gemma-3-4b-it-qat-int4_asym-ov / openvino_detokenizer.xml
Echo9Zulu's picture
Upload 21 files
88cc288 verified
<?xml version="1.0"?>
<net name="detokenizer" version="11">
<layers>
<layer id="0" name="Parameter_2236332" type="Parameter" version="opset1">
<data shape="?,?" element_type="i64" />
<output>
<port id="0" precision="I64" names="Parameter_2236332">
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="1" name="Convert_2236502" 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_2236287" type="Const" version="opset1">
<data element_type="i32" shape="262145" offset="0" size="1048580" />
<output>
<port id="0" precision="I32">
<dim>262145</dim>
</port>
</output>
</layer>
<layer id="3" name="Constant_2236289" type="Const" version="opset1">
<data element_type="i32" shape="262145" offset="1048580" size="1048580" />
<output>
<port id="0" precision="I32">
<dim>262145</dim>
</port>
</output>
</layer>
<layer id="4" name="Constant_2236291" type="Const" version="opset1">
<data element_type="u8" shape="2316374" offset="2097160" size="2316374" />
<output>
<port id="0" precision="U8">
<dim>2316374</dim>
</port>
</output>
</layer>
<layer id="5" name="Slice_2236337" type="Const" version="opset1">
<data element_type="i32" shape="9" offset="4413534" size="36" />
<output>
<port id="0" precision="I32">
<dim>9</dim>
</port>
</output>
</layer>
<layer id="6" name="VocabDecoder_2236339" 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>262145</dim>
</port>
<port id="2" precision="I32">
<dim>262145</dim>
</port>
<port id="3" precision="U8">
<dim>2316374</dim>
</port>
<port id="4" precision="I32">
<dim>9</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="Constant_2236341" type="Const" version="opset1">
<data element_type="u8" shape="3" offset="4413570" size="3" />
<output>
<port id="0" precision="U8">
<dim>3</dim>
</port>
</output>
</layer>
<layer id="8" name="Constant_2236343" type="Const" version="opset1">
<data element_type="u8" shape="1" offset="4413573" size="1" />
<output>
<port id="0" precision="U8">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="9" name="RegexNormalization_2236344" 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>3</dim>
</port>
<port id="4" precision="U8">
<dim>1</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="10" name="ByteFallback_2236345" type="ByteFallback" 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="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="11" name="FuzeRagged_2236346" 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="12" name="UTF8Validate_2236347" 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="13" name="StringTensorPack_2236348" 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_2236349,string_output">
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="14" name="Result_2236349" type="Result" version="opset1" output_names="Result_2236349,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="7" to-layer="9" to-port="0" />
<edge from-layer="6" from-port="8" to-layer="9" to-port="1" />
<edge from-layer="6" from-port="9" to-layer="9" to-port="2" />
<edge from-layer="6" from-port="6" to-layer="11" to-port="1" />
<edge from-layer="6" from-port="5" to-layer="11" to-port="0" />
<edge from-layer="7" from-port="0" to-layer="9" to-port="3" />
<edge from-layer="8" from-port="0" to-layer="9" to-port="4" />
<edge from-layer="9" from-port="6" to-layer="10" to-port="1" />
<edge from-layer="9" from-port="7" to-layer="10" to-port="2" />
<edge from-layer="9" from-port="5" to-layer="10" to-port="0" />
<edge from-layer="10" from-port="3" to-layer="11" to-port="2" />
<edge from-layer="10" from-port="4" to-layer="11" to-port="3" />
<edge from-layer="10" from-port="5" to-layer="12" to-port="2" />
<edge from-layer="11" from-port="4" to-layer="12" to-port="0" />
