tokenizer_config.json

{
  "added_tokens_decoder": {
    "928": {
      "content": "</s>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1186": {
      "content": "<unk>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "61022": {
      "content": "<pad>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "61023": {
      "content": ">>syr_cons<<",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "61024": {
      "content": ">>syr_voc<<",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    ">>syr_cons<<",
    ">>syr_voc<<"
  ],
  "clean_up_tokenization_spaces": false,
  "eos_token": "</s>",
  "extra_special_tokens": {},
  "model_max_length": 512,
  "pad_token": "<pad>",
  "separate_vocabs": false,
  "source_lang": "sem",
  "sp_model_kwargs": {},
  "target_lang": "en",
  "tokenizer_class": "MarianTokenizer",
  "unk_token": "<unk>"
}