tokcpu / binary-counter /tokenizer.json
fMindstormer's picture
Tokenizer CPU
9676339 verified
Raw History Blame Contribute Delete
1.49 kB
{"version":"1.0","truncation":null,"padding":null,"added_tokens":[{"id":16,"content":"1ⓑ","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":false},{"id":17,"content":"β’Ά0","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":false},{"id":18,"content":"⊒1ⓑ","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":false},{"id":19,"content":"β’Ά#","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":false},{"id":20,"content":"0ⓑ","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":false},{"id":21,"content":"1ⓑ","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":false},{"id":22,"content":"0β“‘βŠ£ξ€","single_word":false,"lstrip":false,"rstrip":false,"normalized":false,"special":false}],"normalizer":null,"pre_tokenizer":null,"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":{"#":0,"0":1,"1":2,"⊒":3,"⊣":4,"β’Ά":5,"β’·":6,"ⓐ":7,"β“‘":8,"0β’Ά":16,"1β’Ά":17,"βŠ’β’Ά":18,"β“‘#":19,"β“‘0":20,"β“‘1":21,"β“‘βŠ£":22},"merges":[["0","β’Ά"],["1","β’Ά"],["⊒","β’Ά"],["β“‘","#"],["β“‘","0"],["β“‘","1"],["β“‘","⊣"]]}}