tokcpu / rule110 /tokenizer.json
fMindstormer's picture
Tokenizer CPU
e7dea34 verified
Raw History Blame Contribute Delete
4.59 kB
{"version":"1.0","truncation":null,"padding":null,"added_tokens":[{"id":42,"content":"··","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":false},{"id":43,"content":"Β·β–ˆξ€","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":false},{"id":44,"content":"β–ˆβ–ˆξ€","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":false},{"id":45,"content":"β–ˆβ–ˆξ€‚","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":false},{"id":46,"content":"Β·Β·βŠ£ξ€","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":false},{"id":47,"content":"β–ˆΒ·ξ€","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":false},{"id":48,"content":"β–ˆβ–ˆξ€ƒ","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":false},{"id":49,"content":"β–ˆβ–ˆξ€„","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":false},{"id":50,"content":"β–ˆΒ·ξ€‚","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":false},{"id":51,"content":"β–ˆΒ·βŠ£ξ€","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":false},{"id":52,"content":"··","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":false},{"id":53,"content":"Β·β–ˆξ€‚","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":false},{"id":54,"content":"β–ˆβ–ˆξ€…","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":false},{"id":55,"content":"β–ˆβ–ˆξ€†","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":false},{"id":56,"content":"Β·Β·βŠ£ξ€‚","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":false},{"id":57,"content":"β–ˆΒ·ξ€ƒ","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":false},{"id":58,"content":"β–ˆβ–ˆξ€‡","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":false},{"id":59,"content":"Β·β–ˆξ€ƒ","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":false},{"id":60,"content":"··","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":false},{"id":61,"content":"β–ˆΒ·βŠ£ξ€‚","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":false},{"id":62,"content":"ea","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":false},{"id":63,"content":"fb","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":false},{"id":64,"content":"βŠ’β—¦Β·Β·ξ€","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":false},{"id":65,"content":"βŠ’β—¦Β·β–ˆξ€","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":false},{"id":66,"content":"βŠ’β—¦β–ˆβ–ˆξ€","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":false},{"id":67,"content":"βŠ’β—¦β–ˆβ–ˆξ€‚","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":false},{"id":68,"content":"βŠ’ξ€","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":false},{"id":69,"content":"gc","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":false},{"id":70,"content":"hd","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":false}],"normalizer":null,"pre_tokenizer":{"type":"Split","pattern":{"Regex":".."},"behavior":"Isolated","invert":false},"post_processor":null,"decoder":{"type":"Sequence","decoders":[{"type":"Replace","pattern":{"Regex":"[ξ€€-ξ€Ώ]"},"content":""},{"type":"Fuse"}]},"model":{"type":"BPE","dropout":null,"unk_token":null,"continuing_subword_prefix":null,"end_of_word_suffix":null,"fuse_unk":false,"byte_fallback":false,"ignore_merges":false,"vocab":{"a":0,"b":1,"c":2,"d":3,"e":4,"f":5,"g":6,"h":7,"Β·":8,"⊒":9,"⊣":10,"β–ˆ":11,"β—¦":12,"ae":42,"af":43,"ag":44,"ah":45,"a⊣":46,"be":47,"bf":48,"bg":49,"bh":50,"b⊣":51,"ce":52,"cf":53,"cg":54,"ch":55,"c⊣":56,"de":57,"df":58,"dg":59,"dh":60,"d⊣":61,"Β·Β·":62,"Β·β–ˆ":63,"⊒e":64,"⊒f":65,"⊒g":66,"⊒h":67,"βŠ’β—¦":68,"β–ˆΒ·":69,"β–ˆβ–ˆ":70},"merges":[["a","e"],["a","f"],["a","g"],["a","h"],["a","⊣"],["b","e"],["b","f"],["b","g"],["b","h"],["b","⊣"],["c","e"],["c","f"],["c","g"],["c","h"],["c","⊣"],["d","e"],["d","f"],["d","g"],["d","h"],["d","⊣"],["Β·","Β·"],["Β·","β–ˆ"],["⊒","e"],["⊒","f"],["⊒","g"],["⊒","h"],["⊒","β—¦"],["β–ˆ","Β·"],["β–ˆ","β–ˆ"]]}}