bertin-large-finetuned-sqac / tokenizer_config.json
mrm8488's picture
Initial commit from mrm8488
da1c028
raw history blame
No virus
1.34 kB
{"errors": "replace", "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "special_tokens_map_file": null, "name_or_path": "flax-community/bertin-roberta-large-spanish", "do_lower_case": false, "tokenizer_file": "/root/.cache/huggingface/transformers/abcefe6cb866709f8793e0130a2d9bd883fee0cbcc25ffee734858e4d002c5b6.0803a0fadc521f273c2682a34dc285f90fe9de9e932bbe77401d11672f7fcb60", "tokenizer_class": "RobertaTokenizer"}