tokenizer_config.json

{
  "additional_special_tokens": [
    "<s>NOTUSED",
    "</s>NOTUSED"
  ],
  "bos_token": "<s>",
  "cls_token": "<s>",
  "eos_token": "</s>",
  "mask_token": {
    "__type": "AddedToken",
    "content": "<mask>",
    "lstrip": true,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "model_max_length": 16384,
  "name_or_path": "/data/ccondevaux/scribe/training/ner/phrases/lsg-camembert-base-16384",
  "pad_token": "<pad>",
  "sep_token": "</s>",
  "special_tokens_map_file": null,
  "tokenizer_class": "CamembertTokenizer",
  "unk_token": "<unk>"
}