Files
MiniCPM5-1B-SFT-Fable5/tokenizer_config.json

19 lines
9.6 KiB
JSON
Raw Permalink Normal View History

{
"add_prefix_space": null,
"backend": "tokenizers",
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"from_slow": true,
"is_local": false,
"legacy": false,
"model_max_length": 131072,
"pad_token": "<unused_token_477>",
"padding_side": "left",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "TokenizersBackend",
"unk_token": "<unk>",
"use_default_system_prompt": false,
"chat_template": "{{- bos_token }}{%- if tools %}\n {%- set tool_definitions %}\n {{- \"# Tools\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson(ensure_ascii=False) }}\n {%- endfor %}\n {{- '\\n</tools>\\n\\nTool usage guidelines:\\n- You may call zero or more functions. If no function calls are needed, just answer normally and do not include any <function ... </function>.\\n- When calling a function, return an XML object within <function ... </function> using:\\n<function name=\"function-name\"><param name=\"param-name\">param-value</param></function>\\n- param-value may be multi-line. If it contains <, & or newline characters, wrap it in a CDATA block: <param name=\"param-name\"><![CDATA[...multi-line value...]]></param>' }}\n {%- endset %}\n \n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {%- if '<tool_def_sep>' in messages[0].content %}\n {{- messages[0].content.replace('<tool_def_sep>', tool_definitions) }}\n {%- else %}\n {{- messages[0].content + '\\n\\n' + tool_definitions }}\n {%- endif %}\n {%- else %}\n {{- tool_definitions.lstrip() }}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\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\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\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 \n {%- if message.tool_calls %}\n {%- set content_parts = content.split('<tool_sep>') %}\n {%- set processed_content = content_parts[0] %}\n {%- set tool_calls_count = message.tool_calls|length %}\n {%- set tool_sep_count = content_parts|length - 1 %}\n {%- set min_count = [tool_calls_count, tool_sep_count]|min %}\n \n {%- for i in range(1, content_parts|length) %}\n {%- set tool_index = i - 1 %}\n {%- if tool_index < tool_calls_count %}\n {%- set tool_call = message.tool_calls[tool_index] %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {%- set single_tool_xml %}\n {{- '<function name=\"' ~ tool_call.name ~ '\">' }}\n {%- if tool_call.arguments %}\n {%- set args_dict = tool_call.arguments %}\n {%- for param_name, param_value in args_dict.items() %}\n
}