berties / tokenizer_config.json

HueyNemud

Pretrained on pero-OCR, fine-tuned for NER on pero-OCR

449ee92 over 4 years ago

683 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"], "model_max_length": 512, "name_or_path": "HueyNemud/das22-10-camembert_pretrained", "special_tokens_map_file": "/lrde/home2/jchazalo/.cache/huggingface/transformers/fe0e213c44079a9ee091098f81fff2941484006e9ba3001a9bf1ee9f87537599.cb3ec3a6c1200d181228d8825ae9767572abca54efa1bbb37fd83d721b2ef323", "sp_model_kwargs": {}, "tokenizer_class": "CamembertTokenizer"}