Upload am_base256_tokenizer_sm.json with huggingface_hub
Browse files- am_base256_tokenizer_sm.json +380 -0
am_base256_tokenizer_sm.json
ADDED
|
@@ -0,0 +1,380 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
| 5 |
+
"added_tokens": [
|
| 6 |
+
{
|
| 7 |
+
"id": 0,
|
| 8 |
+
"content": "[STOP]",
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"special": true
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"id": 1,
|
| 17 |
+
"content": "[UNK]",
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"special": true
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"id": 2,
|
| 26 |
+
"content": "[SPACE]",
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"special": true
|
| 32 |
+
}
|
| 33 |
+
],
|
| 34 |
+
"normalizer": null,
|
| 35 |
+
"pre_tokenizer": {
|
| 36 |
+
"type": "Whitespace"
|
| 37 |
+
},
|
| 38 |
+
"post_processor": null,
|
| 39 |
+
"decoder": null,
|
| 40 |
+
"model": {
|
| 41 |
+
"type": "BPE",
|
| 42 |
+
"dropout": null,
|
| 43 |
+
"unk_token": "[UNK]",
|
| 44 |
+
"continuing_subword_prefix": null,
|
| 45 |
+
"end_of_word_suffix": null,
|
| 46 |
+
"fuse_unk": false,
|
| 47 |
+
"byte_fallback": false,
|
| 48 |
+
"ignore_merges": false,
|
| 49 |
+
"vocab": {
|
| 50 |
+
"[STOP]": 0,
|
| 51 |
+
"[UNK]": 1,
|
| 52 |
+
"[SPACE]": 2,
|
| 53 |
+
"'": 3,
|
| 54 |
+
".": 4,
|
| 55 |
+
"/": 5,
|
| 56 |
+
"0": 6,
|
| 57 |
+
"1": 7,
|
| 58 |
+
"2": 8,
|
| 59 |
+
"3": 9,
|
| 60 |
+
"4": 10,
|
| 61 |
+
"5": 11,
|
| 62 |
+
"6": 12,
|
| 63 |
+
"7": 13,
|
| 64 |
+
"8": 14,
|
| 65 |
+
"9": 15,
|
| 66 |
+
":": 16,
|
| 67 |
+
"?": 17,
|
| 68 |
+
"A": 18,
|
| 69 |
+
"B": 19,
|
| 70 |
+
"C": 20,
|
| 71 |
+
"D": 21,
|
| 72 |
+
"E": 22,
|
| 73 |
+
"F": 23,
|
| 74 |
+
"G": 24,
|
| 75 |
+
"H": 25,
|
| 76 |
+
"I": 26,
|
| 77 |
+
"J": 27,
|
| 78 |
+
"L": 28,
|
| 79 |
+
"N": 29,
|
| 80 |
+
"O": 30,
|
| 81 |
+
"P": 31,
|
| 82 |
+
"Q": 32,
|
| 83 |
+
"R": 33,
|
| 84 |
+
"S": 34,
|
| 85 |
+
"T": 35,
|
| 86 |
+
"U": 36,
|
| 87 |
+
"V": 37,
|
| 88 |
+
"W": 38,
|
| 89 |
+
"Y": 39,
|
| 90 |
+
"a": 40,
|
| 91 |
+
"b": 41,
|
| 92 |
+
"c": 42,
|
| 93 |
