helix-mRNA / tokenizer_config.json
mattwoodx's picture
Add tokenizer config
faecb10
raw
history blame
1.42 kB
{
"add_prefix_space": false,
"added_tokens_decoder": {
"0": {
"content": "[BOS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "[CLS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "[MASK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"6": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "[BOS]",
"characters": [
"A",
"C",
"G",
"U",
"N",
"E",
"T"
],
"clean_up_tokenization_spaces": false,
"cls_token": "[CLS]",
"eos_token": "[SEP]",
"mask_token": "[MASK]",
"model_max_length": 12288,
"pad_token": "[PAD]",
"padding_side": "left",
"sep_token": "[SEP]",
"tokenizer_class": "CharTokenizer",
"unk_token": "[UNK]"
}