dpr-xlm-align-C3-zhen / tokenizer_config.json
eugene-yang's picture
commit model
57657e7
{"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": null, "name_or_path": "/exp/eyang/data/checkpoints/sigir-rerun-xlm-align-base.con2.maxsim-cosine.clirmatrix.zhen-step100000", "tokenizer_file": "/exp/eyang/data/checkpoints/sigir-rerun-xlm-align-base.con2.maxsim-cosine.clirmatrix.zhen-step100000/tokenizer.json", "tokenizer_class": "XLMRobertaTokenizer"}