Phi-4-ov-int4 / openvino_tokenizer.xml
lokinfey's picture
Upload 12 files
70a8ef4 verified
<?xml version="1.0"?>
<net name="tokenizer" version="11">
<layers>
<layer id="0" name="Parameter_180186" type="Parameter" version="opset1">
<data shape="?" element_type="string" />
<output>
<port id="0" precision="STRING" names="Parameter_180186">
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="1" name="Constant_180192" 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="StringTensorUnpack_180187" 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="3" name="ShapeOf_180188" 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="4" name="Constant_180189" type="Const" version="opset1">
<data element_type="i32" shape="" offset="0" size="4" />
<output>
<port id="0" precision="I32" />
</output>
</layer>
<layer id="5" name="Constant_180190" type="Const" version="opset1">
<data element_type="i32" shape="" offset="0" size="4" />
<output>
<port id="0" precision="I32" />
</output>
</layer>
<layer id="6" name="Gather_180191" type="Gather" version="opset8">
<data batch_dims="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I32" />
<port id="2" precision="I32" />
</input>
<output>
<port id="3" precision="I64" />
</output>
</layer>
<layer id="7" name="Constant_180193" type="Const" version="opset1">
<data element_type="i32" shape="" offset="4" size="4" />
<output>
<port id="0" precision="I32" />
</output>
</layer>
<layer id="8" name="Range_180194" type="Range" version="opset4">
<data output_type="i32" />
<input>
<port id="0" precision="I32" />
<port id="1" precision="I64" />
<port id="2" precision="I32" />
</input>
<output>
<port id="3" precision="I32">
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="9" name="Constant_180195" type="Const" version="opset1">
<data element_type="i32" shape="" offset="4" size="4" />
<output>
<port id="0" precision="I32" />
</output>
</layer>
<layer id="10" name="Constant_180196" type="Const" version="opset1">
<data element_type="i64" shape="" offset="8" size="8" />
<output>
<port id="0" precision="I64" />
</output>
</layer>
<layer id="11" name="Add_180197" 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="12" name="Constant_180198" type="Const" version="opset1">
<data element_type="i32" shape="" offset="4" size="4" />
<output>
<port id="0" precision="I32" />
</output>
</layer>
<layer id="13" name="Range_180199" type="Range" version="opset4">
<data output_type="i32" />
<input>
<port id="0" precision="I32" />
<port id="1" precision="I64" />
<port id="2" precision="I32" />
</input>
<output>
<port id="3" precision="I32">
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="14" name="Constant_180261" type="Const" version="opset1">
<data element_type="u8" shape="3163" offset="16" size="3163" />
<output>
<port id="0" precision="U8">
<dim>3163</dim>
</port>
</output>
</layer>
<layer id="15" name="SpecialTokensSplit_180262" 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>3163</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="16" name="Constant_180264" type="Const" version="opset1">
<data element_type="u8" shape="115" offset="3179" size="115" />
<output>
<port id="0" precision="U8">
<dim>115</dim>
</port>
</output>
</layer>
<layer id="17" name="RegexSplit_180265" type="RegexSplit" version="extension">
<data behaviour="remove" invert="true" max_splits="-1" />
<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="BOOL">
<dim>-1</dim>
</port>
<port id="6" precision="U8">
<dim>115</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="U8">
<dim>-1</dim>
</port>
<port id="12" precision="BOOL">
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="18" name="Constant_180267" type="Const" version="opset1">
<data element_type="u8" shape="1046586" offset="3294" size="1046586" />
<output>
<port id="0" precision="U8">
<dim>1046586</dim>
</port>
</output>
</layer>
<layer id="19" name="StringTensorUnpack_180268" type="StringTensorUnpack" version="extension">
<data mode="begins_ends" />
<input>
<port id="0" precision="U8">
<dim>1046586</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="20" name="Constant_180273" type="Const" version="opset1">
<data element_type="u8" shape="709852" offset="1049880" size="709852" />
<output>
<port id="0" precision="U8">
<dim>709852</dim>
</port>
</output>
</layer>
