Hugging Face's logo

AIFunOver
/
Falcon3-3B-Instruct-openvino-4bit

Text Generation
Transformers
Safetensors
OpenVINO
llama
falcon3
nncf
4-bit precision
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
AIFunOver commited on
Commit
d1c47f3
·
verified ·
1 Parent(s): c03d2b1

Upload openvino_detokenizer.xml with huggingface_hub

Browse files
Files changed (1) hide show
  1. openvino_detokenizer.xml +336 -0
openvino_detokenizer.xml ADDED
@@ -0,0 +1,336 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="detokenizer" version="11">
3
+ <layers>
4
+ <layer id="0" name="Parameter_539608" type="Parameter" version="opset1">
5
+ <data shape="?,?" element_type="i64" />
6
+ <output>
7
+ <port id="0" precision="I64" names="Parameter_539608">
8
+ <dim>-1</dim>
9
+ <dim>-1</dim>
10
+ </port>
11
+ </output>
12
+ </layer>
13
+ <layer id="1" name="Convert_539629" 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_539583" type="Const" version="opset1">
29
+ <data element_type="u8" shape="1440855" offset="0" size="1440855" />
30
+ <output>
31
+ <port id="0" precision="U8">
32
+ <dim>1440855</dim>
33
+ </port>
34
+ </output>
35
+ </layer>
36
+ <layer id="3" name="StringTensorUnpack_539584" type="StringTensorUnpack" version="extension">
37
+ <data mode="begins_ends" />
38
+ <input>
39
+ <port id="0" precision="U8">
40
+ <dim>1440855</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="Constant_539612" type="Const" version="opset1">
56
+ <data element_type="i32" shape="2022" offset="1440855" size="8088" />
57
+ <output>
58
+ <port id="0" precision="I32">
59
+ <dim>2022</dim>
60
+ </port>
61
+ </output>
62
+ </layer>
63
+ <layer id="5" name="Constant_539610" type="Const" version="opset1">
64
+ <data element_type="i32" shape="1" offset="1448943" size="4" />
65
+ <output>
66
+ <port id="0" precision="I32">
67
+ <dim>1</dim>
68
+ </port>
69
+ </output>
70
+ </layer>
71
+ <layer id="6" name="Constant_539609" type="Const" version="opset1">
72
+ <data element_type="i32" shape="1" offset="1448947" size="4" />
73
+ <output>
74
+ <port id="0" precision="I32">
75
+ <dim>1</dim>
76
+ </port>
77
+ </output>
78
+ </layer>
79
+ <layer id="7" name="Constant_539611" type="Const" version="opset1">
80
+ <data element_type="i32" shape="1" offset="1448951" size="4" />
81
+ <output>
82
+ <port id="0" precision="I32">
83
+ <dim>1</dim>
84
+ </port>
85
+ </output>
86
+ </layer>
87
+ <layer id="8" name="Constant_539614" type="Const" version="opset1">
88
+ <data element_type="i64" shape="1" offset="1448955" size="8" />
89
+ <output>
90
+ <port id="0" precision="I64">
91
+ <dim>1</dim>
92
+ </port>
93
+ </output>
94
+ </layer>
95
+ <layer id="9" name="Slice_539613" type="Slice" version="opset8">
96
+ <input>
97
+ <port id="0" precision="I32">
98
+ <dim>2022</dim>
99
+ </port>
100
+ <port id="1" precision="I32">
101
+ <dim>1</dim>
102
+ </port>
103
+ <port id="2" precision="I32">
104
+ <dim>1</dim>
105
+ </port>
106
+ <port id="3" precision="I32">
107
+ <dim>1</dim>
108
+ </port>
109
+ <port id="4" precision="I64">
110
+ <dim>1</dim>
111
+ </port>
112
+ </input>
113
+ <output>
114
+ <port id="5" precision="I32">
115
