Hugging Face's logo

helenai
/
Phi-3.5-mini-instruct-ov-int4-sym

OpenVINO
phi3
custom_code
Model card Files
xet
Community
helenai commited on
Commit
02e7120
·
verified ·
1 Parent(s): f3f0b97

Upload folder using huggingface_hub

Browse files
Files changed (13) hide show
  1. added_tokens.json +13 -0
  2. config.json +139 -0
  3. generation_config.json +11 -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 +795 -0
  10. special_tokens_map.json +30 -0
  11. tokenizer.json +0 -0
  12. tokenizer.model +3 -0
  13. tokenizer_config.json +132 -0
added_tokens.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|assistant|>": 32001,
3
+ "<|endoftext|>": 32000,
4
+ "<|end|>": 32007,
5
+ "<|placeholder1|>": 32002,
6
+ "<|placeholder2|>": 32003,
7
+ "<|placeholder3|>": 32004,
8
+ "<|placeholder4|>": 32005,
9
+ "<|placeholder5|>": 32008,
10
+ "<|placeholder6|>": 32009,
11
+ "<|system|>": 32006,
12
+ "<|user|>": 32010
13
+ }
config.json ADDED
@@ -0,0 +1,139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "architectures": [
4
+ "Phi3ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "auto_map": {
9
+ "AutoConfig": "microsoft/Phi-3.5-mini-instruct--configuration_phi3.Phi3Config",
10
+ "AutoModelForCausalLM": "microsoft/Phi-3.5-mini-instruct--modeling_phi3.Phi3ForCausalLM"
11
+ },
12
+ "bos_token_id": 1,
13
+ "embd_pdrop": 0.0,
14
+ "eos_token_id": 32000,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 3072,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 8192,
19
+ "max_position_embeddings": 131072,
20
+ "model_type": "phi3",
21
+ "num_attention_heads": 32,
22
+ "num_hidden_layers": 32,
23
+ "num_key_value_heads": 32,
24
+ "original_max_position_embeddings": 4096,
25
+ "pad_token_id": 32000,
26
+ "partial_rotary_factor": 1.0,
27
+ "resid_pdrop": 0.0,
28
+ "rms_norm_eps": 1e-05,
29
+ "rope_scaling": {
30
+ "long_factor": [
31
+ 1.0800000429153442,
32
+ 1.1100000143051147,
33
+ 1.1399999856948853,
34
+ 1.340000033378601,
35
+ 1.5899999141693115,
36
+ 1.600000023841858,
37
+ 1.6200000047683716,
38
+ 2.620000123977661,
39
+ 3.2300000190734863,
40
+ 3.2300000190734863,
41
+ 4.789999961853027,
42
+ 7.400000095367432,
43
+ 7.700000286102295,
44
+ 9.09000015258789,
45
+ 12.199999809265137,
46
+ 17.670000076293945,
47
+ 24.46000099182129,
48
+ 28.57000160217285,
49
+ 30.420001983642578,
50
+ 30.840002059936523,
51
+ 32.590003967285156,
52
+ 32.93000411987305,
53
+ 42.320003509521484,
54
+ 44.96000289916992,
55
+ 50.340003967285156,
56
+ 50.45000457763672,
57
+ 57.55000305175781,
58
+ 57.93000411987305,
59
+ 58.21000289916992,
60
+ 60.1400032043457,
61
+ 62.61000442504883,
62
+ 62.62000274658203,
63
+ 62.71000289916992,
64
+ 63.1400032043457,
65
+ 63.1400032043457,
66
+ 63.77000427246094,
67
+ 63.93000411987305,
68
+ 63.96000289916992,
69
+ 63.970001220703125,
70
+ 64.02999877929688,
71
+ 64.06999969482422,
72
+ 64.08000183105469,
73
+ 64.12000274658203,
74
+ 64.41000366210938,
75
+ 64.4800033569336,
76
+ 64.51000213623047,
77
+ 64.52999877929688,
78
+ 64.83999633789062
79
+ ],
80
+ "short_factor": [
81
+ 1.0,
82
+ 1.0199999809265137,
83
+ 1.0299999713897705,
84
+ 1.0299999713897705,
85
+ 1.0499999523162842,
86
+ 1.0499999523162842,
87
+ 1.0499999523162842,
88
+ 1.0499999523162842,
89
+ 1.0499999523162842,
90
+ 1.0699999332427979,
91
+ 1.0999999046325684,
92
+ 1.1099998950958252,
93
+ 1.1599998474121094,
94
+ 1.1599998474121094,
95
+ 1.1699998378753662,
96
+ 1.2899998426437378,
97
+ 1.339999794960022,
98
+ 1.679999828338623,
99
+ 1.7899998426437378,
100
+ 1.8199998140335083,
101
+ 1.8499997854232788,
102
+ 1.8799997568130493,
103
+ 1.9099997282028198,
104
+ 1.9399996995925903,
105
+ 1.9899996519088745,
106
+ 2.0199997425079346,
107
+ 2.0199997425079346,
108
+ 2.0199997425079346,
109
+ 2.0199997425079346,
110
+ 2.0199997425079346,
111
+ 2.0199997425079346,
112
+ 2.0299997329711914,
113
+ 2.0299997329711914,
114
+ 2.0299997329711914,
115
+ 2.0299997329711914,
116
+ 2.0299997329711914,
117
+ 2.0299997329711914,
118
+ 2.0299997329711914,
119
+ 2.0299997329711914,
120
+ 2.0299997329711914,
121
+ 2.0799996852874756,
122
+ 2.0899996757507324,
123
+ 2.189999580383301,
124
+ 2.2199995517730713,
125
+ 2.5899994373321533,
126
+ 2.729999542236328,
127
+ 2.749999523162842,
128
+ 2.8399994373321533
129
+ ],
130
+ "type": "longrope"
131
+ },
132
+ "rope_theta": 10000.0,
133
+ "sliding_window": 262144,
134
+ "tie_word_embeddings": false,
135
+ "torch_dtype": "bfloat16",
