Hugging Face's logo

keitokei1994
/
sarashina2.2-3b-instruct-v0.1-int4-cw-ov

OpenVINO
llama
Model card Files
xet
Community
keitokei1994 commited on
Commit
9e1931a
·
verified ·
1 Parent(s): b43260c

Upload folder using huggingface_hub

Browse files
Files changed (13) hide show
  1. chat_template.jinja +71 -0
  2. config.json +29 -0
  3. generation_config.json +9 -0
  4. openvino_detokenizer.bin +3 -0
  5. openvino_detokenizer.xml +353 -0
  6. openvino_model.bin +3 -0
  7. openvino_model.xml +0 -0
  8. openvino_tokenizer.bin +3 -0
  9. openvino_tokenizer.xml +645 -0
  10. special_tokens_map.json +51 -0
  11. tokenizer.json +0 -0
  12. tokenizer.model +3 -0
  13. tokenizer_config.json +171 -0
chat_template.jinja ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ {%- set user_messages = messages | selectattr('role', 'equalto', 'user') | list %}
3
+ {%- macro output_available_tools(tools, message) %}
4
+ {%- if tools and (message == user_messages[-1]) %}
5
+ {{- '<|available_tools|>[' }}
6
+ {%- for tool in tools %}
7
+ {%- set tool = tool.function %}
8
+ {{- "{" }}
9
+ {%- for key, val in tool.items() if key != "return" %}
10
+ {%- if val is string %}
11
+ {{- "'" + key + "': '" + val + "'" }}
12
+ {%- else %}
13
+ {{- "'" + key + "': " + val|string }}
14
+ {%- endif %}
15
+ {%- if not loop.last %}
16
+ {{- ", " }}
17
+ {%- endif %}
18
+ {%- endfor %}
19
+ {{- "}" }}
20
+ {%- if not loop.last %}
21
+ {{- ", " }}
22
+ {%- else %}
23
+ {{- "]" }}
24
+ {%- endif %}
25
+ {%- endfor %}
26
+ {{- eos_token -}}
27
+ {%- endif %}
28
+ {%- endmacro %}
29
+
30
+ {%- macro output_tool_results(tool_results) %}
31
+ {{- '<|tool_results|>[' }}
32
+ {%- for tool_result in tool_results %}
33
+ {{- "{'content': " + tool_result.content|string + ", 'call_id': '" + tool_result.call_id + "'}" }}
34
+ {%- endfor %}
35
+ {{- ']' }}
36
+ {{- eos_token -}}
37
+ {%- endmacro %}
38
+
39
+ {%- macro output_tool_calls(tool_calls) %}
40
+ {{- '<|tool_calls|>[' }}
41
+ {%- for tool_call in tool_calls %}
42
+ {{- "{'id': '" + tool_call.id + "', 'name': '" + tool_call.name + "', 'arguments': " + tool_call.arguments|string + '}' }}
43
+ {%- endfor %}
44
+ {{- ']' }}
45
+ {%- endmacro %}
46
+
47
+ {%- for message in messages %}
48
+ {%- if message['role'] == 'user' %}
49
+ {%- if tools is defined %}
50
+ {{- output_available_tools(tools, message) }}
51
+ {%- endif %}
52
+ {{- '<|user|>' + message['content'] + eos_token -}}
53
+ {%- elif message['role'] == 'system' %}
54
+ {{- '<|system|>' + message['content'] + eos_token -}}
55
+ {%- elif message['role'] == 'assistant' %}
56
+ {% set assistant_content = "" %}
57
+ {%- if message.content is defined %}
58
+ {% set assistant_content = message.content %}
59
+ {%- endif %}
60
+ {%- if message.tool_calls is defined and message.tool_calls -%}
61
+ {{- '<|assistant|>' + assistant_content + output_tool_calls(message['tool_calls']) + eos_token -}}
62
+ {%- else %}
63
+ {{- '<|assistant|>' + assistant_content + eos_token }}
64
+ {%- endif %}
65
+ {%- elif message['role'] == 'tool_results' %}
66
+ {{- output_tool_results(message.tool_results) }}
67
+ {%- endif %}
68
+ {%- if loop.last and add_generation_prompt -%}
69
+ {{- '<|assistant|>' -}}
70
+ {%- endif -%}
71
+ {%- endfor %}
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 160,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2560,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 8960,
14
+ "max_position_embeddings": 8192,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 8,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 500000,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.55.4",
27
+ "use_cache": false,
28
+ "vocab_size": 102400
29
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "do_sample": true,
4
+ "eos_token_id": 2,
5
+ "repetition_penalty": 1.05,
6
+ "temperature": 0.7,
7
+ "top_p": 0.9,
8
+ "transformers_version": "4.55.4"
9
+ }
openvino_detokenizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf31c6943c130ef6cd789d835d0f4e6af2620a30618562351102dd2dbe5009b2
3
+ size 1694849
openvino_detokenizer.xml ADDED
@@ -0,0 +1,353 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="detokenizer" version="11">
3
+ <layers>
4
+ <layer id="0" name="Parameter_98487" type="Parameter" version="opset1">
5
+ <data shape="?,?" element_type="i64" />
6
+ <output>
7
+ <port id="0" precision="I64" names="Parameter_98487">
8
+ <dim>-1</dim>
9
+ <dim>-1</dim>
10
+ </port>
11
+ </output>
12
+ </layer>
13
+ <layer id="1" name="Convert_98697" 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_98489" type="Const" version="opset1">
29
+ <data element_type="i32" shape="102400" offset="0" size="409600" />
30
+ <output>
31
+ <port id="0" precision="I32">
32
+ <dim>102400</dim>
33
+ </port>
34
+ </output>
35
+ </layer>
36
+ <layer id="3" name="Constant_98491" type="Const" version="opset1">
37
+ <data element_type="i32" shape="102400" offset="409600" size="409600" />
38
+ <output>
39
+ <port id="0" precision="I32">
40
+ <dim>102400</dim>
41
+ </port>
42
+ </output>
43
+ </layer>
44
+ <layer id="4" name="Constant_98493" type="Const" version="opset1">
45
+ <data element_type="u8" shape="875614" offset="819200" size="875614" />
46
+ <output>
47
+ <port id="0" precision="U8">
48
+ <dim>875614</dim>
49
+ </port>
50
+ </output>
51
+ </layer>
52
+ <layer id="5" name="Slice_98498" type="Const" version="opset1">
53
+ <data element_type="i32" shape="7" offset="1694814" size="28" />
54
+ <output>
55
+ <port id="0" precision="I32">
56
+ <dim>7</dim>
57
+ </port>
58
+ </output>
59
+ </layer>
60
+ <layer id="6" name="VocabDecoder_98500" type="VocabDecoder" version="extension">
61
+ <data skip_tokens="" />
62
+ <input>
63
+ <port id="0" precision="I32">
64
+ <dim>-1</dim>
65
+ <dim>-1</dim>
66
+ </port>
67
+ <port id="1" precision="I32">
68
+ <dim>102400</dim>
