,578 @@
|
|
| 1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
| 5 |
+
"added_tokens": [
|
| 6 |
+
{
|
| 7 |
+
"id": 0,
|
| 8 |
+
"content": "<unk>",
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"special": true
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"id": 1,
|
| 17 |
+
"content": "<s>",
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"special": true
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"id": 2,
|
| 26 |
+
"content": "</s>",
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"special": true
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"id": 3,
|
| 35 |
+
"content": "<pad>",
|
| 36 |
+
"single_word": false,
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"special": true
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"id": 4,
|
| 44 |
+
"content": "mod",
|
| 45 |
+
"single_word": false,
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"id": 5,
|
| 53 |
+
"content": "=",
|
| 54 |
+
"single_word": false,
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"id": 6,
|
| 62 |
+
"content": " ",
|
| 63 |
+
"single_word": false,
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"normalized": false,
|
| 67 |
+
"special": true
|
| 68 |
+
}
|
| 69 |
+
],
|
| 70 |
+
"normalizer": null,
|
| 71 |
+
"pre_tokenizer": {
|
| 72 |
+
"type": "Sequence",
|
| 73 |
+
"pretokenizers": [
|
| 74 |
+
{
|
| 75 |
+
"type": "Split",
|
| 76 |
+
"pattern": {
|
| 77 |
+
"Regex": "\\p{N}{1,2}"
|
| 78 |
+
},
|
| 79 |
+
"behavior": "Isolated",
|
| 80 |
+
"invert": false
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"type": "ByteLevel",
|
| 84 |
+
"add_prefix_space": false,
|
| 85 |
+
"trim_offsets": true,
|
| 86 |
+
"use_regex": false
|
| 87 |
+
}
|
| 88 |
+
]
|
| 89 |
+
},
|
| 90 |
+
"post_processor": null,
|
| 91 |
+
"decoder": {
|
| 92 |
+
"type": "ByteLevel",
|
| 93 |
+
"add_prefix_space": true,
|
| 94 |
+
"trim_offsets": true,
|
| 95 |
+
"use_regex": true
|
| 96 |
+
},
|
| 97 |
+
"model": {
|
| 98 |
+
"type": "BPE",
|
| 99 |
+
"dropout": null,
|
| 100 |
+
"unk_token": "<unk>",
|
| 101 |
+
"continuing_subword_prefix": null,
|
| 102 |
+
"end_of_word_suffix": null,
|
| 103 |
+
"fuse_unk": false,
|
| 104 |
+
"byte_fallback": false,
|
| 105 |
+
"ignore_merges": false,
|
| 106 |
+
"vocab": {
|
