plamo-13b-instruct / tokenizer_config.json
torotoki's picture
Update tokenizer_config.json
2c5c1ab
raw
history blame
2.23 kB
{
"add_bos_token": false,
"add_eos_token": false,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "<cls>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "<sep>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"6": {
"content": "<mask>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<unk>",
"<s>",
"</s>",
"<pad>",
"<cls>",
"<sep>",
"<mask>"
],
"auto_map": {
"AutoTokenizer": [
"tokenization_plamo.PlamoTokenizer",
null
]
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"cls_token": "<cls>",
"eos_token": "</s>",
"local_file_only": true,
"mask_token": "<mask>",
"model_max_length": 8192,
"pad_token": "<pad>",
"sep_token": "<sep>",
"sp_model_kwargs": {},
"tokenizer_class": "PlamoTokenizer",
"tokenizer_file": null,
"unk_token": "<unk>"
}