69
+ </port>
70
+ <port id="2" precision="I32">
71
+ <dim>102400</dim>
72
+ </port>
73
+ <port id="3" precision="U8">
74
+ <dim>875614</dim>
75
+ </port>
76
+ <port id="4" precision="I32">
77
+ <dim>7</dim>
78
+ </port>
79
+ </input>
80
+ <output>
81
+ <port id="5" precision="I32">
82
+ <dim>-1</dim>
83
+ </port>
84
+ <port id="6" precision="I32">
85
+ <dim>-1</dim>
86
+ </port>
87
+ <port id="7" precision="I32">
88
+ <dim>-1</dim>
89
+ </port>
90
+ <port id="8" precision="I32">
91
+ <dim>-1</dim>
92
+ </port>
93
+ <port id="9" precision="U8">
94
+ <dim>-1</dim>
95
+ </port>
96
+ </output>
97
+ </layer>
98
+ <layer id="7" name="Constant_98502" type="Const" version="opset1">
99
+ <data element_type="u8" shape="3" offset="1694842" size="3" />
100
+ <output>
101
+ <port id="0" precision="U8">
102
+ <dim>3</dim>
103
+ </port>
104
+ </output>
105
+ </layer>
106
+ <layer id="8" name="Constant_98504" type="Const" version="opset1">
107
+ <data element_type="u8" shape="1" offset="1694845" size="1" />
108
+ <output>
109
+ <port id="0" precision="U8">
110
+ <dim>1</dim>
111
+ </port>
112
+ </output>
113
+ </layer>
114
+ <layer id="9" name="RegexNormalization_98505" type="RegexNormalization" version="extension">
115
+ <data global_replace="true" />
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
+ <port id="3" precision="U8">
127
+ <dim>3</dim>
128
+ </port>
129
+ <port id="4" precision="U8">
130
+ <dim>1</dim>
131
+ </port>
132
+ </input>
133
+ <output>
134
+ <port id="5" precision="I32">
135
+ <dim>-1</dim>
136
+ </port>
137
+ <port id="6" precision="I32">
138
+ <dim>-1</dim>
139
+ </port>
140
+ <port id="7" precision="U8">
141
+ <dim>-1</dim>
142
+ </port>
143
+ </output>
144
+ </layer>
145
+ <layer id="10" name="ByteFallback_98506" type="ByteFallback" version="extension">
146
+ <input>
147
+ <port id="0" precision="I32">
148
+ <dim>-1</dim>
149
+ </port>
150
+ <port id="1" precision="I32">
151
+ <dim>-1</dim>
152
+ </port>
153
+ <port id="2" precision="U8">
154
+ <dim>-1</dim>
155
+ </port>
156
+ </input>
157
+ <output>
158
+ <port id="3" precision="I32">
159
+ <dim>-1</dim>
160
+ </port>
161
+ <port id="4" precision="I32">
162
+ <dim>-1</dim>
163
+ </port>
164
+ <port id="5" precision="U8">
165
+ <dim>-1</dim>
166
+ </port>
167
+ </output>
168
+ </layer>
169
+ <layer id="11" name="FuzeRagged_98507" type="FuzeRagged" version="extension">
170
+ <input>
171
+ <port id="0" precision="I32">
172
+ <dim>-1</dim>
173
+ </port>
174
+ <port id="1" precision="I32">
175
+ <dim>-1</dim>
176
+ </port>
177
+ <port id="2" precision="I32">
178
+ <dim>-1</dim>
179
+ </port>
180
+ <port id="3" precision="I32">
181
+ <dim>-1</dim>
182
+ </port>
183
+ </input>
184
+ <output>
185
+ <port id="4" precision="I32">
186
+ <dim>-1</dim>
187
+ </port>
188
+ <port id="5" precision="I32">
189
+ <dim>-1</dim>
190
+ </port>
191
+ </output>
192
+ </layer>
193
+ <layer id="12" name="Constant_98509" type="Const" version="opset1">
194
+ <data element_type="u8" shape="2" offset="1694846" size="2" />
195
+ <output>
196
+ <port id="0" precision="U8">
197
+ <dim>2</dim>
198
+ </port>
199
+ </output>
200
+ </layer>
201
+ <layer id="13" name="Constant_98511" type="Const" version="opset1">
202
+ <data element_type="u8" shape="0" offset="1694848" size="1" />
203
+ <output>
204
+ <port id="0" precision="U8">
205
+ <dim>0</dim>
206
+ </port>
207
+ </output>
208
+ </layer>
209
+ <layer id="14" name="RegexNormalization_98512" type="RegexNormalization" version="extension">
210
+ <data global_replace="true" />
211
+ <input>
212
+ <port id="0" precision="I32">
213
+ <dim>-1</dim>
214
+ </port>
215
+ <port id="1" precision="I32">
216
+ <dim>-1</dim>
217
+ </port>
218
+ <port id="2" precision="U8">
219
+ <dim>-1</dim>
220
+ </port>
221
+ <port id="3" precision="U8">
222
+ <dim>2</dim>
223
+ </port>
224
+ <port id="4" precision="U8">
225
+ <dim>0</dim>
226
+ </port>
227
+ </input>
228
+ <output>
229
+ <port id="5" precision="I32">
230
+ <dim>-1</dim>
231
+ </port>
232
+ <port id="6" precision="I32">
233
+ <dim>-1</dim>
234
+ </port>
235
+ <port id="7" precision="U8">
236
+ <dim>-1</dim>
237
+ </port>
238
+ </output>
239
+ </layer>
240
+ <layer id="15" name="UTF8Validate_98513" type="UTF8Validate" version="extension">
241
+ <data replace_mode="true" />
242
+ <input>
243
+ <port id="0" precision="I32">
244
+ <dim>-1</dim>
245
+ </port>
246
+ <port id="1" precision="I32">
247
+ <dim>-1</dim>
248
+ </port>
249
+ <port id="2" precision="U8">
250
+ <dim>-1</dim>
251
+ </port>
252
+ </input>
253
+ <output>
254
+ <port id="3" precision="I32">
255
+ <dim>-1</dim>
256
+ </port>
257
+ <port id="4" precision="I32">
258
+ <dim>-1</dim>
259
+ </port>
260
+ <port id="5" precision="U8">
261
+ <dim>-1</dim>
262
+ </port>
263
+ </output>
264
+ </layer>
265
+ <layer id="16" name="StringTensorPack_98514" type="StringTensorPack" version="opset15">
266
+ <input>
267
+ <port id="0" precision="I32">
268
+ <dim>-1</dim>
269
+ </port>
270
+ <port id="1" precision="I32">
271
+ <dim>-1</dim>
272
+ </port>
273
+ <port id="2" precision="U8">
274
+ <dim>-1</dim>
275
+ </port>
276
+ </input>
277
+ <output>
278
+ <port id="3" precision="STRING" names="Result_98515,string_output">
279
+ <dim>-1</dim>
280
+ </port>
281
+ </output>
282
+ </layer>
283
+ <layer id="17" name="Result_98515" type="Result" version="opset1" output_names="Result_98515,string_output">
284
+ <input>
285
+ <port id="0" precision="STRING">
286
+ <dim>-1</dim>
287
+ </port>
288
+ </input>
289
+ </layer>
290
+ </layers>
291
+ <edges>
292
+ <edge from-layer="0" from-port="0" to-layer="1" to-port="0" />
293
+ <edge from-layer="1" from-port="1" to-layer="6" to-port="0" />
294
+ <edge from-layer="2" from-port="0" to-layer="6" to-port="1" />
295
+ <edge from-layer="3" from-port="0" to-layer="6" to-port="2" />
296
