gemma-2-9b-it-ov-int8 / openvino_detokenizer.xml
fakezeta's picture
Upload folder using huggingface_hub
d0d8c4b verified
<?xml version="1.0"?>
<net name="detokenizer" version="11">
<layers>
<layer id="0" name="Parameter_312413" type="Parameter" version="opset1">
<data shape="?,?" element_type="i64" />
<output>
<port id="0" precision="I64" names="Parameter_312413">
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="1" name="Constant_312389" type="Const" version="opset1">
<data element_type="u8" shape="4241003" offset="0" size="4241003" />
<output>
<port id="0" precision="U8">
<dim>4241003</dim>
</port>
</output>
</layer>
<layer id="2" name="Convert_312423" 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_312414" type="SentencepieceDetokenizer" version="extension">
<input>
<port id="0" precision="U8">
<dim>4241003</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="StringTensorPack_312415" 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="5" name="Result_312416" 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="4" to-port="0" />
<edge from-layer="3" from-port="3" to-layer="4" to-port="1" />
<edge from-layer="3" from-port="4" to-layer="4" to-port="2" />
<edge from-layer="4" from-port="3" to-layer="5" to-port="0" />
</edges>
<rt_info>
<bos_token_id value="2" />
<chat_template value="{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '&lt;start_of_turn>' + role + '&#10;' + message['content'] | trim + '&lt;end_of_turn>&#10;' }}{% endfor %}{% if add_generation_prompt %}{{'&lt;start_of_turn>model&#10;'}}{% endif %}" />
<eos_token_id value="1" />
<original_tokenizer_class value="&lt;class 'transformers.models.gemma.tokenization_gemma_fast.GemmaTokenizerFast'>" />
<pad_token_id value="0" />
</rt_info>
</net>