+
"d": 43,
|
| 94 |
+
"e": 44,
|
| 95 |
+
"f": 45,
|
| 96 |
+
"g": 46,
|
| 97 |
+
"h": 47,
|
| 98 |
+
"i": 48,
|
| 99 |
+
"j": 49,
|
| 100 |
+
"k": 50,
|
| 101 |
+
"l": 51,
|
| 102 |
+
"m": 52,
|
| 103 |
+
"n": 53,
|
| 104 |
+
"o": 54,
|
| 105 |
+
"p": 55,
|
| 106 |
+
"q": 56,
|
| 107 |
+
"r": 57,
|
| 108 |
+
"s": 58,
|
| 109 |
+
"t": 59,
|
| 110 |
+
"u": 60,
|
| 111 |
+
"v": 61,
|
| 112 |
+
"w": 62,
|
| 113 |
+
"x": 63,
|
| 114 |
+
"y": 64,
|
| 115 |
+
"z": 65,
|
| 116 |
+
"{": 66,
|
| 117 |
+
"ü": 67,
|
| 118 |
+
"а": 68,
|
| 119 |
+
"т": 69,
|
| 120 |
+
"ш": 70,
|
| 121 |
+
"ق": 71,
|
| 122 |
+
"م": 72,
|
| 123 |
+
"و": 73,
|
| 124 |
+
"ሀ": 74,
|
| 125 |
+
"ሁ": 75,
|
| 126 |
+
"ሂ": 76,
|
| 127 |
+
"ሃ": 77,
|
| 128 |
+
"ሄ": 78,
|
| 129 |
+
"ህ": 79,
|
| 130 |
+
"ሆ": 80,
|
| 131 |
+
"ሇ": 81,
|
| 132 |
+
"ለ": 82,
|
| 133 |
+
"ሉ": 83,
|
| 134 |
+
"ሊ": 84,
|
| 135 |
+
"ላ": 85,
|
| 136 |
+
"ሌ": 86,
|
| 137 |
+
"ል": 87,
|
| 138 |
+
"ሎ": 88,
|
| 139 |
+
"ሏ": 89,
|
| 140 |
+
"ሐ": 90,
|
| 141 |
+
"ሑ": 91,
|
| 142 |
+
"ሓ": 92,
|
| 143 |
+
"ሔ": 93,
|
| 144 |
+
"ሕ": 94,
|
| 145 |
+
"መ": 95,
|
| 146 |
+
"ሙ": 96,
|
| 147 |
+
"ሚ": 97,
|
| 148 |
+
"ማ": 98,
|
| 149 |
+
"ሜ": 99,
|
| 150 |
+
"ም": 100,
|
| 151 |
+
"ሞ": 101,
|
| 152 |
+
"ሟ": 102,
|
| 153 |
+
"ሠ": 103,
|
| 154 |
+
"ሡ": 104,
|
| 155 |
+
"ሣ": 105,
|
| 156 |
+
"ሥ": 106,
|
| 157 |
+
"ሦ": 107,
|
| 158 |
+
"ረ": 108,
|
| 159 |
+
"ሩ": 109,
|
| 160 |
+
"ሪ": 110,
|
| 161 |
+
"ራ": 111,
|
| 162 |
+
"ሬ": 112,
|
| 163 |
+
"ር": 113,
|
| 164 |
+
"ሮ": 114,
|
| 165 |
+
"ሯ": 115,
|
| 166 |
+
"ሰ": 116,
|
| 167 |
+
"ሱ": 117,
|
| 168 |
+
"ሲ": 118,
|
| 169 |
+
"ሳ": 119,
|
| 170 |
+
"ሴ": 120,
|
| 171 |
+
"ስ": 121,
|
| 172 |
+
"ሶ": 122,
|
| 173 |
+
"ሷ": 123,
|
| 174 |
+
"ሸ": 124,
|
| 175 |
+
"ሹ": 125,
|
| 176 |
+
"ሺ": 126,
|
| 177 |
+
"ሻ": 127,
|
| 178 |
+
"ሼ": 128,
|
| 179 |
+
"ሽ": 129,
|
| 180 |
+
"ሾ": 130,
|
| 181 |
+
"ሿ": 131,
|
| 182 |
+
"ቀ": 132,
|
| 183 |
+
"ቁ": 133,
|
| 184 |
+
"ቂ": 134,
|
| 185 |
+
"ቃ": 135,
|
| 186 |
+
"ቄ": 136,
|
| 187 |
+
"ቅ": 137,
|
| 188 |
+
"ቆ": 138,
|
| 189 |
+
"ቋ": 139,
|
| 190 |
+
"በ": 140,