+ <edge from-layer="4" from-port="0" to-layer="6" to-port="3" />
297
+ <edge from-layer="5" from-port="0" to-layer="6" to-port="4" />
298
+ <edge from-layer="6" from-port="6" to-layer="11" to-port="1" />
299
+ <edge from-layer="6" from-port="5" to-layer="11" to-port="0" />
300
+ <edge from-layer="6" from-port="8" to-layer="9" to-port="1" />
301
+ <edge from-layer="6" from-port="7" to-layer="9" to-port="0" />
302
+ <edge from-layer="6" from-port="9" to-layer="9" to-port="2" />
303
+ <edge from-layer="7" from-port="0" to-layer="9" to-port="3" />
304
+ <edge from-layer="8" from-port="0" to-layer="9" to-port="4" />
305
+ <edge from-layer="9" from-port="5" to-layer="10" to-port="0" />
306
+ <edge from-layer="9" from-port="6" to-layer="10" to-port="1" />
307
+ <edge from-layer="9" from-port="7" to-layer="10" to-port="2" />
308
+ <edge from-layer="10" from-port="3" to-layer="11" to-port="2" />
309
+ <edge from-layer="10" from-port="4" to-layer="11" to-port="3" />
310
+ <edge from-layer="10" from-port="5" to-layer="14" to-port="2" />
311
+ <edge from-layer="11" from-port="5" to-layer="14" to-port="1" />
312
+ <edge from-layer="11" from-port="4" to-layer="14" to-port="0" />
313
+ <edge from-layer="12" from-port="0" to-layer="14" to-port="3" />
314
+ <edge from-layer="13" from-port="0" to-layer="14" to-port="4" />
315
+ <edge from-layer="14" from-port="5" to-layer="15" to-port="0" />
316
+ <edge from-layer="14" from-port="6" to-layer="15" to-port="1" />
317
+ <edge from-layer="14" from-port="7" to-layer="15" to-port="2" />
318
+ <edge from-layer="15" from-port="3" to-layer="16" to-port="0" />
319
+ <edge from-layer="15" from-port="4" to-layer="16" to-port="1" />
320
+ <edge from-layer="15" from-port="5" to-layer="16" to-port="2" />
321
+ <edge from-layer="16" from-port="3" to-layer="17" to-port="0" />
322
+ </edges>
323
+ <rt_info>
324
+ <add_attention_mask value="True" />
325
+ <add_prefix_space />
326
+ <add_special_tokens value="True" />
327
+ <bos_token_id value="1" />
328
+ <chat_template value="&#10;{%- set user_messages = messages | selectattr('role', 'equalto', 'user') | list %}&#10;{%- macro output_available_tools(tools, message) %}&#10;{%- if tools and (message == user_messages[-1]) %}&#10; {{- '&lt;|available_tools|>[' }}&#10; {%- for tool in tools %}&#10; {%- set tool = tool.function %}&#10; {{- &quot;{&quot; }}&#10; {%- for key, val in tool.items() if key != &quot;return&quot; %}&#10; {%- if val is string %}&#10; {{- &quot;'&quot; + key + &quot;': '&quot; + val + &quot;'&quot; }}&#10; {%- else %}&#10; {{- &quot;'&quot; + key + &quot;': &quot; + val|string }}&#10; {%- endif %}&#10; {%- if not loop.last %}&#10; {{- &quot;, &quot; }}&#10; {%- endif %}&#10; {%- endfor %}&#10; {{- &quot;}&quot; }}&#10; {%- if not loop.last %}&#10; {{- &quot;, &quot; }}&#10; {%- else %}&#10; {{- &quot;]&quot; }}&#10; {%- endif %}&#10; {%- endfor %}&#10; {{- eos_token -}}&#10;{%- endif %}&#10;{%- endmacro %}&#10;&#10;{%- macro output_tool_results(tool_results) %}&#10;{{- '&lt;|tool_results|>[' }}&#10;{%- for tool_result in tool_results %}&#10; {{- &quot;{'content': &quot; + tool_result.content|string + &quot;, 'call_id': '&quot; + tool_result.call_id + &quot;'}&quot; }}&#10;{%- endfor %}&#10;{{- ']' }}&#10;{{- eos_token -}}&#10;{%- endmacro %}&#10;&#10;{%- macro output_tool_calls(tool_calls) %}&#10;{{- '&lt;|tool_calls|>[' }}&#10;{%- for tool_call in tool_calls %}&#10; {{- &quot;{'id': '&quot; + tool_call.id + &quot;', 'name': '&quot; + tool_call.name + &quot;', 'arguments': &quot; + tool_call.arguments|string + '}' }}&#10;{%- endfor %}&#10;{{- ']' }}&#10;{%- endmacro %}&#10;&#10;{%- for message in messages %}&#10; {%- if message['role'] == 'user' %}&#10; {%- if tools is defined %}&#10; {{- output_available_tools(tools, message) }}&#10; {%- endif %}&#10; {{- '&lt;|user|>' + message['content'] + eos_token -}}&#10; {%- elif message['role'] == 'system' %}&#10; {{- '&lt;|system|>' + message['content'] + eos_token -}}&#10; {%- elif message['role'] == 'assistant' %}&#10; {% set assistant_content = &quot;&quot; %}&#10; {%- if message.content is defined %}&#10; {% set assistant_content = message.content %}&#10; {%- endif %}&#10; {%- if message.tool_calls is defined and message.tool_calls -%}&#10; {{- '&lt;|assistant|>' + assistant_content + output_tool_calls(message['tool_calls']) + eos_token -}}&#10; {%- else %}&#10; {{- '&lt;|assistant|>' + assistant_content + eos_token }}&#10; {%- endif %}&#10; {%- elif message['role'] == 'tool_results' %}&#10; {{- output_tool_results(message.tool_results) }}&#10; {%- endif %}&#10;{%- if loop.last and add_generation_prompt -%}&#10; {{- '&lt;|assistant|>' -}}&#10;{%- endif -%}&#10;{%- endfor %}&#10;" />
329
+ <clean_up_tokenization_spaces />
330
+ <detokenizer_input_type value="i64" />
331
+ <eos_token_id value="2" />
332
+ <handle_special_tokens_with_re />
333
+ <max_length />
334
+ <number_of_inputs value="1" />
335
+ <openvino_tokenizers_version value="2025.3.0.0-598-57f278c8468" />
336
+ <openvino_version value="2025.3.0-19807-44526285f24-releases/2025/3" />
337
+ <original_post_processor_template value="{&quot;type&quot;: &quot;TemplateProcessing&quot;, &quot;single&quot;: [{&quot;Sequence&quot;: {&quot;id&quot;: &quot;A&quot;, &quot;type_id&quot;: 0}}], &quot;pair&quot;: [{&quot;Sequence&quot;: {&quot;id&quot;: &quot;A&quot;, &quot;type_id&quot;: 0}}, {&quot;Sequence&quot;: {&quot;id&quot;: &quot;B&quot;, &quot;type_id&quot;: 1}}], &quot;special_tokens&quot;: {}}" />
338
+ <original_tokenizer_class value="&lt;class 'transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast'>" />
339
+ <pad_token_id value="3" />
340
+ <processed_post_processor_template value="{&quot;single&quot;: {&quot;ids&quot;: [-1], &quot;type_ids&quot;: [0]}, &quot;pair&quot;: {&quot;ids&quot;: [-1, -2], &quot;type_ids&quot;: [0, 1]}}" />
341
