tokenizer_config.json

{
  "added_tokens_decoder": {
    "151329": {
      "content": "<|endoftext|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151330": {
      "content": "[MASK]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151331": {
      "content": "[gMASK]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151332": {
      "content": "[sMASK]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151333": {
      "content": "<sop>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151334": {
      "content": "<eop>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151335": {
      "content": "<|system|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151336": {
      "content": "<|user|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151337": {
      "content": "<|assistant|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151338": {
      "content": "<|observation|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151339": {
      "content": "<|begin_of_image|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151340": {
      "content": "<|end_of_image|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151341": {
      "content": "<|begin_of_video|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151342": {
      "content": "<|end_of_video|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<|endoftext|>",
    "[MASK]",
    "[gMASK]",
    "[sMASK]",
    "<sop>",
    "<eop>",
    "<|system|>",
    "<|user|>",
    "<|assistant|>",
    "<|observation|>",
    "<|begin_of_image|>",
    "<|end_of_image|>",
    "<|begin_of_video|>",
    "<|end_of_video|>"
  ],
  "chat_template": "[gMASK]<sop>\n{%- if tools -%}\n<|system|>\n# 可用工具\n{% for tool in tools %}\n    {%- set function = tool.function if tool.get(\"function\") else tool %}\n\n## {{ function.name }}\n\n{{ function | tojson(indent=4, ensure_ascii=False) }}\n在调用上述函数时，请使用 Json 格式表示调用的参数。\n{%- endfor %}\n{%- endif -%}\n\n{%- for msg in messages %}\n    {%- if msg.role == 'system' %}\n<|system|>\n{{ msg.content }}\n    {%- endif %}\n{%- endfor %}\n\n{%- for message in messages if message.role != 'system' %}\n    {%- set role = message['role'] %}\n    {%- set content = message['content'] %}\n    {%- set meta = message.get(\"metadata\", \"\") %}\n\n    {%- if role == 'user' %}\n<|user|>\n{{ content }}\n    {%- elif role == 'assistant' and not meta %}\n<|assistant|>\n{{ content }}\n    {%- elif role == 'assistant' and meta %}\n<|assistant|>{{ meta }}\n{{ content }}\n    {%- elif role == 'observation' %}\n<|observation|>\n{{ content }}\n    {%- endif %}\n{%- endfor %}\n{% if add_generation_prompt %}<|assistant|>{% endif %}",
  "clean_up_tokenization_spaces": false,
  "do_lower_case": false,
  "eos_token": "<|user|>",
  "extra_special_tokens": {},
  "model_input_names": [
    "input_ids",
    "attention_mask"
  ],
  "model_max_length": 128000,
  "pad_token": "<|endoftext|>",
  "padding_side": "left",
  "remove_space": false,
  "tokenizer_class": "PreTrainedTokenizer"
}