Upload openvino_detokenizer.xml with huggingface_hub
Browse files- openvino_detokenizer.xml +235 -0
openvino_detokenizer.xml
ADDED
|
@@ -0,0 +1,235 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
<?xml version="1.0"?>
|
| 2 |
+
<net name="detokenizer" version="11">
|
| 3 |
+
<layers>
|
| 4 |
+
<layer id="0" name="Parameter_803321" type="Parameter" version="opset1">
|
| 5 |
+
<data shape="?,?" element_type="i64" />
|
| 6 |
+
<output>
|
| 7 |
+
<port id="0" precision="I64" names="Parameter_803321">
|
| 8 |
+
<dim>-1</dim>
|
| 9 |
+
<dim>-1</dim>
|
| 10 |
+
</port>
|
| 11 |
+
</output>
|
| 12 |
+
</layer>
|
| 13 |
+
<layer id="1" name="Convert_803337" 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_803288" type="Const" version="opset1">
|
| 29 |
+
<data element_type="u8" shape="1351800" offset="0" size="1351800" />
|
| 30 |
+
<output>
|
| 31 |
+
<port id="0" precision="U8">
|
| 32 |
+
<dim>1351800</dim>
|
| 33 |
+
</port>
|
| 34 |
+
</output>
|
| 35 |
+
</layer>
|
| 36 |
+
<layer id="3" name="StringTensorUnpack_803289" type="StringTensorUnpack" version="extension">
|
| 37 |
+
<data mode="begins_ends" />
|
| 38 |
+
<input>
|
| 39 |
+
<port id="0" precision="U8">
|
| 40 |
+
<dim>1351800</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_803322" type="VocabDecoder" version="extension">
|
| 56 |
+
<data skip_tokens="128000, 128001, 128002, 128003, 128004, 128005, 128006, 128007, 128008, 128009, 128010, 128011, 128012, 128013, 128014, 128015, 128016, 128017, 128018, 128019, 128020, 128021, 128022, 128023, 128024, 128025, 128026, 128027, 128028, 128029, 128030, 128031, 128032, 128033, 128034, 128035, 128036, 128037, 128038, 128039, 128040, 128041, 128042, 128043, 128044, 128045, 128046, 128047, 128048, 128049, 128050, 128051, 128052, 128053, 128054, 128055, 128056, 128057, 128058, 128059, 128060, 128061, 128062, 128063, 128064, 128065, 128066, 128067, 128068, 128069, 128070, 128071, 128072, 128073, 128074, 128075, 128076, 128077, 128078, 128079, 128080, 128081, 128082, 128083, 128084, 128085, 128086, 128087, 128088, 128089, 128090, 128091, 128092, 128093, 128094, 128095, 128096, 128097, 128098, 128099, 128100, 128101, 128102, 128103, 128104, 128105, 128106, 128107, 128108, 128109, 128110, 128111, 128112, 128113, 128114, 128115, 128116, 128117, 128118, 128119, 128120, 128121, 128122, 128123, 128124, 128125, 128126, 128127, 128128, 128129, 128130, 128131, 128132, 128133, 128134, 128135, 128136, 128137, 128138, 128139, 128140, 128141, 128142, 128143, 128144, 128145, 128146, 128147, 128148, 128149, 128150, 128151, 128152, 128153, 128154, 128155, 128156, 128157, 128158, 128159, 128160, 128161, 128162, 128163, 128164, 128165, 128166, 128167, 128168, 128169, 128170, 128171, 128172, 128173, 128174, 128175, 128176, 128177, 128178, 128179, 128180, 128181, 128182, 128183, 128184, 128185, 128186, 128187, 128188, 128189, 128190, 128191, 128192, 128193, 128194, 128195, 128196, 128197, 128198, 128199, 128200, 128201, 128202, 128203, 128204, 128205, 128206, 128207, 128208, 128209, 128210, 128211, 128212, 128213, 128214, 128215, 128216, 128217, 128218, 128219, 128220, 128221, 128222, 128223, 128224, 128225, 128226, 128227, 128228, 128229, 128230, 128231, 128232, 128233, 128234, 128235, 128236, 128237, 128238, 128239, 128240, 128241, 128242, 128243, 128244, 128245, 128246, 128247, 128248, 128249, 128250, 128251, 128252, 128253, 128254, 128255" />
|
| 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_803323" 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="Constant_803325" type="Const" version="opset1">
|
| 115 |
+
<data element_type="u8" shape="47" offset="1351800" size="47" />
|
| 116 |
+
<output>
|
| 117 |
+
<port id="0" precision="U8">
|
| 118 |
+
<dim>47</dim>
|
| 119 |
+
</port>
|
| 120 |
+
</output>
|
| 121 |
+
</layer>
|
| 122 |
+
<layer id="7" name="Constant_803327" type="Const" version="opset1">
|
| 123 |
+
<data element_type="u8" shape="2" offset="1351847" size="2" />
|
| 124 |
+
<output>
|
| 125 |
+
<port id="0" precision="U8">
|
| 126 |
+
<dim>2</dim>
|
| 127 |
+
</port>
|
| 128 |
+
</output>
|
| 129 |
+
</layer>
|
| 130 |
+