| 107 |
+
"<unk>": 0,
|
| 108 |
+
"<s>": 1,
|
| 109 |
+
"</s>": 2,
|
| 110 |
+
"<pad>": 3,
|
| 111 |
+
"mod": 4,
|
| 112 |
+
"=": 5,
|
| 113 |
+
" ": 6,
|
| 114 |
+
"0": 7,
|
| 115 |
+
"1": 8,
|
| 116 |
+
"2": 9,
|
| 117 |
+
"3": 10,
|
| 118 |
+
"4": 11,
|
| 119 |
+
"5": 12,
|
| 120 |
+
"6": 13,
|
| 121 |
+
"7": 14,
|
| 122 |
+
"8": 15,
|
| 123 |
+
"9": 16,
|
| 124 |
+
"10": 17,
|
| 125 |
+
"11": 18,
|
| 126 |
+
"12": 19,
|
| 127 |
+
"13": 20,
|
| 128 |
+
"14": 21,
|
| 129 |
+
"15": 22,
|
| 130 |
+
"16": 23,
|
| 131 |
+
"17": 24,
|
| 132 |
+
"18": 25,
|
| 133 |
+
"19": 26,
|
| 134 |
+
"20": 27,
|
| 135 |
+
"21": 28,
|
| 136 |
+
"22": 29,
|
| 137 |
+
"23": 30,
|
| 138 |
+
"24": 31,
|
| 139 |
+
"25": 32,
|
| 140 |
+
"26": 33,
|
| 141 |
+
"27": 34,
|
| 142 |
+
"28": 35,
|
| 143 |
+
"29": 36,
|
| 144 |
+
"30": 37,
|
| 145 |
+
"31": 38,
|
| 146 |
+
"32": 39,
|
| 147 |
+
"33": 40,
|
| 148 |
+
"34": 41,
|
| 149 |
+
"35": 42,
|
| 150 |
+
"36": 43,
|
| 151 |
+
"37": 44,
|
| 152 |
+
"38": 45,
|
| 153 |
+
"39": 46,
|
| 154 |
+
"40": 47,
|
| 155 |
+
"41": 48,
|
| 156 |
+
"42": 49,
|
| 157 |
+
"43": 50,
|
| 158 |
+
"44": 51,
|
| 159 |
+
"45": 52,
|
| 160 |
+
"46": 53,
|
| 161 |
+
"47": 54,
|
| 162 |
+
"48": 55,
|
| 163 |
+
"49": 56,
|
| 164 |
+
"50": 57,
|
| 165 |
+
"51": 58,
|
| 166 |
+
"52": 59,
|
| 167 |
+
"53": 60,
|
| 168 |
+
"54": 61,
|
| 169 |
+
"55": 62,
|
| 170 |
+
"56": 63,
|
| 171 |
+
"57": 64,
|
| 172 |
+
"58": 65,
|
| 173 |
+
"59": 66,
|
| 174 |
+
"60": 67,
|
| 175 |
+
"61": 68,
|
| 176 |
+
"62": 69,
|
| 177 |
+
"63": 70,
|
| 178 |
+
"64": 71,
|
| 179 |
+
"65": 72,
|
| 180 |
+
"66": 73,
|
| 181 |
+
"67": 74,
|
| 182 |
+
"68": 75,
|
| 183 |
+
"69": 76,
|
| 184 |
+
"70": 77,
|
| 185 |
+
"71": 78,
|
| 186 |
+
"72": 79,
|
| 187 |
+
"73": 80,
|
| 188 |
+
"74": 81,
|
| 189 |
+
"75": 82,
|
| 190 |
+
"76": 83,
|
| 191 |
+
"77": 84,
|
| 192 |
+
"78": 85,
|
| 193 |
+
"79": 86,
|
| 194 |
+
"80": 87,
|
| 195 |
+
"81": 88,
|
| 196 |
+
"82": 89,
|
| 197 |
+
"83": 90,
|
| 198 |
+
"84": 91,
|
| 199 |
+
"85": 92,
|
| 200 |
+
"86": 93,
|
| 201 |
+
"87": 94,
|
| 202 |
+
"88": 95,
|
| 203 |
+
"89": 96,
|
| 204 |
+
"90": 97,
|
| 205 |
+
"91": 98,
|
| 206 |
+
"92": 99,
|
| 207 |
+
"93": 100,
|
| 208 |
+
"94": 101,
|
| 209 |
+
"95": 102,
|
| 210 |
+
"96": 103,
|
