MiniCPM-SALA / tokenizer_config.json
BigDong's picture
Upload folder using huggingface_hub
6c071d2 verified
{
"add_bos_token": true,
"add_eos_token": false,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"101": {
"content": "<think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"102": {
"content": "</think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"103": {
"content": "<tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"104": {
"content": "</tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"105": {
"content": "<tools>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"106": {
"content": "</tools>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"107": {
"content": "<parameters>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"108": {
"content": "</parameters>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"109": {
"content": "<arguments>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"110": {
"content": "</arguments>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"111": {
"content": "<function",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"112": {
"content": "</function>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"113": {
"content": "<param",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"114": {
"content": "</param>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"73440": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"73441": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"73442": {
"content": "<tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"73443": {
"content": "</tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"73444": {
"content": "<|im_sep|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"73445": {
"content": "<|fim_prefix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"73446": {
"content": "<|fim_middle|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"73447": {
"content": "<|fim_suffix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|im_end|>",
"<|im_start|>",
"<tool_call>",
"</tool_call>",
"<|im_sep|>",
"<|fim_prefix|>",
"<|fim_middle|>",
"<|fim_suffix|>",
"<tool_response>",
"</tool_response>",
"<tools>",
"</tools>",
"<arguments>",
"</arguments>",
"<parameters>",
"</parameters>",
"<function",
"</function>",
"<param",
"</param>"
],
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"legacy": true,
"model_max_length": 262144,
"pad_token": "</s>",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false,
"chat_template": "{%- 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 {{- '<param name=\"' ~ param_name ~ '\">' }}\n {%- if param_value is string and ('<' in param_value or '&' in param_value or '\\n' in param_value) %}\n {{- '<![CDATA[' + param_value + ']]>' }}\n {%- else %}\n {{- param_value }}\n {%- endif %}\n {{- '</param>' }}\n {%- endfor %}\n {%- endif %}\n {{- '</function>' }}\n {%- endset %}\n {%- set processed_content = processed_content + single_tool_xml + content_parts[i] %}\n {%- else %}\n {%- set processed_content = processed_content + content_parts[i] %}\n {%- endif %}\n {%- endfor %}\n \n {%- if tool_calls_count > tool_sep_count %}\n {%- for remaining_index in range(tool_sep_count, tool_calls_count) %}\n {%- set tool_call = message.tool_calls[remaining_index] %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {%- set remaining_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 {{- '<param name=\"' ~ param_name ~ '\">' }}\n {%- if param_value is string and ('<' in param_value or '&' in param_value or '\\n' in param_value) %}\n {{- '<![CDATA[' + param_value + ']]>' }}\n {%- else %}\n {{- param_value }}\n {%- endif %}\n {{- '</param>' }}\n {%- endfor %}\n {%- endif %}\n {{- '</function>' }}\n {%- endset %}\n {%- set processed_content = processed_content + remaining_tool_xml %}\n {%- endfor %}\n {%- endif %}\n \n {%- set content = processed_content %}\n {%- endif %}\n \n {%- if loop.index0 > ns.last_query_index %}\n {%- if reasoning_content %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n \n {%- if message.tool_calls and not has_tool_sep %}\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 {{- '<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 {{- '<param name=\"' ~ param_name ~ '\">' }}\n {%- if param_value is string and ('<' in param_value or '&' in param_value or '\\n' in param_value) %}\n {{- '<![CDATA[' + param_value + ']]>' }}\n {%- else %}\n {{- param_value }}\n {%- endif %}\n {{- '</param>' }}\n {%- endfor %}\n {%- endif %}\n {{- '</function>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {%- if message.content is string %}\n {{- content }}\n {%- else %}\n {{- message.content | tojson(ensure_ascii=False) }}\n {%- endif %}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}"
}