gemma-2-9b-it-ov-int4 / openvino_tokenizer.xml
fakezeta's picture
Upload folder using huggingface_hub
5d7a128 verified
<?xml version="1.0"?>
<net name="tokenizer" version="11">
<layers>
<layer id="0" name="string_input" type="Parameter" version="opset1">
<data shape="?" element_type="string" />
<output>
<port id="0" precision="STRING" names="string_input">
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="1" name="Constant_312392" type="Const" version="opset1">
<data element_type="i32" shape="" offset="0" size="4" />
<output>
<port id="0" precision="I32" />
</output>
</layer>
<layer id="2" name="Constant_312388" type="Const" version="opset1">
<data element_type="u8" shape="4241003" offset="4" size="4241003" />
<output>
<port id="0" precision="U8">
<dim>4241003</dim>
</port>
</output>
</layer>
<layer id="3" name="SentencepieceTokenizer_312391" type="SentencepieceTokenizer" version="extension">
<data nbest_size="0" alpha="0" add_bos="true" add_eos="false" reverse="true" />
<input>
<port id="0" precision="U8">
<dim>4241003</dim>
</port>
<port id="1" precision="STRING">
<dim>-1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>-1</dim>
<dim>2</dim>
</port>
<port id="3" precision="I32">
<dim>-1</dim>
</port>
<port id="4" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="4" name="Broadcast_312393" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I32" />
<port id="1" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="2" precision="I32">
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="5" name="Constant_312394" type="Const" version="opset1">
<data element_type="i32" shape="" offset="4241007" size="4" />
<output>
<port id="0" precision="I32" />
</output>
</layer>
<layer id="6" name="ShapeOf_312395" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I32">
<dim>-1</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="7" name="Broadcast_312396" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I32" />
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I32">
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="8" name="ScatterNDUpdate_312400" type="ScatterNDUpdate" version="opset4">
<input>
<port id="0" precision="I32">
<dim>-1</dim>
<dim>-1</dim>
</port>
<port id="1" precision="I64">
<dim>-1</dim>
<dim>2</dim>
</port>
<port id="2" precision="I32">
<dim>-1</dim>
</port>
</input>
<output>
<port id="3" precision="I32">
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="9" name="Constant_312404" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4241011" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="10" name="Reverse_312405" type="Reverse" version="opset1">
<data mode="index" />
<input>
<port id="0" precision="I32">
<dim>-1</dim>
<dim>-1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I32">
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="11" name="Reverse_312405" type="Convert" version="opset1">
<data destination_type="i64" />
<input>
<port id="0" precision="I32">
<dim>-1</dim>
<dim>-1</dim>
</port>
</input>
<output>
<port id="1" precision="I64" names="attention_mask">
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="13" name="Constant_312401" type="Const" version="opset1">
<data element_type="i32" shape="" offset="0" size="4" />
<output>
<port id="0" precision="I32" />
</output>
</layer>
<layer id="14" name="Broadcast_312402" type="Broadcast" version="opset3">
<data mode="bidirectional" />
<input>
<port id="0" precision="I32" />
<port id="1" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="2" precision="I32">
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="15" name="ScatterNDUpdate_312403" type="ScatterNDUpdate" version="opset4">
<input>
<port id="0" precision="I32">
<dim>-1</dim>
<dim>-1</dim>
</port>
<port id="1" precision="I64">
<dim>-1</dim>
<dim>2</dim>
</port>
<port id="2" precision="I32">
<dim>-1</dim>
</port>
</input>
<output>
<port id="3" precision="I32">
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="16" name="Constant_312406" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4241011" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="17" name="Reverse_312407" type="Reverse" version="opset1">
<data mode="index" />
<input>
<port id="0" precision="I32">
<dim>-1</dim>
<dim>-1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I32">
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="18" name="Reverse_312407" type="Convert" version="opset1">
<data destination_type="i64" />
<input>
<port id="0" precision="I32">
<dim>-1</dim>
<dim>-1</dim>
</port>
</input>
<output>
<port id="1" precision="I64" names="input_ids">
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="19" name="Result_312408" type="Result" version="opset1">
<input>
<port id="0" precision="I64">
<dim>-1</dim>
<dim>-1</dim>
</port>
</input>
</layer>
<layer id="12" name="Result_312409" type="Result" version="opset1">
<input>
<port id="0" precision="I64">
<dim>-1</dim>
<dim>-1</dim>
</port>
</input>
</layer>
</layers>
<edges>
<edge from-layer="0" from-port="0" to-layer="3" to-port="1" />
<edge from-layer="1" from-port="0" 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="4" to-layer="4" to-port="1" />
<edge from-layer="3" from-port="3" to-layer="6" to-port="0" />
<edge from-layer="3" from-port="2" to-layer="8" to-port="1" />
<edge from-layer="3" from-port="3" to-layer="15" to-port="2" />
<edge from-layer="3" from-port="2" to-layer="15" to-port="1" />
<edge from-layer="3" from-port="4" to-layer="14" to-port="1" />
<edge from-layer="4" from-port="2" to-layer="8" to-port="0" />
<edge from-layer="5" from-port="0" to-layer="7" to-port="0" />
<edge from-layer="6" from-port="1" to-layer="7" to-port="1" />
<edge from-layer="7" from-port="2" to-layer="8" to-port="2" />
<edge from-layer="8" from-port="3" to-layer="10" to-port="0" />
<edge from-layer="9" from-port="0" to-layer="10" to-port="1" />
<edge from-layer="10" from-port="2" to-layer="11" to-port="0" />
<edge from-layer="11" from-port="1" to-layer="12" to-port="0" />
<edge from-layer="13" from-port="0" to-layer="14" to-port="0" />
<edge from-layer="14" from-port="2" to-layer="15" to-port="0" />
<edge from-layer="15" from-port="3" to-layer="17" to-port="0" />
<edge from-layer="16" from-port="0" to-layer="17" to-port="1" />
<edge from-layer="17" from-port="2" to-layer="18" to-port="0" />
<edge from-layer="18" from-port="1" to-layer="19" 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>