+ <dim>2022</dim>
116
+ </port>
117
+ </output>
118
+ </layer>
119
+ <layer id="10" name="VocabDecoder_539615" type="VocabDecoder" version="extension">
120
+ <data skip_tokens="" />
121
+ <input>
122
+ <port id="0" precision="I32">
123
+ <dim>-1</dim>
124
+ <dim>-1</dim>
125
+ </port>
126
+ <port id="1" precision="I32">
127
+ <dim>-1</dim>
128
+ </port>
129
+ <port id="2" precision="I32">
130
+ <dim>-1</dim>
131
+ </port>
132
+ <port id="3" precision="U8">
133
+ <dim>-1</dim>
134
+ </port>
135
+ <port id="4" precision="I32">
136
+ <dim>2022</dim>
137
+ </port>
138
+ </input>
139
+ <output>
140
+ <port id="5" precision="I32">
141
+ <dim>-1</dim>
142
+ </port>
143
+ <port id="6" precision="I32">
144
+ <dim>-1</dim>
145
+ </port>
146
+ <port id="7" precision="I32">
147
+ <dim>-1</dim>
148
+ </port>
149
+ <port id="8" precision="I32">
150
+ <dim>-1</dim>
151
+ </port>
152
+ <port id="9" precision="U8">
153
+ <dim>-1</dim>
154
+ </port>
155
+ </output>
156
+ </layer>
157
+ <layer id="11" name="FuzeRagged_539616" type="FuzeRagged" version="extension">
158
+ <input>
159
+ <port id="0" precision="I32">
160
+ <dim>-1</dim>
161
+ </port>
162
+ <port id="1" precision="I32">
163
+ <dim>-1</dim>
164
+ </port>
165
+ <port id="2" precision="I32">
166
+ <dim>-1</dim>
167
+ </port>
168
+ <port id="3" precision="I32">
169
+ <dim>-1</dim>
170
+ </port>
171
+ </input>
172
+ <output>
173
+ <port id="4" precision="I32">
174
+ <dim>-1</dim>
175
+ </port>
176
+ <port id="5" precision="I32">
177
+ <dim>-1</dim>
178
+ </port>
179
+ </output>
180
+ </layer>
181
+ <layer id="12" name="UTF8Validate_539617" type="UTF8Validate" version="extension">
182
+ <data replace_mode="true" />
183
+ <input>
184
+ <port id="0" precision="I32">
185
+ <dim>-1</dim>
186
+ </port>
187
+ <port id="1" precision="I32">
188
+ <dim>-1</dim>
189
+ </port>
190
+ <port id="2" precision="U8">
191
+ <dim>-1</dim>
192
+ </port>
193
+ </input>
194
+ <output>
195
+ <port id="3" precision="I32">
196
+ <dim>-1</dim>
197
+ </port>
198
+ <port id="4" precision="I32">
199
+ <dim>-1</dim>
200
+ </port>
201
+ <port id="5" precision="U8">
202
+ <dim>-1</dim>
203
+ </port>
204
+ </output>
205
+ </layer>
206
+ <layer id="13" name="Constant_539619" type="Const" version="opset1">
207
+ <data element_type="u8" shape="51" offset="1448963" size="51" />
208
+ <output>
209
+ <port id="0" precision="U8">
210
+ <dim>51</dim>
211
+ </port>
212
+ </output>
213
+ </layer>
214
+ <layer id="14" name="Constant_539621" type="Const" version="opset1">
215
+ <data element_type="u8" shape="2" offset="1449014" size="2" />
216
+ <output>
217
+ <port id="0" precision="U8">
218
+ <dim>2</dim>
219
+ </port>
220
+ </output>
221
+ </layer>
222
+ <layer id="15" name="RegexNormalization_539622" type="RegexNormalization" version="extension">
223
+ <data global_replace="true" />
224
+ <input>
225
+ <port id="0" precision="I32">
226
+ <dim>-1</dim>
227
+ </port>
228
+ <port id="1" precision="I32">
229
+ <dim>-1</dim>
230
+ </port>
231
+ <port id="2" precision="U8">
232
+ <dim>-1</dim>
233
+ </port>
234
+ <port id="3" precision="U8">
235
+ <dim>51</dim>
236
+ </port>
237
