Generator_new_tokenizer / special_tokens_map.json
XuJP264
Declare CRISPR control tokens as additional_special_tokens
8426321
Invalid JSON: Unexpected token ']', ..."s12e>", ] } " is not valid JSON
{
"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
},
"unk_token": {
"content": "<oov>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"additional_special_tokens":[
"<crispr_spacer>",
"<crispr_repeat>",
"<cas1>",
"<cas2>",
"<tracrrna>",
"<cas5>",
"<cas3>",
"<cas4>",
"<cas9>",
"<cas7>",
"<cas8c>",
"<cas6>",
"<csm3gr7>",
"<csn2>",
"<cas10>",
"<cas7b>",
"<cas6e>",
"<cas8e>",
"<cas12f>",
"<cse2gr11>",
"<csx1>",
"<csm2gr11>",
"<csm4>",
"<wyl>",
"<cas12a>",
"<csm6>",
"<deddh>",
"<csm5>",
"<casr>",
"<cas8b1>",
"<csx19>",
"<csx20>",
"<csm5gr7>",
"<cas6f>",
"<cas8b2>",
"<cas5f>",
"<rt>",
"<cas7f>",
"<cas3-cas2>",
"<primpol>",
"<cas8f>",
"<cysh>",
"<cas3hd>",
"<tnib>",
"<csx10gr5>",
"<cas8a1>",
"<csa3>",
"<recd>",
"<cmr1gr7>",
"<cmr4>",
"<cmr6gr7>",
"<cmr3gr5>",
"<cmr5gr11>",
"<cas8b6>",
"<csb2>",
"<cora>",
"<csm4gr5>",
"<abieii>",
"<can2>",
"<cas13d>",
"<csb1gr7>",
"<iscb-hnh>",
"<pd>",
"<tnpa>",
"<cse2>",
"<csb3>",
"<csm3>",
"<cas13b>",
"<unk>",
"<csx16>",
"<tpr>",
"<dhh>",
"<2og>",
"<cas12m>",
"<mem>",
"<csf4>",
"<hearo>",
"<tn7>",
"<tniq>",
"<csf2>",
"<csf3>",
"<csf1>",
"<cas8b4>",
"<tnsd>",
"<heat>",
"<csx17>",
"<cas8u1>",
"<csx3>",
"<htpx>",
"<cas12b>",
"<csm2>",
"<cas10d>",
"<csc2>",
"<cmr3>",
"<cmr5>",
"<csc1gr5>",
"<gramp>",
"<cmr6>",
"<cas8b12>",
"<cas11b>",
"<cas12c>",
"<cas8a4>",
"<tnsb>",
"<nyn>",
"<iscb-nterm>",
"<cas8b3>",
"<cas8a2>",
"<cas5u>",
"<csx27>",
"<csx21>",
"<csx23>",
"<tm>",
"<cas3d>",
"<cas12lambda>",
"<tnsc>",
"<cas8b5>",
"<stand>",
"<st>",
"<iscb-ruvciii-cterm>",
"<cas11>",
"<cas11d2>",
"<cas12j>",
"<cas12d>",
"<cas8b8>",
"<cmr1>",
"<cas12k>",
"<cas12g>",
"<cas13f>",
"<cas8b10>",
"<cas13i>",
"<toprim>",
"<cas12e>",
]
}