+ <sentencepiece_version value="0.2.1" />
342
+ <skip_special_tokens value="True" />
343
+ <streaming_detokenizer value="False" />
344
+ <tiktoken_version value="0.12.0" />
345
+ <tokenizer_output_type value="i64" />
346
+ <tokenizers_version value="0.21.4" />
347
+ <transformers_version value="4.55.4" />
348
+ <use_max_padding value="False" />
349
+ <use_sentencepiece_backend value="False" />
350
+ <utf8_replace_mode value="replace" />
351
+ <with_detokenizer value="True" />
352
+ </rt_info>
353
+ </net>
openvino_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89a8bb0e9ad0e4d2e74dac9b23413408fd5008bc33392aeadebbdc3ab4c565a0
3
+ size 1942948429
openvino_model.xml ADDED
The diff for this file is too large to render. See raw diff
 
openvino_tokenizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:528209f1d3b9c057cf0850fc53b115af85d87a875ecc6f9401f105e59fc247ee
3
+ size 1933606
openvino_tokenizer.xml ADDED
@@ -0,0 +1,645 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="tokenizer" version="11">
3
+ <layers>
4
+ <layer id="0" name="Parameter_98376" type="Parameter" version="opset1">
5
+ <data shape="?" element_type="string" />
6
+ <output>
7
+ <port id="0" precision="STRING" names="Parameter_98376">
8
+ <dim>-1</dim>
9
+ </port>
10
+ </output>
11
+ </layer>
12
+ <layer id="1" name="Constant_98382" type="Const" version="opset1">
13
+ <data element_type="i64" shape="" offset="0" size="8" />
14
+ <output>
15
+ <port id="0" precision="I64" />
16
+ </output>
17
+ </layer>
18
+ <layer id="2" name="StringTensorUnpack_98377" type="StringTensorUnpack" version="opset15">
19
+ <input>
20
+ <port id="0" precision="STRING">
21
+ <dim>-1</dim>
22
+ </port>
23
+ </input>
24
+ <output>
25
+ <port id="1" precision="I32">
26
+ <dim>-1</dim>
27
+ </port>
28
+ <port id="2" precision="I32">
29
+ <dim>-1</dim>
30
+ </port>
31
+ <port id="3" precision="U8">
32
+ <dim>-1</dim>
33
+ </port>
34
+ </output>
35
+ </layer>
36
+ <layer id="3" name="ShapeOf_98378" type="ShapeOf" version="opset3">
37
+ <data output_type="i64" />
38
+ <input>
39
+ <port id="0" precision="I32">
40
+ <dim>-1</dim>
41
+ </port>
42
+ </input>
43
+ <output>
44
+ <port id="1" precision="I64">
45
+ <dim>1</dim>
46
+ </port>
47
+ </output>
48
+ </layer>
49
+ <layer id="4" name="Constant_98379" type="Const" version="opset1">
50
+ <data element_type="i64" shape="" offset="0" size="8" />
51
+ <output>
52
+ <port id="0" precision="I64" />
53
+ </output>
54
+ </layer>
55
+ <layer id="5" name="Constant_98380" type="Const" version="opset1">
56
+ <data element_type="i64" shape="" offset="0" size="8" />
57
+ <output>
58
+ <port id="0" precision="I64" />
59
+ </output>
60
+ </layer>
61
+ <layer id="6" name="Gather_98381" type="Gather" version="opset8">
62
+ <data batch_dims="0" />
63
+ <input>
64
+ <port id="0" precision="I64">
65
+ <dim>1</dim>
66
+ </port>
67
+ <port id="1" precision="I64" />
68
+ <port id="2" precision="I64" />
69
+ </input>
70
+ <output>
71
+ <port id="3" precision="I64" />
72
+ </output>
73
+ </layer>
74
+ <layer id="7" name="Constant_98383" type="Const" version="opset1">
75
+ <data element_type="i64" shape="" offset="8" size="8" />
76
+ <output>
77
+ <port id="0" precision="I64" />
78
+ </output>
79
+ </layer>
80
+ <layer id="8" name="Range_98384" type="Range" version="opset4">
81
+ <data output_type="i32" />
82
+ <input>
83
+ <port id="0" precision="I64" />
84
+ <port id="1" precision="I64" />
85
+ <port id="2" precision="I64" />
86
+ </input>
87
+ <output>
88
+ <port id="3" precision="I32">
89
+ <dim>-1</dim>
90
+ </port>
91
+ </output>
92
+ </layer>
93
+ <layer id="9" name="Constant_98385" type="Const" version="opset1">
94
+ <data element_type="i64" shape="" offset="8" size="8" />
95
+ <output>
96
+ <port id="0" precision="I64" />
97
+ </output>
98
+ </layer>
99
+ <layer id="10" name="Constant_98386" type="Const" version="opset1">
100
+ <data element_type="i64" shape="" offset="8" size="8" />
101
+ <output>
102
+ <port id="0" precision="I64" />
103
+ </output>
104
+ </layer>
105
+ <layer id="11" name="Add_98387" type="Add" version="opset1">
106
+ <data auto_broadcast="numpy" />
107
+ <input>
108
+ <port id="0" precision="I64" />
109
+ <port id="1" precision="I64" />
110
+ </input>
111
+ <output>
112
+ <port id="2" precision="I64" />
113
+ </output>
114
+ </layer>
115
+ <layer id="12" name="Constant_98388" type="Const" version="opset1">
116
+ <data element_type="i64" shape="" offset="8" size="8" />
117
+ <output>
118
+ <port id="0" precision="I64" />
119
+ </output>
120
+ </layer>
121
+ <layer id="13" name="Range_98389" type="Range" version="opset4">
122
+ <data output_type="i32" />
123
+ <input>
124
+ <port id="0" precision="I64" />
125
+ <port id="1" precision="I64" />
126
+ <port id="2" precision="I64" />
127
+ </input>
128
+ <output>
129
+ <port id="3" precision="I32">
130
+ <dim>-1</dim>
131
+ </port>
132
+ </output>
133
+ </layer>
134
+ <layer id="14" name="Constant_98453" type="Const" version="opset1">
135
+ <data element_type="u8" shape="271" offset="16" size="271" />
136
+ <output>
137
+ <port id="0" precision="U8">
138
+ <dim>271</dim>
139
+ </port>
140
+ </output>
141
+ </layer>
142
+ <layer id="15" name="SpecialTokensSplit_98454" type="SpecialTokensSplit" version="extension">
143
+ <input>
144
+ <port id="0" precision="I32">
145
+ <dim>-1</dim>
146
+ </port>
147
+ <port id="1" precision="I32">
148
+ <dim>-1</dim>
149
+ </port>
150
+ <port id="2" precision="I32">
151
+ <dim>-1</dim>
152
+ </port>
153
+ <port id="3" precision="I32">
154
+ <dim>-1</dim>
155
+ </port>
156
+ <port id="4" precision="U8">
157
+ <dim>-1</dim>
158
+ </port>
159
+ <port id="5" precision="U8">
160
+ <dim>271</dim>
161
+ </port>
162
+ </input>
163
+ <output>
164
+ <port id="6" precision="I32">
165
+ <dim>-1</dim>
166
+ </port>
167
+ <port id="7" precision="I32">