136
+ "transformers_version": "4.51.3",
137
+ "use_cache": true,
138
+ "vocab_size": 32064
139
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": [
5
+ 32007,
6
+ 32001,
7
+ 32000
8
+ ],
9
+ "pad_token_id": 32000,
10
+ "transformers_version": "4.51.3"
11
+ }
openvino_detokenizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03033c0408d4ab0211cc6ebed4996eba143e9eb7ff87cce30d46beb111c411d7
3
+ size 467235
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_135166" type="Parameter" version="opset1">
5
+ <data shape="?,?" element_type="i64" />
6
+ <output>
7
+ <port id="0" precision="I64" names="Parameter_135166">
8
+ <dim>-1</dim>
9
+ <dim>-1</dim>
10
+ </port>
11
+ </output>
12
+ </layer>
13
+ <layer id="1" name="Convert_135370" 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_135122" type="Const" version="opset1">
29
+ <data element_type="i32" shape="32011" offset="0" size="128044" />
30
+ <output>
31
+ <port id="0" precision="I32">
32
+ <dim>32011</dim>
33
+ </port>
34
+ </output>
35
+ </layer>
36
+ <layer id="3" name="Constant_135124" type="Const" version="opset1">
37
+ <data element_type="i32" shape="32011" offset="128044" size="128044" />
38
+ <output>
39
+ <port id="0" precision="I32">
40
+ <dim>32011</dim>
41
+ </port>
42
+ </output>
43
+ </layer>
44
+ <layer id="4" name="Constant_135126" type="Const" version="opset1">
45
+ <data element_type="u8" shape="211088" offset="256088" size="211088" />
46
+ <output>
47
+ <port id="0" precision="U8">
48
+ <dim>211088</dim>
49
+ </port>
50
+ </output>
51
+ </layer>
52
+ <layer id="5" name="Slice_135171" type="Const" version="opset1">
53
+ <data element_type="i32" shape="13" offset="467176" size="52" />
54
+ <output>
55
+ <port id="0" precision="I32">
56
+ <dim>13</dim>
57
+ </port>
58
+ </output>
59
+ </layer>
60
+ <layer id="6" name="VocabDecoder_135173" 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>32011</dim>
69
+ </port>
70
+ <port id="2" precision="I32">
71
+ <dim>32011</dim>
72
+ </port>
73
+ <port id="3" precision="U8">
74
+ <dim>211088</dim>
75
+ </port>
76
+ <port id="4" precision="I32">
77
+ <dim>13</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_135175" type="Const" version="opset1">
99
+ <data element_type="u8" shape="3" offset="467228" 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_135177" type="Const" version="opset1">
107
+ <data element_type="u8" shape="1" offset="467231" 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_135178" 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_135179" 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_135180" 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_135182" type="Const" version="opset1">
194
+ <data element_type="u8" shape="2" offset="467232" 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_135184" type="Const" version="opset1">
202
+ <data element_type="u8" shape="0" offset="467234" 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_135185" 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_135186" 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_135187" 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_135188,string_output">
279
+ <dim>-1</dim>
280
+ </port>
281
+ </output>
282
+ </layer>
283
+ <layer id="17" name="Result_135188" type="Result" version="opset1" output_names="Result_135188,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="7" to-layer="9" to-port="0" />
299
+ <edge from-layer="6" from-port="8" to-layer="9" to-port="1" />
300
+ <edge from-layer="6" from-port="9" to-layer="9" to-port="2" />
301
+ <edge from-layer="6" from-port="5" to-layer="11" to-port="0" />
302
+ <edge from-layer="6" from-port="6" to-layer="11" to-port="1" />
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="4" to-layer="14" to-port="0" />
312
+ <edge from-layer="11" from-port="5" to-layer="14" to-port="1" />
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="{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'&lt;|system|>&#10;' + message['content'] + '&lt;|end|>&#10;'}}{% elif message['role'] == 'user' %}{{'&lt;|user|>&#10;' + message['content'] + '&lt;|end|>&#10;'}}{% elif message['role'] == 'assistant' %}{{'&lt;|assistant|>&#10;' + message['content'] + '&lt;|end|>&#10;'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '&lt;|assistant|>&#10;' }}{% else %}{{ eos_token }}{% endif %}" />
329
+ <clean_up_tokenization_spaces />
330
+ <detokenizer_input_type value="i64" />
331