<layer id="21" name="StringTensorUnpack_180274" type="StringTensorUnpack" version="extension">
<data mode="begins_ends" />
<input>
<port id="0" precision="U8">
<dim>709852</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="22" name="Constant_180276" type="Const" version="opset1">
<data element_type="u8" shape="733738" offset="1759732" size="733738" />
<output>
<port id="0" precision="U8">
<dim>733738</dim>
</port>
</output>
</layer>
<layer id="23" name="StringTensorUnpack_180277" type="StringTensorUnpack" version="extension">
<data mode="begins_ends" />
<input>
<port id="0" precision="U8">
<dim>733738</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_180270" type="Const" version="opset1">
<data element_type="u8" shape="73372" offset="2493470" size="73372" />
<output>
<port id="0" precision="U8">
<dim>73372</dim>
</port>
</output>
</layer>
<layer id="25" name="StringTensorUnpack_180271" type="StringTensorUnpack" version="extension">
<data mode="begins_ends" />
<input>
<port id="0" precision="U8">
<dim>73372</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_180278" type="Const" version="opset1">
<data element_type="i32" shape="4128" offset="2566842" size="16512" />
<output>
<port id="0" precision="I32">
<dim>4128</dim>
</port>
</output>
</layer>
<layer id="27" name="BPETokenizer_180279" type="BPETokenizer" version="extension">
<data unk_token="" fuse_unk="false" suffix_indicator="" end_suffix="" byte_fallback="false" cache_capacity="20070" />
<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>4128</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="28" name="Subtract_180280" 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="29" name="Constant_180281" type="Const" version="opset1">
<data element_type="i32" shape="" offset="2583354" size="4" />
<output>
<port id="0" precision="I32" />
</output>
</layer>
<layer id="30" name="Minimum_180282" 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="31" name="Subtract_180283" 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="32" name="Subtract_180284" 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_180285" type="Const" version="opset1">
<data element_type="i32" shape="" offset="0" size="4" />
<output>
<port id="0" precision="I32" />
</output>
</layer>
<layer id="34" name="ReduceMax_180286" 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="35" name="Constant_180287" type="Const" version="opset1">
<data element_type="i32" shape="" offset="2583358" size="4" />
<output>
<port id="0" precision="I32" />
</output>
</layer>
<layer id="36" name="RaggedToDense_180288" 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="37" name="Convert_180289" 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="38" name="Convert_180289" 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="40" name="RaggedToDense_180288.0" 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="41" name="Result_180290" type="Result" version="opset1">
<input>
<port id="0" precision="I64">
<dim>-1</dim>
<dim>-1</dim>
</port>
</input>
</layer>
<layer id="39" name="Result_180291" 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="2" to-port="0" />
<edge from-layer="1" from-port="0" to-layer="8" to-port="0" />
<edge from-layer="2" from-port="1" to-layer="3" to-port="0" />
<edge from-layer="2" from-port="2" to-layer="15" to-port="3" />
<edge from-layer="2" from-port="1" to-layer="15" to-port="2" />
<edge from-layer="2" from-port="3" to-layer="15" to-port="4" />
<edge from-layer="3" from-port="1" to-layer="6" to-port="0" />
<edge from-layer="4" from-port="0" to-layer="6" to-port="1" />
<edge from-layer="5" from-port="0" to-layer="6" to-port="2" />
<edge from-layer="6" from-port="3" to-layer="8" to-port="1" />
<edge from-layer="6" from-port="3" to-layer="11" to-port="0" />
<edge from-layer="7" from-port="0" to-layer="8" to-port="2" />
<edge from-layer="8" from-port="3" to-layer="15" to-port="0" />
<edge from-layer="9" from-port="0" to-layer="13" to-port="0" />
<edge from-layer="10" from-port="0" to-layer="11" to-port="1" />
<edge from-layer="11" from-port="2" to-layer="13" to-port="1" />
<edge from-layer="12" from-port="0" to-layer="13" to-port="2" />
<edge from-layer="13" from-port="3" to-layer="15" to-port="1" />
<edge from-layer="14" from-port="0" to-layer="15" to-port="5" />
<edge from-layer="15" from-port="6" to-layer="17" to-port="0" />
