sealion-bert / tokenizer_config.json
carlesoctav's picture
Upload tokenizer
a4c6a10 verified
{
"add_bos_token": true,
"add_eos_token": true,
"added_tokens_decoder": {
"0": {
"content": "<|pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<|bos|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<|eos|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<|mask|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"8": {
"content": "<|unk|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"auto_map": {
"AutoTokenizer": [
"aisingapore/sealion-bert-base--tokenization_SEA_BPE.SEABPETokenizer",
null
]
},
"bos_token": "<|bos|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|eos|>",
"legacy": true,
"mask_token": "<|mask|>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<|pad|>",
"sp_model_kwargs": {},
"tokenizer_class": "SEABPETokenizer",
"unk_token": "<|unk|>"
}