+ <eos_token_id value="32000" />
332
+ <handle_special_tokens_with_re />
333
+ <max_length />
334
+ <number_of_inputs value="1" />
335
+ <openvino_tokenizers_version value="2025.3.0.0-570-5c466f128db" />
336
+ <openvino_version value="2025.3.0-19339-f4f4ce0d147" />
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="32000" />
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="0.2.0" />
342
+ <skip_special_tokens value="True" />
343
+ <streaming_detokenizer value="False" />
344
+ <tiktoken_version value="0.9.0" />
345
+ <tokenizer_output_type value="i64" />
346
+ <tokenizers_version value="0.21.1" />
347
+ <transformers_version value="4.51.3" />
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:b97ba1abb57cec27cf13a3f192b11c88294f367a4c87d8465ee114c07962caf9
3
+ size 2011963656
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:b02483286ce1a6c0d4722125d6a6e69313d2920b3f5475d253652cafa802aa0a
3
+ size 1881988
openvino_tokenizer.xml ADDED
@@ -0,0 +1,795 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="tokenizer" version="11">
3
+ <layers>
4
+ <layer id="0" name="Parameter_135032" type="Parameter" version="opset1">
5
+ <data shape="?" element_type="string" />
6
+ <output>
7
+ <port id="0" precision="STRING" names="Parameter_135032">
8
+ <dim>-1</dim>
9
+ </port>
10
+ </output>
11
+ </layer>
12
+ <layer id="1" name="Constant_135038" type="Const" version="opset1">
13
+ <data element_type="i32" shape="" offset="0" size="4" />
14
+ <output>
15
+ <port id="0" precision="I32" />
16
+ </output>
17
+ </layer>
18
+ <layer id="2" name="StringTensorUnpack_135033" 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_135034" 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_135035" type="Const" version="opset1">
50
+ <data element_type="i32" shape="" offset="0" size="4" />
51
+ <output>
52
+ <port id="0" precision="I32" />
53
+ </output>
54
+ </layer>
55
+ <layer id="5" name="Constant_135036" type="Const" version="opset1">
56
+ <data element_type="i32" shape="" offset="0" size="4" />
57
+ <output>
58
+ <port id="0" precision="I32" />
59
+ </output>
60
+ </layer>
61
+ <layer id="6" name="Gather_135037" 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="I32" />
68
+ <port id="2" precision="I32" />
69
+ </input>
70
+ <output>
71
+ <port id="3" precision="I64" />
72
+ </output>
73
+ </layer>
74
+ <layer id="7" name="Constant_135039" type="Const" version="opset1">
75
+ <data element_type="i32" shape="" offset="4" size="4" />
76
+ <output>
77
+ <port id="0" precision="I32" />
78
+ </output>
79
+ </layer>
80
+ <layer id="8" name="Range_135040" type="Range" version="opset4">
81
+ <data output_type="i32" />
82
+ <input>
83
+ <port id="0" precision="I32" />
84
+ <port id="1" precision="I64" />
85
+ <port id="2" precision="I32" />
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_135041" type="Const" version="opset1">
94
+ <data element_type="i32" shape="" offset="4" size="4" />
95
+ <output>
96
+ <port id="0" precision="I32" />
97
+ </output>
98
+ </layer>
99
+ <layer id="10" name="Constant_135042" 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_135043" 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_135044" type="Const" version="opset1">
116
+ <data element_type="i32" shape="" offset="4" size="4" />
117
+ <output>
118
+ <port id="0" precision="I32" />
119
+ </output>
120
+ </layer>
121
+ <layer id="13" name="Range_135045" type="Range" version="opset4">
122
+ <data output_type="i32" />
123
+ <input>
124
+ <port id="0" precision="I32" />
125
+ <port id="1" precision="I64" />
126
+ <port id="2" precision="I32" />
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_135109" type="Const" version="opset1">
135
+ <data element_type="u8" shape="328" offset="16" size="328" />
136
+ <output>
137
+ <port id="0" precision="U8">
138
+ <dim>328</dim>
139
+ </port>
140
+ </output>
141
+ </layer>
142
+ <layer id="15" name="SpecialTokensSplit_135110" 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>328</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_135112" type="Const" version="opset1">
185
+ <data element_type="u8" shape="13" offset="344" size="13" />
186
+ <output>
187
+ <port id="0" precision="U8">
188
+ <dim>13</dim>
189
+ </port>
190
+ </output>
191
+ </layer>
192
+ <layer id="17" name="Constant_135114" type="Const" version="opset1">
193
+ <data element_type="u8" shape="5" offset="357" size="5" />
194
+ <output>
195