168
+ <dim>-1</dim>
169
+ </port>
170
+ <port id="8" precision="I32">
171
+ <dim>-1</dim>
172
+ </port>
173
+ <port id="9" precision="I32">
174
+ <dim>-1</dim>
175
+ </port>
176
+ <port id="10" precision="U8">
177
+ <dim>-1</dim>
178
+ </port>
179
+ <port id="11" precision="BOOL">
180
+ <dim>-1</dim>
181
+ </port>
182
+ </output>
183
+ </layer>
184
+ <layer id="16" name="Constant_98456" type="Const" version="opset1">
185
+ <data element_type="u8" shape="1" offset="287" size="1" />
186
+ <output>
187
+ <port id="0" precision="U8">
188
+ <dim>1</dim>
189
+ </port>
190
+ </output>
191
+ </layer>
192
+ <layer id="17" name="Constant_98458" type="Const" version="opset1">
193
+ <data element_type="u8" shape="3" offset="288" size="3" />
194
+ <output>
195
+ <port id="0" precision="U8">
196
+ <dim>3</dim>
197
+ </port>
198
+ </output>
199
+ </layer>
200
+ <layer id="18" name="RegexNormalization_98459" type="RegexNormalization" version="extension">
201
+ <data global_replace="true" />
202
+ <input>
203
+ <port id="0" precision="I32">
204
+ <dim>-1</dim>
205
+ </port>
206
+ <port id="1" precision="I32">
207
+ <dim>-1</dim>
208
+ </port>
209
+ <port id="2" precision="U8">
210
+ <dim>-1</dim>
211
+ </port>
212
+ <port id="3" precision="BOOL">
213
+ <dim>-1</dim>
214
+ </port>
215
+ <port id="4" precision="U8">
216
+ <dim>1</dim>
217
+ </port>
218
+ <port id="5" precision="U8">
219
+ <dim>3</dim>
220
+ </port>
221
+ </input>
222
+ <output>
223
+ <port id="6" precision="I32">
224
+ <dim>-1</dim>
225
+ </port>
226
+ <port id="7" precision="I32">
227
+ <dim>-1</dim>
228
+ </port>
229
+ <port id="8" precision="U8">
230
+ <dim>-1</dim>
231
+ </port>
232
+ <port id="9" precision="BOOL">
233
+ <dim>-1</dim>
234
+ </port>
235
+ </output>
236
+ </layer>
237
+ <layer id="19" name="Constant_98461" type="Const" version="opset1">
238
+ <data element_type="i32" shape="102400" offset="291" size="409600" />
239
+ <output>
240
+ <port id="0" precision="I32">
241
+ <dim>102400</dim>
242
+ </port>
243
+ </output>
244
+ </layer>
245
+ <layer id="20" name="Constant_98463" type="Const" version="opset1">
246
+ <data element_type="i32" shape="102400" offset="409891" size="409600" />
247
+ <output>
248
+ <port id="0" precision="I32">
249
+ <dim>102400</dim>
250
+ </port>
251
+ </output>
252
+ </layer>
253
+ <layer id="21" name="Constant_98465" type="Const" version="opset1">
254
+ <data element_type="u8" shape="909286" offset="819491" size="909286" />
255
+ <output>
256
+ <port id="0" precision="U8">
257
+ <dim>909286</dim>
258
+ </port>
259
+ </output>
260
+ </layer>
261
+ <layer id="22" name="Constant_98466_compressed" type="Const" version="opset1">
262
+ <data element_type="f16" shape="102400" offset="1728777" size="204800" />
263
+ <output>
264
+ <port id="0" precision="FP16">
265
+ <dim>102400</dim>
266
+ </port>
267
+ </output>
268
+ </layer>
269
+ <layer id="23" name="Constant_98466" type="Convert" version="opset1">
270
+ <data destination_type="f32" />
271
+ <rt_info>
272
+ <attribute name="decompression" version="0" />
273
+ </rt_info>
274
+ <input>
275
+ <port id="0" precision="FP16">
276
+ <dim>102400</dim>
277
+ </port>
278
+ </input>
279
+ <output>
280
+ <port id="1" precision="FP32">
281
+ <dim>102400</dim>
282
+ </port>
283
+ </output>
284
+ </layer>
285
+ <layer id="24" name="UnigramTokenizer_98467" type="UnigramTokenizer" version="extension">
286
+ <data byte_fallback="true" unk_token_id="0" fuse_unk="true" min_score="inf" />
287
+ <input>
288
+ <port id="0" precision="I32">
289
+ <dim>-1</dim>
290
+ </port>
291
+ <port id="1" precision="I32">
292
+ <dim>-1</dim>
293
+ </port>
294
+ <port id="2" precision="I32">
295
+ <dim>-1</dim>
296
+ </port>
297
+ <port id="3" precision="I32">
298
+ <dim>-1</dim>
299
+ </port>
300
+ <port id="4" precision="U8">
301
+ <dim>-1</dim>
302
+ </port>
303
+ <port id="5" precision="I32">
304
+ <dim>102400</dim>
305
+ </port>
306
+ <port id="6" precision="I32">
307
+ <dim>102400</dim>
308
+ </port>
309
+ <port id="7" precision="U8">
310
+ <dim>909286</dim>
311
+ </port>
312
+ <port id="8" precision="FP32">
313
+ <dim>102400</dim>
314
+ </port>
315
+ </input>
316
+ <output>
317
+ <port id="9" precision="I32">
318
+ <dim>-1</dim>
319
+ </port>
320
+ <port id="10" precision="I32">
321
+ <dim>-1</dim>
322
+ </port>
323
+ <port id="11" precision="I32">
324
+ <dim>-1</dim>
325
+ </port>
326
+ </output>
327
+ </layer>
328
+ <layer id="25" name="Constant_98468" type="Const" version="opset1">
329
+ <data element_type="i32" shape="" offset="1933577" size="4" />
330
+ <output>
331
+ <port id="0" precision="I32" />
332
+ </output>
333
+ </layer>
334
+ <layer id="26" name="Constant_98470" type="Const" version="opset1">
335
+ <data element_type="u8" shape="4" offset="1933581" size="4" />
336
+ <output>
337
+ <port id="0" precision="U8">
338
+ <dim>4</dim>
339
+ </port>
340
+ </output>
341
+ </layer>
342
+ <layer id="27" name="Constant_98472" type="Const" version="opset1">
343
+ <data element_type="u8" shape="13" offset="1933585" size="13" />
344
+ <output>
345
+ <port id="0" precision="U8">
346
+ <dim>13</dim>
347
+ </port>
348
+ </output>
349
+ </layer>
350
+ <layer id="28" name="Truncate_98473" type="Truncate" version="extension">
351
+ <data m_num_inputs="1" />
352
+ <input>
353
+ <port id="0" precision="I32">
354
+ <dim>-1</dim>
355
+ </port>
356
+ <port id="1" precision="I32">
357
+ <dim>-1</dim>
358
+ </port>
359
+ <port id="2" precision="I32">
360
+ <dim>-1</dim>
361
+ </port>
362
+ <port id="3" precision="I32" />
363
+ <port id="4" precision="U8">
364
+ <dim>4</dim>
365
+ </port>
366
+ <port id="5" precision="U8">
367
+ <dim>13</dim>
368
+ </port>
369
+ </input>
370
+ <output>
371
+ <port id="6" precision="I32">
372
+ <dim>-1</dim>
373
+ </port>
374
+ <port id="7" precision="I32">
375
+ <dim>-1</dim>
376
+ </port>
