{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 0, "content": "([bos])", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 1, "content": "([eos])", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 2, "content": "([unk])", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 3, "content": "([pad])", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 4, "content": "([mask])", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 497, "content": "(LNG)", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 498, "content": "(UNK)", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 499, "content": "(SPN)", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false } ], "normalizer": null, "pre_tokenizer": { "type": "ByteLevel", "add_prefix_space": true, "trim_offsets": true, "use_regex": true }, "post_processor": { "type": "TemplateProcessing", "single": [ { "Sequence": { "id": "A", "type_id": 0 } }, { "SpecialToken": { "id": "([eos])", "type_id": 0 } } ], "pair": [ { "Sequence": { "id": "A", "type_id": 0 } }, { "SpecialToken": { "id": "([eos])", "type_id": 0 } }, { "Sequence": { "id": "B", "type_id": 1 } }, { "SpecialToken": { "id": "([eos])", "type_id": 1 } } ], "special_tokens": { "([bos])": { "id": "([bos])", "ids": [ 0 ], "tokens": [ "([bos])" ] }, "([eos])": { "id": "([eos])", "ids": [ 1 ], "tokens": [ "([eos])" ] } } }, "decoder": { "type": "ByteLevel", "add_prefix_space": true, "trim_offsets": true, "use_regex": true }, "model": { "type": "BPE", "dropout": null, "unk_token": "([unk])", "continuing_subword_prefix": null, "end_of_word_suffix": null, "fuse_unk": false, "byte_fallback": false, "vocab": { "([bos])": 0, "([eos])": 1, "([unk])": 2, "([pad])": 3, "([mask])": 4, "!": 5, "%": 6, "'": 7, "(": 8, ")": 9, "*": 10, "+": 