+ <port id="0" precision="U8">
196
+ <dim>5</dim>
197
+ </port>
198
+ </output>
199
+ </layer>
200
+ <layer id="18" name="RegexNormalization_135115" 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>13</dim>
217
+ </port>
218
+ <port id="5" precision="U8">
219
+ <dim>5</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_135117" type="Const" version="opset1">
238
+ <data element_type="u8" shape="1" offset="362" size="1" />
239
+ <output>
240
+ <port id="0" precision="U8">
241
+ <dim>1</dim>
242
+ </port>
243
+ </output>
244
+ </layer>
245
+ <layer id="20" name="Constant_135119" type="Const" version="opset1">
246
+ <data element_type="u8" shape="3" offset="363" size="3" />
247
+ <output>
248
+ <port id="0" precision="U8">
249
+ <dim>3</dim>
250
+ </port>
251
+ </output>
252
+ </layer>
253
+ <layer id="21" name="RegexNormalization_135120" type="RegexNormalization" version="extension">
254
+ <data global_replace="true" />
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
+ <port id="3" precision="BOOL">
266
+ <dim>-1</dim>
267
+ </port>
268
+ <port id="4" precision="U8">
269
+ <dim>1</dim>
270
+ </port>
271
+ <port id="5" precision="U8">
272
+ <dim>3</dim>
273
+ </port>
274
+ </input>
275
+ <output>
276
+ <port id="6" precision="I32">
277
+ <dim>-1</dim>
278
+ </port>
279
+ <port id="7" precision="I32">
280
+ <dim>-1</dim>
281
+ </port>
282
+ <port id="8" precision="U8">
283
+ <dim>-1</dim>
284
+ </port>
285
+ <port id="9" precision="BOOL">
286
+ <dim>-1</dim>
287
+ </port>
288
+ </output>
289
+ </layer>
290
+ <layer id="22" name="Constant_135122" type="Const" version="opset1">
291
+ <data element_type="i32" shape="32011" offset="366" size="128044" />
292
+ <output>
293
+ <port id="0" precision="I32">
294
+ <dim>32011</dim>
295
+ </port>
296
+ </output>
297
+ </layer>
298
+ <layer id="23" name="Constant_135124" type="Const" version="opset1">
299
+ <data element_type="i32" shape="32011" offset="128410" size="128044" />
300
+ <output>
301
+ <port id="0" precision="I32">
302
+ <dim>32011</dim>
303
+ </port>
304
+ </output>
305
+ </layer>
306
+ <layer id="24" name="Constant_135126" type="Const" version="opset1">
307
+ <data element_type="u8" shape="211088" offset="256454" size="211088" />
308
+ <output>
309
+ <port id="0" precision="U8">
310
+ <dim>211088</dim>
311
+ </port>
312
+ </output>
313
+ </layer>
314
+ <layer id="25" name="Constant_135134" type="Const" version="opset1">
315
+ <data element_type="i32" shape="61249" offset="467542" size="244996" />
316
+ <output>
317
+ <port id="0" precision="I32">
318
+ <dim>61249</dim>
319
+ </port>
320
+ </output>
321
+ </layer>
322
+ <layer id="26" name="Constant_135136" type="Const" version="opset1">
323
+ <data element_type="i32" shape="61249" offset="712538" size="244996" />
324
+ <output>
325
+ <port id="0" precision="I32">
326
+ <dim>61249</dim>
327
+ </port>
328
+ </output>
329
+ </layer>
330
+ <layer id="27" name="Constant_135138" type="Const" version="opset1">
331
+ <data element_type="u8" shape="254123" offset="957534" size="254123" />
332
+ <output>
333
+ <port id="0" precision="U8">
334
+ <dim>254123</dim>
335
+ </port>
336
+ </output>
337
+ </layer>
338
+ <layer id="28" name="Constant_135140" type="Const" version="opset1">
339
+ <data element_type="i32" shape="61249" offset="1211657" size="244996" />
340
+ <output>
341
+ <port id="0" precision="I32">
342
+ <dim>61249</dim>
343
+ </port>
344
+ </output>
345
+ </layer>
346
+ <layer id="29" name="Constant_135142" type="Const" version="opset1">
347
+ <data element_type="i32" shape="61249" offset="1456653" size="244996" />
348
+ <output>
349
+ <port id="0" precision="I32">
350
+ <dim>61249</dim>
351
+ </port>
352
+ </output>
353
+ </layer>
354
+ <layer id="30" name="Constant_135144" type="Const" version="opset1">
355
+ <data element_type="u8" shape="167806" offset="1701649" size="167806" />
356
+ <output>
357
+ <port id="0" precision="U8">
358
+ <dim>167806</dim>
359
+ </port>
360
+ </output>
361
+ </layer>
362
+ <layer id="31" name="Constant_135128" type="Const" version="opset1">
363
+ <data element_type="i32" shape="475" offset="1869455" size="1900" />
364
+ <output>
365
+ <port id="0" precision="I32">
366
+ <dim>475</dim>
367
+ </port>
368
+ </output>
369
+ </layer>
370
+ <layer id="32" name="Constant_135130" type="Const" version="opset1">
371
+ <data element_type="i32" shape="475" offset="1871355" size="1900" />
372
+ <output>
373
+ <port id="0" precision="I32">
