88 lines
1.8 KiB
JSON
88 lines
1.8 KiB
JSON
|
{
|
||
|
|
"add_bos_token": true,
|
||
|
|
"add_eos_token": false,
|
||
|
|
"added_tokens_decoder": {
|
||
|
|
"0": {
|
||
|
|
"content": "<unk>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"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
|
||
|
|
},
|
||
|
|
"32000": {
|
||
|
|
"content": "<CLS>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"32001": {
|
||
|
|
"content": "<SEP>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"32002": {
|
||
|
|
"content": "<EOD>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"32003": {
|
||
|
|
"content": "<MASK>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"32004": {
|
||
|
|
"content": "<PAD>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"additional_special_tokens": [
|
||
|
|
"<EOD>"
|
||
|
|
],
|
||
|
|
"bos_token": "<s>",
|
||
|
|
"clean_up_tokenization_spaces": false,
|
||
|
|
"cls_token": "<CLS>",
|
||
|
|
"eos_token": "</s>",
|
||
|
|
"legacy": true,
|
||
|
|
"mask_token": "<MASK>",
|
||
|
|
"model_max_length": 2048,
|
||
|
|
"pad_token": "<PAD>",
|
||
|
|
"sep_token": "<SEP>",
|
||
|
|
"sp_model_kwargs": {},
|
||
|
|
"spaces_between_special_tokens": false,
|
||
|
|
"tokenizer_class": "LlamaTokenizer",
|
||
|
|
"unk_token": "<unk>",
|
||
|
|
"use_default_system_prompt": true
|
||
|
|
}
|