MiniCPM5-1B-int4-g128-ov / openvino_detokenizer.xml

Initial release: first OpenVINO IR of MiniCPM5-1B (int4 g128, no-think rt_info template, probe-validated)

7eb10d3 verified 3 months ago

17.9 kB

	<?xml version="1.0"?>
	<net name="detokenizer" version="11">
	<layers>
	<layer id="0" name="Parameter_79702" type="Parameter" version="opset1">
	<data shape="?,?" element_type="i64" />
	<output>
	<port id="0" precision="I64" names="Parameter_79702">
	<dim>-1</dim>
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="1" name="Convert_79738" type="Convert" version="opset1">
	<data destination_type="i32" />
	<input>
	<port id="0" precision="I64">
	<dim>-1</dim>
	<dim>-1</dim>
	</port>
	</input>
	<output>
	<port id="1" precision="I32">
	<dim>-1</dim>
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="2" name="Constant_79704" type="Const" version="opset1">
	<data element_type="i32" shape="130560" offset="0" size="522240" />
	<output>
	<port id="0" precision="I32">
	<dim>130560</dim>
	</port>
	</output>
	</layer>
	<layer id="3" name="Constant_79706" type="Const" version="opset1">
	<data element_type="i32" shape="130560" offset="522240" size="522240" />
	<output>
	<port id="0" precision="I32">
	<dim>130560</dim>
	</port>
	</output>
	</layer>
	<layer id="4" name="Constant_79708" type="Const" version="opset1">
	<data element_type="u8" shape="869396" offset="1044480" size="869396" />
	<output>
	<port id="0" precision="U8">
	<dim>869396</dim>
	</port>
	</output>
	</layer>
	<layer id="5" name="Slice_79713" type="Const" version="opset1">
	<data element_type="i32" shape="30" offset="1913876" size="120" />
	<output>
	<port id="0" precision="I32">
	<dim>30</dim>
	</port>
	</output>
	</layer>
	<layer id="6" name="VocabDecoder_79715" type="VocabDecoder" version="extension">
	<data skip_tokens="" />
	<input>
	<port id="0" precision="I32">
	<dim>-1</dim>
	<dim>-1</dim>
	</port>
	<port id="1" precision="I32">
	<dim>130560</dim>
	</port>
	<port id="2" precision="I32">
	<dim>130560</dim>
	</port>
	<port id="3" precision="U8">
	<dim>869396</dim>
	</port>
	<port id="4" precision="I32">
	<dim>30</dim>
	</port>
	</input>
	<output>
	<port id="5" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="6" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="7" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="8" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="9" precision="U8">
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="7" name="FuzeRagged_79716" type="FuzeRagged" version="extension">
	<input>
	<port id="0" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="1" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="2" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="3" precision="I32">
	<dim>-1</dim>
	</port>
	</input>
	<output>
	<port id="4" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="5" precision="I32">
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="8" name="UTF8Validate_79717" type="UTF8Validate" version="extension">
	<data replace_mode="true" />
	<input>
	<port id="0" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="1" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="2" precision="U8">
	<dim>-1</dim>
	</port>
	</input>
	<output>
	<port id="3" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="4" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="5" precision="U8">
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="9" name="StringTensorPack_79718" type="StringTensorPack" version="opset15">
	<input>
	<port id="0" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="1" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="2" precision="U8">
	<dim>-1</dim>
	</port>
	</input>
	<output>
	<port id="3" precision="STRING" names="Result_79719,string_output">
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="10" name="Result_79719" type="Result" version="opset1" output_names="Result_79719,string_output">
	<input>
	<port id="0" precision="STRING">
	<dim>-1</dim>
	</port>
	</input>
	</layer>
	</layers>
	<edges>
	<edge from-layer="0" from-port="0" to-layer="1" to-port="0" />
	<edge from-layer="1" from-port="1" to-layer="6" to-port="0" />
	<edge from-layer="2" from-port="0" to-layer="6" to-port="1" />
