tokenizer_config.json

{
  "add_prefix_space": false,
  "added_tokens_decoder": {
    "151643": {
      "content": "<|endoftext|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151644": {
      "content": "<|im_start|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151645": {
      "content": "<|im_end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151646": {
      "content": "<|PAD_TOKEN|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<|im_start|>",
    "<|im_end|>"
  ],
  "bos_token": null,
  "chat_template": "{{ bos_token }}{% for message in messages %}{% if message['from'] == 'human' %}{{'<|user|>\n' + message['value'] + '<|end|>\n'}}{% elif message['from'] == 'gpt' %}{{'<|assistant|>\n' + message['value'] + '<|end|>\n'}}{% else %}{{'<|' + message['from'] + '|>\n' + message['value'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% endif %}",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|endoftext|>",
  "errors": "replace",
  "model_max_length": 131072,
  "pad_token": "<|PAD_TOKEN|>",
  "padding_side": "left",
  "split_special_tokens": false,
  "tokenizer_class": "Qwen2Tokenizer",
  "unk_token": null
}