| 211 |
+
"97": 104,
|
| 212 |
+
"98": 105,
|
| 213 |
+
"99": 106
|
| 214 |
+
},
|
| 215 |
+
"merges": [
|
| 216 |
+
[
|
| 217 |
+
"1",
|
| 218 |
+
"0"
|
| 219 |
+
],
|
| 220 |
+
[
|
| 221 |
+
"1",
|
| 222 |
+
"1"
|
| 223 |
+
],
|
| 224 |
+
[
|
| 225 |
+
"1",
|
| 226 |
+
"2"
|
| 227 |
+
],
|
| 228 |
+
[
|
| 229 |
+
"1",
|
| 230 |
+
"3"
|
| 231 |
+
],
|
| 232 |
+
[
|
| 233 |
+
"1",
|
| 234 |
+
"4"
|
| 235 |
+
],
|
| 236 |
+
[
|
| 237 |
+
"1",
|
| 238 |
+
"5"
|
| 239 |
+
],
|
| 240 |
+
[
|
| 241 |
+
"1",
|
| 242 |
+
"6"
|
| 243 |
+
],
|
| 244 |
+
[
|
| 245 |
+
"1",
|
| 246 |
+
"7"
|
| 247 |
+
],
|
| 248 |
+
[
|
| 249 |
+
"1",
|
| 250 |
+
"8"
|
| 251 |
+
],
|
| 252 |
+
[
|
| 253 |
+
"1",
|
| 254 |
+
"9"
|
| 255 |
+
],
|
| 256 |
+
[
|
| 257 |
+
"2",
|
| 258 |
+
"0"
|
| 259 |
+
],
|
| 260 |
+
[
|
| 261 |
+
"2",
|
| 262 |
+
"1"
|
| 263 |
+
],
|
| 264 |
+
[
|
| 265 |
+
"2",
|
| 266 |
+
"2"
|
| 267 |
+
],
|
| 268 |
+
[
|
| 269 |
+
"2",
|
| 270 |
+
"3"
|
| 271 |
+
],
|
| 272 |
+
[
|
| 273 |
+
"2",
|
| 274 |
+
"4"
|
| 275 |
+
],
|
| 276 |
+
[
|
| 277 |
+
"2",
|
| 278 |
+
"5"
|
| 279 |
+
],
|
| 280 |
+
[
|
| 281 |
+
"2",
|
| 282 |
+
"6"
|
| 283 |
+
],
|
| 284 |
+
[
|
| 285 |
+
"2",
|
| 286 |
+
"7"
|
| 287 |
+
],
|
| 288 |
+
[
|
| 289 |
+
"2",
|
| 290 |
+
"8"
|
| 291 |
+
],
|
| 292 |
+
[
|
| 293 |
+
"2",
|
| 294 |
+
"9"
|
| 295 |
+
],
|
| 296 |
+
[
|
| 297 |
+
"3",
|
| 298 |
+
"0"
|
| 299 |
+
],
|
| 300 |
+
[
|
| 301 |
+
"3",
|
| 302 |
+
"1"
|
| 303 |
+
],
|
| 304 |
+
[
|
| 305 |
+
"3",
|
| 306 |
+
"2"
|
| 307 |
+
],
|
| 308 |
+
[
|
| 309 |
+
"3",
|
| 310 |
+
"3"
|
| 311 |
+
],
|
| 312 |
+
[
|
| 313 |
+
"3",
|
| 314 |
+
"4"
|
| 315 |
+
],
|
| 316 |
+
[
|
| 317 |
+
"3",
|
| 318 |
+
"5"
|
| 319 |
+
],
|
| 320 |
+
[
|
| 321 |
+
"3",
|
| 322 |
+
"6"
|
| 323 |
+
],
|
| 324 |
+
[
|
| 325 |
+
"3",
|
| 326 |
+
"7"
|
| 327 |
+
],
|
| 328 |
+
[
|
| 329 |
+
"3",
|
| 330 |
+
"8"
|
| 331 |
+
],
|
| 332 |
+
[
|
| 333 |
+
"3",
|
| 334 |
+
"9"
|
| 335 |
+
],
|
| 336 |
+
[
|
| 337 |
+
"4",
|
| 338 |
+
"0"
|
| 339 |
+
],
|
| 340 |
+
[
|
| 341 |
+
"4",
|
| 342 |
+
"1"
|
| 343 |
+
],
|
| 344 |
+
[
|
| 345 |
+
"4",
|
| 346 |
+
"2"
|
| 347 |
+
],
|
| 348 |
+
[
|
| 349 |
+
"4",
|
| 350 |
+
"3"
|
| 351 |
+
],
|
| 352 |
+
[
|
| 353 |
+
"4",
|
| 354 |
+
"4"
|
| 355 |
+
],
|
| 356 |
