Hugging Face's logo

FluidInference
/
phi-4-mini-instruct-fp16-ov-npu

Text Generation
OpenVINO
phi3
nlp
code
conversational
custom_code
Model card Files
xet
 Community
phi-4-mini-instruct-fp16-ov-npu / openvino_detokenizer.xml
bweng's picture
bweng
Upload folder using huggingface_hub
75959bd verified
raw
history blame contribute delete
6.96 kB
<?xml version="1.0"?>
<net name="detokenizer" version="11">
 <layers>
 <layer id="0" name="Parameter_172325" type="Parameter" version="opset1">
 <data shape="?,?" element_type="i64" />
 <output>
 <port id="0" precision="I64" names="Parameter_172325">
 <dim>-1</dim>
 <dim>-1</dim>
 </port>
 </output>
 </layer>
 <layer id="1" name="Convert_172495" 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_172327" type="Const" version="opset1">
 <data element_type="i32" shape="200029" offset="0" size="800116" />
 <output>
 <port id="0" precision="I32">
 <dim>200029</dim>
 </port>
 </output>
 </layer>
 <layer id="3" name="Constant_172329" type="Const" version="opset1">
 <data element_type="i32" shape="200029" offset="800116" size="800116" />
 <output>
 <port id="0" precision="I32">
 <dim>200029</dim>
 </port>
 </output>
 </layer>
 <layer id="4" name="Constant_172331" type="Const" version="opset1">
 <data element_type="u8" shape="1398089" offset="1600232" size="1398089" />
 <output>
 <port id="0" precision="U8">
 <dim>1398089</dim>
 </port>
 </output>
 </layer>
 <layer id="5" name="Slice_172336" type="Const" version="opset1">
 <data element_type="i32" shape="7" offset="2998321" size="28" />
 <output>
 <port id="0" precision="I32">
 <dim>7</dim>
 </port>
 </output>
 </layer>
 <layer id="6" name="VocabDecoder_172338" 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>200029</dim>
 </port>
 <port id="2" precision="I32">
 <dim>200029</dim>
 </port>
 <port id="3" precision="U8">
 <dim>1398089</dim>
 </port>
 <port id="4" precision="I32">
 <dim>7</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="FuzeRagged_172339" 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="8" name="UTF8Validate_172340" 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="9" name="StringTensorPack_172341" 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_172342,string_output">
 <dim>-1</dim>
 </port>
 </output>
 </layer>
 <layer id="10" name="Result_172342" type="Result" version="opset1" output_names="Result_172342,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="7" to-port="2" />
 <edge from-layer="6" from-port="9" to-layer="8" to-port="2" />
 <edge from-layer="6" from-port="8" to-layer="7" to-port="3" />
 <edge from-layer="6" from-port="6" to-layer="7" to-port="1" />
 <edge from-layer="6" from-port="5" to-layer="7" to-port="0" />
 <edge from-layer="7" from-port="4" to-layer="8" to-port="0" />
 <edge from-layer="7" from-port="5" to-layer="8" to-port="1" />
 <edge from-layer="8" from-port="3" to-layer="9" to-port="0" />
 <edge from-layer="8" from-port="4" to-layer="9" to-port="1" />
 <edge from-layer="8" from-port="5" to-layer="9" to-port="2" />
 <edge from-layer="9" from-port="3" to-layer="10" to-port="0" />
 </edges>
 <rt_info>
 <add_attention_mask value="True" />
 <add_prefix_space />
 <add_special_tokens value="True" />
 <bos_token_id value="199999" />
 <chat_template value="{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '&lt;|' + message['role'] + '|>' + message['content'] + '&lt;|tool|>' + message['tools'] + '&lt;|/tool|>' + '&lt;|end|>' }}{% else %}{{ '&lt;|' + message['role'] + '|>' + message['content'] + '&lt;|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '&lt;|assistant|>' }}{% else %}{{ eos_token }}{% endif %}" />
 <clean_up_tokenization_spaces />
 <detokenizer_input_type value="i64" />
 <eos_token_id value="199999" />
 <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_tokenizer_class value="&lt;class 'transformers.models.gpt2.tokenization_gpt2_fast.GPT2TokenizerFast'>" />
 <pad_token_id value="199999" />
 <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="4.49.0" />
 <use_max_padding value="False" />
 <use_sentencepiece_backend value="False" />
 <utf8_replace_mode value="replace" />
 <with_detokenizer value="True" />
 </rt_info>
</net>