11, ",": 12, "-": 13, ".": 14, "/": 15, "0": 16, "1": 17, "2": 18, "3": 19, "4": 20, "5": 21, "6": 22, "7": 23, "8": 24, "9": 25, ":": 26, ";": 27, "?": 28, "A": 29, "B": 30, "C": 31, "D": 32, "E": 33, "F": 34, "G": 35, "H": 36, "I": 37, "J": 38, "K": 39, "L": 40, "M": 41, "N": 42, "O": 43, "P": 44, "Q": 45, "R": 46, "S": 47, "T": 48, "U": 49, "V": 50, "W": 51, "X": 52, "Y": 53, "Z": 54, "a": 55, "b": 56, "c": 57, "d": 58, "e": 59, "f": 60, "g": 61, "h": 62, "i": 63, "j": 64, "k": 65, "l": 66, "m": 67, "n": 68, "o": 69, "p": 70, "q": 71, "r": 72, "s": 73, "t": 74, "u": 75, "v": 76, "w": 77, "x": 78, "y": 79, "z": 80, "¡": 81, "£": 82, "¤": 83, "¥": 84, "¦": 85, "§": 86, "¨": 87, "©": 88, "ª": 89, "¬": 90, "®": 91, "¯": 92, "±": 93, "²": 94, "³": 95, "´": 96, "µ": 97, "¶": 98, "·": 99, "¸": 100, "¹": 101, "º": 102, "»": 103, "¼": 104, "½": 105, "¾": 106, "¿": 107, "Â": 108, "Ã": 109, "Ä": 110, "Å": 111, "Ì": 112, "Î": 113, "Ï": 114, "â": 115, "Ġ": 116, "Ģ": 117, "ģ": 118, "Ĥ": 119, "ĥ": 120, "Ħ": 121, "ħ": 122, "Ĩ": 123, "ĩ": 124, "Ī": 125, "ī": 126, "Ĭ": 127, "ĭ": 128, "Į": 129, "į": 130, "İ": 131, "IJ": 132, "ij": 133, "Ĵ": 134, "ĵ": 135, "Ķ": 136, "ķ": 137, "ĸ": 138, "Ĺ": 139, "ĺ": 140, "Ļ": 141, "ļ": 142, "Ľ": 143, "ľ": 144, "Ŀ": 145, "ŀ": 146, "Ł": 147, "ł": 148, "Ń": 149, "ĠÎ": 150, "α": 151, "ÏĦ": 152, "ι": 153, "ο": 154, "ε": 155, "ν": 156, "Ïģ": 157, "ĠÏ": 158, "Ïħ": 159, "ÏĤ": 160, "η": 161, "Ïĥ": 162, "ĠÏĦ": 163, "μ": 164, "ί": 165, "ÏĢ": 166, "λ": 167, "κ": 168, "ĠÏĢ": 169, "ά": 170, "οÏħ": 171, "Ġκ": 172, "ÏĮ": 173, "Ġε": 174, "Ġα": 175, "ÎŃ": 176, "ĠÏĥ": 177, "Ïī": 178, "αι": 179, "ή": 180, "Ïį": 181, "Ġμ": 182, "γ": 183, "ει": 184, "Ïĩ": 185, "Ïİ": 186, "ια": 187, "με": 188, "Ġν": 189, "ικ": 190, "Ġδ": 191, "ĠÏĦη": 192, "Ġκαι": 