1 line
3.1 MiB
JSON
1 line
3.1 MiB
JSON
|
{"version": "1.0", "truncation": null, "padding": null, "added_tokens": [{"id": 0, "content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 1, "content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 2, "content": "</s>", "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": "<|system|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 5, "content": "<|user|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 6, "content": "<|assistant|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 7, "content": "<|end|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}], "normalizer": {"type": "NFC"}, "pre_tokenizer": {"type": "ByteLevel", "add_prefix_space": false, "trim_offsets": true, "use_regex": true}, "post_processor": {"type": "TemplateProcessing", "single": [{"SpecialToken": {"id": "<s>", "type_id": 0}}, {"Sequence": {"id": "A", "type_id": 0}}], "pair": [{"SpecialToken": {"id": "<s>", "type_id": 0}}, {"Sequence": {"id": "A", "type_id": 0}}, {"Sequence": {"id": "B", "type_id": 1}}], "special_tokens": {"<s>": {"id": "<s>", "ids": [1], "tokens": ["<s>"]}}}, "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, "ignore_merges": false, "vocab": {"<unk>": 0, "<s>": 1, "</s>": 2, "<pad>": 3, "<|system|>": 4, "<|user|>": 5, "<|assistant|>": 6, "<|end|>": 7, "!": 8, "\"": 9, "#": 10, "$": 11, "%": 12, "&": 13, "'": 14, "(": 15, ")": 16, "*": 17, "+": 18, ",": 19, "-": 20, ".": 21, "/": 22, "0": 23, "1": 24, "2": 25, "3": 26, "4": 27, "5": 28, "6": 29, "7": 30, "8": 31, "9": 32, ":": 33, ";": 34, "<": 35, "=": 36, ">": 37, "?": 38, "@": 39, "A": 40, "B": 41, "C": 42, "D": 43, "E": 44, "F": 45, "G": 46, "H": 47, "I": 48, "J": 49, "K": 50, "L": 51, "M": 52, "N": 53, "O": 54, "P": 55, "Q": 56, "R": 57, "S": 58, "T": 59, "U": 60, "V": 61, "W": 62, "X": 63, "Y": 64, "Z": 65, "[": 66, "\\": 67, "]": 68, "^": 69, "_": 70, "`": 71, "a": 72, "b": 73, "c": 74, "d": 75, "e": 76, "f": 77, "g": 78, "h": 79, "i": 80, "j": 81, "k": 82, "l": 83, "m": 84, "n": 85, "o": 86, "p": 87, "q": 88, "r": 89, "s": 90, "t": 91, "u": 92, "v": 93, "w": 94, "x": 95, "y": 96, "z": 97, "{": 98, "|": 99, "}": 100, "~": 101, "¡": 102, "¢": 103, "£": 104, "¤": 105, "¥": 106, "¦": 107, "§": 108, "¨": 109, "©": 110, "ª": 111, "«": 112, "¬": 113, "®": 114, "¯": 115, "°": 116, "±": 117, "²": 118, "³": 119, "´": 120, "µ": 121, "¶": 122, "·": 123, "¸": 124, "¹": 125, "º": 126, "»": 127, "¼": 128, "½": 129, "¾": 130, "¿": 131, "À": 132, "Á": 133, "Â": 134, "Ã": 135, "Ä": 136, "Å": 137, "Æ": 138, "Ç": 139, "È": 140, "É": 141, "Ê": 142, "Ë": 143, "Ì": 144, "Í": 145, "Î": 146, "Ï": 147, "Ð": 148, "Ñ": 149, "Ò": 150, "Ó": 151, "Ô": 152, "Õ": 153, "Ö": 154, "×": 155, "Ø": 156, "Ù": 157, "Ú": 158, "Û": 159, "Ü": 160, "Ý": 161, "Þ": 162, "ß": 163, "à": 164, "á": 165, "â": 166, "ã": 167, "ä": 168, "å": 169, "æ": 170, "ç": 171, "è": 172, "é": 173, "ê": 174, "ë": 175, "ì": 176, "í": 177, "î": 178, "ï": 179, "ð": 180, "ñ": 181, "ò": 182, "ó": 183, "ô": 184, "õ": 185, "ö": 186, "÷": 187, "ø": 188, "ù": 189, "ú": 190, "û": 191, "ü": 192, "ý": 193, "þ": 194, "ÿ": 195, "Ā": 196, "ā": 197, "Ă": 198, "ă": 199, "Ą": 200, "ą": 201, "Ć": 202, "ć": 203, "Ĉ": 204, "ĉ": 205, "Ċ": 206, "ċ": 207, "Č": 208, "č": 209, "Ď": 210, "ď": 211, "Đ": 212, "đ": 213, "Ē": 214
|