+ <port id="4" precision="U8">
238
+ <dim>2</dim>
239
+ </port>
240
+ </input>
241
+ <output>
242
+ <port id="5" precision="I32">
243
+ <dim>-1</dim>
244
+ </port>
245
+ <port id="6" precision="I32">
246
+ <dim>-1</dim>
247
+ </port>
248
+ <port id="7" precision="U8">
249
+ <dim>-1</dim>
250
+ </port>
251
+ </output>
252
+ </layer>
253
+ <layer id="16" name="StringTensorPack_539623" type="StringTensorPack" version="extension">
254
+ <data mode="begins_ends" />
255
+ <input>
256
+ <port id="0" precision="I32">
257
+ <dim>-1</dim>
258
+ </port>
259
+ <port id="1" precision="I32">
260
+ <dim>-1</dim>
261
+ </port>
262
+ <port id="2" precision="U8">
263
+ <dim>-1</dim>
264
+ </port>
265
+ </input>
266
+ <output>
267
+ <port id="3" precision="STRING" names="string_output">
268
+ <dim>-1</dim>
269
+ </port>
270
+ </output>
271
+ </layer>
272
+ <layer id="17" name="Result_539624" type="Result" version="opset1">
273
+ <input>
274
+ <port id="0" precision="STRING">
275
+ <dim>-1</dim>
276
+ </port>
277
+ </input>
278
+ </layer>
279
+ </layers>
280
+ <edges>
281
+ <edge from-layer="0" from-port="0" to-layer="1" to-port="0" />
282
+ <edge from-layer="1" from-port="1" to-layer="10" to-port="0" />
283
+ <edge from-layer="2" from-port="0" to-layer="3" to-port="0" />
284
+ <edge from-layer="3" from-port="1" to-layer="10" to-port="1" />
285
+ <edge from-layer="3" from-port="2" to-layer="10" to-port="2" />
286
+ <edge from-layer="3" from-port="3" to-layer="10" to-port="3" />
287
+ <edge from-layer="4" from-port="0" to-layer="9" to-port="0" />
288
+ <edge from-layer="5" from-port="0" to-layer="9" to-port="1" />
289
+ <edge from-layer="6" from-port="0" to-layer="9" to-port="2" />
290
+ <edge from-layer="7" from-port="0" to-layer="9" to-port="3" />
291
+ <edge from-layer="8" from-port="0" to-layer="9" to-port="4" />
292
+ <edge from-layer="9" from-port="5" to-layer="10" to-port="4" />
293
+ <edge from-layer="10" from-port="7" to-layer="11" to-port="2" />
294
+ <edge from-layer="10" from-port="9" to-layer="12" to-port="2" />
295
+ <edge from-layer="10" from-port="8" to-layer="11" to-port="3" />
296
+ <edge from-layer="10" from-port="6" to-layer="11" to-port="1" />
297
+ <edge from-layer="10" from-port="5" to-layer="11" to-port="0" />
298
+ <edge from-layer="11" from-port="4" to-layer="12" to-port="0" />
299
+ <edge from-layer="11" from-port="5" to-layer="12" to-port="1" />
300
+ <edge from-layer="12" from-port="3" to-layer="15" to-port="0" />
301
+ <edge from-layer="12" from-port="4" to-layer="15" to-port="1" />
302
+ <edge from-layer="12" from-port="5" to-layer="15" to-port="2" />
303
+ <edge from-layer="13" from-port="0" to-layer="15" to-port="3" />
304
+ <edge from-layer="14" from-port="0" to-layer="15" to-port="4" />
305
+ <edge from-layer="15" from-port="5" to-layer="16" to-port="0" />
306
+ <edge from-layer="15" from-port="6" to-layer="16" to-port="1" />
307
+ <edge from-layer="15" from-port="7" to-layer="16" to-port="2" />
308
+ <edge from-layer="16" from-port="3" to-layer="17" to-port="0" />
309
+ </edges>
310
+ <rt_info>
311
+ <add_attention_mask value="True" />
312
+ <add_prefix_space />
313
