tokenizer_config.json

{
  "add_prefix_space": false,
  "added_tokens_decoder": {
    "50256": {
      "content": "<|endoftext|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "auto_map": {
    "AutoProcessor": "processing_jat.JatProcessor"
  },
  "bos_token": "<|endoftext|>",
  "clean_up_tokenization_spaces": true,
  "eos_token": "<|endoftext|>",
  "model_input_names": [
    "input_ids",
    "attention_mask"
  ],
  "model_max_length": 512,
  "pad_token": "<|endoftext|>",
  "processor_class": "JatProcessor",
  "tokenizer_class": "GPT2Tokenizer",
  "unk_token": "<|endoftext|>"
}