|
|
<?xml version="1.0"?> |
|
|
<net name="detokenizer" version="11"> |
|
|
<layers> |
|
|
<layer id="0" name="Parameter_246879" type="Parameter" version="opset1"> |
|
|
<data shape="?,?" element_type="i64" /> |
|
|
<output> |
|
|
<port id="0" precision="I64" names="Parameter_246879"> |
|
|
<dim>-1</dim> |
|
|
<dim>-1</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="1" name="Convert_247074" 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_246881" type="Const" version="opset1"> |
|
|
<data element_type="i32" shape="128256" offset="0" size="513024" /> |
|
|
<output> |
|
|
<port id="0" precision="I32"> |
|
|
<dim>128256</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="3" name="Constant_246883" type="Const" version="opset1"> |
|
|
<data element_type="i32" shape="128256" offset="513024" size="513024" /> |
|
|
<output> |
|
|
<port id="0" precision="I32"> |
|
|
<dim>128256</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="4" name="Constant_246885" type="Const" version="opset1"> |
|
|
<data element_type="u8" shape="838669" offset="1026048" size="838669" /> |
|
|
<output> |
|
|
<port id="0" precision="U8"> |
|
|
<dim>838669</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="5" name="Slice_246890" type="Const" version="opset1"> |
|
|
<data element_type="i32" shape="250" offset="1864717" size="1000" /> |
|
|
<output> |
|
|
<port id="0" precision="I32"> |
|
|
<dim>250</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="6" name="VocabDecoder_246892" 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>128256</dim> |
|
|
</port> |
|
|
<port id="2" precision="I32"> |
|
|
<dim>128256</dim> |
|
|
</port> |
|
|
<port id="3" precision="U8"> |
|
|
<dim>838669</dim> |
|
|
</port> |
|
|
<port id="4" precision="I32"> |
|
|
<dim>250</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_246893" 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_246894" 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="Constant_246896" type="Const" version="opset1"> |
|
|
<data element_type="u8" shape="51" offset="1865717" size="51" /> |
|
|
<output> |
|
|
<port id="0" precision="U8"> |
|
|
<dim>51</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="10" name="Constant_246898" type="Const" version="opset1"> |
|
|
<data element_type="u8" shape="2" offset="1865768" size="2" /> |
|
|
<output> |
|
|
<port id="0" precision="U8"> |
|
|
<dim>2</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="11" name="RegexNormalization_246899" type="RegexNormalization" version="extension"> |
|
|
<data global_replace="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> |
|
|
<port id="3" precision="U8"> |
|
|
<dim>51</dim> |
|
|
</port> |
|
|
<port id="4" precision="U8"> |
|
|
<dim>2</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="U8"> |
|
|
<dim>-1</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="12" name="StringTensorPack_246900" 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_246901,string_output"> |
|
|
<dim>-1</dim> |
|
|
</port> |
|
|
</output> |
|
|
</layer> |
|
|
<layer id="13" name="Result_246901" type="Result" version="opset1" output_names="Result_246901,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="5" to-layer="8" to-port="1" /> |
|
|
<edge from-layer="7" from-port="4" to-layer="8" to-port="0" /> |
|
|
<edge from-layer="8" from-port="3" to-layer="11" to-port="0" /> |
|
|
<edge from-layer="8" from-port="4" to-layer="11" to-port="1" /> |
|
|
<edge from-layer="8" from-port="5" to-layer="11" to-port="2" /> |
|
|
<edge from-layer="9" from-port="0" to-layer="11" to-port="3" /> |
|
|
<edge from-layer="10" from-port="0" to-layer="11" to-port="4" /> |
|
|
<edge from-layer="11" from-port="5" to-layer="12" to-port="0" /> |
|
|
<edge from-layer="11" from-port="6" to-layer="12" to-port="1" /> |
|
|
<edge from-layer="11" from-port="7" to-layer="12" to-port="2" /> |
|
|
<edge from-layer="12" from-port="3" to-layer="13" to-port="0" /> |
|
|
</edges> |
|
|
<rt_info> |
|
|
<add_attention_mask value="True" /> |
|
|
<add_prefix_space /> |
|
|
<add_special_tokens value="True" /> |
|
|
<bos_token_id value="128000" /> |
|
|