|
| 191 |
+
"ቡ": 141,
|
| 192 |
+
"ቢ": 142,
|
| 193 |
+
"ባ": 143,
|
| 194 |
+
"ቤ": 144,
|
| 195 |
+
"ብ": 145,
|
| 196 |
+
"ቦ": 146,
|
| 197 |
+
"ቧ": 147,
|
| 198 |
+
"ቨ": 148,
|
| 199 |
+
"ቩ": 149,
|
| 200 |
+
"ቪ": 150,
|
| 201 |
+
"ቫ": 151,
|
| 202 |
+
"ቬ": 152,
|
| 203 |
+
"ቭ": 153,
|
| 204 |
+
"ቮ": 154,
|
| 205 |
+
"ተ": 155,
|
| 206 |
+
"ቱ": 156,
|
| 207 |
+
"ቲ": 157,
|
| 208 |
+
"ታ": 158,
|
| 209 |
+
"ቴ": 159,
|
| 210 |
+
"ት": 160,
|
| 211 |
+
"ቶ": 161,
|
| 212 |
+
"ቷ": 162,
|
| 213 |
+
"ቸ": 163,
|
| 214 |
+
"ቹ": 164,
|
| 215 |
+
"ቺ": 165,
|
| 216 |
+
"ቻ": 166,
|
| 217 |
+
"ቼ": 167,
|
| 218 |
+
"ች": 168,
|
| 219 |
+
"ቾ": 169,
|
| 220 |
+
"ቿ": 170,
|
| 221 |
+
"ኃ": 171,
|
| 222 |
+
"ኅ": 172,
|
| 223 |
+
"ኋ": 173,
|
| 224 |
+
"ነ": 174,
|
| 225 |
+
"ኑ": 175,
|
| 226 |
+
"ኒ": 176,
|
| 227 |
+
"ና": 177,
|
| 228 |
+
"ኔ": 178,
|
| 229 |
+
"ን": 179,
|
| 230 |
+
"ኖ": 180,
|
| 231 |
+
"ኗ": 181,
|
| 232 |
+
"ኘ": 182,
|
| 233 |
+
"ኙ": 183,
|
| 234 |
+
"ኚ": 184,
|
| 235 |
+
"ኛ": 185,
|
| 236 |
+
"ኜ": 186,
|
| 237 |
+
"ኝ": 187,
|
| 238 |
+
"ኞ": 188,
|
| 239 |
+
"ኟ": 189,
|
| 240 |
+
"አ": 190,
|
| 241 |
+
"ኡ": 191,
|
| 242 |
+
"ኢ": 192,
|
| 243 |
+
"ኣ": 193,
|
| 244 |
+
"ኤ": 194,
|
| 245 |
+
"እ": 195,
|
| 246 |
+
"ኦ": 196,
|
| 247 |
+
"ኧ": 197,
|
| 248 |
+
"ከ": 198,
|
| 249 |
+
"ኩ": 199,
|
| 250 |
+
"ኪ": 200,
|
| 251 |
+
"ካ": 201,
|
| 252 |
+
"ኬ": 202,
|
| 253 |
+
"ክ": 203,
|
| 254 |
+
"ኮ": 204,
|
| 255 |
+
"ኳ": 205,
|
| 256 |
+
"ኸ": 206,
|
| 257 |
+
"ኽ": 207,
|
| 258 |
+
"ወ": 208,
|
| 259 |
+
"ዉ": 209,
|
| 260 |
+
"ዊ": 210,
|
| 261 |
+
"ዋ": 211,
|
| 262 |
+
"ዌ": 212,
|
| 263 |
+
"ው": 213,
|
| 264 |
+
"ዎ": 214,
|
| 265 |
+
"ዐ": 215,
|
| 266 |
+
"ዑ": 216,
|
| 267 |
+
"ዒ": 217,
|
| 268 |
+
"ዓ": 218,
|
| 269 |
+
"ዔ": 219,
|
| 270 |
+
"ዕ": 220,
|
| 271 |
+
"ዖ": 221,
|
| 272 |
+
"ዘ": 222,
|
| 273 |
+
"ዙ": 223,
|
| 274 |
+
"ዚ": 224,
|
| 275 |
+
"ዛ": 225,
|
| 276 |
+
"ዜ": 226,
|
| 277 |
+
"ዝ": 227,
|
| 278 |
+
"ዞ": 228,
|
| 279 |
+
"ዟ": 229,
|
| 280 |
+
"ዠ": 230,
|
| 281 |
+
"ዡ": 231,
|
| 282 |
+
"ዢ": 232,
|
| 283 |
+
"ዣ": 233,
|
| 284 |
+
"ዤ": 234,
|
| 285 |
+