+ <add_special_tokens value="True" />
314
+ <chat_template value="{% if tools %}{% for message in messages %}{% if message['role'] == 'system' %}{{ '&lt;|system|>&#10;' + message['content'] + '&#10;You are an expert in composing functions. You are given a question and a set of possible functions. &#10;Based on the question, you will need to make one or more function/tool calls to achieve the purpose. &#10;If none of the functions can be used, point it out and refuse to answer. &#10;If the given question lacks the parameters required by the function, also point it out.&#10;&#10; You have access to the following tools:&#10;&lt;tools>' + tools|tojson + '&lt;/tools>&#10;&#10;The output MUST strictly adhere to the following format, and NO other text MUST be included.&#10;The example format is as follows. Please make sure the parameter type is correct. If no function call is needed, please make the tool calls an empty list [].&#10;&lt;tool_call>[&#10;{&quot;name&quot;: &quot;function_name1&quot;, &quot;arguments&quot;: {&quot;argument1&quot;: &quot;value1&quot;, &quot;argument2&quot;: &quot;value2&quot;}},&#10;... (more tool calls as required)&#10;]&lt;/tool_call>' }}{% elif message['role'] == 'user' %}{{ '&lt;|user|>&#10;' + message['content'] + '&#10;' }}{% elif message['role'] == 'assistant' %}{% if not loop.last %}{{ '&lt;|assistant|>&#10;' + message['content'] + eos_token + '&#10;' }}{% else %}{{ '&lt;|assistant|>&#10;' + message['content'] + eos_token }}{% endif %}{% endif %}{% if loop.last and add_generation_prompt %}{{ '&lt;|assistant|>&#10;' }}{% endif %}{% endfor %}{% else %}{% for message in messages %}{% if message['role'] == 'system' %}{{ '&lt;|system|>&#10;' + message['content'] + '&#10;' }}{% elif message['role'] == 'user' %}{{ '&lt;|user|>&#10;' + message['content'] + '&#10;' }}{% elif message['role'] == 'assistant' %}{% if not loop.last %}{{ '&lt;|assistant|>&#10;' + message['content'] + eos_token + '&#10;' }}{% else %}{{ '&lt;|assistant|>&#10;' + message['content'] + eos_token }}{% endif %}{% endif %}{% if loop.last and add_generation_prompt %}{{ '&lt;|assistant|>&#10;' }}{% endif %}{% endfor %}{% endif %}" />
315
+ <clean_up_tokenization_spaces />
316
+ <detokenizer_input_type value="i64" />
317
+ <eos_token_id value="11" />
318
+ <handle_special_tokens_with_re />
319
+ <number_of_inputs value="1" />
320
+ <openvino_tokenizers_version value="2025.0.0.0.dev20241226" />
321
+ <openvino_version value="2025.0.0.dev20241226" />
322
+ <original_tokenizer_class value="&lt;class 'transformers.tokenization_utils_fast.PreTrainedTokenizerFast'>" />
323
+ <pad_token_id value="2023" />
324
+ <sentencepiece_version value="0.2.0" />
325
+ <skip_special_tokens value="True" />
326
+ <streaming_detokenizer value="False" />
327
+ <tiktoken_version value="0.8.0" />
328
+ <tokenizer_output_type value="i64" />
329
+ <tokenizers_version value="0.21.0" />
330
+ <transformers_version value="4.47.1" />
331
+ <use_max_padding value="False" />
332
+ <use_sentencepiece_backend value="False" />
333
+ <utf8_replace_mode value="replace" />
334
+ <with_detokenizer value="True" />
335
+ </rt_info>
336
+ </net>