Mistral-NeMo-Minitron-8B-Instruct-OpenVINO
/
Mistral-NeMo-Minitron-8B-Instruct-int4_asym-ov
/openvino_detokenizer.xml
<net name="detokenizer" version="11"> | |
<layers> | |
<layer id="0" name="Parameter_112755" type="Parameter" version="opset1"> | |
<data shape="?,?" element_type="i64" /> | |
<output> | |
<port id="0" precision="I64" names="Parameter_112755"> | |
<dim>-1</dim> | |
<dim>-1</dim> | |
</port> | |
</output> | |
</layer> | |
<layer id="1" name="Convert_112925" 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_112757" type="Const" version="opset1"> | |
<data element_type="i32" shape="131072" offset="0" size="524288" /> | |
<output> | |
<port id="0" precision="I32"> | |
<dim>131072</dim> | |
</port> | |
</output> | |
</layer> | |
<layer id="3" name="Constant_112759" type="Const" version="opset1"> | |
<data element_type="i32" shape="131072" offset="524288" size="524288" /> | |
<output> | |
<port id="0" precision="I32"> | |
<dim>131072</dim> | |
</port> | |
</output> | |
</layer> | |
<layer id="4" name="Constant_112761" type="Const" version="opset1"> | |
<data element_type="u8" shape="891120" offset="1048576" size="891120" /> | |
<output> | |
<port id="0" precision="U8"> | |
<dim>891120</dim> | |
</port> | |
</output> | |
</layer> | |
<layer id="5" name="Slice_112766" type="Const" version="opset1"> | |
<data element_type="i32" shape="1000" offset="1939696" size="4000" /> | |
<output> | |
<port id="0" precision="I32"> | |
<dim>1000</dim> | |
</port> | |
</output> | |
</layer> | |
<layer id="6" name="VocabDecoder_112768" 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>131072</dim> | |
</port> | |
<port id="2" precision="I32"> | |
<dim>131072</dim> | |
</port> | |
<port id="3" precision="U8"> | |
<dim>891120</dim> | |
</port> | |
<port id="4" precision="I32"> | |
<dim>1000</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_112769" 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_112770" 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_112771" 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_112772,string_output"> | |
<dim>-1</dim> | |
</port> | |
</output> | |
</layer> | |
<layer id="10" name="Result_112772" type="Result" version="opset1" output_names="Result_112772,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="1" /> | |
<chat_template value="{{'<extra_id_0>System'}}{% for message in messages %}{% if message['role'] == 'system' %}{{' ' + message['content'].strip()}}{% endif %}{% endfor %}{{' '}}{% for message in messages %}{% if message['role'] == 'user' %}{{ ' <extra_id_1>User ' + message['content'].strip() + ' <extra_id_1>Assistant ' }}{% elif message['role'] == 'assistant' %}{{ message['content'].strip() }}{% endif %}{% endfor %}" /> | |
<clean_up_tokenization_spaces /> | |
<detokenizer_input_type value="i64" /> | |
<eos_token_id value="2" /> | |
<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_post_processor_template value="{"type": "TemplateProcessing", "single": [{"SpecialToken": {"id": "<s>", "type_id": 0}}, {"Sequence": {"id": "A", "type_id": 0}}], "pair": [{"SpecialToken": {"id": "<s>", "type_id": 0}}, {"Sequence": {"id": "A", "type_id": 0}}, {"SpecialToken": {"id": "<s>", "type_id": 1}}, {"Sequence": {"id": "B", "type_id": 1}}], "special_tokens": {"</s>": {"id": "</s>", "ids": [2], "tokens": ["</s>"]}, "<s>": {"id": "<s>", "ids": [1], "tokens": ["<s>"]}}}" /> | |
<original_tokenizer_class value="<class 'transformers.tokenization_utils_fast.PreTrainedTokenizerFast'>" /> | |
<processed_post_processor_template value="{"single": {"ids": [1, -1], "type_ids": [0, 0]}, "pair": {"ids": [1, -1, 1, -2], "type_ids": [0, 0, 1, 1]}}" /> | |
<sentencepiece_version value="0.2.0" /> | |
<skip_special_tokens value="True" /> | |
<streaming_detokenizer value="False" /> | |
<tokenizer_output_type value="i64" /> | |
<tokenizers_version value="0.21.1" /> | |
<transformers_version value="4.51.3" /> | |
<use_max_padding value="False" /> | |
<use_sentencepiece_backend value="False" /> | |
<utf8_replace_mode value="replace" /> | |
<with_detokenizer value="True" /> | |
</rt_info> | |
</net> | |