tokenizer_config.json

{
  "add_bos_token": true,
  "add_eos_token": false,
  "add_prefix_space": null,
  "added_tokens_decoder": {
    "32000": {
      "content": "<|begin_of_text|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32001": {
      "content": "<|end_of_text|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32002": {
      "content": "<|pad|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32003": {
      "content": "<|start_header_id|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32004": {
      "content": "<|end_header_id|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32005": {
      "content": "<|eot_id|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32006": {
      "content": "<unk>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "bos_token": "<|begin_of_text|>",
  "chat_template": "{{- bos_token }}{%- if messages[0]['role'] == 'system' %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + messages[0]['content'] | trim + '<|eot_id|>' }}{%- set messages = messages[1:] %}{%- endif %}{% for message in messages %}{% if message.role in ['user', 'assistant'] %}{{ '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n' + message['content'] | trim + '<|eot_id|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}}",
  "clean_up_tokenization_spaces": true,
  "eos_token": "<|eot_id|>",
  "extra_special_tokens": {},
  "legacy": true,
  "model_max_length": 8192,
  "pad_token": "<|pad|>",
  "padding_side": "left",
  "tokenizer_class": "LlamaTokenizerFast",
  "unk_token": "<unk>",
  "use_default_system_prompt": false
}