374
+ <dim>475</dim>
375
+ </port>
376
+ </output>
377
+ </layer>
378
+ <layer id="33" name="Constant_135132" type="Const" version="opset1">
379
+ <data element_type="u8" shape="6808" offset="1873255" size="6808" />
380
+ <output>
381
+ <port id="0" precision="U8">
382
+ <dim>6808</dim>
383
+ </port>
384
+ </output>
385
+ </layer>
386
+ <layer id="34" name="Constant_135145" type="Const" version="opset1">
387
+ <data element_type="i32" shape="475" offset="1880063" size="1900" />
388
+ <output>
389
+ <port id="0" precision="I32">
390
+ <dim>475</dim>
391
+ </port>
392
+ </output>
393
+ </layer>
394
+ <layer id="35" name="BPETokenizer_135146" type="BPETokenizer" version="extension">
395
+ <data unk_token="&lt;unk>" fuse_unk="true" suffix_indicator="" end_suffix="" byte_fallback="true" cache_capacity="20000" />
396
+ <input>
397
+ <port id="0" precision="I32">
398
+ <dim>-1</dim>
399
+ </port>
400
+ <port id="1" precision="I32">
401
+ <dim>-1</dim>
402
+ </port>
403
+ <port id="2" precision="I32">
404
+ <dim>-1</dim>
405
+ </port>
406
+ <port id="3" precision="I32">
407
+ <dim>-1</dim>
408
+ </port>
409
+ <port id="4" precision="U8">
410
+ <dim>-1</dim>
411
+ </port>
412
+ <port id="5" precision="I32">
413
+ <dim>32011</dim>
414
+ </port>
415
+ <port id="6" precision="I32">
416
+ <dim>32011</dim>
417
+ </port>
418
+ <port id="7" precision="U8">
419
+ <dim>211088</dim>
420
+ </port>
421
+ <port id="8" precision="I32">
422
+ <dim>61249</dim>
423
+ </port>
424
+ <port id="9" precision="I32">
425
+ <dim>61249</dim>
426
+ </port>
427
+ <port id="10" precision="U8">
428
+ <dim>254123</dim>
429
+ </port>
430
+ <port id="11" precision="I32">
431
+ <dim>61249</dim>
432
+ </port>
433
+ <port id="12" precision="I32">
434
+ <dim>61249</dim>
435
+ </port>
436
+ <port id="13" precision="U8">
437
+ <dim>167806</dim>
438
+ </port>
439
+ <port id="14" precision="I32">
440
+ <dim>475</dim>
441
+ </port>
442
+ <port id="15" precision="I32">
443
+ <dim>475</dim>
444
+ </port>
445
+ <port id="16" precision="U8">
446
+ <dim>6808</dim>
447
+ </port>
448
+ <port id="17" precision="I32">
449
+ <dim>475</dim>
450
+ </port>
451
+ </input>
452
+ <output>
453
+ <port id="18" precision="I32">
454
+ <dim>-1</dim>
455
+ </port>
456
+ <port id="19" precision="I32">
457
+ <dim>-1</dim>
458
+ </port>
459
+ <port id="20" precision="I32">
460
+ <dim>-1</dim>
461
+ </port>
462
+ </output>
463
+ </layer>
464
+ <layer id="36" name="Constant_135147" type="Const" version="opset1">
465
+ <data element_type="i32" shape="" offset="1881963" size="4" />
466
+ <output>
467
+ <port id="0" precision="I32" />
468
+ </output>
469
+ </layer>
470
+ <layer id="37" name="Constant_135149" type="Const" version="opset1">
471
+ <data element_type="u8" shape="4" offset="1881967" size="4" />
472
+ <output>
473
+ <port id="0" precision="U8">
474
+ <dim>4</dim>
475
+ </port>
476
+ </output>
477
+ </layer>
478
+ <layer id="38" name="Constant_135151" type="Const" version="opset1">
479
+ <data element_type="u8" shape="13" offset="1881971" size="13" />
480
+ <output>
481
+ <port id="0" precision="U8">
482
+ <dim>13</dim>
483
+ </port>
484
+ </output>
485
+ </layer>
486
+ <layer id="39" name="Truncate_135152" type="Truncate" version="extension">
487
+ <data m_num_inputs="1" />
488
+ <input>
489
+ <port id="0" precision="I32">
490
+ <dim>-1</dim>
491
+ </port>
492
+ <port id="1" precision="I32">
493
+ <dim>-1</dim>
494
+ </port>
495
+ <port id="2" precision="I32">
496
+ <dim>-1</dim>
497
+ </port>
498
+ <port id="3" precision="I32" />
499
+ <port id="4" precision="U8">
500
+ <dim>4</dim>
501
+ </port>
502
+ <port id="5" precision="U8">
503
+ <dim>13</dim>
504
+ </port>
505
+ </input>
506
+ <output>
507
+ <port id="6" precision="I32">
508
+ <dim>-1</dim>
509
+ </port>
510
+ <port id="7" precision="I32">
511
+ <dim>-1</dim>
512
+ </port>
513
+ <port id="8" precision="I32">
514
+ <dim>-1</dim>
515
+ </port>
516
+ </output>
517
+ </layer>
518
+ <layer id="40" name="Constant_135153" type="Const" version="opset1">
519
+ <data element_type="i32" shape="1" offset="0" size="4" />
520
+ <output>
521
+ <port id="0" precision="I32">
522
+ <dim>1</dim>
523
+ </port>
524
+ </output>
525
+ </layer>
526
+ <layer id="41" name="CombineSegments_135154" type="CombineSegments" version="extension">
527
+ <input>
528
+ <port id="0" precision="I32">
529
+ <dim>-1</dim>
530
+ </port>
531
+ <port id="1" precision="I32">
532
+ <dim>-1</dim>
533
