chemlactica-125m / special_tokens_map.json
yerevann's picture
Upload tokenizer
811b8c8 verified
raw
history blame
1.93 kB
{
"additional_special_tokens": [
"[SYNONYM]",
"[RELATED]",
"[SIMILAR]",
"[PROPERTY]",
"[SAS]",
"[WEIGHT]",
"[TPSA]",
"[CLOGP]",
"[QED]",
"[NUMHDONORS]",
"[NUMHACCEPTORS]",
"[NUMHETEROATOMS]",
"[NUMROTATABLEBONDS]",
"[NOCOUNT]",
"[NHOHCOUNT]",
"[RINGCOUNT]",
"[HEAVYATOMCOUNT]",
"[FRACTIONCSP3]",
"[NUMAROMATICRINGS]",
"[NUMSATURATEDRINGS]",
"[NUMAROMATICHETEROCYCLES]",
"[NUMAROMATICCARBOCYCLES]",
"[NUMSATURATEDHETEROCYCLES]",
"[NUMSATURATEDCARBOCYCLES]",
"[NUMALIPHATICRINGS]",
"[NUMALIPHATICHETEROCYCLES]",
"[NUMALIPHATICCARBOCYCLES]",
"[IUPAC]",
"[VAR_NAME]",
"[VAR_DESC]",
"[VAR_VAL]",
"[ASSAY_NAME]",
"[ASSAY_DESC]",
"[/SYNONYM]",
"[/RELATED]",
"[/SIMILAR]",
"[/PROPERTY]",
"[/SAS]",
"[/WEIGHT]",
"[/TPSA]",
"[/CLOGP]",
"[/QED]",
"[/NUMHDONORS]",
"[/NUMHACCEPTORS]",
"[/NUMHETEROATOMS]",
"[/NUMROTATABLEBONDS]",
"[/NOCOUNT]",
"[/NHOHCOUNT]",
"[/RINGCOUNT]",
"[/HEAVYATOMCOUNT]",
"[/FRACTIONCSP3]",
"[/NUMAROMATICRINGS]",
"[/NUMSATURATEDRINGS]",
"[/NUMAROMATICHETEROCYCLES]",
"[/NUMAROMATICCARBOCYCLES]",
"[/NUMSATURATEDHETEROCYCLES]",
"[/NUMSATURATEDCARBOCYCLES]",
"[/NUMALIPHATICRINGS]",
"[/NUMALIPHATICHETEROCYCLES]",
"[/NUMALIPHATICCARBOCYCLES]",
"[/IUPAC]",
"[/VAR_NAME]",
"[/VAR_DESC]",
"[/VAR_VAL]",
"[/ASSAY_NAME]",
"[/ASSAY_DESC]"
],
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}