dolphin-2.9.3-mistral-7b-32k-ov / openvino_detokenizer.xml
doberst's picture
Upload 4 files
a32b8e9 verified
raw
history blame
4.74 kB
<?xml version="1.0"?>
<net name="detokenizer" version="11">
<layers>
<layer id="0" name="Parameter_33" type="Parameter" version="opset1">
<data shape="?,?" element_type="i64" />
<output>
<port id="0" precision="I64" names="Parameter_33">
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="1" name="Constant_2" type="Const" version="opset1">
<data element_type="u8" shape="587448" offset="0" size="587448" />
<output>
<port id="0" precision="U8">
<dim>587448</dim>
</port>
</output>
</layer>
<layer id="2" name="Convert_48" 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="3" name="SentencepieceDetokenizer_34" type="SentencepieceDetokenizer" version="extension">
<input>
<port id="0" precision="U8">
<dim>587448</dim>
</port>
<port id="1" precision="I32">
<dim>-1</dim>
<dim>-1</dim>
</port>
</input>
<output>
<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>
</output>
</layer>
<layer id="4" name="Constant_36" type="Const" version="opset1">
<data element_type="u8" shape="10" offset="587448" size="10" />
<output>
<port id="0" precision="U8">
<dim>10</dim>
</port>
</output>
</layer>
<layer id="5" name="Constant_38" type="Const" version="opset1">
<data element_type="u8" shape="2" offset="587458" size="2" />
<output>
<port id="0" precision="U8">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="6" name="RegexNormalization_39" 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>10</dim>
</port>
<port id="4" precision="U8">
<dim>2</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="7" name="StringTensorPack_40" 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="8" name="Result_41" 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="2" to-port="0" />
<edge from-layer="1" from-port="0" to-layer="3" to-port="0" />
<edge from-layer="2" from-port="1" to-layer="3" to-port="1" />
<edge from-layer="3" from-port="2" to-layer="6" to-port="0" />
<edge from-layer="3" from-port="3" to-layer="6" to-port="1" />
<edge from-layer="3" from-port="4" 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="5" to-layer="7" to-port="0" />
<edge from-layer="6" from-port="6" to-layer="7" to-port="1" />
<edge from-layer="6" from-port="7" to-layer="7" to-port="2" />
<edge from-layer="7" from-port="3" to-layer="8" to-port="0" />
</edges>
<rt_info>
<bos_token_id value="1" />
<chat_template value="{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'&lt;|im_start|>' + message['role'] + '&#10;' + message['content'] + '&lt;|im_end|>' + '&#10;'}}{% endfor %}{% if add_generation_prompt %}{{ '&lt;|im_start|>assistant&#10;' }}{% endif %}" />
<eos_token_id value="32768" />
<original_tokenizer_class value="&lt;class 'transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast'>" />
<pad_token_id value="2" />
</rt_info>
</net>