Upload openvino_detokenizer.xml with huggingface_hub
Browse files- openvino_detokenizer.xml +183 -0
openvino_detokenizer.xml
ADDED
|
@@ -0,0 +1,183 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
<?xml version="1.0"?>
|
| 2 |
+
<net name="detokenizer" version="11">
|
| 3 |
+
<layers>
|
| 4 |
+
<layer id="0" name="Parameter_408297" type="Parameter" version="opset1">
|
| 5 |
+
<data shape="?,?" element_type="i64" />
|
| 6 |
+
<output>
|
| 7 |
+
<port id="0" precision="I64" names="Parameter_408297">
|
| 8 |
+
<dim>-1</dim>
|
| 9 |
+
<dim>-1</dim>
|
| 10 |
+
</port>
|
| 11 |
+
</output>
|
| 12 |
+
</layer>
|
| 13 |
+
<layer id="1" name="Convert_408308" type="Convert" version="opset1">
|
| 14 |
+
<data destination_type="i32" />
|
| 15 |
+
<input>
|
| 16 |
+
<port id="0" precision="I64">
|
| 17 |
+
<dim>-1</dim>
|
| 18 |
+
<dim>-1</dim>
|
| 19 |
+
</port>
|
| 20 |
+
</input>
|
| 21 |
+
<output>
|
| 22 |
+
<port id="1" precision="I32">
|
| 23 |
+
<dim>-1</dim>
|
| 24 |
+
<dim>-1</dim>
|
| 25 |
+
</port>
|
| 26 |
+
</output>
|
| 27 |
+
</layer>
|
| 28 |
+
<layer id="2" name="Constant_408272" type="Const" version="opset1">
|
| 29 |
+
<data element_type="u8" shape="1582931" offset="0" size="1582931" />
|
| 30 |
+
<output>
|
| 31 |
+
<port id="0" precision="U8">
|
| 32 |
+
<dim>1582931</dim>
|
| 33 |
+
</port>
|
| 34 |
+
</output>
|
| 35 |
+
</layer>
|
| 36 |
+
<layer id="3" name="StringTensorUnpack_408273" type="StringTensorUnpack" version="extension">
|
| 37 |
+
<data mode="begins_ends" />
|
| 38 |
+
<input>
|
| 39 |
+
<port id="0" precision="U8">
|
| 40 |
+
<dim>1582931</dim>
|
| 41 |
+
</port>
|
| 42 |
+
</input>
|
| 43 |
+
<output>
|
| 44 |
+
<port id="1" precision="I32">
|
| 45 |
+
<dim>-1</dim>
|
| 46 |
+
</port>
|
| 47 |
+
<port id="2" precision="I32">
|
| 48 |
+
<dim>-1</dim>
|
| 49 |
+
</port>
|
| 50 |
+
<port id="3" precision="U8">
|
| 51 |
+
<dim>-1</dim>
|
| 52 |
+
</port>
|
| 53 |
+
</output>
|
| 54 |
+
</layer>
|
| 55 |
+
<layer id="4" name="VocabDecoder_408298" type="VocabDecoder" version="extension">
|
| 56 |
+
<data skip_tokens="151643, 151644, 151645, 151646, 151647, 151648, 151649, 151650, 151651, 151652, 151653, 151654, 151655, 151656" />
|
| 57 |
+
<input>
|
| 58 |
+
<port id="0" precision="I32">
|
| 59 |
+
<dim>-1</dim>
|
| 60 |
+
<dim>-1</dim>
|
| 61 |
+
</port>
|
| 62 |
+
<port id="1" precision="I32">
|
| 63 |
+
<dim>-1</dim>
|
| 64 |
+
</port>
|
| 65 |
+
<port id="2" precision="I32">
|
| 66 |
+
<dim>-1</dim>
|
| 67 |
+
</port>
|
| 68 |
+
<port id="3" precision="U8">
|
| 69 |
+
<dim>-1</dim>
|
| 70 |
+
</port>
|
| 71 |
+
</input>
|
| 72 |
+
<output>
|
| 73 |
+
<port id="4" precision="I32">
|
| 74 |
+
<dim>-1</dim>
|
| 75 |
+
</port>
|
| 76 |
+
<port id="5" precision="I32">
|
| 77 |
+
<dim>-1</dim>
|
| 78 |
+
</port>
|
| 79 |
+
<port id="6" precision="I32">
|
| 80 |
+
<dim>-1</dim>
|
| 81 |
+
</port>
|
| 82 |
+
<port id="7" precision="I32">
