tokenizer_config.json

{
  "add_prefix_space": false,
  "bos_token": {
    "__type": "AddedToken",
    "content": "",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "cls_token": {
    "__type": "AddedToken",
    "content": "",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "eos_token": {
    "__type": "AddedToken",
    "content": "",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "mask_token": {
    "__type": "AddedToken",
    "content": "",
    "lstrip": true,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "model_max_length": 2048,
  "name_or_path": "../models/canine-c-bak-semisupervised-v1-1",
  "pad_token": {
    "__type": "AddedToken",
    "content": "\u0000",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "sep_token": {
    "__type": "AddedToken",
    "content": "",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "special_tokens_map_file": "C:\\Users\\david/.cache\\huggingface\\hub\\models--google--canine-c\\snapshots\\59de14c6de8e676db78de601ac4cb470b56d4d25\\special_tokens_map.json",
  "tokenizer_class": "CanineTokenizer"
}