+ </port>
534
+ <port id="2" precision="I32">
535
+ <dim>-1</dim>
536
+ </port>
537
+ <port id="3" precision="I32">
538
+ <dim>1</dim>
539
+ </port>
540
+ </input>
541
+ <output>
542
+ <port id="4" precision="I32">
543
+ <dim>-1</dim>
544
+ </port>
545
+ <port id="5" precision="I32">
546
+ <dim>-1</dim>
547
+ </port>
548
+ <port id="6" precision="I32">
549
+ <dim>-1</dim>
550
+ </port>
551
+ <port id="7" precision="I32">
552
+ <dim>-1</dim>
553
+ </port>
554
+ <port id="8" precision="I32">
555
+ <dim>-1</dim>
556
+ </port>
557
+ <port id="9" precision="I32">
558
+ <dim>-1</dim>
559
+ </port>
560
+ </output>
561
+ </layer>
562
+ <layer id="42" name="Subtract_135155" type="Subtract" version="opset1">
563
+ <data auto_broadcast="numpy" />
564
+ <input>
565
+ <port id="0" precision="I32">
566
+ <dim>-1</dim>
567
+ </port>
568
+ <port id="1" precision="I32">
569
+ <dim>-1</dim>
570
+ </port>
571
+ </input>
572
+ <output>
573
+ <port id="2" precision="I32">
574
+ <dim>-1</dim>
575
+ </port>
576
+ </output>
577
+ </layer>
578
+ <layer id="43" name="Constant_135156" type="Const" version="opset1">
579
+ <data element_type="i32" shape="" offset="0" size="4" />
580
+ <output>
581
+ <port id="0" precision="I32" />
582
+ </output>
583
+ </layer>
584
+ <layer id="44" name="ReduceMax_135157" type="ReduceMax" version="opset1">
585
+ <data keep_dims="false" />
586
+ <input>
587
+ <port id="0" precision="I32">
588
+ <dim>-1</dim>
589
+ </port>
590
+ <port id="1" precision="I32" />
591
+ </input>
592
+ <output>
593
+ <port id="2" precision="I32" />
594
+ </output>
595
+ </layer>
596
+ <layer id="45" name="Constant_135158" type="Const" version="opset1">
597
+ <data element_type="i32" shape="" offset="1881984" size="4" />
598
+ <output>
599
+ <port id="0" precision="I32" />
600
+ </output>
601
+ </layer>
602
+ <layer id="46" name="RaggedToDense_135159" type="RaggedToDense" version="extension">
603
+ <data pad_right="false" m_pad_max_length="false" />
604
+ <input>
605
+ <port id="0" precision="I32">
606
+ <dim>-1</dim>
607
+ </port>
608
+ <port id="1" precision="I32">
609
+ <dim>-1</dim>
610
+ </port>
611
+ <port id="2" precision="I32">
612
+ <dim>-1</dim>
613
+ </port>
614
+ <port id="3" precision="I32" />
615
+ <port id="4" precision="I32" />
616
+ </input>
617
+ <output>
618
+ <port id="5" precision="I32">
619
+ <dim>-1</dim>
620
+ <dim>-1</dim>
621
+ </port>
622
+ <port id="6" precision="BOOL">
623
+ <dim>-1</dim>
624
+ <dim>-1</dim>
625
+ </port>
626
+ </output>
627
+ </layer>
628
+ <layer id="47" name="Convert_135160" type="Convert" version="opset1">
629
+ <data destination_type="i32" />
630
+ <input>
631
+ <port id="0" precision="BOOL">
632
+ <dim>-1</dim>
633
+ <dim>-1</dim>
634
+ </port>
635
+ </input>
636
+ <output>
637
+ <port id="1" precision="I32">
638
+ <dim>-1</dim>
639
+ <dim>-1</dim>
640
+ </port>
641
+ </output>
642
+ </layer>
643
+ <layer id="48" name="Convert_135160.0" type="Convert" version="opset1">
644
+ <data destination_type="i64" />
645
+ <input>
646
+ <port id="0" precision="I32">
647
+ <dim>-1</dim>
648
+ <dim>-1</dim>
649
+ </port>
650
+ </input>
651
+ <output>
652
+ <port id="1" precision="I64" names="attention_mask">
653
+ <dim>-1</dim>
654
+ <dim>-1</dim>
655
+ </port>
656
+ </output>
657
+ </layer>
658
+ <layer id="50" name="RaggedToDense_135159.0" type="Convert" version="opset1">
659
+ <data destination_type="i64" />
660
+ <input>
661
+ <port id="0" precision="I32">
662
+ <dim>-1</dim>
663
+ <dim>-1</dim>
664
+ </port>
665
+ </input>
666
+ <output>
667
+ <port id="1" precision="I64" names="input_ids">
668
+ <dim>-1</dim>
669
+ <dim>-1</dim>
670
+ </port>
671
+ </output>
672
+ </layer>
673
+ <layer id="51" name="Result_135163" type="Result" version="opset1" output_names="input_ids">
674
+ <input>
675
+ <port id="0" precision="I64">
676
+ <dim>-1</dim>
677
+ <dim>-1</dim>
678
+ </port>
679
+ </input>
680
+ </layer>
681
+ <layer id="49" name="Result_135165" type="Result" version="opset1" output_names="attention_mask">
682
+ <input>
683
+ <port id="0" precision="I64">
684
+ <dim>-1</dim>
685
+ <dim>-1</dim>
686
+ </port>
687
+ </input>
688
+ </layer>
689
+ </layers>
690
+ <edges>
691
+ <edge from-layer="0" from-port="0" to-layer="2" to-port="0" />
692
+ <edge from-layer="1" from-port="0" to-layer="8" to-port="0" />
693
+ <edge from-layer="2" from-port="1" to-layer="3" to-port="0" />
694
+ <edge from-layer="2" from-port="1" to-layer="15" to-port="2" />