193, "Ġνα": 194, "δ": 195, "θ": 196, "Ïģο": 197, "ÏĨ": 198, "ÏĦα": 199, "ÏĦε": 200, "ία": 201, "ÏĢο": 202, "ĠÏĦο": 203, "Ġγ": 204, "μα": 205, "Ïģα": 206, "Ïĥη": 207, "Ġο": 208, "ÏĦη": 209, "Ïģι": 210, "ÏĦο": 211, "ĠÎŃ": 212, "Ġθ": 213, "ίν": 214, "Ïīν": 215, "ĠÏĮ": 216, "β": 217, "Ġγια": 218, "οÏħμε": 219, "ÏĦι": 220, "Ġη": 221, "ĠÏĦην": 222, "να": 223, "νο": 224, "ĠÏĦοÏħ": 225, "ĠαÏħ": 226, "Ġ,": 227, "Ġμε": 228, "Ġ.": 229, "ĠÏĢÏģ": 230, "ολ": 231, "ÏĦικ": 232, "ĠÏĥÏħ": 233, "εÏĤ": 234, "ξ": 235, "Ġκα": 236, "ÏħÏģ": 237, "ÏĢÏĮ": 238, "οÏį": 239, "ĠαÏħÏĦ": 240, "Ġθα": 241, "ζ": 242, "ĠÏĦηÏĤ": 243, "αÏĤ": 244, "οι": 245, "ÎŃÏĤ": 246, "ÏĢα": 247, "ĠÏħ": 248, "εί": 249, "Ġλ": 250, "ÏĥÏĦ": 251, "ĠÏĢÏģο": 252, "Ġείν": 253, "Ġείναι": 254, "Ïĥει": 255, "ĠÏĢοÏħ": 256, "ÏĦαι": 257, "ĠÏĦα": 258, "Ïģά": 259, "ĠÏĩ": 260, "λο": 261, "ĠεÏĢ": 262, "οÏħν": 263, "ĠÏĢολ": 264, "Ġδε": 265, "ĠÎķ": 266, "ĠÎŃÏĩ": 267, "ÏĨο": 268, "Ïİν": 269, "ĠÏĦι": 270, "ĠÏĥÏĦη": 271, "Ġβ": 272, "ÏĦά": 273, "Ïģί": 274, "Ġαν": 275, "ĠÏĢα": 276, "ĠαÏĢÏĮ": 277, "Ġ(": 278, "λα": 279, "λη": 280, "ιÏĥ": 281, "Ïĩα": 282, "ήÏĤ": 283, "Ïģγ": 284, "ιο": 285, "ÎŃÏĢ": 286, "ĠÏĥε": 287, "ÏħÏģÏī": 288, "ĠÏĦÏīν": 289, "ĠεÏħ": 290, "ÏĬ": 291, "μÎŃ": 292, "ĠÏĦιÏĤ": 293, "άν": 294, "θε": 295, "ÏħÏģÏīÏĢα": 296, "Ġδεν": 297, "αÏĥ": 298, "Ïģε": 299, "μο": 300, "λε": 301, "ĠÏħÏĢ": 302, "ĠÏĨ": 303, "ĠÏĥÏĦο": 304, "ÏĬκ": 305, "λά": 306, "ĠÏĥÏĦην": 307, "ĠÏĮÏĦι": 308, "οÏħÏĤ": 309, "ÏĥειÏĤ": 310, "ÏħÏģÏīÏĢαÏĬκ": 311, "ÎŃÏĢει": 312, "Ġά": 313, "ÏģÏĩ": 314, "ÏīÏĤ": 315, "ĠαÏĢο": 316, "ÏĥοÏħμε": 317, "κα": 318, "ĠÏĥÏħν": 319, "ĠμαÏĤ": 320, "ÏĥηÏĤ": 321, "Īη": 322, "ĠαÏħÏĦÏĮ": 323, "Ġοι": 324, "ĠÏĢÏģÎŃÏĢει": 325, "ÏģÏĮ": 326, "Ïĥε": 327, "ĠÏĦοÏħÏĤ": 328, "ÏĩαÏģι": 329, "ίαÏĤ": 330, "ĠμÎŃ": 331, "ĠεÏħÏĩαÏģι": 