377
+ <port id="8" precision="I32">
378
+ <dim>-1</dim>
379
+ </port>
380
+ </output>
381
+ </layer>
382
+ <layer id="29" name="Constant_98474" type="Const" version="opset1">
383
+ <data element_type="i32" shape="1" offset="1933598" size="4" />
384
+ <output>
385
+ <port id="0" precision="I32">
386
+ <dim>1</dim>
387
+ </port>
388
+ </output>
389
+ </layer>
390
+ <layer id="30" name="CombineSegments_98475" type="CombineSegments" version="extension">
391
+ <input>
392
+ <port id="0" precision="I32">
393
+ <dim>-1</dim>
394
+ </port>
395
+ <port id="1" precision="I32">
396
+ <dim>-1</dim>
397
+ </port>
398
+ <port id="2" precision="I32">
399
+ <dim>-1</dim>
400
+ </port>
401
+ <port id="3" precision="I32">
402
+ <dim>1</dim>
403
+ </port>
404
+ </input>
405
+ <output>
406
+ <port id="4" precision="I32">
407
+ <dim>-1</dim>
408
+ </port>
409
+ <port id="5" precision="I32">
410
+ <dim>-1</dim>
411
+ </port>
412
+ <port id="6" precision="I32">
413
+ <dim>-1</dim>
414
+ </port>
415
+ <port id="7" precision="I32">
416
+ <dim>-1</dim>
417
+ </port>
418
+ <port id="8" precision="I32">
419
+ <dim>-1</dim>
420
+ </port>
421
+ <port id="9" precision="I32">
422
+ <dim>-1</dim>
423
+ </port>
424
+ </output>
425
+ </layer>
426
+ <layer id="31" name="Subtract_98476" type="Subtract" version="opset1">
427
+ <data auto_broadcast="numpy" />
428
+ <input>
429
+ <port id="0" precision="I32">
430
+ <dim>-1</dim>
431
+ </port>
432
+ <port id="1" precision="I32">
433
+ <dim>-1</dim>
434
+ </port>
435
+ </input>
436
+ <output>
437
+ <port id="2" precision="I32">
438
+ <dim>-1</dim>
439
+ </port>
440
+ </output>
441
+ </layer>
442
+ <layer id="32" name="Constant_98477" type="Const" version="opset1">
443
+ <data element_type="i32" shape="" offset="1933598" size="4" />
444
+ <output>
445
+ <port id="0" precision="I32" />
446
+ </output>
447
+ </layer>
448
+ <layer id="33" name="ReduceMax_98478" type="ReduceMax" version="opset1">
449
+ <data keep_dims="false" />
450
+ <input>
451
+ <port id="0" precision="I32">
452
+ <dim>-1</dim>
453
+ </port>
454
+ <port id="1" precision="I32" />
455
+ </input>
456
+ <output>
457
+ <port id="2" precision="I32" />
458
+ </output>
459
+ </layer>
460
+ <layer id="34" name="Constant_98479" type="Const" version="opset1">
461
+ <data element_type="i32" shape="" offset="1933602" size="4" />
462
+ <output>
463
+ <port id="0" precision="I32" />
464
+ </output>
465
+ </layer>
466
+ <layer id="35" name="RaggedToDense_98480" type="RaggedToDense" version="extension">
467
+ <data pad_right="false" m_pad_max_length="false" />
468
+ <input>
469
+ <port id="0" precision="I32">
470
+ <dim>-1</dim>
471
+ </port>
472
+ <port id="1" precision="I32">
473
+ <dim>-1</dim>
474
+ </port>
475
+ <port id="2" precision="I32">
476
+ <dim>-1</dim>
477
+ </port>
478
+ <port id="3" precision="I32" />
479
+ <port id="4" precision="I32" />
480
+ </input>
481
+ <output>
482
+ <port id="5" precision="I32">
483
+ <dim>-1</dim>
484
+ <dim>-1</dim>
485
+ </port>
486
+ <port id="6" precision="BOOL">
487
+ <dim>-1</dim>
488
+ <dim>-1</dim>
489
+ </port>
490
+ </output>
491
+ </layer>
492
+ <layer id="36" name="Convert_98481" type="Convert" version="opset1">
493
+ <data destination_type="i32" />
494
+ <input>
495
+ <port id="0" precision="BOOL">
496
+ <dim>-1</dim>
497
+ <dim>-1</dim>
498
+ </port>
499
+ </input>
500
+ <output>
501
+ <port id="1" precision="I32">
502
+ <dim>-1</dim>
503
+ <dim>-1</dim>
504
+ </port>
505
+ </output>
506
+ </layer>
507
+ <layer id="37" name="Convert_98481.0" type="Convert" version="opset1">
508
+ <data destination_type="i64" />
509
+ <input>
510
+ <port id="0" precision="I32">
511
+ <dim>-1</dim>
512
+ <dim>-1</dim>
513
+ </port>
514
+ </input>
515
+ <output>
516
+ <port id="1" precision="I64" names="attention_mask">
517
+ <dim>-1</dim>
518
+ <dim>-1</dim>
519
+ </port>
520
+ </output>
521
+ </layer>
522
+ <layer id="39" name="RaggedToDense_98480.0" type="Convert" version="opset1">
523
+ <data destination_type="i64" />
524
+ <input>
525
+ <port id="0" precision="I32">
526
+ <dim>-1</dim>
527
+ <dim>-1</dim>
528
+ </port>
529
+ </input>
530
+ <output>
531
+ <port id="1" precision="I64" names="input_ids">
532
+ <dim>-1</dim>
533
+ <dim>-1</dim>
534
+ </port>
535
+ </output>
536
+ </layer>
537
+ <layer id="40" name="Result_98484" type="Result" version="opset1" output_names="input_ids">
538
+ <input>
539
+ <port id="0" precision="I64">
540
+ <dim>-1</dim>
541
+ <dim>-1</dim>
542
+ </port>
543
+ </input>
544
+ </layer>
545
+ <layer id="38" name="Result_98486" type="Result" version="opset1" output_names="attention_mask">
546
+ <input>
547
+ <port id="0" precision="I64">
548
+ <dim>-1</dim>
549
+ <dim>-1</dim>
550
+ </port>
551
+ </input>
552
+ </layer>
553
+ </layers>
554
+ <edges>
555
+ <edge from-layer="0" from-port="0" to-layer="2" to-port="0" />
556
+ <edge from-layer="1" from-port="0" to-layer="8" to-port="0" />
557
+ <edge from-layer="2" from-port="1" to-layer="3" to-port="0" />
558
+ <edge from-layer="2" from-port="3" to-layer="15" to-port="4" />
559
+ <edge from-layer="2" from-port="2" to-layer="15" to-port="3" />
560
+ <edge from-layer="2" from-port="1" to-layer="15" to-port="2" />
561
+ <edge from-layer="3" from-port="1" to-layer="6" to-port="0" />
562
+ <edge from-layer="4" from-port="0" to-layer="6" to-port="1" />
563
+ <edge from-layer="5" from-port="0" to-layer="6" to-port="2" />
564
+ <edge from-layer="6" from-port="3" to-layer="8" to-port="1" />
565
+ <edge from-layer="6" from-port="3" to-layer="11" to-port="0" />
566
+ <edge from-layer="7" from-port="0" to-layer="8" to-port="2" />
567
+ <edge from-layer="8" from-port="3" to-layer="15" to-port="0" />
568
+ <edge from-layer="9" from-port="0" to-layer="13" to-port="0" />
569
+ <edge from-layer="10" from-port="0" to-layer="11" to-port="1" />
570
