gemma-7b-it-int8-ov / openvino_tokenizer.xml
openvino-ci's picture
Upload folder using huggingface_hub
a6a2f49 verified
<?xml version="1.0"?>
<net name="tokenizer" version="11">
<layers>
<layer id="0" name="Parameter_62426" type="Parameter" version="opset1">
<data shape="?" element_type="string" />
<output>
<port id="0" precision="STRING" names="Parameter_62426">
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="1" name="Constant_62526" type="Const" version="opset1">
<data element_type="i32" shape="" offset="0" size="4" />
<output>
<port id="0" precision="I32" />
</output>
</layer>
<layer id="2" name="Constant_62527" type="Const" version="opset1">
<data element_type="i32" shape="" offset="4" size="4" />
<output>
<port id="0" precision="I32" />
</output>
</layer>
<layer id="3" name="Constant_62528" type="Const" version="opset1">
<data element_type="i32" shape="1" offset="8" size="4" />
<output>
<port id="0" precision="I32">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="4" name="Constant_62432" type="Const" version="opset1">
<data element_type="i64" shape="" offset="12" size="8" />
<output>
<port id="0" precision="I64" />
</output>
</layer>
<layer id="5" name="StringTensorUnpack_62427" type="StringTensorUnpack" version="extension">
<data mode="begins_ends" />
<input>
<port id="0" precision="STRING">
<dim>-1</dim>
</port>
</input>
<output>
<port id="1" precision="I32">
<dim>-1</dim>
</port>
<port id="2" precision="I32">
<dim>-1</dim>
</port>
<port id="3" precision="U8">
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="6" name="ShapeOf_62428" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I32">
<dim>-1</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="7" name="Constant_62429" type="Const" version="opset1">
<data element_type="i64" shape="" offset="12" size="8" />
<output>
<port id="0" precision="I64" />
</output>
</layer>
<layer id="8" name="Constant_62430" type="Const" version="opset1">
<data element_type="i64" shape="" offset="12" size="8" />
<output>
<port id="0" precision="I64" />
</output>
</layer>
<layer id="9" name="Gather_62431" type="Gather" version="opset8">
<data batch_dims="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64" />
<port id="2" precision="I64" />
</input>
<output>
<port id="3" precision="I64" />
</output>
</layer>
<layer id="10" name="Constant_62433" type="Const" version="opset1">
<data element_type="i64" shape="" offset="20" size="8" />
<output>
<port id="0" precision="I64" />
</output>
</layer>
<layer id="11" name="Range_62434" type="Range" version="opset4">
<data output_type="i32" />
<input>
<port id="0" precision="I64" />
<port id="1" precision="I64" />
<port id="2" precision="I64" />
</input>
<output>
<port id="3" precision="I32">
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="12" name="Constant_62435" type="Const" version="opset1">
<data element_type="i64" shape="" offset="20" size="8" />
<output>
<port id="0" precision="I64" />
</output>
</layer>
<layer id="13" name="Constant_62436" type="Const" version="opset1">
<data element_type="i64" shape="" offset="20" size="8" />
<output>
<port id="0" precision="I64" />
</output>
</layer>
<layer id="14" name="Add_62437" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64" />
<port id="1" precision="I64" />
</input>
<output>
<port id="2" precision="I64" />
</output>
</layer>
<layer id="15" name="Constant_62438" type="Const" version="opset1">
<data element_type="i64" shape="" offset="20" size="8" />
<output>
<port id="0" precision="I64" />
</output>
</layer>
<layer id="16" name="Range_62439" type="Range" version="opset4">
<data output_type="i32" />
<input>
<port id="0" precision="I64" />
<port id="1" precision="I64" />
<port id="2" precision="I64" />
</input>
<output>