<layer id="8" name="RegexNormalization_803328" type="RegexNormalization" version="extension">
|
| 131 |
+
<data global_replace="true" />
|
| 132 |
+
<input>
|
| 133 |
+
<port id="0" precision="I32">
|
| 134 |
+
<dim>-1</dim>
|
| 135 |
+
</port>
|
| 136 |
+
<port id="1" precision="I32">
|
| 137 |
+
<dim>-1</dim>
|
| 138 |
+
</port>
|
| 139 |
+
<port id="2" precision="U8">
|
| 140 |
+
<dim>-1</dim>
|
| 141 |
+
</port>
|
| 142 |
+
<port id="3" precision="U8">
|
| 143 |
+
<dim>47</dim>
|
| 144 |
+
</port>
|
| 145 |
+
<port id="4" precision="U8">
|
| 146 |
+
<dim>2</dim>
|
| 147 |
+
</port>
|
| 148 |
+
</input>
|
| 149 |
+
<output>
|
| 150 |
+
<port id="5" precision="I32">
|
| 151 |
+
<dim>-1</dim>
|
| 152 |
+
</port>
|
| 153 |
+
<port id="6" precision="I32">
|
| 154 |
+
<dim>-1</dim>
|
| 155 |
+
</port>
|
| 156 |
+
<port id="7" precision="U8">
|
| 157 |
+
<dim>-1</dim>
|
| 158 |
+
</port>
|
| 159 |
+
</output>
|
| 160 |
+
</layer>
|
| 161 |
+
<layer id="9" name="StringTensorPack_803329" type="StringTensorPack" version="extension">
|
| 162 |
+
<data mode="begins_ends" />
|
| 163 |
+
<input>
|
| 164 |
+
<port id="0" precision="I32">
|
| 165 |
+
<dim>-1</dim>
|
| 166 |
+
</port>
|
| 167 |
+
<port id="1" precision="I32">
|
| 168 |
+
<dim>-1</dim>
|
| 169 |
+
</port>
|
| 170 |
+
<port id="2" precision="U8">
|
| 171 |
+
<dim>-1</dim>
|
| 172 |
+
</port>
|
| 173 |
+
</input>
|
| 174 |
+
<output>
|
| 175 |
+
<port id="3" precision="STRING" names="string_output">
|
| 176 |
+
<dim>-1</dim>
|
| 177 |
+
</port>
|
| 178 |
+
</output>
|
| 179 |
+
</layer>
|
| 180 |
+
<layer id="10" name="Result_803330" type="Result" version="opset1">
|
| 181 |
+
<input>
|
| 182 |
+
<port id="0" precision="STRING">
|
| 183 |
+
<dim>-1</dim>
|
| 184 |
+
</port>
|
| 185 |
+
</input>
|
| 186 |
+
</layer>
|
| 187 |
+
</layers>
|
| 188 |
+
<edges>
|
| 189 |
+
<edge from-layer="0" from-port="0" to-layer="1" to-port="0" />
|
| 190 |
+
<edge from-layer="1" from-port="1" to-layer="4" to-port="0" />
|
| 191 |
+
<edge from-layer="2" from-port="0" to-layer="3" to-port="0" />
|
| 192 |
+
<edge from-layer="3" from-port="1" to-layer="4" to-port="1" />
|
| 193 |
+
<edge from-layer="3" from-port="2" to-layer="4" to-port="2" />
|
| 194 |
+
<edge from-layer="3" from-port="3" to-layer="4" to-port="3" />
|
| 195 |
+
<edge from-layer="4" from-port="7" to-layer="5" to-port="3" />
|
| 196 |
+
<edge from-layer="4" from-port="8" to-layer="8" to-port="2" />
|
| 197 |
+
<edge from-layer="4" from-port="6" to-layer="5" to-port="2" />
|
| 198 |
+
<edge from-layer="4" from-port="5" to-layer="5" to-port="1" />
|
| 199 |
+
<edge from-layer="4" from-port="4" to-layer="5" to-port="0" />
|
| 200 |
+
<edge from-layer="5" from-port="4" to-layer="8" to-port="0" />
|
| 201 |
+
<edge from-layer="5" from-port="5" to-layer="8" to-port="1" />
|
| 202 |
+
<edge from-layer="6" from-port="0" to-layer="8" to-port="3" />
|
| 203 |
+
<edge from-layer="7" from-port="0" to-layer="8" to-port="4" />
|
| 204 |
+
<edge from-layer="8" from-port="5" to-layer="9" to-port="0" />
|
| 205 |
+
<edge from-layer="8" from-port="6" to-layer="9" to-port="1" />
|
| 206 |
+
<edge from-layer="8" from-port="7" to-layer="9" to-port="2" />
|
| 207 |
+
<edge from-layer="9" from-port="3" to-layer="10" to-port="0" />
|
| 208 |
+
</edges>
|
| 209 |
+
<rt_info>
|
| 210 |
+
<add_attention_mask value="True" />
|
| 211 |
+
<add_prefix_space />
|
| 212 |
+
<add_special_tokens value="True" />
|
| 213 |
+
<bos_token_id value="128000" />
|
| 214 |
+
<chat_template value="{{- bos_token }} {%- if custom_tools is defined %} {%- set tools = custom_tools %} {%- endif %} {%- if not tools_in_user_message is defined %} {%- set tools_in_user_message = true %} {%- endif %} {%- if not date_string is defined %} {%- set date_string = "26 Jul 2024" %} {%- endif %} {%- if not tools is defined %} {%- set tools = none %} {%- endif %} {#- This block extracts the system message, so we can slot it into the right place. #} {%- if messages[0]['role'] == 'system' %} {%- set system_message = messages[0]['content']|trim %} {%- set messages = messages[1:] %} {%- else %} {%- set system_message = "" %} {%- endif %} {#- System message + builtin tools #} {{- "<|start_header_id|>system<|end_header_id|>\n\n" }} {%- if builtin_tools is defined or tools is not none %} {{- "Environment: ipython\n" }} {%- endif %} {%- if builtin_tools is defined %} {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}} {%- endif %} {{- "Cutting Knowledge Date: December 2023\n" }} {{- "Today Date: " + date_string + "\n\n" }} {%- if tools is not none and not tools_in_user_message %} {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }} {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }} {{- "Do not use variables.