+ <edge from-layer="11" from-port="2" to-layer="13" to-port="1" />
571
+ <edge from-layer="12" from-port="0" to-layer="13" to-port="2" />
572
+ <edge from-layer="13" from-port="3" to-layer="15" to-port="1" />
573
+ <edge from-layer="14" from-port="0" to-layer="15" to-port="5" />
574
+ <edge from-layer="15" from-port="9" to-layer="18" to-port="1" />
575
+ <edge from-layer="15" from-port="7" to-layer="24" to-port="1" />
576
+ <edge from-layer="15" from-port="6" to-layer="24" to-port="0" />
577
+ <edge from-layer="15" from-port="11" to-layer="18" to-port="3" />
578
+ <edge from-layer="15" from-port="10" to-layer="18" to-port="2" />
579
+ <edge from-layer="15" from-port="8" to-layer="18" to-port="0" />
580
+ <edge from-layer="16" from-port="0" to-layer="18" to-port="4" />
581
+ <edge from-layer="17" from-port="0" to-layer="18" to-port="5" />
582
+ <edge from-layer="18" from-port="8" to-layer="24" to-port="4" />
583
+ <edge from-layer="18" from-port="7" to-layer="24" to-port="3" />
584
+ <edge from-layer="18" from-port="6" to-layer="24" to-port="2" />
585
+ <edge from-layer="19" from-port="0" to-layer="24" to-port="5" />
586
+ <edge from-layer="20" from-port="0" to-layer="24" to-port="6" />
587
+ <edge from-layer="21" from-port="0" to-layer="24" to-port="7" />
588
+ <edge from-layer="22" from-port="0" to-layer="23" to-port="0" />
589
+ <edge from-layer="23" from-port="1" to-layer="24" to-port="8" />
590
+ <edge from-layer="24" from-port="9" to-layer="28" to-port="0" />
591
+ <edge from-layer="24" from-port="10" to-layer="28" to-port="1" />
592
+ <edge from-layer="24" from-port="11" to-layer="28" to-port="2" />
593
+ <edge from-layer="25" from-port="0" to-layer="28" to-port="3" />
594
+ <edge from-layer="26" from-port="0" to-layer="28" to-port="4" />
595
+ <edge from-layer="27" from-port="0" to-layer="28" to-port="5" />
596
+ <edge from-layer="28" from-port="6" to-layer="30" to-port="0" />
597
+ <edge from-layer="28" from-port="7" to-layer="30" to-port="1" />
598
+ <edge from-layer="28" from-port="8" to-layer="30" to-port="2" />
599
+ <edge from-layer="29" from-port="0" to-layer="30" to-port="3" />
600
+ <edge from-layer="30" from-port="5" to-layer="31" to-port="0" />
601
+ <edge from-layer="30" from-port="4" to-layer="31" to-port="1" />
602
+ <edge from-layer="30" from-port="4" to-layer="35" to-port="0" />
603
+ <edge from-layer="30" from-port="5" to-layer="35" to-port="1" />
604
+ <edge from-layer="30" from-port="6" to-layer="35" to-port="2" />
605
+ <edge from-layer="31" from-port="2" to-layer="33" to-port="0" />
606
+ <edge from-layer="32" from-port="0" to-layer="33" to-port="1" />
607
+ <edge from-layer="33" from-port="2" to-layer="35" to-port="3" />
608
+ <edge from-layer="34" from-port="0" to-layer="35" to-port="4" />
609
+ <edge from-layer="35" from-port="6" to-layer="36" to-port="0" />
610
+ <edge from-layer="35" from-port="5" to-layer="39" to-port="0" />
611
+ <edge from-layer="36" from-port="1" to-layer="37" to-port="0" />
612
+ <edge from-layer="37" from-port="1" to-layer="38" to-port="0" />
613
+ <edge from-layer="39" from-port="1" to-layer="40" to-port="0" />
614
+ </edges>
615
+ <rt_info>
616
+ <add_attention_mask value="True" />
617
+ <add_prefix_space />
618
+ <add_special_tokens value="True" />
619
+ <bos_token_id value="1" />
620
+ <chat_template value="&#10;{%- set user_messages = messages | selectattr('role', 'equalto', 'user') | list %}&#10;{%- macro output_available_tools(tools, message) %}&#10;{%- if tools and (message == user_messages[-1]) %}&#10; {{- '&lt;|available_tools|>[' }}&#10; {%- for tool in tools %}&#10; {%- set tool = tool.function %}&#10; {{- &quot;{&quot; }}&#10; {%- for key, val in tool.items() if key != &quot;return&quot; %}&#10; {%- if val is string %}&#10; {{- &quot;'&quot; + key + &quot;': '&quot; + val + &quot;'&quot; }}&#10; {%- else %}&#10; {{- &quot;'&quot; + key + &quot;': &quot; + val|string }}&#10; {%- endif %}&#10; {%- if not loop.last %}&#10; {{- &quot;, &quot; }}&#10; {%- endif %}&#10; {%- endfor %}&#10; {{- &quot;}&quot; }}&#10; {%- if not loop.last %}&#10; {{- &quot;, &quot; }}&#10; {%- else %}&#10; {{- &quot;]&quot; }}&#10; {%- endif %}&#10; {%- endfor %}&#10; {{- eos_token -}}&#10;{%- endif %}&#10;{%- endmacro %}&#10;&#10;{%- macro output_tool_results(tool_results) %}&#10;{{- '&lt;|tool_results|>[' }}&#10;{%- for tool_result in tool_results %}&#10; {{- &quot;{'content': &quot; + tool_result.content|string + &quot;, 'call_id': '&quot; + tool_result.call_id + &quot;'}&quot; }}&#10;{%- endfor %}&#10;{{- ']' }}&#10;{{- eos_token -}}&#10;{%- endmacro %}&#10;&#10;{%- macro output_tool_calls(tool_calls) %}&#10;{{- '&lt;|tool_calls|>[' }}&#10;{%- for tool_call in tool_calls %}&#10; {{- &quot;{'id': '&quot; + tool_call.id + &quot;', 'name': '&quot; + tool_call.name + &quot;', 'arguments': &quot; + tool_call.arguments|string + '}' }}&#10;{%- endfor %}&#10;{{- ']' }}&#10;{%- endmacro %}&#10;&#10;{%- for message in messages %}&#10; {%- if message['role'] == 'user' %}&#10; {%- if tools is defined %}&#10; {{- output_available_tools(tools, message) }}&#10; {%- endif %}&#10; {{- '&lt;|user|>' + message['content'] + eos_token -}}&#10; {%- elif message['role'] == 'system' %}&#10; {{- '&lt;|system|>' + message['content'] + eos_token -}}&#10; {%- elif message['role'] == 'assistant' %}&#10; {% set assistant_content = &quot;&quot; %}&#10; {%- if message.content is defined %}&#10; {% set assistant_content = message.content %}&#10; {%- endif %}&#10; {%- if message.tool_calls is defined and message.tool_calls -%}&#10; {{- '&lt;|assistant|>' + assistant_content + output_tool_calls(message['tool_calls']) + eos_token -}}&#10; {%- else %}&#10; {{- '&lt;|assistant|>' + assistant_content + eos_token }}&#10; {%- endif %}&#10; {%- elif message['role'] == 'tool_results' %}&#10; {{- output_tool_results(message.tool_results) }}&#10; {%- endif %}&#10;{%- if loop.last and add_generation_prompt -%}&#10; {{- '&lt;|assistant|>' -}}&#10;{%- endif -%}&#10;{%- endfor %}&#10;" />
