DCS_sanskrit_distilbert / tokenizer_config.json
1
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "max_len": 512, "model_type": "bert", "keep_accents": true, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "/content/data_dir"}