45 lines
947 B
JSON
45 lines
947 B
JSON
{
|
|
"add_bos_token": false,
|
|
"add_eos_token": false,
|
|
"added_tokens_decoder": {
|
|
"0": {
|
|
"content": "<unk>",
|
|
"lstrip": false,
|
|
"normalized": true,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"1": {
|
|
"content": "<|startoftext|>",
|
|
"lstrip": false,
|
|
"normalized": true,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"2": {
|
|
"content": "<|endoftext|>",
|
|
"lstrip": false,
|
|
"normalized": true,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
}
|
|
},
|
|
"auto_map": {
|
|
"AutoTokenizer": [
|
|
"tokenization_yi.YiTokenizer",
|
|
null
|
|
]
|
|
},
|
|
"bos_token": "<|startoftext|>",
|
|
"clean_up_tokenization_spaces": false,
|
|
"eos_token": "<|endoftext|>",
|
|
"model_max_length": 200000,
|
|
"pad_token": "<unk>",
|
|
"sp_model_kwargs": {},
|
|
"tokenizer_class": "YiTokenizer",
|
|
"unk_token": "<unk>"
|
|
}
|