tokenizer_config.json

{
  "add_bos_token": false,
  "add_eos_token": false,
  "bos_token": "<|startoftext|>",
  "chat_template": "{%- if messages[0].role == 'system' %}\n {{- '<role>SYSTEM</role>' + messages[0].content + '\\n' }}\n{%- elif tools %}\n {{- '<role>SYSTEM</role>' }}\n{%- else %}\n {{- '<role>SYSTEM</role>\u4f60\u662f\u4e00\u4e2a\u667a\u80fd\u52a9\u624b\uff08AI Assistant\uff09\uff0c\u662f\u7531\u8682\u8681\u96c6\u56e2\u7684\u767e\u7075\u56e2\u961f\uff08Bailing team\uff09\u5f00\u53d1\u3002You are an AI Assistant, developed by the Bailing team at Ant Group.\\n' }}\n{%- endif %}\n{%- if tools %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nIf none of the functions can be used, point it out. If the given question lacks the parameters required by the function, also point it out. \\nIf you need to use a function, for each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call>\\n\" }}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if message.role == \"user\" %}\n {{- '<role>HUMAN</role>' + message.content }}\n {%- elif message.role == \"system\" and not loop.first %}\n {{- '<role>SYSTEM</role>' + message.content }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<role>ASSISTANT</role>' + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<role>ASSISTANT</role>' + content }}\n {%- endif %}\n {%- else %}\n {{- '<role>ASSISTANT</role>' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<role>OBSERVATION</role>' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<role>ASSISTANT</role><think>\\n' }}\n{%- endif %}\n",
  "clean_up_tokenization_spaces": false,
  "cls_token": "[CLS]",
  "eos_token": "<|endoftext|>",
  "fast_tokenizer": true,
  "gmask_token": "[gMASK]",
  "merges_file": null,
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "<|endoftext|>",
  "tokenizer_class": "PreTrainedTokenizerFast",
  "trust_remote_code": true,
  "vocab_file": null
}