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
    }
  },
  "additional_special_tokens": [
    "<|im_start|>",
    "<|im_end|>"
  ],
  "auto_map": {
    "AutoTokenizer": [
      "dunzhang/stella_en_1.5B_v5--tokenization_qwen.Qwen2Tokenizer",
      "dunzhang/stella_en_1.5B_v5--tokenization_qwen.Qwen2TokenizerFast"
    ]
  },
  "bos_token": null,
  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|endoftext|>",
  "errors": "replace",
  "model_max_length": 32768,
  "pad_token": "<|endoftext|>",
  "split_special_tokens": false,
  "tokenizer_class": "Qwen2Tokenizer",
  "unk_token": null
}