+
[
|
| 357 |
+
"4",
|
| 358 |
+
"5"
|
| 359 |
+
],
|
| 360 |
+
[
|
| 361 |
+
"4",
|
| 362 |
+
"6"
|
| 363 |
+
],
|
| 364 |
+
[
|
| 365 |
+
"4",
|
| 366 |
+
"7"
|
| 367 |
+
],
|
| 368 |
+
[
|
| 369 |
+
"4",
|
| 370 |
+
"8"
|
| 371 |
+
],
|
| 372 |
+
[
|
| 373 |
+
"4",
|
| 374 |
+
"9"
|
| 375 |
+
],
|
| 376 |
+
[
|
| 377 |
+
"5",
|
| 378 |
+
"0"
|
| 379 |
+
],
|
| 380 |
+
[
|
| 381 |
+
"5",
|
| 382 |
+
"1"
|
| 383 |
+
],
|
| 384 |
+
[
|
| 385 |
+
"5",
|
| 386 |
+
"2"
|
| 387 |
+
],
|
| 388 |
+
[
|
| 389 |
+
"5",
|
| 390 |
+
"3"
|
| 391 |
+
],
|
| 392 |
+
[
|
| 393 |
+
"5",
|
| 394 |
+
"4"
|
| 395 |
+
],
|
| 396 |
+
[
|
| 397 |
+
"5",
|
| 398 |
+
"5"
|
| 399 |
+
],
|
| 400 |
+
[
|
| 401 |
+
"5",
|
| 402 |
+
"6"
|
| 403 |
+
],
|
| 404 |
+
[
|
| 405 |
+
"5",
|
| 406 |
+
"7"
|
| 407 |
+
],
|
| 408 |
+
[
|
| 409 |
+
"5",
|
| 410 |
+
"8"
|
| 411 |
+
],
|
| 412 |
+
[
|
| 413 |
+
"5",
|
| 414 |
+
"9"
|
| 415 |
+
],
|
| 416 |
+
[
|
| 417 |
+
"6",
|
| 418 |
+
"0"
|
| 419 |
+
],
|
| 420 |
+
[
|
| 421 |
+
"6",
|
| 422 |
+
"1"
|
| 423 |
+
],
|
| 424 |
+
[
|
| 425 |
+
"6",
|
| 426 |
+
"2"
|
| 427 |
+
],
|
| 428 |
+
[
|
| 429 |
+
"6",
|
| 430 |
+
"3"
|
| 431 |
+
],
|
| 432 |
+
[
|
| 433 |
+
"6",
|
| 434 |
+
"4"
|
| 435 |
+
],
|
| 436 |
+
[
|
| 437 |
+
"6",
|
| 438 |
+
"5"
|
| 439 |
+
],
|
| 440 |
+
[
|
| 441 |
+
"6",
|
| 442 |
+
"6"
|
| 443 |
+
],
|
| 444 |
+
[
|
| 445 |
+
"6",
|
| 446 |
+
"7"
|
| 447 |
+
],
|
| 448 |
+
[
|
| 449 |
+
"6",
|
| 450 |
+
"8"
|
| 451 |
+
],
|
| 452 |
+
[
|
| 453 |
+
"6",
|
| 454 |
+
"9"
|
| 455 |
+
],
|
| 456 |
+
[
|
| 457 |
+
"7",
|
| 458 |
+
"0"
|
| 459 |
+
],
|
| 460 |
+
[
|
| 461 |
+
"7",
|
| 462 |
+
"1"
|
| 463 |
+
],
|
| 464 |
+
[
|
| 465 |
+
"7",
|
| 466 |
+
"2"
|
| 467 |
+
],
|
| 468 |
+
[
|
| 469 |
+
"7",
|
| 470 |
+
"3"
|
| 471 |
+
],
|
| 472 |
+
[
|
| 473 |
+
"7",
|
| 474 |
+
"4"
|
| 475 |
+
],
|
| 476 |
+
[
|
| 477 |
+
"7",
|
| 478 |
+
"5"
|
| 479 |
+
],
|
| 480 |
+
[
|
| 481 |
+
"7",
|
| 482 |
+
"6"
|
| 483 |
+
],
|
| 484 |
+
[
|
| 485 |
+
"7",
|
| 486 |
+
"7"
|
| 487 |
+
],
|
| 488 |
+
[
|
| 489 |
+
"7",
|
| 490 |
+
"8"
|
| 491 |
+
],
|
| 492 |
+
[
|
| 493 |
+
"7",
|
| 494 |
+
"9"
|
| 495 |
+
],
|
| 496 |
+
[
|
| 497 |
+
"8",
|
| 498 |
+
"0"
|
| 499 |
+
],
|
| 500 |
+
[
|
| 501 |
+
"8",
|
| 502 |
+
"1"
|
| 503 |
