marathi-topic-short-doc / tokenizer_config.json
l3cube-pune's picture
Update model files
2aace5f
raw
history blame contribute delete
531 Bytes
{
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": false,
"lowercase": false,
"mask_token": "[MASK]",
"model_max_length": 512,
"name_or_path": "l3cube-pune/marathi-topic-short",
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": "l3cube-pune/marathi-topic-short/special_tokens_map.json",
"strip_accents": false,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}