tokenizer_config.json

{
  "tokenizer_class": "PreTrainedTokenizerFast",
  "bos_token": "<|im_start|>",
  "eos_token": "<|endoftext|>",
  "unk_token": "<unk>",
  "pad_token": "<|endoftext|>",
  "add_bos_token": false,
  "add_eos_token": false,
  "model_max_length": 4096,
  "clean_up_tokenization_spaces": false,
  "added_tokens_decoder": {
    "0": {
      "content": "<unk>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<|endoftext|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "<|im_start|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "3": {
      "content": "<|im_end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  }
}