tokenizer_config.json

{"src_lang": "en", "bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "special_tokens_map_file": "/nlsasfs/home/ai4bharat/gramesh/fine-tuning/IndicXLM/tools/indicXLM_sentencepiece_hf2_og_base_paragraphs/special_tokens_map.json", "name_or_path": "/nlsasfs/home/ai4bharat/gramesh/fine-tuning/IndicXLM/tools/indicXLM_sentencepiece_hf2_og_base_paragraphs/", "tokenizer_class": "IndicBERTSentencePieceTokenizer"}