46 lines
1.0 KiB
JSON
46 lines
1.0 KiB
JSON
{
|
|
"added_tokens_decoder": {
|
|
"0": {
|
|
"content": "[UNK]",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"1": {
|
|
"content": "<|begin_of_text|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"2": {
|
|
"content": "<|end_of_text|>",
|
|
"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
|
|
}
|
|
},
|
|
"clean_up_tokenization_spaces": true,
|
|
"model_max_length": 1000000000000000019884624838656,
|
|
"tokenizer_class": "PreTrainedTokenizerFast",
|
|
"return_token_type_ids": false,
|
|
"use_token_type_ids": false,
|
|
"bos_token": "<|end_of_text|>",
|
|
"eos_token": "<|end_of_text|>",
|
|
"unk_token": "[UNK]",
|
|
"vocab_size": 65536
|
|
}
|