|
| 83 |
+
<dim>-1</dim>
|
| 84 |
+
</port>
|
| 85 |
+
<port id="8" precision="U8">
|
| 86 |
+
<dim>-1</dim>
|
| 87 |
+
</port>
|
| 88 |
+
</output>
|
| 89 |
+
</layer>
|
| 90 |
+
<layer id="5" name="FuzeRagged_408299" type="FuzeRagged" version="extension">
|
| 91 |
+
<input>
|
| 92 |
+
<port id="0" precision="I32">
|
| 93 |
+
<dim>-1</dim>
|
| 94 |
+
</port>
|
| 95 |
+
<port id="1" precision="I32">
|
| 96 |
+
<dim>-1</dim>
|
| 97 |
+
</port>
|
| 98 |
+
<port id="2" precision="I32">
|
| 99 |
+
<dim>-1</dim>
|
| 100 |
+
</port>
|
| 101 |
+
<port id="3" precision="I32">
|
| 102 |
+
<dim>-1</dim>
|
| 103 |
+
</port>
|
| 104 |
+
</input>
|
| 105 |
+
<output>
|
| 106 |
+
<port id="4" precision="I32">
|
| 107 |
+
<dim>-1</dim>
|
| 108 |
+
</port>
|
| 109 |
+
<port id="5" precision="I32">
|
| 110 |
+
<dim>-1</dim>
|
| 111 |
+
</port>
|
| 112 |
+
</output>
|
| 113 |
+
</layer>
|
| 114 |
+
<layer id="6" name="StringTensorPack_408300" type="StringTensorPack" version="extension">
|
| 115 |
+
<data mode="begins_ends" />
|
| 116 |
+
<input>
|
| 117 |
+
<port id="0" precision="I32">
|
| 118 |
+
<dim>-1</dim>
|
| 119 |
+
</port>
|
| 120 |
+
<port id="1" precision="I32">
|
| 121 |
+
<dim>-1</dim>
|
| 122 |
+
</port>
|
| 123 |
+
<port id="2" precision="U8">
|
| 124 |
+
<dim>-1</dim>
|
| 125 |
+
</port>
|
| 126 |
+
</input>
|
| 127 |
+
<output>
|
| 128 |
+
<port id="3" precision="STRING" names="string_output">
|
| 129 |
+
<dim>-1</dim>
|
| 130 |
+
</port>
|
| 131 |
+
</output>
|
| 132 |
+
</layer>
|
| 133 |
+
<layer id="7" name="Result_408301" type="Result" version="opset1">
|
| 134 |
+
<input>
|
| 135 |
+
<port id="0" precision="STRING">
|
| 136 |
+
<dim>-1</dim>
|
| 137 |
+
</port>
|
| 138 |
+
</input>
|
| 139 |
+
</layer>
|
| 140 |
+
</layers>
|
| 141 |
+
<edges>
|
| 142 |
+
<edge from-layer="0" from-port="0" to-layer="1" to-port="0" />
|
| 143 |
+
<edge from-layer="1" from-port="1" to-layer="4" to-port="0" />
|
| 144 |
+
<edge from-layer="2" from-port="0" to-layer="3" to-port="0" />
|
| 145 |
+
<edge from-layer="3" from-port="1" to-layer="4" to-port="1" />
|
| 146 |
+
<edge from-layer="3" from-port="2" to-layer="4" to-port="2" />
|
| 147 |
+
<edge from-layer="3" from-port="3" to-layer="4" to-port="3" />
|
| 148 |
+
<edge from-layer="4" from-port="4" to-layer="5" to-port="0" />
|
| 149 |
+
<edge from-layer="4" from-port="5" to-layer="5" to-port="1" />
|
| 150 |
+
<edge from-layer="4" from-port="6" to-layer="5" to-port="2" />
|
| 151 |
+
<edge from-layer="4" from-port="7" to-layer="5" to-port="3" />
|
| 152 |
+
<edge from-layer="4" from-port="8" to-layer="6" to-port="2" />
|
| 153 |
+
<edge from-layer="5" from-port="4" to-layer="6" to-port="0" />
|
| 154 |
+
<edge from-layer="5" from-port="5" to-layer="6" to-port="1" />
|
| 155 |
+
<edge from-layer="6" from-port="3" to-layer="7" to-port="0" />
|
| 156 |
+
</edges>
|
| 157 |
+
<rt_info>
|
| 158 |
+
