add tokenizer
Browse files- added_tokens.json +1 -1
- vocab.json +1 -1
added_tokens.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"<s>":
|
|
|
1 |
+
{"<s>": 97, "</s>": 98}
|
vocab.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"
|
|
|
1 |
+
{"#": 1, "(": 2, ")": 3, "*": 4, "+": 5, "=": 6, "@": 7, "\\": 8, "_": 9, "`": 10, "a": 11, "b": 12, "c": 13, "d": 14, "e": 15, "f": 16, "g": 17, "h": 18, "i": 19, "j": 20, "k": 21, "l": 22, "m": 23, "n": 24, "o": 25, "p": 26, "q": 27, "r": 28, "s": 29, "t": 30, "u": 31, "v": 32, "w": 33, "x": 34, "y": 35, "z": 36, "|": 0, "£": 38, "¤": 39, "¨": 40, "©": 41, "«": 42, "®": 43, "»": 44, "¼": 45, "½": 46, "¾": 47, "á": 48, "é": 49, "ì": 50, "ï": 51, "ñ": 52, "ò": 53, "ö": 54, "ù": 55, "ü": 56, "ā": 57, "ć": 58, "ē": 59, "ğ": 60, "ī": 61, "ō": 62, "œ": 63, "ş": 64, "š": 65, "ū": 66, "ž": 67, "ȃ": 68, "ȏ": 69, "ʺ": 70, "ʼ": 71, "ʽ": 72, "˝": 73, "ˮ": 74, "΄": 75, "а": 76, "в": 77, "к": 78, "р": 79, "ḥ": 80, "ẓ": 81, "ị": 82, "‐": 83, "–": 84, "—": 85, "’": 86, "„": 87, "‟": 88, "•": 89, "…": 90, "″": 91, "‽": 92, "€": 93, "™": 94, "−": 95, "fi": 96, "[UNK]": 96, "[PAD]": 97}
|