Hugging Face's logo

llmware
/
slim-extract-qwen-1.5b-ov

OpenVINO
qwen2
green
p1
llmware-fx
ov
emerald
Model card Files
xet
Community
doberst commited on
Commit
671260d
·
verified ·
1 Parent(s): fdac73c

Upload 13 files

Browse files
Files changed (11) hide show
  1. added_tokens.json +5 -0
  2. config.json +35 -0
  3. generation_config.json +6 -0
  4. merges.txt +0 -0
  5. openvino_detokenizer.xml +9 -9
  6. openvino_model.xml +0 -0
  7. openvino_tokenizer.xml +64 -64
  8. special_tokens_map.json +20 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +43 -0
  11. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "llmware/slim-qwen-extract-1.5b",
3
+ "aib_version": "model_archive_072424_qwen15_extract_eot_4",
4
+ "architectures": [
5
+ "Qwen2ForCausalLM"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 151643,
9
+ "eos_token_id": 151643,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 1536,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 8960,
14
+ "max_position_embeddings": 131072,
15
+ "max_window_layers": 28,
16
+ "model_type": "qwen2",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 2,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_theta": 1000000.0,
22
+ "sliding_window": null,
23
+ "tie_word_embeddings": true,
24
+ "torch_dtype": "bfloat16",
25
+ "trained": "custom training",
26
+ "training_comments": "qwen2-1.5b-extract-eot-072424-4",
27
+ "training_dataset": [
28
+ "extract2_new_031724_eot_2_9442.jsonl"
29
+ ],
30
+ "training_timestamp": "Wed Jul 24 10:43:25 2024",
31
+ "transformers_version": "4.44.2",
32
+ "use_cache": true,
33
+ "use_sliding_window": false,
34
+ "vocab_size": 151936
35
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": 151643,
4
+ "max_new_tokens": 2048,
5
+ "transformers_version": "4.44.2"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
openvino_detokenizer.xml CHANGED
@@ -1,16 +1,16 @@
1
  <?xml version="1.0"?>
2
  <net name="detokenizer" version="11">
3
  <layers>
4
- <layer id="0" name="Parameter_186" type="Parameter" version="opset1">
5
  <data shape="?,?" element_type="i64" />
6
  <output>
7
- <port id="0" precision="I64" names="Parameter_186">
8
  <dim>-1</dim>
9
  <dim>-1</dim>
10
  </port>
11
  </output>
12
  </layer>
13
- <layer id="1" name="Convert_197" type="Convert" version="opset1">
14
  <data destination_type="i32" />
15
  <input>
16
  <port id="0" precision="I64">
@@ -25,7 +25,7 @@
25
  </port>
26
  </output>
27
  </layer>
28
- <layer id="2" name="Constant_89" type="Const" version="opset1">
29
  <data element_type="u8" shape="1976110" offset="0" size="1976110" />
30
  <output>
31
  <port id="0" precision="U8">
@@ -33,7 +33,7 @@
33
  </port>
34
  </output>
35
  </layer>
36
- <layer id="3" name="StringTensorUnpack_90" type="StringTensorUnpack" version="extension">
37
  <data mode="begins_ends" />
38
  <input>
39
  <port id="0" precision="U8">
@@ -52,7 +52,7 @@
52
  </port>
53
  </output>
54
  </layer>
55
- <layer id="4" name="VocabDecoder_187" type="VocabDecoder" version="extension">
56
  <data skip_tokens="151643, 151644, 151645" />
57
  <input>
58
  <port id="0" precision="I32">
@@ -87,7 +87,7 @@
87
  </port>
88
  </output>
89
  </layer>
90
- <layer id="5" name="CharsToBytes_188" type="CharsToBytes" version="extension">
91
  <input>
92
  <port id="0" precision="I32">
93
  <dim>-1</dim>
@@ -117,7 +117,7 @@
117
  </port>
118
  </output>
119
  </layer>
120
- <layer id="6" name="StringTensorPack_189" type="StringTensorPack" version="extension">
121
  <data mode="begins_ends" />
122
  <input>
123
  <port id="0" precision="I32">
@@ -136,7 +136,7 @@
136
  </port>
137
  </output>
138
  </layer>
139
- <layer id="7" name="Result_190" type="Result" version="opset1">
140
  <input>
141
  <port id="0" precision="STRING">
142
  <dim>-1</dim>
 
