diff --git a/vocab.txt b/vocab.txt new file mode 100644 index 0000000000000000000000000000000000000000..ce0d5f80782d52779e924a84f8990ae5f750066d --- /dev/null +++ b/vocab.txt @@ -0,0 +1,128000 @@ +[PAD] +[UNK] +[CLS] +[SEP] +[MASK] +##> +< +##hashtag +##user + +[UNUSED_1] +[UNUSED_2] +[UNUSED_3] +[UNUSED_4] +[UNUSED_5] +[UNUSED_6] +[UNUSED_7] +[UNUSED_8] +[UNUSED_9] +[UNUSED_10] +[UNUSED_11] +[UNUSED_12] +[UNUSED_13] +[UNUSED_14] +[UNUSED_15] +[UNUSED_16] +[UNUSED_17] +[UNUSED_18] +[UNUSED_19] +[UNUSED_20] +[UNUSED_21] +[UNUSED_22] +[UNUSED_23] +[UNUSED_24] +[UNUSED_25] +[UNUSED_26] +[UNUSED_27] +[UNUSED_28] +[UNUSED_29] +[UNUSED_30] +[UNUSED_31] +[UNUSED_32] +[UNUSED_33] +[UNUSED_34] +[UNUSED_35] +[UNUSED_36] +[UNUSED_37] +[UNUSED_38] +[UNUSED_39] +[UNUSED_40] +[UNUSED_41] +[UNUSED_42] +[UNUSED_43] +[UNUSED_44] +[UNUSED_45] +[UNUSED_46] +[UNUSED_47] +[UNUSED_48] +[UNUSED_49] +[UNUSED_50] +[UNUSED_51] +[UNUSED_52] +[UNUSED_53] +[UNUSED_54] +[UNUSED_55] +[UNUSED_56] +[UNUSED_57] +[UNUSED_58] +[UNUSED_59] +[UNUSED_60] +[UNUSED_61] +[UNUSED_62] +[UNUSED_63] +[UNUSED_64] +[UNUSED_65] +[UNUSED_66] +[UNUSED_67] +[UNUSED_68] +[UNUSED_69] +[UNUSED_70] +[UNUSED_71] +[UNUSED_72] +[UNUSED_73] +[UNUSED_74] +[UNUSED_75] +[UNUSED_76] +[UNUSED_77] +[UNUSED_78] +[UNUSED_79] +[UNUSED_80] +[UNUSED_81] +[UNUSED_82] +[UNUSED_83] +[UNUSED_84] +[UNUSED_85] +[UNUSED_86] +[UNUSED_87] +[UNUSED_88] +[UNUSED_89] +[UNUSED_90] +[UNUSED_91] +[UNUSED_92] +[UNUSED_93] +[UNUSED_94] +[UNUSED_95] +[UNUSED_96] +[UNUSED_97] +[UNUSED_98] +[UNUSED_99] +[UNUSED_100] +[UNUSED_101] +[UNUSED_102] +[UNUSED_103] +[UNUSED_104] +[UNUSED_105] +[UNUSED_106] +[UNUSED_107] +[UNUSED_108] +[UNUSED_109] +[UNUSED_110] +[UNUSED_111] +[UNUSED_112] +[UNUSED_113] +[UNUSED_114] +[UNUSED_115] +[UNUSED_116] +[UNUSED_117] +[UNUSED_118] +[UNUSED_119] +[UNUSED_120] +[UNUSED_121] +[UNUSED_122] +[UNUSED_123] +[UNUSED_124] +[UNUSED_125] +[UNUSED_126] +[UNUSED_127] +[UNUSED_128] +[UNUSED_129] +[UNUSED_130] +[UNUSED_131] +[UNUSED_132] +[UNUSED_133] +[UNUSED_134] +[UNUSED_135] +[UNUSED_136] +[UNUSED_137] +[UNUSED_138] +[UNUSED_139] +[UNUSED_140] +[UNUSED_141] +[UNUSED_142] +[UNUSED_143] +[UNUSED_144] +[UNUSED_145] +[UNUSED_146] +[UNUSED_147] +[UNUSED_148] +[UNUSED_149] +[UNUSED_150] +[UNUSED_151] +[UNUSED_152] +[UNUSED_153] +[UNUSED_154] +[UNUSED_155] +[UNUSED_156] +[UNUSED_157] +[UNUSED_158] +[UNUSED_159] +[UNUSED_160] +[UNUSED_161] +[UNUSED_162] +[UNUSED_163] +[UNUSED_164] +[UNUSED_165] +[UNUSED_166] +[UNUSED_167] +[UNUSED_168] +[UNUSED_169] +[UNUSED_170] +[UNUSED_171] +[UNUSED_172] +[UNUSED_173] +[UNUSED_174] +[UNUSED_175] +[UNUSED_176] +[UNUSED_177] +[UNUSED_178] +[UNUSED_179] +[UNUSED_180] +[UNUSED_181] +[UNUSED_182] +[UNUSED_183] +[UNUSED_184] +[UNUSED_185] +[UNUSED_186] +[UNUSED_187] +[UNUSED_188] +[UNUSED_189] +[UNUSED_190] +[UNUSED_191] +[UNUSED_192] +[UNUSED_193] +[UNUSED_194] +[UNUSED_195] +[UNUSED_196] +[UNUSED_197] +[UNUSED_198] +[UNUSED_199] +[UNUSED_200] +[UNUSED_201] +[UNUSED_202] +[UNUSED_203] +[UNUSED_204] +[UNUSED_205] +[UNUSED_206] +[UNUSED_207] +[UNUSED_208] +[UNUSED_209] +[UNUSED_210] +[UNUSED_211] +[UNUSED_212] +[UNUSED_213] +[UNUSED_214] +[UNUSED_215] +[UNUSED_216] +[UNUSED_217] +[UNUSED_218] +[UNUSED_219] +[UNUSED_220] +[UNUSED_221] +[UNUSED_222] +[UNUSED_223] +[UNUSED_224] +[UNUSED_225] +[UNUSED_226] +[UNUSED_227] +[UNUSED_228] +[UNUSED_229] +[UNUSED_230] +[UNUSED_231] +[UNUSED_232] +[UNUSED_233] +[UNUSED_234] +[UNUSED_235] +[UNUSED_236] +[UNUSED_237] +[UNUSED_238] +[UNUSED_239] +[UNUSED_240] +[UNUSED_241] +[UNUSED_242] +[UNUSED_243] +[UNUSED_244] +[UNUSED_245] +[UNUSED_246] +[UNUSED_247] +[UNUSED_248] +[UNUSED_249] +[UNUSED_250] +[UNUSED_251]