\n\n" }} {%- for t in tools %} {{- t | tojson(indent=4) }} {{- "\n\n" }} {%- endfor %} {%- endif %} {{- system_message }} {{- "<|eot_id|>" }} {#- Custom tools are passed in a user message with some extra guidance #} {%- if tools_in_user_message and not tools is none %} {#- Extract the first user message so we can plug it in here #} {%- if messages | length != 0 %} {%- set first_user_message = messages[0]['content']|trim %} {%- set messages = messages[1:] %} {%- else %} {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }} {%- endif %} {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}} {{- "Given the following functions, please respond with a JSON for a function call " }} {{- "with its proper arguments that best answers the given prompt.\n\n" }} {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }} {{- "Do not use variables.\n\n" }} {%- for t in tools %} {{- t | tojson(indent=4) }} {{- "\n\n" }} {%- endfor %} {{- first_user_message + "<|eot_id|>"}} {%- endif %} {%- for message in messages %} {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %} {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }} {%- elif 'tool_calls' in message %} {%- if not message.tool_calls|length == 1 %} {{- raise_exception("This model only supports single tool-calls at once!") }} {%- endif %} {%- set tool_call = message.tool_calls[0].function %} {%- if builtin_tools is defined and tool_call.name in builtin_tools %} {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}} {{- "<|python_tag|>" + tool_call.name + ".call(" }} {%- for arg_name, arg_val in tool_call.arguments | items %} {{- arg_name + '="' + arg_val + '"' }} {%- if not loop.last %} {{- ", " }} {%- endif %} {%- endfor %} {{- ")" }} {%- else %} {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}} {{- '{"name": "' + tool_call.name + '", ' }} {{- '"parameters": ' }} {{- tool_call.arguments | tojson }} {{- "}" }} {%- endif %} {%- if builtin_tools is defined %} {#- This means we're in ipython mode #} {{- "<|eom_id|>" }} {%- else %} {{- "<|eot_id|>" }} {%- endif %} {%- elif message.role == "tool" or message.role == "ipython" %} {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }} {%- if message.content is mapping or message.content is iterable %} {{- message.content | tojson }} {%- else %} {{- message.content }} {%- endif %} {{- "<|eot_id|>" }} {%- endif %} {%- endfor %} {%- if add_generation_prompt %} {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }} {%- endif %} " />
|
| 215 |
+
<clean_up_tokenization_spaces />
|
| 216 |
+
<detokenizer_input_type value="i64" />
|
| 217 |
+
<eos_token_id value="128009" />
|
| 218 |
+
<handle_special_tokens_with_re />
|
| 219 |
+
<number_of_inputs value="1" />
|
| 220 |
+
<openvino_tokenizers_version value="2024.5.0.0.dev20241030" />
|
| 221 |
+
<openvino_version value="2024.5.0.dev20241030" />
|
| 222 |
+
<original_tokenizer_class value="<class 'transformers.tokenization_utils_fast.PreTrainedTokenizerFast'>" />
|
| 223 |
+
<sentencepiece_version value="0.2.0" />
|
| 224 |
+
<skip_special_tokens value="True" />
|
| 225 |
+
<streaming_detokenizer value="False" />
|
| 226 |
+
<tiktoken_version value="0.8.0" />
|
| 227 |
+
<tokenizer_output_type value="i64" />
|
| 228 |
+
<tokenizers_version value="0.20.1" />
|
| 229 |
+
<transformers_version value="4.45.2" />
|
| 230 |
+
<use_max_padding value="False" />
|
| 231 |
+
<use_sentencepiece_backend value="False" />
|
| 232 |
+
<utf8_replace_mode />
|
| 233 |
+
<with_detokenizer value="True" />
|
| 234 |
+
</rt_info>
|
| 235 |
+
</net>
|