<port id="3" precision="I32">
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="17" name="Constant_62501" type="Const" version="opset1">
<data element_type="u8" shape="5282" offset="28" size="5282" />
<output>
<port id="0" precision="U8">
<dim>5282</dim>
</port>
</output>
</layer>
<layer id="18" name="SpecialTokensSplit_62502" type="SpecialTokensSplit" 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>
<port id="4" precision="U8">
<dim>-1</dim>
</port>
<port id="5" precision="U8">
<dim>5282</dim>
</port>
</input>
<output>
<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="I32">
<dim>-1</dim>
</port>
<port id="10" precision="U8">
<dim>-1</dim>
</port>
<port id="11" precision="BOOL">
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="19" name="Constant_62504" type="Const" version="opset1">
<data element_type="u8" shape="1" offset="5310" size="1" />
<output>
<port id="0" precision="U8">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="20" name="Constant_62506" type="Const" version="opset1">
<data element_type="u8" shape="3" offset="5311" size="3" />
<output>
<port id="0" precision="U8">
<dim>3</dim>
</port>
</output>
</layer>
<layer id="21" name="RegexNormalization_62507" 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="BOOL">
<dim>-1</dim>
</port>
<port id="4" precision="U8">
<dim>1</dim>
</port>
<port id="5" precision="U8">
<dim>3</dim>
</port>
</input>
<output>
<port id="6" precision="I32">
<dim>-1</dim>
</port>
<port id="7" precision="I32">
<dim>-1</dim>
</port>
<port id="8" precision="U8">
<dim>-1</dim>
</port>
<port id="9" precision="BOOL">
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="22" name="Constant_62509" type="Const" version="opset1">
<data element_type="u8" shape="2955910" offset="5314" size="2955910" />
<output>
<port id="0" precision="U8">
<dim>2955910</dim>
</port>
</output>
</layer>
<layer id="23" name="StringTensorUnpack_62510" type="StringTensorUnpack" version="extension">
<data mode="begins_ends" />
<input>
<port id="0" precision="U8">
<dim>2955910</dim>
</port>
</input>
<output>
<port id="1" precision="I32">
<dim>-1</dim>
</port>
<port id="2" precision="I32">
<dim>-1</dim>
</port>
<port id="3" precision="U8">
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="24" name="Constant_62515" type="Const" version="opset1">
<data element_type="u8" shape="5031736" offset="2961224" size="5031736" />
<output>
<port id="0" precision="U8">
<dim>5031736</dim>
</port>
</output>
</layer>
<layer id="25" name="StringTensorUnpack_62516" type="StringTensorUnpack" version="extension">
<data mode="begins_ends" />
<input>
<port id="0" precision="U8">
<dim>5031736</dim>
</port>
</input>
<output>
<port id="1" precision="I32">
<dim>-1</dim>
</port>
<port id="2" precision="I32">
<dim>-1</dim>
</port>
<port id="3" precision="U8">
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="26" name="Constant_62518" type="Const" version="opset1">
<data element_type="u8" shape="4245743" offset="7992960" size="4245743" />
<output>
<port id="0" precision="U8">
<dim>4245743</dim>
</port>
</output>
</layer>
<layer id="27" name="StringTensorUnpack_62519" type="StringTensorUnpack" version="extension">
<data mode="begins_ends" />
<input>
<port id="0" precision="U8">
<dim>4245743</dim>
</port>
</input>
<output>
<port id="1" precision="I32">
<dim>-1</dim>
</port>
<port id="2" precision="I32">
<dim>-1</dim>
</port>
<port id="3" precision="U8">
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="28" name="Constant_62512" type="Const" version="opset1">
<data element_type="u8" shape="4170" offset="12238703" size="4170" />
<output>
<port id="0" precision="U8">
<dim>4170</dim>
</port>
</output>
</layer>
<layer id="29" name="StringTensorUnpack_62513" type="StringTensorUnpack" version="extension">