621
+ <clean_up_tokenization_spaces />
622
+ <detokenizer_input_type value="i64" />
623
+ <eos_token_id value="2" />
624
+ <handle_special_tokens_with_re />
625
+ <max_length />
626
+ <number_of_inputs value="1" />
627
+ <openvino_tokenizers_version value="2025.3.0.0-598-57f278c8468" />
628
+ <openvino_version value="2025.3.0-19807-44526285f24-releases/2025/3" />
629
+ <original_post_processor_template value="{&quot;type&quot;: &quot;TemplateProcessing&quot;, &quot;single&quot;: [{&quot;Sequence&quot;: {&quot;id&quot;: &quot;A&quot;, &quot;type_id&quot;: 0}}], &quot;pair&quot;: [{&quot;Sequence&quot;: {&quot;id&quot;: &quot;A&quot;, &quot;type_id&quot;: 0}}, {&quot;Sequence&quot;: {&quot;id&quot;: &quot;B&quot;, &quot;type_id&quot;: 1}}], &quot;special_tokens&quot;: {}}" />
630
+ <original_tokenizer_class value="&lt;class 'transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast'>" />
631
+ <pad_token_id value="3" />
632
+ <processed_post_processor_template value="{&quot;single&quot;: {&quot;ids&quot;: [-1], &quot;type_ids&quot;: [0]}, &quot;pair&quot;: {&quot;ids&quot;: [-1, -2], &quot;type_ids&quot;: [0, 1]}}" />
633
+ <sentencepiece_version value="0.2.1" />
634
+ <skip_special_tokens value="True" />
635
+ <streaming_detokenizer value="False" />
636
+ <tiktoken_version value="0.12.0" />
637
+ <tokenizer_output_type value="i64" />
638
+ <tokenizers_version value="0.21.4" />
639
+ <transformers_version value="4.55.4" />
640
+ <use_max_padding value="False" />
641
+ <use_sentencepiece_backend value="False" />
642
+ <utf8_replace_mode value="replace" />
643
+ <with_detokenizer value="True" />
644
+ </rt_info>
645
+ </net>
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<cls>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "<sep>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:008293028e1a9d9a1038d9b63d989a2319797dfeaa03f171093a57b33a3a8277
3
+ size 1831879
tokenizer_config.json ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_dummy_prefix_space": false,
4
+ "add_eos_token": false,
5
+ "add_prefix_space": false,
6
+ "added_tokens_decoder": {
7
+ "0": {
8
+ "content": "<unk>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false,
13
+ "special": true
14
+ },
15
+ "1": {
16
+ "content": "<s>",
17
+ "lstrip": false,
18
+ "normalized": false,
19
+ "rstrip": false,
20
+ "single_word": false,
21
+ "special": true
22
+ },
23
+ "2": {
24
+ "content": "</s>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false,
29
+ "special": true
30
+ },
31
+ "3": {
32
+ "content": "<pad>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false,
37
+ "special": true
38
+ },
39
+ "4": {
40
+ "content": "<sep>",
41
+ "lstrip": false,
42
+ "normalized": false,
43
+ "rstrip": false,
44
+ "single_word": false,
45
+ "special": true
46
+ },
47
+ "5": {
48
+ "content": "<mask>",
49
+ "lstrip": false,
50
+ "normalized": false,
51
+ "rstrip": false,
52
+ "single_word": false,
53
+ "special": true
54
+ },
55
+ "6": {
56
+ "content": "<cls>",
57
+ "lstrip": false,
58
+ "normalized": false,
59
+ "rstrip": false,
60
+ "single_word": false,
61
+ "special": true
62
+ },
63
+ "7": {
64
+ "content": "<|system|>",
65
+ "lstrip": false,
66
+ "normalized": false,
67
+ "rstrip": false,
68
+ "single_word": false,
69
+ "special": false
70
+ },
71
+ "8": {
72
+ "content": "<|assistant|>",
73
+ "lstrip": false,
74
+ "normalized": false,
75
+ "rstrip": false,
76
+ "single_word": false,
77
+ "special": false
78
+ },
79
+ "9": {
80
+ "content": "<|user|>",
81
+ "lstrip": false,
82
+ "normalized": false,
83
+ "rstrip": false,
84
+ "single_word": false,
85
+ "special": false
86
+ },
87
+ "10": {
88
+ "content": "<|available_tools|>",
89
+ "lstrip": false,
90
+ "normalized": false,
91
+ "rstrip": false,
92
+ "single_word": false,
93
+ "special": false
94
+ },
95
+ "11": {
96
+ "content": "<|tool_calls|>",
97
+ "lstrip": false,
98
+ "normalized": false,
99
+ "rstrip": false,
100
+ "single_word": false,
101
+ "special": false
102
+ },
103
+ "12": {
104
+ "content": "<|tool_results|>",
105
+ "lstrip": false,
106
+ "normalized": false,
107
+ "rstrip": false,
108
+ "single_word": false,
109
+ "special": false
110
+ },
111
+ "13": {
112
+ "content": "<|code|>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false,
117
+ "special": false
118
+ },
119
+ "14": {
120
+ "content": "<|file|>",
121
+ "lstrip": false,
122
+ "normalized": false,
123
+ "rstrip": false,
124
+ "single_word": false,
125
+ "special": false
126
+ },
127
+ "102397": {
128
+ "content": "<|prefix|>",
129
+ "lstrip": false,
130
+ "normalized": false,
131
+ "rstrip": false,
132
+ "single_word": false,
133
+ "special": false
134
+ },
135
+ "102398": {
136
+ "content": "<|suffix|>",
137
+ "lstrip": false,
138
+ "normalized": false,
139
+ "rstrip": false,
140
+ "single_word": false,
141
+ "special": false
142
+ },
143
+ "102399": {
144
+ "content": "<|middle|>",
145
+ "lstrip": false,
146
+ "normalized": false,
147
+ "rstrip": false,
148
+ "single_word": false,
149
+ "special": false
150
+ }
151
+ },
152
+ "bos_token": "<s>",
153
+ "clean_up_tokenization_spaces": false,
154
+ "cls_token": "<cls>",
155
+ "do_lower_case": false,
156
+ "eos_token": "</s>",
157
+ "extra_ids": 0,
158
+ "extra_special_tokens": {},
159
+ "keep_accents": true,
160
+ "legacy": false,
161
+ "mask_token": "<mask>",
162
+ "model_max_length": 1000000000000000019884624838656,
163
+ "pad_token": "<pad>",
164
+ "padding_side": "right",
165
+ "sep_token": "<sep>",
166
+ "sp_model_kwargs": {},
167
+ "spaces_between_special_tokens": false,
168
+ "tokenizer_class": "LlamaTokenizer",
169
+ "unk_token": "<unk>",
170
+ "use_default_system_prompt": false
171
+ }