tokenizer_config.json

{
  "added_tokens_decoder": {
    "0": {
      "content": "<unk>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<s>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "<|im_end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "3": {
      "content": "[INST]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "4": {
      "content": "[/INST]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "5": {
      "content": "<<SYS>>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "6": {
      "content": "<</SYS>>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "bos_token": "<s>",
  "chat_template": "{%- set ns = namespace(found=false) -%}\n{%- for message in messages -%}\n    {%- if message['role'] == 'system' -%}\n        {%- set ns.found = true -%}\n    {%- endif -%}\n{%- endfor -%}\n{%- for message in messages %}\n    {%- if message['role'] == 'system' -%}\n        {{- '<|im_start|>system\n' + message['content'].rstrip() + '<|im_end|>\n' -}}\n    {%- else -%}\n        {%- if message['role'] == 'user' -%}\n            {{-'<|im_start|>user\n' + message['content'].rstrip() + '<|im_end|>\n'-}}\n        {%- else -%}\n            {{-'<|im_start|>assistant\n' + message['content'] + '<|im_end|>\n' -}}\n        {%- endif -%}\n    {%- endif -%}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n    {{-'<|im_start|>assistant\n'-}}\n{%- endif -%}",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|im_end|>",
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "<unk>",
  "tokenizer_class": "PreTrainedTokenizerFast",
  "unk_token": "<unk>"
}