332, "Ġεί": 333, "ĠÏĢε": 334, "γκ": 335, "εÏĦαι": 336, "ον": 337, "ĠÏĦον": 338, "Ġδια": 339, "NG": 340, "LNG": 341, "Ïĥα": 342, "ÎŃÏģ": 343, "ÏĥÏĦÏİ": 344, "ĠÏĢÏģÏĮ": 345, "ÏĥÏĦε": 346, "Ġεν": 347, "ĠÎķÏħÏģÏīÏĢαÏĬκ": 348, "ιά": 349, "Ïģη": 350, "ĠÏĢολÏį": 351, "Ġή": 352, "ĠθÎŃ": 353, "ÏĢε": 354, "νÏī": 355, "ÏĦή": 356, "μαÏĦα": 357, "ÏĦική": 358, "ĠÏĥαÏĤ": 359, "ĠεÏħÏĩαÏģιÏĥÏĦÏİ": 360, "ĠεÏĢι": 361, "Ġ;": 362, "κε": 363, "ÏĦÏĮ": 364, "Ġκά": 365, "ĠÎŃνα": 366, "Ġαλ": 367, "ĠμÏĢο": 368, "ÏįÏģι": 369, "νη": 370, "ĠÎļ": 371, "γο": 372, "Ïĥι": 373, "ĠÏĪη": 374, "ÏĥÏī": 375, "ÏĦÏģο": 376, "ική": 377, "θη": 378, "μά": 379, "εδ": 380, "ĠεÏĢί": 381, "λή": 382, "ĠκÏįÏģι": 383, "άλ": 384, "Ġμια": 385, "Ġεκ": 386, "μÏĮ": 387, "ĠÏĥÏħμ": 388, "Ïģία": 389, "ÏĦαν": 390, "μή": 391, "ĠαÏħÏĦή": 392, "αν": 393, "ÏİÏģα": 394, "ÏĦί": 395, "ĠÏĥη": 396, "ĠÎŃÏĩοÏħμε": 397, "ĠÏĢαÏģα": 398, "ĠκαÏĦά": 399, "εια": 400, "ĠÏĢÏģοÏĥ": 401, "Ġξ": 402, "Ġανα": 403, "ÏĦοÏį": 404, "δο": 405, "ÏģοÏį": 406, "ίζ": 407, "ελ": 408, "Ġ2": 409, "ĠÏĢεÏģι": 410, "ÏĦικÏĮ": 411, "βα": 412, "ĠÎŃÏĩει": 413, "Ġεξ": 414, "Ïģή": 415, "ĠκαÏĦα": 416, "ÏĢη": 417, "λογ": 418, "ÏģÏī": 419, "ÏĦεÏĤ": 420, "οÏĤ": 421, "Ġαλλά": 422, "ίεÏĤ": 423, "ĠκÏħÏģ": 424, "ĠÎĪ": 425, "Ġ1": 426, "Ġδη": 427, "ĠÏħÏĢά": 428, "Ġεγκ": 429, "Ġι": 430, "Ġδικ": 431, "ĠÎĪνÏī": 432, "ÏĦηÏĦα": 433, "ÏģÏİ": 434, "ĠÏĥÏĦα": 435, "θεί": 436, "ÏĢοι": 437, "ÏįÏĦε": 438, "Ġακ": 439, "μη": 440, "ικά": 441, "ξη": 442, "ĠÏĥÏĦι": 443, "ÏĦικά": 444, "Ġζ": 445, "Ġκοι": 446, "ικÏĮ": 447, "ĠÏĦÏİÏģα": 448, "Ġλοι": 449, "ÏĢι": 450, "ĠÏĢολι": 451, "ĠÏĮλ": 452, "ίνεÏĦαι": 453, "ĠÏħÏĢάÏģÏĩ": 454, "ĠοÏĢο": 455, "ĠλÏĮ": 456, "ĠÏħÏĢο": 457, "οÏįν": 458, "κÏģα": 459, "ÏĢÏĮν": 460, "ĠÏĥημα": 461, "ĠλοιÏĢÏĮν": 462, "εν": 463, "00": 464, "ĠαÏĢ": 