genia-modelo3 / tokenizer_config.json
jotaTest's picture
Upload tokenizer
a7b4915 verified
{
"added_tokens_decoder": {
"0": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "[EMPTY]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"101": {
"content": "[CLS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"102": {
"content": "[SEP]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"103": {
"content": "[MASK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"[EMPTY]"
],
"cell_trim_length": -1,
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"drop_rows_to_fit": false,
"empty_token": "[EMPTY]",
"mask_token": "[MASK]",
"max_column_id": 512,
"max_question_length": null,
"max_row_id": 512,
"min_question_length": null,
"model_max_length": 512,
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"strip_accents": null,
"strip_column_names": false,
"tokenize_chinese_chars": true,
"tokenizer_class": "TapasTokenizer",
"unk_token": "[UNK]",
"update_answer_coordinates": false
}