xlm-roberta-10-final / tokenizer_config.json
joaomiguel26's picture
add tokenizer
04602dc
raw
history blame contribute delete
628 Bytes
{"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": {}, "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": "/mnt/shared/home/jalves/.cache/huggingface/transformers/daeda8d936162ca65fe6dd158ecce1d8cb56c17d89b78ab86be1558eaef1d76a.a984cf52fc87644bd4a2165f1e07e0ac880272c1e82d648b4674907056912bd7", "name_or_path": "xlm-roberta-base", "tokenizer_class": "XLMRobertaTokenizer"}