Phi-3.5-mini-instruct-ov-int8 / openvino_detokenizer.xml
helenai's picture
Upload folder using huggingface_hub
310d289 verified
<?xml version="1.0"?>
<net name="detokenizer" version="11">
<layers>
<layer id="0" name="Parameter_135039" type="Parameter" version="opset1">
<data shape="?,?" element_type="i64" />
<output>
<port id="0" precision="I64" names="Parameter_135039">
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="1" name="Convert_135234" 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_134995" type="Const" version="opset1">
<data element_type="i32" shape="32011" offset="0" size="128044" />
<output>
<port id="0" precision="I32">
<dim>32011</dim>
</port>
</output>
</layer>
<layer id="3" name="Constant_134997" type="Const" version="opset1">
<data element_type="i32" shape="32011" offset="128044" size="128044" />
<output>
<port id="0" precision="I32">
<dim>32011</dim>
</port>
</output>
</layer>
<layer id="4" name="Constant_134999" type="Const" version="opset1">
<data element_type="u8" shape="211088" offset="256088" size="211088" />
<output>
<port id="0" precision="U8">
<dim>211088</dim>
</port>
</output>
</layer>
<layer id="5" name="Slice_135044" type="Const" version="opset1">
<data element_type="i32" shape="13" offset="467176" size="52" />
<output>
<port id="0" precision="I32">
<dim>13</dim>
</port>
</output>
</layer>
<layer id="6" name="VocabDecoder_135046" 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>32011</dim>
</port>
<port id="2" precision="I32">
<dim>32011</dim>
</port>
<port id="3" precision="U8">
<dim>211088</dim>
</port>
<port id="4" precision="I32">
<dim>13</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_135048" type="Const" version="opset1">
<data element_type="u8" shape="3" offset="467228" size="3" />
<output>
<port id="0" precision="U8">
<dim>3</dim>
</port>
</output>
</layer>
<layer id="8" name="Constant_135050" type="Const" version="opset1">
<data element_type="u8" shape="1" offset="467231" size="1" />
<output>
<port id="0" precision="U8">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="9" name="RegexNormalization_135051" 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_135052" 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_135053" 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="Constant_135055" type="Const" version="opset1">
<data element_type="u8" shape="2" offset="467232" size="2" />
<output>
<port id="0" precision="U8">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="13" name="Constant_135057" type="Const" version="opset1">
<data element_type="u8" shape="0" offset="467234" size="1" />
<output>
<port id="0" precision="U8">
<dim>0</dim>
</port>
</output>
</layer>
<layer id="14" name="RegexNormalization_135058" 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>2</dim>
</port>
<port id="4" precision="U8">
<dim>0</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="15" name="UTF8Validate_135059" 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="16" name="StringTensorPack_135060" 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_135061,string_output">
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="17" name="Result_135061" type="Result" version="opset1" output_names="Result_135061,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="5" to-layer="11" to-port="0" />
<edge from-layer="6" from-port="6" to-layer="11" to-port="1" />
<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="5" to-layer="10" to-port="0" />
<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="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="14" to-port="2" />
<edge from-layer="11" from-port="4" to-layer="14" to-port="0" />
<edge from-layer="11" from-port="5" to-layer="14" to-port="1" />
<edge from-layer="12" from-port="0" to-layer="14" to-port="3" />
<edge from-layer="13" from-port="0" to-layer="14" to-port="4" />
<edge from-layer="14" from-port="5" to-layer="15" to-port="0" />
<edge from-layer="14" from-port="6" to-layer="15" to-port="1" />
<edge from-layer="14" from-port="7" to-layer="15" to-port="2" />
<edge from-layer="15" from-port="3" to-layer="16" to-port="0" />
<edge from-layer="15" from-port="4" to-layer="16" to-port="1" />
<edge from-layer="15" from-port="5" to-layer="16" to-port="2" />
<edge from-layer="16" from-port="3" to-layer="17" to-port="0" />
</edges>
<rt_info>
<add_attention_mask value="True" />
<add_prefix_space />
<add_special_tokens value="True" />
<bos_token_id value="1" />
<chat_template value="{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'&lt;|system|>&#10;' + message['content'] + '&lt;|end|>&#10;'}}{% elif message['role'] == 'user' %}{{'&lt;|user|>&#10;' + message['content'] + '&lt;|end|>&#10;'}}{% elif message['role'] == 'assistant' %}{{'&lt;|assistant|>&#10;' + message['content'] + '&lt;|end|>&#10;'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '&lt;|assistant|>&#10;' }}{% else %}{{ eos_token }}{% endif %}" />
<clean_up_tokenization_spaces />
<detokenizer_input_type value="i64" />
<eos_token_id value="32000" />
<handle_special_tokens_with_re />
<max_length />
<number_of_inputs value="1" />
<openvino_tokenizers_version value="2025.2.0.0-566-85be884a69f" />
<openvino_version value="2025.2.0-19140-c01cd93e24d-releases/2025/2" />
<original_post_processor_template value="{&quot;type&quot;: &quot;TemplateProcessing&quot;, &quot;single&quot;: [{&quot;Sequence&quot;: {&quot;id&quot;: &quot;A&quot;, &quot;type_id&quot;: 0}}], &quot;pair&quot;: [{&quot;Sequence&quot;: {&quot;id&quot;: &quot;A&quot;, &quot;type_id&quot;: 0}}, {&quot;Sequence&quot;: {&quot;id&quot;: &quot;B&quot;, &quot;type_id&quot;: 1}}], &quot;special_tokens&quot;: {}}" />
<original_tokenizer_class value="&lt;class 'transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast'>" />
<pad_token_id value="32000" />
<processed_post_processor_template value="{&quot;single&quot;: {&quot;ids&quot;: [-1], &quot;type_ids&quot;: [0]}, &quot;pair&quot;: {&quot;ids&quot;: [-1, -2], &quot;type_ids&quot;: [0, 1]}}" />
<sentencepiece_version value="0.2.0" />
<skip_special_tokens value="True" />
<streaming_detokenizer value="False" />
<tiktoken_version value="0.9.0" />
<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>