tiny-bart-sst2-distilled / tokenizer_config.json
aravindhank's picture
End of training
b25dadd verified
raw
history blame
1.26 kB
{
"add_prefix_space": true,
"added_tokens_decoder": {
"0": {
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<pad>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"50264": {
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "<s>",
"eos_token": "</s>",
"errors": "replace",
"is_split_into_words": true,
"mask_token": "<mask>",
"model_max_length": 1024,
"pad_token": "<pad>",
"padding": true,
"sep_token": "</s>",
"tokenizer_class": "BartTokenizer",
"truncation": true,
"unk_token": "<unk>"
}