+
],
|
| 504 |
+
[
|
| 505 |
+
"8",
|
| 506 |
+
"2"
|
| 507 |
+
],
|
| 508 |
+
[
|
| 509 |
+
"8",
|
| 510 |
+
"3"
|
| 511 |
+
],
|
| 512 |
+
[
|
| 513 |
+
"8",
|
| 514 |
+
"4"
|
| 515 |
+
],
|
| 516 |
+
[
|
| 517 |
+
"8",
|
| 518 |
+
"5"
|
| 519 |
+
],
|
| 520 |
+
[
|
| 521 |
+
"8",
|
| 522 |
+
"6"
|
| 523 |
+
],
|
| 524 |
+
[
|
| 525 |
+
"8",
|
| 526 |
+
"7"
|
| 527 |
+
],
|
| 528 |
+
[
|
| 529 |
+
"8",
|
| 530 |
+
"8"
|
| 531 |
+
],
|
| 532 |
+
[
|
| 533 |
+
"8",
|
| 534 |
+
"9"
|
| 535 |
+
],
|
| 536 |
+
[
|
| 537 |
+
"9",
|
| 538 |
+
"0"
|
| 539 |
+
],
|
| 540 |
+
[
|
| 541 |
+
"9",
|
| 542 |
+
"1"
|
| 543 |
+
],
|
| 544 |
+
[
|
| 545 |
+
"9",
|
| 546 |
+
"2"
|
| 547 |
+
],
|
| 548 |
+
[
|
| 549 |
+
"9",
|
| 550 |
+
"3"
|
| 551 |
+
],
|
| 552 |
+
[
|
| 553 |
+
"9",
|
| 554 |
+
"4"
|
| 555 |
+
],
|
| 556 |
+
[
|
| 557 |
+
"9",
|
| 558 |
+
"5"
|
| 559 |
+
],
|
| 560 |
+
[
|
| 561 |
+
"9",
|
| 562 |
+
"6"
|
| 563 |
+
],
|
| 564 |
+
[
|
| 565 |
+
"9",
|
| 566 |
+
"7"
|
| 567 |
+
],
|
| 568 |
+
[
|
| 569 |
+
"9",
|
| 570 |
+
"8"
|
| 571 |
+
],
|
| 572 |
+
[
|
| 573 |
+
"9",
|
| 574 |
+
"9"
|
| 575 |
+
]
|
| 576 |
+
]
|
| 577 |
+
}
|
| 578 |
+
}
|
tokenizer_config.json
CHANGED
|
@@ -1 +1,74 @@
|
|
| 1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<unk>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<pad>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "mod",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"5": {
|
| 44 |
+
"content": "=",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"6": {
|
| 52 |
+
"content": " ",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
}
|
| 59 |
+
},
|
| 60 |
+
"additional_special_tokens": [
|
| 61 |
+
"mod",
|
| 62 |
+
"=",
|
| 63 |
+
" "
|
| 64 |
+
],
|
| 65 |
+
"bos_token": "<s>",
|
| 66 |
+
"clean_up_tokenization_spaces": false,
|
| 67 |
+
"eos_token": "</s>",
|
| 68 |
+
"extra_special_tokens": {},
|
| 69 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 70 |
+
"pad_token": "<pad>",
|
| 71 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 72 |
+
"unk_token": "<unk>",
|
| 73 |
+
"number_handling": "ltr_2digit"
|
| 74 |
+
}
|
vocab.json
CHANGED
|
@@ -1,109 +1,109 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"93": 100,
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
