IUPAC-FAST-TOKENIZER / tokenizer_config.json
BioMike's picture
Upload 3 files
03272d7 verified
{
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<eos>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<bos>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "<mask>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<pad>",
"clean_up_tokenization_spaces": true,
"eos_token": "<eos>",
"model_max_length": 512,
"pad_token": "<bos>",
"padding_side": "right",
"tokenizer_class": "PreTrainedTokenizerFast",
"truncation_side": "right",
"unk_token": "<unk>",
"mask_token": "<mask>"
}