tokenizer_config.json

{
  "add_bos_token": false,
  "add_eos_token": false,
  "add_prefix_space": false,
  "added_tokens_decoder": {
    "3251": {
      "content": "�",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "199999": {
      "content": "<|endoftext|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "200018": {
      "content": "<|endofprompt|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "200019": {
      "content": "<|assistant|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": true
    },
    "200020": {
      "content": "<|end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": true
    },
    "200021": {
      "content": "<|user|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": true
    },
    "200022": {
      "content": "<|system|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": true
    },
    "200023": {
      "content": "<|tool|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "200024": {
      "content": "<|/tool|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "200025": {
      "content": "<|tool_call|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "200026": {
      "content": "<|/tool_call|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "200027": {
      "content": "<|tool_response|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "200028": {
      "content": "<|tag|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": true
    },
    "200029": {
      "content": "<｜PAD▁TOKEN｜>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "bos_token": "<|endoftext|>",
  "chat_template": "{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|im_start|>system<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'user') %}{{'<|im_start|>user<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'assistant') %}{{'<|im_start|>assistant<|im_sep|>' + message['content'] + '<|im_end|>'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant<|im_sep|>' }}{% endif %}",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|end|>",
  "extra_special_tokens": {},
  "model_max_length": 131072,
  "pad_token": "<｜PAD▁TOKEN｜>",
  "padding_side": "right",
  "tokenizer_class": "GPT2Tokenizer",
  "unk_token": "�"
}