tokun / tokenizer_config.json
apehex's picture
Upload tokenizer
99b2871 verified
raw
history blame
1.38 kB
{
"added_tokens_decoder": {
"0": {
"content": "\u0000",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "\u0002",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "\u0003",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"17": {
"content": "\u0011",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"26": {
"content": "\u001a",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"29": {
"content": "\u001d",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "\u0002",
"clean_up_tokenization_spaces": true,
"cls_token": "\u0011",
"eos_token": "\u0003",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "\u0000",
"sep_token": "\u001d",
"split_special_tokens": true,
"tokenizer_class": "ByteTokenizer",
"unk_token": "\u001a",
"vocab_size": 256
}