tokenizer_config.json

{
  "model_type": "bpe",
  "tokenizer_class": "PreTrainedTokenizerFast",
  "bos_token": "<s>",
  "eos_token": "</s>",
  "unk_token": "<unk>",
  "pad_token": "<pad>",
  "clean_up_tokenization_spaces": true,
  "added_tokens_decoder": {
    "0": { "content": "<pad>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true },
    "1": { "content": "<unk>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true },
    "2": { "content": "<s>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true },
    "3": { "content": "</s>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true },
    "4": { "content": "<|user|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true },
    "5": { "content": "<|assistant|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }
  }
}