<chat_template value="{%- set thinking_prompt = 'You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </think> tags, and then provide your solution or response to the problem.' %} {%- set standard_prompt = 'You are Hermes, created by Nous Research.' %} {%- if not thinking is defined %}{% set thinking = false %}{% endif %} {%- if not keep_cots is defined %}{% set keep_cots = false %}{% endif %} {%- if thinking %}{%- set system_prompt = thinking_prompt %}{%- else %}{%- set system_prompt = standard_prompt %}{%- endif %} {%- if tools %} {{- bos_token + '<|start_header_id|>system<|end_header_id|>\n' }} {%- if messages[0]['role'] == 'system' %} {{- messages[0]['content'] }} {%- else %} {{- system_prompt }} {%- endif %} {{- "\n\n# Tools\n\nYou are a function calling AI model. You 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>" }} {%- for tool in tools %} {{- "\n" }} {{- tool | tojson }} {%- endfor %} {{- "\n</tools>\n\nFor 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><|eot_id|>" }} {%- else %} {%- if messages[0]['role'] == 'system' %} {{- bos_token + '<|start_header_id|>system<|end_header_id|>\n\n' + messages[0]['content'] + '<|eot_id|>' }} {%- else %} {{- bos_token + '<|start_header_id|>system<|end_header_id|>\n\n' + system_prompt + '<|eot_id|>' }} {%- endif %} {%- endif %} {%- for message in messages %} {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} {{- '<|start_header_id|>' + message.role + '<|end_header_id|>\n\n' + message.content + '<|eot_id|>' }} {%- elif (message.role == "assistant" and not message.tool_calls) %} {{- '<|start_header_id|>' + message.role + '<|end_header_id|>\n' }} {%- if message.content %} {%- set content = message['content'] -%} {%- if thinking %} {%- if not keep_cots %} {%- set content = '<think> </think>' + content.split('</think>', 1)[1] -%} {%- endif %} {%- endif %} {{- '\n' + content + '<|eot_id|>' }} {%- endif %} {%- elif message.role == "assistant" %} {{- '<|start_header_id|>' + message.role + '<|end_header_id|>\n' }} {%- if message.content %} {%- set content = message['content'] -%} {%- if thinking %} {%- if not keep_cots %} {%- set content = '<think> </think>' + content.split('</think>', 1)[1] -%} {%- endif %} {%- endif %} {{- '\n' + content }} {%- endif %} {%- for tool_call in message.tool_calls %} {%- if tool_call.function is defined %} {%- set tool_call = tool_call.function %} {%- endif %} {{- '\n<tool_call>\n{"name": "' }} {{- tool_call.name }} {{- '", "arguments": ' }} {{- tool_call.arguments | tojson }} {{- '}\n</tool_call>' }} {%- endfor %} {{- '<|eot_id|>' }} {%- elif message.role == "tool" %} {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %} {{- '<|start_header_id|>user<|end_header_id|>\n' }} {%- endif %} {{- '\n<tool_response>\n' }} {{- message.content }} {{- '\n</tool_response>' }} {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} {{- '<|eot_id|>' }} {%- endif %} {%- endif %} {%- endfor %} {%- if add_generation_prompt %} {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }} {%- endif %} " /> |
|
|
<clean_up_tokenization_spaces /> |
|
|
<detokenizer_input_type value="i64" /> |
|
|
<eos_token_id value="128009" /> |
|
|
<handle_special_tokens_with_re /> |
|
|
<max_length /> |
|
|
<number_of_inputs value="1" /> |
|
|
<openvino_tokenizers_version value="2025.2.0.1-567-7885335c24b" /> |
|
|
<openvino_version value="2025.2.0-19140-c01cd93e24d-releases/2025/2" /> |
|
|
<original_post_processor_template value="{"type": "Sequence", "processors": [{"type": "ByteLevel", "add_prefix_space": true, "trim_offsets": false, "use_regex": true}, {"type": "TemplateProcessing", "single": [{"SpecialToken": {"id": "<|begin_of_text|>", "type_id": 0}}, {"Sequence": {"id": "A", "type_id": 0}}], "pair": [{"SpecialToken": {"id": "<|begin_of_text|>", "type_id": 0}}, {"Sequence": {"id": "A", "type_id": 0}}, {"SpecialToken": {"id": "<|begin_of_text|>", "type_id": 1}}, {"Sequence": {"id": "B", "type_id": 1}}], "special_tokens": {"<|begin_of_text|>": {"id": "<|begin_of_text|>", "ids": [128000], "tokens": ["<|begin_of_text|>"]}}}]}" /> |
|
|
<original_tokenizer_class value="<class 'transformers.tokenization_utils_fast.PreTrainedTokenizerFast'>" /> |
|
|
<pad_token_id value="128001" /> |
|
|
<processed_post_processor_template value="{"single": {"ids": [128000, -1], "type_ids": [0, 0]}, "pair": {"ids": [128000, -1, 128000, -2], "type_ids": [0, 0, 1, 1]}}" /> |
|
|
<sentencepiece_version value="0.2.0" /> |
|
|
<skip_special_tokens value="True" /> |
|
|
<streaming_detokenizer value="False" /> |
|
|
<tokenizer_output_type value="i64" /> |
|
|
<tokenizers_version value="0.21.1" /> |
|
|
<transformers_version value="4.51.3" /> |
|
|
<use_max_padding value="False" /> |
|
|
<use_sentencepiece_backend value="False" /> |
|
|
<utf8_replace_mode value="replace" /> |
|
|
<with_detokenizer value="True" /> |
|
|
</rt_info> |
|
|
</net> |
|
|
|