proj8-lab2 / tokenizer_config.json
hojzas's picture
Add SetFit model
be7b558 verified
{
"added_tokens_decoder": {
"0": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<pad>",
"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
},
"3": {
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"104": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"30526": {
"content": "<mask>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "<s>",
"do_lower_case": true,
"eos_token": "</s>",
"mask_token": "<mask>",
"max_length": 128,
"model_max_length": 512,
"pad_to_multiple_of": null,
"pad_token": "<pad>",
"pad_token_type_id": 0,
"padding_side": "right",
"sep_token": "</s>",
"stride": 0,
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "MPNetTokenizer",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "[UNK]"
}