<edge from-layer="11" from-port="5" to-layer="12" to-port="1" />
<edge from-layer="12" from-port="3" to-layer="13" to-port="0" />
<edge from-layer="12" from-port="4" to-layer="13" to-port="1" />
<edge from-layer="12" from-port="5" to-layer="13" to-port="2" />
<edge from-layer="13" from-port="3" to-layer="14" to-port="0" />
</edges>
<rt_info>
<add_attention_mask value="True" />
<add_prefix_space />
<add_special_tokens value="True" />
<bos_token_id value="2" />
<chat_template value="{{ bos_token }}&#10;{%- if messages[0]['role'] == 'system' -%}&#10; {%- if messages[0]['content'] is string -%}&#10; {%- set first_user_prefix = messages[0]['content'] + '&#10;&#10;' -%}&#10; {%- else -%}&#10; {%- set first_user_prefix = messages[0]['content'][0]['text'] + '&#10;&#10;' -%}&#10; {%- endif -%}&#10; {%- set loop_messages = messages[1:] -%}&#10;{%- else -%}&#10; {%- set first_user_prefix = &quot;&quot; -%}&#10; {%- set loop_messages = messages -%}&#10;{%- endif -%}&#10;{%- for message in loop_messages -%}&#10; {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}&#10; {{ raise_exception(&quot;Conversation roles must alternate user/assistant/user/assistant/...&quot;) }}&#10; {%- endif -%}&#10; {%- if (message['role'] == 'assistant') -%}&#10; {%- set role = &quot;model&quot; -%}&#10; {%- else -%}&#10; {%- set role = message['role'] -%}&#10; {%- endif -%}&#10; {{ '&lt;start_of_turn>' + role + '&#10;' + (first_user_prefix if loop.first else &quot;&quot;) }}&#10; {%- if message['content'] is string -%}&#10; {{ message['content'] | trim }}&#10; {%- elif message['content'] is iterable -%}&#10; {%- for item in message['content'] -%}&#10; {%- if item['type'] == 'image' -%}&#10; {{ '&lt;start_of_image>' }}&#10; {%- elif item['type'] == 'text' -%}&#10; {{ item['text'] | trim }}&#10; {%- endif -%}&#10; {%- endfor -%}&#10; {%- else -%}&#10; {{ raise_exception(&quot;Invalid content type&quot;) }}&#10; {%- endif -%}&#10; {{ '&lt;end_of_turn>&#10;' }}&#10;{%- endfor -%}&#10;{%- if add_generation_prompt -%}&#10; {{'&lt;start_of_turn>model&#10;'}}&#10;{%- endif -%}&#10;" />
<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="2025.1.0.0-523-710ddf14de8" />
<openvino_version value="2025.1.0-18503-6fec06580ab-releases/2025/1" />
<original_post_processor_template value="{&quot;type&quot;: &quot;TemplateProcessing&quot;, &quot;single&quot;: [{&quot;SpecialToken&quot;: {&quot;id&quot;: &quot;&lt;bos>&quot;, &quot;type_id&quot;: 0}}, {&quot;Sequence&quot;: {&quot;id&quot;: &quot;A&quot;, &quot;type_id&quot;: 0}}], &quot;pair&quot;: [{&quot;SpecialToken&quot;: {&quot;id&quot;: &quot;&lt;bos>&quot;, &quot;type_id&quot;: 0}}, {&quot;Sequence&quot;: {&quot;id&quot;: &quot;A&quot;, &quot;type_id&quot;: 0}}, {&quot;SpecialToken&quot;: {&quot;id&quot;: &quot;&lt;bos>&quot;, &quot;type_id&quot;: 1}}, {&quot;Sequence&quot;: {&quot;id&quot;: &quot;B&quot;, &quot;type_id&quot;: 1}}], &quot;special_tokens&quot;: {&quot;&lt;bos>&quot;: {&quot;id&quot;: &quot;&lt;bos>&quot;, &quot;ids&quot;: [2], &quot;tokens&quot;: [&quot;&lt;bos>&quot;]}}}" />
<original_tokenizer_class value="&lt;class 'transformers.models.gemma.tokenization_gemma_fast.GemmaTokenizerFast'>" />
<pad_token_id value="0" />
<processed_post_processor_template value="{&quot;single&quot;: {&quot;ids&quot;: [2, -1], &quot;type_ids&quot;: [0, 0]}, &quot;pair&quot;: {&quot;ids&quot;: [2, -1, 2, -2], &quot;type_ids&quot;: [0, 0, 1, 1]}}" />
<sentencepiece_version value="0.2.0" />
<skip_special_tokens value="True" />
<streaming_detokenizer value="False" />
<tiktoken_version value="0.7.0" />
<tokenizer_output_type value="i64" />
<tokenizers_version value="0.21.1" />
<transformers_version value="4.50.2" />
<use_max_padding value="False" />
<use_sentencepiece_backend value="False" />
<utf8_replace_mode value="replace" />
<with_detokenizer value="True" />
</rt_info>
</net>