{ "added_tokens_decoder": { "0": { "content": "<s>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "1": { "content": "<pad>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "2": { "content": "</s>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "3": { "content": "<unk>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true } }, "bos_token": "<s>", "clean_up_tokenization_spaces": true, "do_lower_case": false, "eos_token": "</s>", "model_max_length": 256, "pad_token": "<pad>", "name_or_path": "ai4bharat/indictrans2-en-indic-1B", "tokenizer_class": "IndicTransTokenizer", "auto_map": { "AutoTokenizer": [ "tokenization_indictrans.IndicTransTokenizer", null ] }, "unk_token": "<unk>" }