openvino_detokenizer.xml

<?xml version="1.0"?>
<net name="detokenizer" version="11">
	<layers>
		<layer id="0" name="Parameter_67076" type="Parameter" version="opset1">
			<data shape="?,?" element_type="i64" />
			<output>
				<port id="0" precision="I64" names="Parameter_67076">
					<dim>-1</dim>
					<dim>-1</dim>
				</port>
			</output>
		</layer>
		<layer id="1" name="Convert_67087" 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_67051" type="Const" version="opset1">
			<data element_type="u8" shape="1582607" offset="0" size="1582607" />
			<output>
				<port id="0" precision="U8">
					<dim>1582607</dim>
				</port>
			</output>
		</layer>
		<layer id="3" name="StringTensorUnpack_67052" type="StringTensorUnpack" version="extension">
			<data mode="begins_ends" />
			<input>
				<port id="0" precision="U8">
					<dim>1582607</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_67077" type="VocabDecoder" version="extension">
			<data skip_tokens="151643, 151644, 151645, 151646" />
			<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="FuzeRagged_67078" 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="6" name="StringTensorPack_67079" 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="7" name="Result_67080" 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="4" to-layer="5" to-port="0" />
		<edge from-layer="4" from-port="5" to-layer="5" to-port="1" />
		<edge from-layer="4" from-port="6" to-layer="5" to-port="2" />
		<edge from-layer="4" from-port="7" to-layer="5" to-port="3" />
		<edge from-layer="4" from-port="8" to-layer="6" to-port="2" />
		<edge from-layer="5" from-port="4" to-layer="6" to-port="0" />
		<edge from-layer="5" from-port="5" to-layer="6" to-port="1" />
		<edge from-layer="6" from-port="3" to-layer="7" to-port="0" />
	</edges>
	<rt_info>
		<add_attention_mask value="True" />
		<add_prefix_space />
		<add_special_tokens value="True" />
		<chat_template value="{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '&lt;|im_start|>system&#10;You are a helpful assistant.&lt;|im_end|>&#10;' }}{% endif %}{{'&lt;|im_start|>' + message['role'] + '&#10;' + message['content'] + '&lt;|im_end|>' + '&#10;'}}{% endfor %}{% if add_generation_prompt %}{{ '&lt;|im_start|>assistant&#10;' }}{% endif %}" />
		<clean_up_tokenization_spaces />
		<detokenizer_input_type value="i64" />
		<eos_token_id value="151645" />
		<handle_special_tokens_with_re />
		<number_of_inputs value="1" />
		<openvino_tokenizers_version value="2024.5.0.0" />
		<openvino_version value="2024.5.0" />
		<original_tokenizer_class value="&lt;class 'transformers.models.qwen2.tokenization_qwen2_fast.Qwen2TokenizerFast'>" />
		<pad_token_id value="151643" />
		<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="0.20.3" />
		<transformers_version value="4.46.3" />
		<use_max_padding value="False" />
		<use_sentencepiece_backend value="False" />
		<utf8_replace_mode />
		<with_detokenizer value="True" />
	</rt_info>
</net>