{
  "add_bos_token": true,
  "add_eos_token": false,
  "add_prefix_space": null,
  "added_tokens_decoder": {
    "32000": {
      "content": "õ",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "32001": {
      "content": "÷",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "32002": {
      "content": "Á",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "32003": {
      "content": "ý",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "32004": {
      "content": "À",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "32005": {
      "content": "ÿ",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "32006": {
      "content": "ø",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "32007": {
      "content": "ú",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "32008": {
      "content": "þ",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "32009": {
      "content": "ü",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "32010": {
      "content": "ù",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "32011": {
      "content": "ö",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "32012": {
      "content": "û",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "32013": {
      "content": "<｜begin▁of▁sentence｜>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32014": {
      "content": "<｜end▁of▁sentence｜>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32015": {
      "content": "<｜fim▁hole｜>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "32016": {
      "content": "<｜fim▁begin｜>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "32017": {
      "content": "<｜fim▁end｜>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "32018": {
      "content": "<pad>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "32019": {
      "content": "<|User|>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "32020": {
      "content": "<|Assistant|>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "32021": {
      "content": "<|im_end|>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "bos_token": "<｜begin▁of▁sentence｜>",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|im_end|>",
  "extra_special_tokens": {},
  "legacy": true,
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "<｜end▁of▁sentence｜>",
  "tokenizer_class": "LlamaTokenizerFast",
  "unk_token": null,
  "use_default_system_prompt": false,
  "chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n    {%- if messages[0]['content'] is string -%}\n        {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n    {%- else -%}\n        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n    {%- endif -%}\n    {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n    {%- set first_user_prefix = \"\" -%}\n    {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n        {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n    {%- endif -%}\n    {%- if (message['role'] == 'assistant') -%}\n        {%- set role = \"model\" -%}\n    {%- else -%}\n        {%- set role = message['role'] -%}\n    {%- endif -%}\n    {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n    {%- if message['content'] is string -%}\n        {{ message['content'] | trim }}\n    {%- elif message['content'] is iterable -%}\n        {%- for item in message['content'] -%}\n            {%- if item['type'] == 'image' -%}\n                {{ '<start_of_image>' }}\n            {%- elif item['type'] == 'text' -%}\n                {{ item['text'] | trim }}\n            {%- endif -%}\n        {%- endfor -%}\n    {%- else -%}\n        {{ raise_exception(\"Invalid content type\") }}\n    {%- endif -%}\n    {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n    {{ '<start_of_turn>model\n' }}\n{%- endif -%}\n"
}