465, "ĠÏĪηÏĨο": 466, "Ġκάν": 467, "ÏĪ": 468, "ÏĦοÏĤ": 469, "ÏģÎŃ": 470, "ĠÎł": 471, "ĠΣ": 472, "ĠÎĴ": 473, "ĠÎķÏħÏģÏīÏĢαÏĬκή": 474, "ĠÏĪηÏĨοÏĨο": 475, "μÎŃν": 476, "αλ": 477, "ÏİÏĤ": 478, "ιλ": 479, "ÏĮÏĥ": 480, "οÏįμε": 481, "δη": 482, "Ġάλ": 483, "λÎŃ": 484, "Ïĥία": 485, "ĠÎľ": 486, "ÏĦηÏĥη": 487, "ομ": 488, "Ġδι": 489, "ĠÏĥÏĦ": 490, "ĠÏĦμή": 491, "μαÏĥÏĦε": 492, "Ïģεί": 493, "ĠÏĥÏĩ": 494, "ÏģεÏĤ": 495, "ĠÏĮÏĢ": 496 }, "merges": [ "Ġ Î", "Î ±", "Ï Ħ", "Î ¹", "Î ¿", "Î µ", "Î ½", "Ï ģ", "Ġ Ï", "Ï ħ", "Ï Ĥ", "Î ·", "Ï ĥ", "Ġ ÏĦ", "Î ¼", "Î ¯", "Ï Ģ", "Î »", "Î º", "ĠÏ Ģ", "Î ¬", "ο Ïħ", "ĠÎ º", "Ï Į", "ĠÎ µ", "ĠÎ ±", "Î Ń", "ĠÏ ĥ", "Ï ī", "α ι", "Î ®", "Ï į", "ĠÎ ¼", "Î ³", "ε ι", "Ï ĩ", "Ï İ", "ι α", "μ ε", "ĠÎ ½", "ι κ", "ĠÎ ´", "ĠÏĦ η", "Ġκ αι", "Ġν α", "Î ´", "Î ¸", "Ïģ ο", "Ï Ĩ", "ÏĦ α", "ÏĦ ε", "ί α", "ÏĢ Î¿", "ĠÏĦ ο", "ĠÎ ³", "μ α", "Ïģ α", "Ïĥ η", "ĠÎ ¿", "ÏĦ η", "Ïģ ι", "ÏĦ ο", "ĠÎ Ń", "ĠÎ ¸", "ί ν", "Ïī ν", "ĠÏ Į", "Î ²", "Ġγ ια", "οÏħ με", "ÏĦ ι", "ĠÎ ·", "ĠÏĦη ν", "ν α", "ν ο", "ĠÏĦ οÏħ", "Ġα Ïħ", "Ġ ,", "Ġμ ε", "Ġ .", "ĠÏĢ Ïģ", "ο λ", "ÏĦ ικ", "ĠÏĥ Ïħ", "ε ÏĤ", "Î ¾", "Ġκ α", "Ïħ Ïģ", "ÏĢ ÏĮ", "ο Ïį", "ĠαÏħ ÏĦ", "Ġθ α", "Î ¶", "ĠÏĦη ÏĤ", "α ÏĤ", "ο ι", "ÎŃ ÏĤ", "ÏĢ Î±", "ĠÏ ħ", "ε ί", "ĠÎ »", "Ïĥ ÏĦ", "ĠÏĢ Ïģο", "Ġε ίν", "Ġείν αι", "Ïĥ ει", "ĠÏĢ Î¿Ïħ", "ÏĦ αι", "ĠÏĦ α", "Ïģ ά", "ĠÏ ĩ", "λ ο", "Ġε ÏĢ", "οÏħ ν", "ĠÏĢ Î¿Î»", "Ġδ ε", "ĠÎ ķ", "ĠÎŃ Ïĩ", "ÏĨ ο", "Ïİ Î½", "ĠÏĦ ι", "ĠÏĥ ÏĦη", "ĠÎ ²", "ÏĦ ά", "Ïģ ί", "Ġα ν", "ĠÏĢ Î±", "Ġα ÏĢÏĮ", "Ġ (", "λ α", "λ η", "ι Ïĥ", "Ïĩ α", "ή ÏĤ", "Ïģ γ", "ι ο", "ÎŃ ÏĢ", "ĠÏĥ ε", "ÏħÏģ Ïī", "ĠÏĦ Ïīν", "Ġε Ïħ", "Ï Ĭ", "μ ÎŃ", "ĠÏĦι ÏĤ", "ά ν", "θ ε", "ÏħÏģÏī ÏĢα", "Ġδε ν", "α Ïĥ", "Ïģ ε", "μ ο", "λ ε", "ĠÏħ ÏĢ", "ĠÏ Ĩ", "ĠÏĥ ÏĦο", "ÏĬ κ", "λ ά", "ĠÏĥÏĦη ν", "ĠÏĮ ÏĦι", "οÏħ ÏĤ", "Ïĥει ÏĤ", "ÏħÏģÏīÏĢα