"79": 86,
|
| 8 |
-
"96": 103,
|
| 9 |
-
"37": 44,
|
| 10 |
-
"92": 99,
|
| 11 |
-
"95": 102,
|
| 12 |
-
"7": 14,
|
| 13 |
-
"32": 39,
|
| 14 |
-
"41": 48,
|
| 15 |
"50": 57,
|
| 16 |
-
"
|
| 17 |
-
"
|
| 18 |
-
"59": 66,
|
| 19 |
-
"25": 32,
|
| 20 |
-
"11": 18,
|
| 21 |
-
"99": 106,
|
| 22 |
"26": 33,
|
| 23 |
-
"88": 95,
|
| 24 |
-
"1": 8,
|
| 25 |
-
"74": 81,
|
| 26 |
-
"84": 91,
|
| 27 |
-
"46": 53,
|
| 28 |
"83": 90,
|
| 29 |
-
"
|
| 30 |
-
"
|
| 31 |
-
"
|
| 32 |
-
"
|
| 33 |
-
"
|
| 34 |
-
"
|
| 35 |
-
"
|
| 36 |
-
"
|
| 37 |
-
"68": 75,
|
| 38 |
-
"42": 49,
|
| 39 |
-
"28": 35,
|
| 40 |
-
"94": 101,
|
| 41 |
-
"90": 97,
|
| 42 |
"65": 72,
|
| 43 |
"70": 77,
|
| 44 |
"66": 73,
|
| 45 |
-
"
|
| 46 |
-
"
|
| 47 |
-
"
|
| 48 |
-
"33": 40,
|
| 49 |
"<unk>": 0,
|
| 50 |
-
"
|
| 51 |
-
"
|
| 52 |
-
"
|
| 53 |
-
"
|
| 54 |
-
"
|
| 55 |
"82": 89,
|
| 56 |
-
"
|
| 57 |
-
"
|
| 58 |
-
"
|
| 59 |
-
"
|
| 60 |
-
"34": 41,
|
| 61 |
-
"67": 74,
|
| 62 |
-
"97": 104,
|
| 63 |
-
"<s>": 1,
|
| 64 |
-
"49": 56,
|
| 65 |
"39": 46,
|
| 66 |
-
"
|
| 67 |
-
"
|
| 68 |
-
"
|
| 69 |
-
"55": 62,
|
| 70 |
-
"6": 13,
|
| 71 |
-
"52": 59,
|
| 72 |
-
"45": 52,
|
| 73 |
-
"3": 10,
|
| 74 |
-
"4": 11,
|
| 75 |
-
"54": 61,
|
| 76 |
-
"<pad>": 3,
|
| 77 |
-
"53": 60,
|
| 78 |
-
"19": 26,
|
| 79 |
"10": 17,
|
| 80 |
-
"
|
|
|
|
|
|
|
|
|
|
| 81 |
"27": 34,
|
| 82 |
-
"
|
| 83 |
-
"
|
| 84 |
-
"
|
| 85 |
-
"
|
| 86 |
-
"62": 69,
|
| 87 |
-
" ": 6,
|
| 88 |
-
"35": 42,
|
| 89 |
"31": 38,
|
| 90 |
-
"
|
| 91 |
-
"
|
| 92 |
-
"72": 79,
|
| 93 |
-
"36": 43,
|
| 94 |
-
"60": 67,
|
| 95 |
-
"80": 87,
|
| 96 |
-
"16": 23,
|
| 97 |
"9": 16,
|
| 98 |
-
"
|
| 99 |
-
"
|
| 100 |
-
"
|
| 101 |
-
"
|
| 102 |
-
"81": 88,
|
| 103 |
-
"13": 20,
|
| 104 |
-
"57": 64,
|
| 105 |
-
"87": 94,
|
| 106 |
-
"20": 27,
|
| 107 |
"15": 22,
|
| 108 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 109 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"22": 29,
|
| 3 |
+
"17": 24,
|
| 4 |
+
"14": 21,
|
| 5 |
+
"86": 93,
|
| 6 |
+
"68": 75,
|
| 7 |
+
"13": 20,
|
| 8 |
+
" ": 6,
|
| 9 |
+
"11": 18,
|
| 10 |
+
"<s>": 1,
|
| 11 |
+
"77": 84,
|
| 12 |
+
"<pad>": 3,
|
| 13 |
+
"24": 31,
|
| 14 |
+
"5": 12,
|
| 15 |
+
"=": 5,
|
| 16 |
+
"63": 70,
|
| 17 |
+
"61": 68,
|
| 18 |
+
"96": 103,
