kanon-tokenizer / tokenizer_config.json
umarbutler's picture
initial commit
a7568ea verified
{
"add_prefix_space": false,
"added_tokens_decoder": {
"0": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<|nothingword|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<|magicword|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "<|hiddenword|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|startoftext|>",
"clean_up_tokenization_spaces": false,
"cls_token": "<|startoftext|>",
"eos_token": "<|endoftext|>",
"mask_token": "<|hiddenword|>",
"model_max_length": 512,
"pad_token": "<|nothingword|>",
"sep_token": "<|endoftext|>",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|magicword|>"
}