1
  <?xml version="1.0"?>
2
  <net name="detokenizer" version="11">
3
  <layers>
4
+ <layer id="0" name="Parameter_322697" type="Parameter" version="opset1">
5
  <data shape="?,?" element_type="i64" />
6
  <output>
7
+ <port id="0" precision="I64" names="Parameter_322697">
8
  <dim>-1</dim>
9
  <dim>-1</dim>
10
  </port>
11
  </output>
12
  </layer>
13
+ <layer id="1" name="Convert_322708" type="Convert" version="opset1">
14
  <data destination_type="i32" />
15
  <input>
16
  <port id="0" precision="I64">
 
25
  </port>
26
  </output>
27
  </layer>
28
+ <layer id="2" name="Constant_322600" type="Const" version="opset1">
29
  <data element_type="u8" shape="1976110" offset="0" size="1976110" />
30
  <output>
31
  <port id="0" precision="U8">
 
33
  </port>
34
  </output>
35
  </layer>
36
+ <layer id="3" name="StringTensorUnpack_322601" type="StringTensorUnpack" version="extension">
37
  <data mode="begins_ends" />
38
  <input>
39
  <port id="0" precision="U8">
 
52
  </port>
53
  </output>
54
  </layer>
55
+ <layer id="4" name="VocabDecoder_322698" type="VocabDecoder" version="extension">
56
  <data skip_tokens="151643, 151644, 151645" />
57
  <input>
58
  <port id="0" precision="I32">
 
87
  </port>
88
  </output>
89
  </layer>
90
+ <layer id="5" name="CharsToBytes_322699" type="CharsToBytes" version="extension">
91
  <input>
92
  <port id="0" precision="I32">
93
  <dim>-1</dim>
 
117
  </port>
118
  </output>
119
  </layer>
120
+ <layer id="6" name="StringTensorPack_322700" type="StringTensorPack" version="extension">
121
  <data mode="begins_ends" />
122
  <input>
123
  <port id="0" precision="I32">
 
136
  </port>
137
  </output>
138
  </layer>
139
+ <layer id="7" name="Result_322701" type="Result" version="opset1">
140
  <input>
141
  <port id="0" precision="STRING">
142
  <dim>-1</dim>
openvino_model.xml ADDED
The diff for this file is too large to render. See raw diff
 
