teacher_trainer / tokenizer_config.json
davidadamczyk's picture
Add SetFit model
f3e1008
raw
history blame contribute delete
548 Bytes
{
"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]"
}