	<edge from-layer="3" from-port="0" to-layer="6" to-port="2" />
	<edge from-layer="4" from-port="0" to-layer="6" to-port="3" />
	<edge from-layer="5" from-port="0" to-layer="6" to-port="4" />
	<edge from-layer="6" from-port="5" to-layer="7" to-port="0" />
	<edge from-layer="6" from-port="6" to-layer="7" to-port="1" />
	<edge from-layer="6" from-port="7" to-layer="7" to-port="2" />
	<edge from-layer="6" from-port="8" to-layer="7" to-port="3" />
	<edge from-layer="6" from-port="9" to-layer="8" to-port="2" />
	<edge from-layer="7" from-port="4" to-layer="8" to-port="0" />
	<edge from-layer="7" from-port="5" to-layer="8" to-port="1" />
	<edge from-layer="8" from-port="3" to-layer="9" to-port="0" />
	<edge from-layer="8" from-port="4" to-layer="9" to-port="1" />
	<edge from-layer="8" from-port="5" to-layer="9" to-port="2" />
	<edge from-layer="9" from-port="3" to-layer="10" to-port="0" />
	</edges>
	<rt_info>
	<info name="OpenVINO Runtime" value="2026.3.0-22098-367f60d8408" />
	<add_attention_mask value="True" />
	<add_prefix_space />
	<add_special_tokens value="True" />
	<bos_token_id value="0" />
	<chat_template value="{{- bos_token }}{%- if tools %} {%- set tool_definitions %} {{- "# Tools\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }} {%- for tool in tools %} {{- "\n" }} {{- tool \| tojson(ensure_ascii=False) }} {%- endfor %} {{- '\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>' }} {%- endset %} {{- '<\|im_start\|>system\n' }} {%- if messages[0].role == 'system' %} {%- if '<tool_def_sep>' in messages[0].content %} {{- messages[0].content.replace('<tool_def_sep>', tool_definitions) }} {%- else %} {{- messages[0].content + '\n\n' + tool_definitions }} {%- endif %} {%- else %} {{- tool_definitions.lstrip() }} {%- endif %} {{- '<\|im_end\|>\n' }} {%- else %} {%- if messages[0].role == 'system' %} {{- '<\|im_start\|>system\n' + messages[0].content + '<\|im_end\|>\n' }} {%- endif %} {%- endif %} {%- set ns = namespace(multi_step_tool=true, last_query_index=messages\|length - 1) %} {%- for message in messages[::-1] %} {%- set index = (messages\|length - 1) - loop.index0 %} {%- 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>')) %} {%- set ns.multi_step_tool = false %} {%- set ns.last_query_index = index %} {%- endif %} {%- endfor %} {%- for message in messages %} {%- if message.content is string %} {%- set content = message.content %} {%- else %} {%- set content = '' %} {%- endif %} {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} {{- '<\|im_start\|>' + message.role + '\n' + content + '<\|im_end\|>' + '\n' }} {%- elif message.role == "assistant" %} {%- set reasoning_content = '' %} {%- if message.reasoning_content is string %} {%- set reasoning_content = message.reasoning_content %} {%- else %} {%- if '</think>' in content %} {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %} {%- set content = content.split('</think>')[-1].lstrip('\n') %} {%- endif %} {%- endif %} {%- if message.tool_calls %} {%- set content_parts = content.split('<tool_sep>') %} {%- set processed_content = content_parts[0] %} {%- set tool_calls_count = message.tool_calls\|length %} {%- set tool_sep_count = content_parts\|length - 1 %} {%- set min_count = [tool_calls_count, tool_sep_count]\|min %} {%- for i in range(1, content_parts\|length) %} {%- set tool_index = i - 1 %} {%- if tool_index < tool_calls_count %} {%- set tool_call = message.tool_calls[tool_index] %} {%- if tool_call.function %} {%- set tool_call = tool_call.function %} {%- endif %} {%- set single_tool_xml %} {{- '<function name="' ~ tool_call.name ~ '">' }} {%- if tool_call.arguments %} {%- set args_dict = tool_call.arguments %} {%- for param_name, param_value in args_dict.items() %} {{- '<param name="' ~ param_name ~ '">' }} {%- if param_value is string and ('<' in param_value or '&' in param_value or '\n' in param_value) %} {{- '<![CDATA[' + param_value + ']]>' }} {%- else %} {{- param_value }} {%- endif %} {{- '</param>' }} {%- endfor %} {%- endif %} {{- '</function>' }} {%- endset %} {%- set processed_content = processed_content + single_tool_xml + content_parts[i] %} {%- else %} {%- set processed_content = processed_content + content_parts[i] %} {%- endif %} {%- endfor %} {%- if tool_calls_count > tool_sep_count %} {%- for remaining_index in range(tool_sep_count, tool_calls_count) %} {%- set tool_call = message.tool_calls[remaining_index] %} {%- if tool_call.function %} {%- set tool_call = tool_call.function %} {%- endif %} {%- set remaining_tool_xml %} {{- '<function name="' ~ tool_call.name ~ '">' }} {%- if tool_call.arguments %} {%- set args_dict = tool_call.arguments %} {%- for param_name, param_value in args_dict.items() %} {{- '<param name="' ~ param_name ~ '">' }} {%- if param_value is string and ('<' in param_value or '&' in param_value or '\n' in param_value) %} {{- '<![CDATA[' + param_value + ']]>' }} {%- else %} {{- param_value }} {%- endif %} {{- '</param>' }} {%- endfor %} {%- endif %} {{- '</function>' }} {%- endset %} {%- set processed_content = processed_content + remaining_tool_xml %} {%- endfor %} {%- endif %} {%- set content = processed_content %} {%- endif %} {%- if loop.index0 > ns.last_query_index %} {%- if reasoning_content %} {{- '<\|im_start\|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }} {%- else %} {{- '<\|im_start\|>' + message.role + '\n' + content }} {%- endif %} {%- else %} {{- '<\|im_start\|>' + message.role + '\n' + content }} {%- endif %} {%- if message.tool_calls and not has_tool_sep %} {%- for tool_call in message.tool_calls %} {%- if (loop.first and content) or (not loop.first) %} {{- '\n' }} {%- endif %} {%- if tool_call.function %} {%- set tool_call = tool_call.function %} {%- endif %} {{- '<function name="' ~ tool_call.name ~ '">' }} {%- if tool_call.arguments %} {%- set args_dict = tool_call.arguments %} {%- for param_name, param_value in args_dict.items() %} {{- '<param name="' ~ param_name ~ '">' }} {%- if param_value is string and ('<' in param_value or '&' in param_value or '\n' in param_value) %} {{- '<![CDATA[' + param_value + ']]>' }} {%- else %} {{- param_value }} {%- endif %} {{- '</param>' }} {%- endfor %} {%- endif %} {{- '</function>' }} {%- endfor %} {%- endif %} {{- '<\|im_end\|>\n' }} {%- elif message.role == "tool" %} {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} {{- '<\|im_start\|>user' }} {%- endif %} {{- '\n<tool_response>\n' }} {%- if message.content is string %} {{- content }} {%- else %} {{- message.content \| tojson(ensure_ascii=False) }} {%- endif %} {{- '\n</tool_response>' }} {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} {{- '<\|im_end\|>\n' }} {%- endif %} {%- endif %} {%- endfor %} {%- if add_generation_prompt %} {{- '<\|im_start\|>assistant\n' }} {%- if enable_thinking is defined %} {%- if enable_thinking is false %} {{- '<think>\n\n</think>\n\n' }} {%- elif enable_thinking is true %} {{- '<think>\n' }} {%- endif %} {%- endif %} {%- endif %} " />
	<clean_up_tokenization_spaces />
	<detokenizer_input_type value="i64" />
	<eos_token_id value="1" />
	<handle_special_tokens_with_re />
	<max_length />
	<number_of_inputs value="1" />
	<openvino_tokenizers_version value="2026.3.0.0-683-6d28e696dfa" />
	<openvino_version value="2026.3.0-22098-367f60d8408" />
	<original_post_processor_template value="{"type": "TemplateProcessing", "single": [{"SpecialToken": {"id": "<s>", "type_id": 0}}, {"Sequence": {"id": "A", "type_id": 0}}], "pair": [{"SpecialToken": {"id": "<s>", "type_id": 0}}, {"Sequence": {"id": "A", "type_id": 0}}, {"SpecialToken": {"id": "<s>", "type_id": 1}}, {"Sequence": {"id": "B", "type_id": 1}}], "special_tokens": {"<s>": {"id": "<s>", "ids": [0], "tokens": ["<s>"]}}}" />
	<original_tokenizer_class value="<class 'transformers.tokenization_utils_fast.PreTrainedTokenizerFast'>" />
	<pad_token_id value="1" />
	<processed_post_processor_template value="{"single": {"ids": [0, -1], "type_ids": [0, 0]}, "pair": {"ids": [0, -1, 0, -2], "type_ids": [0, 0, 1, 1]}}" />
	<skip_special_tokens value="True" />
	<streaming_detokenizer value="False" />
	<tiktoken_version value="0.13.0" />
	<tokenizer_output_type value="i64" />
	<tokenizers_version value="0.23.0rc0" />
	<transformers_version value="4.57.6" />
	<use_max_padding value="False" />
	<use_sentencepiece_backend value="False" />
	<utf8_replace_mode value="replace" />
	<with_detokenizer value="True" />
	</rt_info>
	</net>