59 lines
1.3 KiB
JSON
59 lines
1.3 KiB
JSON
{
|
|
"add_prefix_space": false,
|
|
"backend": "tokenizers",
|
|
"bos_token": "<|endoftext|>",
|
|
"clean_up_tokenization_spaces": true,
|
|
"cls_token": "<|cls|>",
|
|
"eod_token": "<|endoftext|>",
|
|
"eos_token": "<|im_end|>",
|
|
"errors": "replace",
|
|
"extra_special_tokens": [
|
|
"<|endoftext|>",
|
|
"<|pad|>",
|
|
"<|unk|>",
|
|
"<|sep|>",
|
|
"<|mask|>",
|
|
"<|cls|>",
|
|
"<|image|>",
|
|
"<|audio|>",
|
|
"<|user|>",
|
|
"<|system|>",
|
|
"<|assistant|>",
|
|
"<|extra_id_0|>",
|
|
"<|extra_id_1|>",
|
|
"<|extra_id_2|>",
|
|
"<|extra_id_3|>",
|
|
"<|extra_id_4|>",
|
|
"<|extra_id_5|>",
|
|
"<|extra_id_6|>",
|
|
"<|extra_id_7|>",
|
|
"<|extra_id_8|>",
|
|
"<|extra_id_9|>",
|
|
"<|extra_id_10|>",
|
|
"<|extra_id_13|>",
|
|
"<|im_start|>",
|
|
"<|im_sep|>",
|
|
"<|im_end|>",
|
|
"<|resident_reg|>",
|
|
"<|foreigner_reg|>",
|
|
"<|business_reg|>",
|
|
"<|credit_card|>",
|
|
"<|passport|>",
|
|
"<|driver_license|>",
|
|
"<|telephone|>",
|
|
"<|health_insurance|>",
|
|
"<|bank_account|>"
|
|
],
|
|
"is_local": false,
|
|
"mask_token": "<|mask|>",
|
|
"model_max_length": 16384,
|
|
"model_specific_special_tokens": {
|
|
"eod_token": "<|endoftext|>"
|
|
},
|
|
"pad_token": "<|im_end|>",
|
|
"sep_token": "<|sep|>",
|
|
"tokenizer_class": "TokenizersBackend",
|
|
"unk_token": "<|unk|>",
|
|
"vocab_size": 102400
|
|
}
|