"ዥ": 235,
|
| 286 |
+
"ዦ": 236,
|
| 287 |
+
"ዧ": 237,
|
| 288 |
+
"የ": 238,
|
| 289 |
+
"ዩ": 239,
|
| 290 |
+
"ዪ": 240,
|
| 291 |
+
"ያ": 241,
|
| 292 |
+
"ዬ": 242,
|
| 293 |
+
"ይ": 243,
|
| 294 |
+
"ዮ": 244,
|
| 295 |
+
"ደ": 245,
|
| 296 |
+
"ዱ": 246,
|
| 297 |
+
"ዲ": 247,
|
| 298 |
+
"ዳ": 248,
|
| 299 |
+
"ዴ": 249,
|
| 300 |
+
"ድ": 250,
|
| 301 |
+
"ዶ": 251,
|
| 302 |
+
"ዷ": 252,
|
| 303 |
+
"ጀ": 253,
|
| 304 |
+
"ጁ": 254,
|
| 305 |
+
"ጂ": 255,
|
| 306 |
+
"ጃ": 256,
|
| 307 |
+
"ጄ": 257,
|
| 308 |
+
"ጅ": 258,
|
| 309 |
+
"ጆ": 259,
|
| 310 |
+
"ጇ": 260,
|
| 311 |
+
"ገ": 261,
|
| 312 |
+
"ጉ": 262,
|
| 313 |
+
"ጊ": 263,
|
| 314 |
+
"ጋ": 264,
|
| 315 |
+
"ጌ": 265,
|
| 316 |
+
"ግ": 266,
|
| 317 |
+
"ጎ": 267,
|
| 318 |
+
"ጓ": 268,
|
| 319 |
+
"ጠ": 269,
|
| 320 |
+
"ጡ": 270,
|
| 321 |
+
"ጢ": 271,
|
| 322 |
+
"ጣ": 272,
|
| 323 |
+
"ጤ": 273,
|
| 324 |
+
"ጥ": 274,
|
| 325 |
+
"ጦ": 275,
|
| 326 |
+
"ጧ": 276,
|
| 327 |
+
"ጨ": 277,
|
| 328 |
+
"ጩ": 278,
|
| 329 |
+
"ጪ": 279,
|
| 330 |
+
"ጫ": 280,
|
| 331 |
+
"ጬ": 281,
|
| 332 |
+
"ጭ": 282,
|
| 333 |
+
"ጮ": 283,
|
| 334 |
+
"ጯ": 284,
|
| 335 |
+
"ጲ": 285,
|
| 336 |
+
"ጳ": 286,
|
| 337 |
+
"ጴ": 287,
|
| 338 |
+
"ጵ": 288,
|
| 339 |
+
"ጶ": 289,
|
| 340 |
+
"ጸ": 290,
|
| 341 |
+
"ጹ": 291,
|
| 342 |
+
"ጺ": 292,
|
| 343 |
+
"ጻ": 293,
|
| 344 |
+
"ጼ": 294,
|
| 345 |
+
"ጽ": 295,
|
| 346 |
+
"ጾ": 296,
|
| 347 |
+
"ጿ": 297,
|
| 348 |
+
"ፀ": 298,
|
| 349 |
+
"ፁ": 299,
|
| 350 |
+
"ፂ": 300,
|
| 351 |
+
"ፃ": 301,
|
| 352 |
+
"ፄ": 302,
|
| 353 |
+
"ፅ": 303,
|
| 354 |
+
"ፆ": 304,
|
| 355 |
+
"ፈ": 305,
|
| 356 |
+
"ፉ": 306,
|
| 357 |
+
"ፊ": 307,
|
| 358 |
+
"ፋ": 308,
|
| 359 |
+
"ፌ": 309,
|
| 360 |
+
"ፍ": 310,
|
| 361 |
+
"ፎ": 311,
|
| 362 |
+
"ፏ": 312,
|
| 363 |
+
"ፐ": 313,
|
| 364 |
+
"ፑ": 314,
|
| 365 |
+
"ፒ": 315,
|
| 366 |
+
"ፓ": 316,
|
| 367 |
+
"ፔ": 317,
|
| 368 |
+
"ፕ": 318,
|
| 369 |
+
"ፖ": 319,
|
| 370 |
+
"።": 320,
|
| 371 |
+
"፯": 321,
|
| 372 |
+
"፱": 322,
|
| 373 |
+
"፲": 323,
|
| 374 |
+
"፺": 324,
|
| 375 |
+
"፻": 325
|
| 376 |
+
},
|
| 377 |
+
"merges": [],
|
| 378 |
+
"language": "am"
|
| 379 |
+
}
|
| 380 |
+
}
|