ÏĬκ", "ÎŃÏĢ ÎµÎ¹", "ĠÎ ¬", "Ïģ Ïĩ", "Ïī ÏĤ", "Ġα ÏĢο", "Ïĥ οÏħμε", "κ α", "ĠÏĥÏħ ν", "Ġμ αÏĤ", "Ïĥη ÏĤ", "Ī Î·", "ĠαÏħÏĦ ÏĮ", "Ġο ι", "ĠÏĢÏģ ÎŃÏĢει", "Ïģ ÏĮ", "Ïĥ ε", "ĠÏĦοÏħ ÏĤ", "Ïĩα Ïģι", "ία ÏĤ", "Ġμ ÎŃ", "ĠεÏħ ÏĩαÏģι", "Ġε ί", "ĠÏĢ Îµ", "γ κ", "ε ÏĦαι", "ο ν", "ĠÏĦο ν", "Ġδ ια", "N G", "L NG", "Ïĥ α", "ÎŃ Ïģ", "ÏĥÏĦ Ïİ", "ĠÏĢÏģ ÏĮ", "Ïĥ ÏĦε", "Ġε ν", "ĠÎķ ÏħÏģÏīÏĢαÏĬκ", "ι ά", "Ïģ η", "ĠÏĢολ Ïį", "ĠÎ ®", "Ġθ ÎŃ", "ÏĢ Îµ", "ν Ïī", "ÏĦ ή", "μα ÏĦα", "ÏĦικ ή", "ĠÏĥ αÏĤ", "ĠεÏħÏĩαÏģι ÏĥÏĦÏİ", "ĠεÏĢ Î¹", "Ġ ;", "κ ε", "ÏĦ ÏĮ", "Ġκ ά", "ĠÎŃ Î½Î±", "Ġα λ", "Ġμ ÏĢο", "Ïį Ïģι", "ν η", "ĠÎ ļ", "γ ο", "Ïĥ ι", "ĠÏ Īη", "Ïĥ Ïī", "ÏĦ Ïģο", "ικ ή", "θ η", "μ ά", "ε δ", "ĠεÏĢ Î¯", "λ ή", "Ġκ ÏįÏģι", "ά λ", "Ġμ ια", "Ġε κ", "μ ÏĮ", "ĠÏĥÏħ μ", "Ïģ ία", "ÏĦα ν", "μ ή", "ĠαÏħÏĦ ή", "α ν", "Ïİ Ïģα", "ÏĦ ί", "ĠÏĥ η", "ĠÎŃÏĩ οÏħμε", "ĠÏĢα Ïģα", "Ġκα ÏĦά", "ει α", "ĠÏĢÏģο Ïĥ", "ĠÎ ¾", "Ġα να", "ÏĦο Ïį", "δ ο", "Ïģο Ïį", "ί ζ", "ε λ", "Ġ 2", "ĠÏĢε Ïģι", "ÏĦικ ÏĮ", "β α", "ĠÎŃÏĩ ει", "Ġε ξ", "Ïģ ή", "Ġκα ÏĦα", "ÏĢ Î·", "λο γ", "Ïģ Ïī", "ÏĦε ÏĤ", "ο ÏĤ", "Ġαλ λά", "ί εÏĤ", "Ġκ ÏħÏģ", "ĠÎ Ī", "Ġ 1", "Ġδ η", "ĠÏħÏĢ Î¬", "Ġε γκ", "ĠÎ ¹", "Ġδ ικ", "ĠÎĪ Î½Ïī", "ÏĦη ÏĦα", "Ïģ Ïİ", "ĠÏĥ ÏĦα", "θ εί", "ÏĢο ι", "Ïį ÏĦε", "Ġα κ", "μ η", "ικ ά", "ξ η", "ĠÏĥ ÏĦι", "ÏĦικ ά", "ĠÎ ¶", "Ġκ οι", "ικ ÏĮ", "ĠÏĦ ÏİÏģα", "Ġλ οι", "ÏĢ Î¹", "ĠÏĢολ ι", "ĠÏĮ λ", "ίν εÏĦαι", "ĠÏħÏĢά ÏģÏĩ", "Ġο ÏĢο", "Ġλ ÏĮ", "ĠÏħ ÏĢο", "οÏį ν", "κ Ïģα", "ÏĢÏĮ ν", "ĠÏĥη μα", "Ġλοι ÏĢÏĮν", "ε ν", "0 0", "Ġα ÏĢ", "ĠÏĪη ÏĨο", "Ġκ άν", "Ï Ī", "ÏĦο ÏĤ", "Ïģ ÎŃ", "ĠÎ ł", "ĠÎ £", "ĠÎ Ĵ", "ĠÎķÏħÏģÏīÏĢαÏĬκ ή", "ĠÏĪηÏĨο ÏĨο", "μÎŃ Î½", "α λ", "Ïİ ÏĤ", "ι λ", "ÏĮ Ïĥ", "οÏį με", "δ η", "Ġά λ", "λ ÎŃ", "Ïĥ ία", "ĠÎ ľ", "ÏĦη Ïĥη", "ο μ", "Ġδ ι", "ĠÏĥ ÏĦ", "ĠÏĦ μή", "μα ÏĥÏĦε", "Ïģ εί", "ĠÏĥ Ïĩ", "Ïģ εÏĤ", "ĠÏĮ ÏĢ" ] } }