Phi-3.5-mini-instruct-openvino-4bit / openvino_detokenizer.xml
AIFunOver's picture
Upload openvino_detokenizer.xml with huggingface_hub
2aa89e4 verified
<?xml version="1.0"?>
<net name="detokenizer" version="11">
<layers>
<layer id="0" name="Parameter_501779" type="Parameter" version="opset1">
<data shape="?,?" element_type="i64" />
<output>
<port id="0" precision="I64" names="Parameter_501779">
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="1" name="Convert_501801" 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_501749" type="Const" version="opset1">
<data element_type="u8" shape="339140" offset="0" size="339140" />
<output>
<port id="0" precision="U8">
<dim>339140</dim>
</port>
</output>
</layer>
<layer id="3" name="StringTensorUnpack_501750" type="StringTensorUnpack" version="extension">
<data mode="begins_ends" />
<input>
<port id="0" precision="U8">
<dim>339140</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="4" name="VocabDecoder_501780" type="VocabDecoder" version="extension">
<data skip_tokens="0, 1, 32000, 32001, 32002, 32003, 32004, 32005, 32006, 32007, 32008, 32009, 32010" />
<input>
<port id="0" precision="I32">
<dim>-1</dim>
<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="U8">
<dim>-1</dim>
</port>
</input>
<output>
<port id="4" precision="I32">
<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="I32">
<dim>-1</dim>
</port>
<port id="8" precision="U8">
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="5" name="Constant_501782" type="Const" version="opset1">
<data element_type="u8" shape="3" offset="339140" size="3" />
<output>
<port id="0" precision="U8">
<dim>3</dim>
</port>
</output>
</layer>
<layer id="6" name="Constant_501784" type="Const" version="opset1">
<data element_type="u8" shape="1" offset="339143" size="1" />
<output>
<port id="0" precision="U8">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="7" name="RegexNormalization_501785" 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="8" name="ByteFallback_501786" 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="9" name="FuzeRagged_501787" 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="10" name="Constant_501789" type="Const" version="opset1">
<data element_type="u8" shape="2" offset="339144" size="2" />
<output>
<port id="0" precision="U8">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="11" name="Constant_501791" type="Const" version="opset1">
<data element_type="u8" shape="0" offset="339146" size="1" />
<output>
<port id="0" precision="U8">
<dim>0</dim>
</port>
</output>
</layer>
<layer id="12" name="RegexNormalization_501792" 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="13" name="StringTensorPack_501793" type="StringTensorPack" version="extension">
<data mode="begins_ends" />
<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="string_output">
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="14" name="Result_501794" type="Result" version="opset1">
<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="4" to-port="0" />
<edge from-layer="2" from-port="0" to-layer="3" to-port="0" />
<edge from-layer="3" from-port="1" to-layer="4" to-port="1" />
<edge from-layer="3" from-port="2" to-layer="4" to-port="2" />
<edge from-layer="3" from-port="3" to-layer="4" to-port="3" />
<edge from-layer="4" from-port="6" to-layer="7" to-port="0" />
<edge from-layer="4" from-port="7" to-layer="7" to-port="1" />
<edge from-layer="4" from-port="8" to-layer="7" to-port="2" />
<edge from-layer="4" from-port="5" to-layer="9" to-port="1" />
<edge from-layer="4" from-port="4" to-layer="9" to-port="0" />
<edge from-layer="5" from-port="0" to-layer="7" to-port="3" />
<edge from-layer="6" from-port="0" to-layer="7" to-port="4" />
<edge from-layer="7" from-port="7" to-layer="8" to-port="2" />
<edge from-layer="7" from-port="6" to-layer="8" to-port="1" />
<edge from-layer="7" from-port="5" to-layer="8" to-port="0" />
<edge from-layer="8" from-port="3" to-layer="9" to-port="2" />
<edge from-layer="8" from-port="4" to-layer="9" to-port="3" />
<edge from-layer="8" from-port="5" to-layer="12" to-port="2" />
<edge from-layer="9" from-port="4" to-layer="12" to-port="0" />
<edge from-layer="9" from-port="5" to-layer="12" to-port="1" />
<edge from-layer="10" from-port="0" to-layer="12" to-port="3" />
<edge from-layer="11" from-port="0" to-layer="12" to-port="4" />
<edge from-layer="12" from-port="5" to-layer="13" to-port="0" />
<edge from-layer="12" from-port="6" to-layer="13" to-port="1" />
<edge from-layer="12" from-port="7" 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="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 />
<number_of_inputs value="1" />
<openvino_tokenizers_version value="2024.5.0.0.dev20241030" />
<openvino_version value="2024.5.0.dev20241030" />
<original_tokenizer_class value="&lt;class 'transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast'>" />
<pad_token_id value="32000" />
<sentencepiece_version value="0.2.0" />
<skip_special_tokens value="True" />
<streaming_detokenizer value="False" />
<tiktoken_version value="0.8.0" />
<tokenizer_output_type value="i64" />
<tokenizers_version value="0.20.1" />
<transformers_version value="4.45.2" />
<use_max_padding value="False" />
<use_sentencepiece_backend value="False" />
<utf8_replace_mode />
<with_detokenizer value="True" />
</rt_info>
</net>