hate-bert-hasoc-marathi / tokenizer_config.json

Initial commit for hate speech detection model trained on HASOC Marathi dataset

8463b5c about 3 years ago

510 Bytes

{"do_lower_case": false, "remove_space": true, "keep_accents": false, "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": {}, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "l3cube-pune/hate-bert-hasoc-marathi", "tokenizer_class": "AlbertTokenizer"}