695
+ <edge from-layer="2" from-port="2" to-layer="15" to-port="3" />
696
+ <edge from-layer="2" from-port="3" to-layer="15" to-port="4" />
697
+ <edge from-layer="3" from-port="1" to-layer="6" to-port="0" />
698
+ <edge from-layer="4" from-port="0" to-layer="6" to-port="1" />
699
+ <edge from-layer="5" from-port="0" to-layer="6" to-port="2" />
700
+ <edge from-layer="6" from-port="3" to-layer="8" to-port="1" />
701
+ <edge from-layer="6" from-port="3" to-layer="11" to-port="0" />
702
+ <edge from-layer="7" from-port="0" to-layer="8" to-port="2" />
703
+ <edge from-layer="8" from-port="3" to-layer="15" to-port="0" />
704
+ <edge from-layer="9" from-port="0" to-layer="13" to-port="0" />
705
+ <edge from-layer="10" from-port="0" to-layer="11" to-port="1" />
706
+ <edge from-layer="11" from-port="2" to-layer="13" to-port="1" />
707
+ <edge from-layer="12" from-port="0" to-layer="13" to-port="2" />
708
+ <edge from-layer="13" from-port="3" to-layer="15" to-port="1" />
709
+ <edge from-layer="14" from-port="0" to-layer="15" to-port="5" />
710
+ <edge from-layer="15" from-port="8" to-layer="18" to-port="0" />
711
+ <edge from-layer="15" from-port="9" to-layer="18" to-port="1" />
712
+ <edge from-layer="15" from-port="10" to-layer="18" to-port="2" />
713
+ <edge from-layer="15" from-port="11" to-layer="18" to-port="3" />
714
+ <edge from-layer="15" from-port="6" to-layer="35" to-port="0" />
715
+ <edge from-layer="15" from-port="7" to-layer="35" to-port="1" />
716
+ <edge from-layer="16" from-port="0" to-layer="18" to-port="4" />
717
+ <edge from-layer="17" from-port="0" to-layer="18" to-port="5" />
718
+ <edge from-layer="18" from-port="6" to-layer="21" to-port="0" />
719
+ <edge from-layer="18" from-port="7" to-layer="21" to-port="1" />
720
+ <edge from-layer="18" from-port="8" to-layer="21" to-port="2" />
721
+ <edge from-layer="18" from-port="9" to-layer="21" to-port="3" />
722
+ <edge from-layer="19" from-port="0" to-layer="21" to-port="4" />
723
+ <edge from-layer="20" from-port="0" to-layer="21" to-port="5" />
724
+ <edge from-layer="21" from-port="6" to-layer="35" to-port="2" />
725
+ <edge from-layer="21" from-port="7" to-layer="35" to-port="3" />
726
+ <edge from-layer="21" from-port="8" to-layer="35" to-port="4" />
727
+ <edge from-layer="22" from-port="0" to-layer="35" to-port="5" />
728
+ <edge from-layer="23" from-port="0" to-layer="35" to-port="6" />
729
+ <edge from-layer="24" from-port="0" to-layer="35" to-port="7" />
730
+ <edge from-layer="25" from-port="0" to-layer="35" to-port="8" />
731
+ <edge from-layer="26" from-port="0" to-layer="35" to-port="9" />
732
+ <edge from-layer="27" from-port="0" to-layer="35" to-port="10" />
733
+ <edge from-layer="28" from-port="0" to-layer="35" to-port="11" />
734
+ <edge from-layer="29" from-port="0" to-layer="35" to-port="12" />
735
+ <edge from-layer="30" from-port="0" to-layer="35" to-port="13" />
736
+ <edge from-layer="31" from-port="0" to-layer="35" to-port="14" />
737
+ <edge from-layer="32" from-port="0" to-layer="35" to-port="15" />
738
+ <edge from-layer="33" from-port="0" to-layer="35" to-port="16" />
739
+ <edge from-layer="34" from-port="0" to-layer="35" to-port="17" />
740
+ <edge from-layer="35" from-port="18" to-layer="39" to-port="0" />
741
+ <edge from-layer="35" from-port="19" to-layer="39" to-port="1" />
742
+ <edge from-layer="35" from-port="20" to-layer="39" to-port="2" />
743
+ <edge from-layer="36" from-port="0" to-layer="39" to-port="3" />
744
+ <edge from-layer="37" from-port="0" to-layer="39" to-port="4" />
745
+ <edge from-layer="38" from-port="0" to-layer="39" to-port="5" />
746
+ <edge from-layer="39" from-port="6" to-layer="41" to-port="0" />
747
+ <edge from-layer="39" from-port="7" to-layer="41" to-port="1" />
748
+ <edge from-layer="39" from-port="8" to-layer="41" to-port="2" />
749
+ <edge from-layer="40" from-port="0" to-layer="41" to-port="3" />
750
+ <edge from-layer="41" from-port="5" to-layer="42" to-port="0" />
751
+ <edge from-layer="41" from-port="4" to-layer="42" to-port="1" />
752
+ <edge from-layer="41" from-port="4" to-layer="46" to-port="0" />
753
+ <edge from-layer="41" from-port="5" to-layer="46" to-port="1" />
754
+ <edge from-layer="41" from-port="6" to-layer="46" to-port="2" />
755
+ <edge from-layer="42" from-port="2" to-layer="44" to-port="0" />
756
+ <edge from-layer="43" from-port="0" to-layer="44" to-port="1" />
757
