est-roberta / tokenizer_config.json

Fixed the tokenizer configuration to get it working with Transformers v5

a546f91 verified about 2 months ago

507 Bytes

{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "additional_special_tokens": ["<s>NOTUSED", "</s>NOTUSED"], "special_tokens_map_file": null, "name_or_path": "EMBEDDIA/est-roberta", "sp_model_kwargs": {}, "tokenizer_class": "RobertaTokenizer", "model_max_length": 512, "do_lower_case": false}