{ | |
"additional_special_tokens": [ | |
"<ar>", | |
"<he>", | |
"<vi>", | |
"<id>", | |
"<jv>", | |
"<ms>", | |
"<tl>", | |
"<eu>", | |
"<ml>", | |
"<ta>", | |
"<te>", | |
"<af>", | |
"<nl>", | |
"<en>", | |
"<de>", | |
"<el>", | |
"<bn>", | |
"<hi>", | |
"<mr>", | |
"<ur>", | |
"<fa>", | |
"<fr>", | |
"<it>", | |
"<pt>", | |
"<es>", | |
"<bg>", | |
"<ru>", | |
"<ja>", | |
"<ka>", | |
"<ko>", | |
"<th>", | |
"<sw>", | |
"<my>", | |
"<zh>", | |
"<kk>", | |
"<tr>", | |
"<et>", | |
"<fi>", | |
"<hu>", | |
"</ar>", | |
"</he>", | |
"</vi>", | |
"</id>", | |
"</jv>", | |
"</ms>", | |
"</tl>", | |
"</eu>", | |
"</ml>", | |
"</ta>", | |
"</te>", | |
"</af>", | |
"</nl>", | |
"</en>", | |
"</de>", | |
"</el>", | |
"</bn>", | |
"</hi>", | |
"</mr>", | |
"</ur>", | |
"</fa>", | |
"</fr>", | |
"</it>", | |
"</pt>", | |
"</es>", | |
"</bg>", | |
"</ru>", | |
"</ja>", | |
"</ka>", | |
"</ko>", | |
"</th>", | |
"</sw>", | |
"</my>", | |
"</zh>", | |
"</kk>", | |
"</tr>", | |
"</et>", | |
"</fi>", | |
"</hu>" | |
], | |
"bos_token": { | |
"content": "<s>", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false | |
}, | |
"cls_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 | |
}, | |
"mask_token": { | |
"content": "<mask>", | |
"lstrip": true, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false | |
}, | |
"pad_token": { | |
"content": "<pad>", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false | |
}, | |
"sep_token": { | |
"content": "</s>", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false | |
}, | |
"unk_token": { | |
"content": "<unk>", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false | |
} | |
} | |