+ <edge from-layer="44" from-port="2" to-layer="46" to-port="3" />
758
+ <edge from-layer="45" from-port="0" to-layer="46" to-port="4" />
759
+ <edge from-layer="46" from-port="6" to-layer="47" to-port="0" />
760
+ <edge from-layer="46" from-port="5" to-layer="50" to-port="0" />
761
+ <edge from-layer="47" from-port="1" to-layer="48" to-port="0" />
762
+ <edge from-layer="48" from-port="1" to-layer="49" to-port="0" />
763
+ <edge from-layer="50" from-port="1" to-layer="51" to-port="0" />
764
+ </edges>
765
+ <rt_info>
766
+ <add_attention_mask value="True" />
767
+ <add_prefix_space />
768
+ <add_special_tokens value="True" />
769
+ <bos_token_id value="1" />
770
+ <chat_template value="{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'&lt;|system|>&#10;' + message['content'] + '&lt;|end|>&#10;'}}{% elif message['role'] == 'user' %}{{'&lt;|user|>&#10;' + message['content'] + '&lt;|end|>&#10;'}}{% elif message['role'] == 'assistant' %}{{'&lt;|assistant|>&#10;' + message['content'] + '&lt;|end|>&#10;'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '&lt;|assistant|>&#10;' }}{% else %}{{ eos_token }}{% endif %}" />
771
+ <clean_up_tokenization_spaces />
772
+ <detokenizer_input_type value="i64" />
773
+ <eos_token_id value="32000" />
774
+ <handle_special_tokens_with_re />
775
+ <max_length />
776
+ <number_of_inputs value="1" />
777
+ <openvino_tokenizers_version value="2025.3.0.0-570-5c466f128db" />
778
+ <openvino_version value="2025.3.0-19339-f4f4ce0d147" />
779
+ <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;: {}}" />
780
+ <original_tokenizer_class value="&lt;class 'transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast'>" />
781
+ <pad_token_id value="32000" />
782
+ <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]}}" />
783
+ <sentencepiece_version value="0.2.0" />
784
+ <skip_special_tokens value="True" />
785
+ <streaming_detokenizer value="False" />
786
+ <tiktoken_version value="0.9.0" />
787
+ <tokenizer_output_type value="i64" />
788
+ <tokenizers_version value="0.21.1" />
789
+ <transformers_version value="4.51.3" />
790
+ <use_max_padding value="False" />
791
+ <use_sentencepiece_backend value="False" />
792
+ <utf8_replace_mode value="replace" />
793
+ <with_detokenizer value="True" />
794
+ </rt_info>
795
+ </net>
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,132 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": true,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "32000": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|assistant|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": true,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<|placeholder1|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": true,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<|placeholder2|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": true,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<|placeholder3|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": true,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "32005": {
71
+ "content": "<|placeholder4|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": true,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "32006": {
79
+ "content": "<|system|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": true,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "32007": {
87
+ "content": "<|end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": true,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "32008": {
95
+ "content": "<|placeholder5|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": true,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "32009": {
103
+ "content": "<|placeholder6|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": true,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "32010": {
111
+ "content": "<|user|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": true,
115
+ "single_word": false,
116
+ "special": true
117
+ }
118
+ },
119
+ "bos_token": "<s>",
120
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
121
+ "clean_up_tokenization_spaces": false,
122
+ "eos_token": "<|endoftext|>",
123
+ "extra_special_tokens": {},
124
+ "legacy": false,
125
+ "model_max_length": 131072,
126
+ "pad_token": "<|endoftext|>",
127
+ "padding_side": "left",
128
+ "sp_model_kwargs": {},
129
+ "tokenizer_class": "LlamaTokenizer",
130
+ "unk_token": "<unk>",
131
+ "use_default_system_prompt": false
132
+ }