<data mode="begins_ends" />
<input>
<port id="0" precision="U8">
<dim>4170</dim>
</port>
</input>
<output>
<port id="1" precision="I32">
<dim>-1</dim>
</port>
<port id="2" precision="I32">
<dim>-1</dim>
</port>
<port id="3" precision="U8">
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="30" name="Constant_62520" type="Const" version="opset1">
<data element_type="i32" shape="216" offset="12242873" size="864" />
<output>
<port id="0" precision="I32">
<dim>216</dim>
</port>
</output>
</layer>
<layer id="31" name="BPETokenizer_62521" type="BPETokenizer" version="extension">
<data unk_token="&lt;unk>" fuse_unk="true" suffix_indicator="" end_suffix="" byte_fallback="true" cache_capacity="51200" />
<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>
<port id="4" precision="U8">
<dim>-1</dim>
</port>
<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>
<port id="8" precision="I32">
<dim>-1</dim>
</port>
<port id="9" precision="I32">
<dim>-1</dim>
</port>
<port id="10" precision="U8">
<dim>-1</dim>
</port>
<port id="11" precision="I32">
<dim>-1</dim>
</port>
<port id="12" precision="I32">
<dim>-1</dim>
</port>
<port id="13" precision="U8">
<dim>-1</dim>
</port>
<port id="14" precision="I32">
<dim>-1</dim>
</port>
<port id="15" precision="I32">
<dim>-1</dim>
</port>
<port id="16" precision="U8">
<dim>-1</dim>
</port>
<port id="17" precision="I32">
<dim>216</dim>
</port>
</input>
<output>
<port id="18" precision="I32">
<dim>-1</dim>
</port>
<port id="19" precision="I32">
<dim>-1</dim>
</port>
<port id="20" precision="I32">
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="32" name="Subtract_62522" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I32">
<dim>-1</dim>
</port>
<port id="1" precision="I32">
<dim>-1</dim>
</port>
</input>
<output>
<port id="2" precision="I32">
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="33" name="Constant_62523" type="Const" version="opset1">
<data element_type="i32" shape="" offset="12243737" size="4" />
<output>
<port id="0" precision="I32" />
</output>
</layer>
<layer id="34" name="Minimum_62524" type="Minimum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I32">
<dim>-1</dim>
</port>
<port id="1" precision="I32" />
</input>
<output>
<port id="2" precision="I32">
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="35" name="Subtract_62525" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I32">
<dim>-1</dim>
</port>
<port id="1" precision="I32">
<dim>-1</dim>
</port>
</input>
<output>
<port id="2" precision="I32">
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="36" name="Constant_62529" type="Const" version="opset1">
<data element_type="i32" shape="2" offset="12" size="8" />
<output>
<port id="0" precision="I32">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="37" name="CombineSegments_62530" type="CombineSegments" version="extension">
<input>
<port id="0" precision="I32" />
<port id="1" precision="I32" />
<port id="2" precision="I32">
<dim>1</dim>
</port>
<port id="3" precision="I32">
<dim>-1</dim>
</port>
<port id="4" precision="I32">
<dim>-1</dim>
</port>
<port id="5" precision="I32">
<dim>-1</dim>
</port>
<port id="6" precision="I32">
<dim>2</dim>
</port>
</input>
<output>
<port id="7" precision="I32">
<dim>-1</dim>
</port>
<port id="8" precision="I32">
<dim>-1</dim>
</port>
<port id="9" precision="I32">
<dim>-1</dim>
</port>
<port id="10" precision="I32">
<dim>-1</dim>
</port>
<port id="11" precision="I32">
<dim>-1</dim>
</port>
<port id="12" precision="I32">
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="38" name="Subtract_62531" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I32">
<dim>-1</dim>
</port>
<port id="1" precision="I32">
<dim>-1</dim>
</port>