<add_attention_mask value="True" />
|
| 159 |
+
<add_prefix_space />
|
| 160 |
+
<add_special_tokens value="True" />
|
| 161 |
+
<chat_template value="{%- if tools %} {{- '<|im_start|>system\n' }} {%- if messages[0]['role'] == 'system' %} {{- messages[0]['content'] }} {%- else %} {{- 'You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step.' }} {%- endif %} {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }} {%- for tool in tools %} {{- "\n" }} {{- tool | tojson }} {%- endfor %} {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }} {%- else %} {%- if messages[0]['role'] == 'system' %} {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }} {%- else %} {{- '<|im_start|>system\nYou are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step.<|im_end|>\n' }} {%- endif %} {%- endif %} {%- for message in messages %} {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %} {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }} {%- elif message.role == "assistant" %} {{- '<|im_start|>' + message.role }} {%- if message.content %} {{- '\n' + message.content }} {%- endif %} {%- for tool_call in message.tool_calls %} {%- if tool_call.function is defined %} {%- set tool_call = tool_call.function %} {%- endif %} {{- '\n<tool_call>\n{"name": "' }} {{- tool_call.name }} {{- '", "arguments": ' }} {{- tool_call.arguments | tojson }} {{- '}\n</tool_call>' }} {%- endfor %} {{- '<|im_end|>\n' }} {%- elif message.role == "tool" %} {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %} {{- '<|im_start|>user' }} {%- endif %} {{- '\n<tool_response>\n' }} {{- message.content }} {{- '\n</tool_response>' }} {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} {{- '<|im_end|>\n' }} {%- endif %} {%- endif %} {%- endfor %} {%- if add_generation_prompt %} {{- '<|im_start|>assistant\n' }} {%- endif %} " />
|
| 162 |
+
<clean_up_tokenization_spaces />
|
| 163 |
+
<detokenizer_input_type value="i64" />
|
| 164 |
+
<eos_token_id value="151645" />
|
| 165 |
+
<handle_special_tokens_with_re />
|
| 166 |
+
<number_of_inputs value="1" />
|
| 167 |
+
<openvino_tokenizers_version value="2024.5.0.0" />
|
| 168 |
+
<openvino_version value="2024.5.0" />
|
| 169 |
+
<original_tokenizer_class value="<class 'transformers.models.qwen2.tokenization_qwen2_fast.Qwen2TokenizerFast'>" />
|
| 170 |
+
<pad_token_id value="151643" />
|
| 171 |
+
<sentencepiece_version value="0.2.0" />
|
| 172 |
+
<skip_special_tokens value="True" />
|
| 173 |
+
<streaming_detokenizer value="False" />
|
| 174 |
+
<tiktoken_version value="0.8.0" />
|
| 175 |
+
<tokenizer_output_type value="i64" />
|
| 176 |
+
<tokenizers_version value="0.20.1" />
|
| 177 |
+
<transformers_version value="4.46.3" />
|
| 178 |
+
<use_max_padding value="False" />
|
| 179 |
+
<use_sentencepiece_backend value="False" />
|
| 180 |
+
<utf8_replace_mode />
|
| 181 |
+
<with_detokenizer value="True" />
|
| 182 |
+
</rt_info>
|
| 183 |
+
</net>
|