<edge from-layer="15" from-port="7" to-layer="17" to-port="1" />
<edge from-layer="15" from-port="8" to-layer="17" to-port="2" />
<edge from-layer="15" from-port="9" to-layer="17" to-port="3" />
<edge from-layer="15" from-port="10" to-layer="17" to-port="4" />
<edge from-layer="15" from-port="11" to-layer="17" to-port="5" />
<edge from-layer="16" from-port="0" to-layer="17" to-port="6" />
<edge from-layer="17" from-port="11" to-layer="27" to-port="4" />
<edge from-layer="17" from-port="8" to-layer="27" to-port="1" />
<edge from-layer="17" from-port="9" to-layer="27" to-port="2" />
<edge from-layer="17" from-port="10" to-layer="27" to-port="3" />
<edge from-layer="17" from-port="7" to-layer="27" to-port="0" />
<edge from-layer="18" from-port="0" to-layer="19" to-port="0" />
<edge from-layer="19" from-port="1" to-layer="27" to-port="5" />
<edge from-layer="19" from-port="2" to-layer="27" to-port="6" />
<edge from-layer="19" from-port="3" to-layer="27" to-port="7" />
<edge from-layer="20" from-port="0" to-layer="21" to-port="0" />
<edge from-layer="21" from-port="1" to-layer="27" to-port="8" />
<edge from-layer="21" from-port="2" to-layer="27" to-port="9" />
<edge from-layer="21" from-port="3" to-layer="27" to-port="10" />
<edge from-layer="22" from-port="0" to-layer="23" to-port="0" />
<edge from-layer="23" from-port="1" to-layer="27" to-port="11" />
<edge from-layer="23" from-port="2" to-layer="27" to-port="12" />
<edge from-layer="23" from-port="3" to-layer="27" to-port="13" />
<edge from-layer="24" from-port="0" to-layer="25" to-port="0" />
<edge from-layer="25" from-port="1" to-layer="27" to-port="14" />
<edge from-layer="25" from-port="2" to-layer="27" to-port="15" />
<edge from-layer="25" from-port="3" to-layer="27" to-port="16" />
<edge from-layer="26" from-port="0" to-layer="27" to-port="17" />
<edge from-layer="27" from-port="19" to-layer="28" to-port="0" />
<edge from-layer="27" from-port="18" to-layer="28" to-port="1" />
<edge from-layer="27" from-port="19" to-layer="36" to-port="1" />
<edge from-layer="27" from-port="19" to-layer="31" to-port="0" />
<edge from-layer="27" from-port="19" to-layer="32" to-port="0" />
<edge from-layer="27" from-port="20" to-layer="36" to-port="2" />
<edge from-layer="28" from-port="2" to-layer="30" to-port="0" />
<edge from-layer="29" from-port="0" to-layer="30" to-port="1" />
<edge from-layer="30" from-port="2" to-layer="31" to-port="1" />
<edge from-layer="31" from-port="2" to-layer="32" to-port="1" />
<edge from-layer="31" from-port="2" to-layer="36" 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="36" to-port="3" />
<edge from-layer="35" from-port="0" to-layer="36" to-port="4" />
<edge from-layer="36" from-port="6" to-layer="37" to-port="0" />
<edge from-layer="36" from-port="5" to-layer="40" to-port="0" />
<edge from-layer="37" from-port="1" to-layer="38" to-port="0" />
<edge from-layer="38" from-port="1" to-layer="39" to-port="0" />
<edge from-layer="40" from-port="1" to-layer="41" to-port="0" />
</edges>
<rt_info>
<add_attention_mask value="True" />
<add_prefix_space />
<add_special_tokens value="True" />
<bos_token_id value="100257" />
<chat_template value="{% for message in messages %}{% if (message['role'] == 'system') %}{{'&lt;|im_start|>system&lt;|im_sep|>' + message['content'] + '&lt;|im_end|>'}}{% elif (message['role'] == 'user') %}{{'&lt;|im_start|>user&lt;|im_sep|>' + message['content'] + '&lt;|im_end|>&lt;|im_start|>assistant&lt;|im_sep|>'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '&lt;|im_end|>'}}{% endif %}{% endfor %}" />
<clean_up_tokenization_spaces />
<detokenizer_input_type value="i64" />
<eos_token_id value="100257" />
<handle_special_tokens_with_re />
<number_of_inputs value="1" />
<openvino_tokenizers_version value="2024.5.0.0" />
<openvino_version value="2024.5.0" />
<original_tokenizer_class value="&lt;class 'transformers.models.gpt2.tokenization_gpt2_fast.GPT2TokenizerFast'>" />
<pad_token_id value="100257" />
<sentencepiece_version value="0.2.0" />
<skip_special_tokens value="True" />
<streaming_detokenizer value="False" />
<tokenizer_output_type value="i64" />
<tokenizers_version value="0.19.1" />
<transformers_version value="4.44.2" />
<use_max_padding value="False" />
<use_sentencepiece_backend value="False" />
<utf8_replace_mode />
<with_detokenizer value="True" />
</rt_info>
</net>