</input>
<output>
<port id="2" precision="I32">
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="39" name="Constant_62532" type="Const" version="opset1">
<data element_type="i32" shape="" offset="0" size="4" />
<output>
<port id="0" precision="I32" />
</output>
</layer>
<layer id="40" name="ReduceMax_62533" type="ReduceMax" version="opset1">
<data keep_dims="false" />
<input>
<port id="0" precision="I32">
<dim>-1</dim>
</port>
<port id="1" precision="I32" />
</input>
<output>
<port id="2" precision="I32" />
</output>
</layer>
<layer id="41" name="Constant_62534" type="Const" version="opset1">
<data element_type="i32" shape="" offset="0" size="4" />
<output>
<port id="0" precision="I32" />
</output>
</layer>
<layer id="42" name="RaggedToDense_62535" type="RaggedToDense" version="extension">
<data pad_right="false" />
<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" />
<port id="4" precision="I32" />
</input>
<output>
<port id="5" precision="I32">
<dim>-1</dim>
<dim>-1</dim>
</port>
<port id="6" precision="BOOL">
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="43" name="Convert_62536" type="Convert" version="opset1">
<data destination_type="i32" />
<input>
<port id="0" precision="BOOL">
<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="44" name="Convert_62536" type="Convert" version="opset1">
<data destination_type="i64" />
<input>
<port id="0" precision="I32">
<dim>-1</dim>
<dim>-1</dim>
</port>
</input>
<output>
<port id="1" precision="I64" names="attention_mask">
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="46" name="RaggedToDense_62535.0" type="Convert" version="opset1">
<data destination_type="i64" />
<input>
<port id="0" precision="I32">
<dim>-1</dim>
<dim>-1</dim>
</port>
</input>
<output>
<port id="1" precision="I64" names="input_ids">
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="47" name="Result_62539" type="Result" version="opset1">
<input>
<port id="0" precision="I64">
<dim>-1</dim>
<dim>-1</dim>
</port>
</input>
</layer>
<layer id="45" name="Result_62541" type="Result" version="opset1">
<input>
<port id="0" precision="I64">
<dim>-1</dim>
<dim>-1</dim>
</port>
</input>
</layer>
</layers>
<edges>
<edge from-layer="0" from-port="0" to-layer="5" to-port="0" />
<edge from-layer="1" from-port="0" to-layer="37" to-port="0" />
<edge from-layer="2" from-port="0" to-layer="37" to-port="1" />
<edge from-layer="3" from-port="0" to-layer="37" to-port="2" />
<edge from-layer="4" from-port="0" to-layer="11" to-port="0" />
<edge from-layer="5" from-port="1" to-layer="6" to-port="0" />
<edge from-layer="5" from-port="3" to-layer="18" to-port="4" />
<edge from-layer="5" from-port="2" to-layer="18" to-port="3" />
<edge from-layer="5" from-port="1" to-layer="18" to-port="2" />
<edge from-layer="6" from-port="1" to-layer="9" to-port="0" />
<edge from-layer="7" from-port="0" to-layer="9" to-port="1" />
<edge from-layer="8" from-port="0" to-layer="9" to-port="2" />
<edge from-layer="9" from-port="3" to-layer="14" to-port="0" />
<edge from-layer="9" from-port="3" to-layer="11" to-port="1" />
<edge from-layer="10" from-port="0" to-layer="11" to-port="2" />
<edge from-layer="11" from-port="3" to-layer="18" to-port="0" />
<edge from-layer="12" from-port="0" to-layer="16" to-port="0" />
<edge from-layer="13" from-port="0" to-layer="14" to-port="1" />
<edge from-layer="14" from-port="2" to-layer="16" to-port="1" />
<edge from-layer="15" from-port="0" to-layer="16" to-port="2" />
<edge from-layer="16" from-port="3" to-layer="18" to-port="1" />
<edge from-layer="17" from-port="0" to-layer="18" to-port="5" />
<edge from-layer="18" from-port="6" to-layer="31" to-port="0" />
<edge from-layer="18" from-port="7" to-layer="31" to-port="1" />