|
| 19 |
+
"98": 105,
|
| 20 |
"93": 100,
|
| 21 |
+
"55": 62,
|
| 22 |
+
"91": 98,
|
| 23 |
+
"3": 10,
|
| 24 |
+
"21": 28,
|
| 25 |
+
"40": 47,
|
| 26 |
+
"78": 85,
|
| 27 |
+
"59": 66,
|
| 28 |
+
"23": 30,
|
| 29 |
+
"52": 59,
|
| 30 |
+
"87": 94,
|
| 31 |
+
"64": 71,
|
| 32 |
+
"16": 23,
|
| 33 |
+
"8": 15,
|
| 34 |
+
"90": 97,
|
| 35 |
+
"49": 56,
|
| 36 |
+
"48": 55,
|
| 37 |
+
"</s>": 2,
|
| 38 |
+
"28": 35,
|
| 39 |
+
"60": 67,
|
| 40 |
+
"80": 87,
|
| 41 |
+
"34": 41,
|
| 42 |
+
"54": 61,
|
| 43 |
+
"35": 42,
|
| 44 |
+
"45": 52,
|
| 45 |
+
"4": 11,
|
| 46 |
"79": 86,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
"50": 57,
|
| 48 |
+
"58": 65,
|
| 49 |
+
"18": 25,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
"26": 33,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
"83": 90,
|
| 52 |
+
"0": 7,
|
| 53 |
+
"19": 26,
|
| 54 |
+
"53": 60,
|
| 55 |
+
"25": 32,
|
| 56 |
+
"56": 63,
|
| 57 |
+
"62": 69,
|
| 58 |
+
"89": 96,
|
| 59 |
+
"29": 36,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 60 |
"65": 72,
|
| 61 |
"70": 77,
|
| 62 |
"66": 73,
|
| 63 |
+
"67": 74,
|
| 64 |
+
"6": 13,
|
| 65 |
+
"94": 101,
|
|
|
|
| 66 |
"<unk>": 0,
|
| 67 |
+
"33": 40,
|
| 68 |
+
"44": 51,
|
| 69 |
+
"12": 19,
|
| 70 |
+
"36": 43,
|
| 71 |
+
"75": 82,
|
| 72 |
"82": 89,
|
| 73 |
+
"2": 9,
|
| 74 |
+
"72": 79,
|
| 75 |
+
"76": 83,
|
| 76 |
+
"84": 91,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 77 |
"39": 46,
|
| 78 |
+
"51": 58,
|
| 79 |
+
"43": 50,
|
| 80 |
+
"71": 78,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 81 |
"10": 17,
|
| 82 |
+
"74": 81,
|
| 83 |
+
"95": 102,
|
| 84 |
+
"81": 88,
|
| 85 |
+
"92": 99,
|
| 86 |
"27": 34,
|
| 87 |
+
"1": 8,
|
| 88 |
+
"30": 37,
|
| 89 |
+
"69": 76,
|
| 90 |
+
"73": 80,
|
|
|
|
|
|
|
|
|
|
| 91 |
"31": 38,
|
| 92 |
+
"7": 14,
|
| 93 |
+
"88": 95,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 94 |
"9": 16,
|
| 95 |
+
"47": 54,
|
| 96 |
+
"99": 106,
|
| 97 |
+
"mod": 4,
|
| 98 |
+
"46": 53,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 99 |
"15": 22,
|
| 100 |
+
"97": 104,
|
| 101 |
+
"41": 48,
|
| 102 |
+
"20": 27,
|
| 103 |
+
"42": 49,
|
| 104 |
+
"32": 39,
|
| 105 |
+
"37": 44,
|
| 106 |
+
"57": 64,
|
| 107 |
+
"85": 92,
|
| 108 |
+
"38": 45
|
| 109 |
}
|