tokenizer_config.json

{
  "tokenizer_class": "LlamaTokenizer",
  "model_max_length": 512,
  "bos_token": "<s>",
  "eos_token": "</s>",
  "unk_token": "<unk>",
  "pad_token": "<pad>",
  "legacy": false,
  "add_prefix_space": false,
  "add_bos_token": false,
  "add_eos_token": false,
  "added_tokens_decoder": {
    "4": {
      "content": "<|im_start|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "5": {
      "content": "<|im_end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "chat_template": "{% for message in messages %} <|im_start|>{{ message['role'] }}\n{{ message['content'] }}\n<|im_end|>\n{% endfor %}{% if add_generation_prompt %} <|im_start|>assistant\n{% endif %}"
}