<edge from-layer="18" from-port="11" to-layer="21" to-port="3" />
<edge from-layer="18" from-port="10" to-layer="21" to-port="2" />
<edge from-layer="18" from-port="9" to-layer="21" to-port="1" />
<edge from-layer="18" from-port="8" to-layer="21" to-port="0" />
<edge from-layer="19" from-port="0" to-layer="21" to-port="4" />
<edge from-layer="20" from-port="0" to-layer="21" to-port="5" />
<edge from-layer="21" from-port="6" to-layer="31" to-port="2" />
<edge from-layer="21" from-port="7" to-layer="31" to-port="3" />
<edge from-layer="21" from-port="8" to-layer="31" to-port="4" />
<edge from-layer="22" from-port="0" to-layer="23" to-port="0" />
<edge from-layer="23" from-port="1" to-layer="31" to-port="5" />
<edge from-layer="23" from-port="2" to-layer="31" to-port="6" />
<edge from-layer="23" from-port="3" to-layer="31" to-port="7" />
<edge from-layer="24" from-port="0" to-layer="25" to-port="0" />
<edge from-layer="25" from-port="1" to-layer="31" to-port="8" />
<edge from-layer="25" from-port="3" to-layer="31" to-port="10" />
<edge from-layer="25" from-port="2" to-layer="31" to-port="9" />
<edge from-layer="26" from-port="0" to-layer="27" to-port="0" />
<edge from-layer="27" from-port="1" to-layer="31" to-port="11" />
<edge from-layer="27" from-port="2" to-layer="31" to-port="12" />
<edge from-layer="27" from-port="3" to-layer="31" to-port="13" />
<edge from-layer="28" from-port="0" to-layer="29" to-port="0" />
<edge from-layer="29" from-port="1" to-layer="31" to-port="14" />
<edge from-layer="29" from-port="2" to-layer="31" to-port="15" />
<edge from-layer="29" from-port="3" to-layer="31" to-port="16" />
<edge from-layer="30" from-port="0" to-layer="31" to-port="17" />
<edge from-layer="31" from-port="20" to-layer="37" to-port="5" />
<edge from-layer="31" from-port="19" to-layer="37" to-port="4" />
<edge from-layer="31" from-port="19" to-layer="35" to-port="0" />
<edge from-layer="31" from-port="18" to-layer="32" to-port="1" />
<edge from-layer="31" from-port="19" to-layer="32" to-port="0" />
<edge from-layer="32" from-port="2" to-layer="34" to-port="0" />
<edge from-layer="33" from-port="0" to-layer="34" to-port="1" />
<edge from-layer="34" from-port="2" to-layer="35" to-port="1" />
<edge from-layer="35" from-port="2" to-layer="37" to-port="3" />
<edge from-layer="36" from-port="0" to-layer="37" to-port="6" />
<edge from-layer="37" from-port="8" to-layer="38" to-port="0" />
<edge from-layer="37" from-port="7" to-layer="38" to-port="1" />
<edge from-layer="37" from-port="7" to-layer="42" to-port="0" />
<edge from-layer="37" from-port="8" to-layer="42" to-port="1" />
<edge from-layer="37" from-port="9" to-layer="42" to-port="2" />
<edge from-layer="38" from-port="2" to-layer="40" to-port="0" />
<edge from-layer="39" from-port="0" to-layer="40" to-port="1" />
<edge from-layer="40" from-port="2" to-layer="42" to-port="3" />
<edge from-layer="41" from-port="0" to-layer="42" to-port="4" />
<edge from-layer="42" from-port="6" to-layer="43" to-port="0" />
<edge from-layer="42" from-port="5" to-layer="46" to-port="0" />
<edge from-layer="43" from-port="1" to-layer="44" to-port="0" />
<edge from-layer="44" from-port="1" to-layer="45" to-port="0" />
<edge from-layer="46" from-port="1" to-layer="47" to-port="0" />
</edges>
<rt_info>
<bos_token_id value="2" />
<chat_template value="{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '&lt;start_of_turn>' + role + '&#10;' + message['content'] | trim + '&lt;end_of_turn>&#10;' }}{% endfor %}{% if add_generation_prompt %}{{'&lt;start_of_turn>model&#10;'}}{% endif %}" />
<eos_token_id value="1" />
<original_tokenizer_class value="&lt;class 'transformers.models.gemma.tokenization_gemma_fast.GemmaTokenizerFast'>" />
<pad_token_id value="0" />
</rt_info>
</net>