marathi-albert / tokenizer_config.json
l3cube-pune's picture
Initial commit for MahaAlBERT model trained on L3Cube-MahaMono Corpus
5fd3005
{"do_lower_case": false, "remove_space": true, "keep_accents": true, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "max_len": 512, "model_type": "albert", "special_tokens_map_file": null, "name_or_path": "l3cube-pune/marathi-albert", "tokenizer_class": "AlbertTokenizer"}