openvino_tokenizer.xml CHANGED
@@ -1,21 +1,21 @@
1
  <?xml version="1.0"?>
2
  <net name="tokenizer" version="11">
3
  <layers>
4
- <layer id="0" name="Parameter_1" type="Parameter" version="opset1">
5
  <data shape="?" element_type="string" />
6
  <output>
7
- <port id="0" precision="STRING" names="Parameter_1">
8
  <dim>-1</dim>
9
  </port>
10
  </output>
11
  </layer>
12
- <layer id="1" name="Constant_8" 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_2" type="StringTensorUnpack" version="extension">
19
  <data mode="begins_ends" />
20
  <input>
21
  <port id="0" precision="STRING">
@@ -34,7 +34,7 @@
34
  </port>
35
  </output>
36
  </layer>
37
- <layer id="3" name="NormalizeUnicode_3" type="NormalizeUnicode" version="extension">
38
  <data normalization_form="NFC" />
39
  <input>
40
  <port id="0" precision="I32">
@@ -59,7 +59,7 @@
59
  </port>
60
  </output>
61
  </layer>
62
- <layer id="4" name="ShapeOf_4" type="ShapeOf" version="opset3">
63
  <data output_type="i64" />
64
  <input>
65
  <port id="0" precision="I32">
@@ -72,19 +72,19 @@
72
  </port>
73
  </output>
74
  </layer>
75
- <layer id="5" name="Constant_5" type="Const" version="opset1">
76
  <data element_type="i32" shape="" offset="0" size="4" />
77
  <output>
78
  <port id="0" precision="I32" />
79
  </output>
80
  </layer>
81
- <layer id="6" name="Constant_6" type="Const" version="opset1">
82
  <data element_type="i32" shape="" offset="0" size="4" />
83
  <output>
84
  <port id="0" precision="I32" />
85
  </output>
86
  </layer>
87
- <layer id="7" name="Gather_7" type="Gather" version="opset8">
88
  <data batch_dims="0" />
89
  <input>
90
  <port id="0" precision="I64">
@@ -97,13 +97,13 @@
97
  <port id="3" precision="I64" />
98
  </output>
99
  </layer>
100
- <layer id="8" name="Constant_9" type="Const" version="opset1">
101
  <data element_type="i32" shape="" offset="4" size="4" />
102
  <output>
103
  <port id="0" precision="I32" />
104
  </output>
105
  </layer>
106
- <layer id="9" name="Range_10" type="Range" version="opset4">
107
  <data output_type="i32" />
108
  <input>
109
  <port id="0" precision="I32" />
@@ -116,19 +116,19 @@
116
  </port>
117
  </output>
118
  </layer>
119
- <layer id="10" name="Constant_12" type="Const" version="opset1">
120
  <data element_type="i32" shape="" offset="4" size="4" />
121
  <output>
122
  <port id="0" precision="I32" />
123
  </output>
124
  </layer>
125
- <layer id="11" name="Constant_13" type="Const" version="opset1">
126
  <data element_type="i64" shape="" offset="8" size="8" />
127
  <output>
128
  <port id="0" precision="I64" />
129
  </output>
130
  </layer>
131
- <layer id="12" name="Add_14" type="Add" version="opset1">
132
  <data auto_broadcast="numpy" />
133
  <input>
134
  <port id="0" precision="I64" />
@@ -138,13 +138,13 @@
138
  <port id="2" precision="I64" />
139
  </output>
140
  </layer>
141
- <layer id="13" name="Constant_15" type="Const" version="opset1">
142
  <data element_type="i32" shape="" offset="4" size="4" />
143
  <output>
144
  <port id="0" precision="I32" />
145
  </output>
146
  </layer>
147
- <layer id="14" name="Range_16" type="Range" version="opset4">
148
  <data output_type="i32" />
149
  <input>
150
  <port id="0" precision="I32" />
@@ -157,7 +157,7 @@
157
  </port>
158
  </output>
159
  </layer>
160
- <layer id="15" name="Constant_79" type="Const" version="opset1">
161
  <data element_type="u8" shape="49" offset="16" size="49" />
162
  <output>
163
  <port id="0" precision="U8">
@@ -165,7 +165,7 @@
165
  </port>
166
  </output>
167
  </layer>
168
- <layer id="16" name="RegexSplit_80" type="RegexSplit" version="extension">
169
  <data behaviour="isolate" invert="false" max_splits="-1" />
170
  <input>
171
  <port id="0" precision="I32">
@@ -205,7 +205,7 @@
205
  </port>
206
  </output>
207
  </layer>
208
- <layer id="17" name="Constant_85" type="Const" version="opset1">
209
  <data element_type="u8" shape="110" offset="65" size="110" />
210
  <output>
211
  <port id="0" precision="U8">
@@ -213,7 +213,7 @@
213
  </port>
214
  </output>
215
  </layer>
216
- <layer id="18" name="Constant_82" type="Const" version="opset1">
217
  <data element_type="u8" shape="55" offset="175" size="55" />
218
  <output>
219
  <port id="0" precision="U8">
@@ -221,7 +221,7 @@
221
  </port>
222
  </output>
223
  </layer>
224
- <layer id="19" name="StringTensorUnpack_83" type="StringTensorUnpack" version="extension">
225
  <data mode="begins_ends" />
226
  <input>
227
  <port id="0" precision="U8">
@@ -240,7 +240,7 @@
240
  </port>
241
  </output>
242
  </layer>
243
- <layer id="20" name="RegexSplit_86" type="RegexSplit" version="extension">
244
  <data behaviour="isolate" invert="false" max_splits="-1" />
245
  <input>
246
  <port id="0" precision="I32">
@@ -289,7 +289,7 @@
289
  </port>
290
  </output>
291
  </layer>
292
- <layer id="21" name="BytesToChars_87" type="BytesToChars" version="extension">
293
  <input>
294
  <port id="0" precision="I32">
295
  <dim>-1</dim>
@@ -325,7 +325,7 @@
325
  </port>
326
  </output>
327
  </layer>
328
- <layer id="22" name="Constant_89" type="Const" version="opset1">
329
  <data element_type="u8" shape="1976110" offset="230" size="1976110" />
330
  <output>
331
  <port id="0" precision="U8">
@@ -333,7 +333,7 @@
333
  </port>
334
  </output>
335
  </layer>
336
- <layer id="23" name="StringTensorUnpack_90" type="StringTensorUnpack" version="extension">
337
  <data mode="begins_ends" />
338
  <input>
339
  <port id="0" precision="U8">
@@ -352,7 +352,7 @@
352
  </port>
353
  </output>
354
  </layer>
355
- <layer id="24" name="Constant_170" type="Const" version="opset1">
356
  <data element_type="u8" shape="2126008" offset="1976340" size="2126008" />
357
  <output>
358
  <port id="0" precision="U8">
@@ -360,7 +360,7 @@
360
  </port>
361
  </output>
362
  </layer>
363
- <layer id="25" name="StringTensorUnpack_171" type="StringTensorUnpack" version="extension">
364
  <data mode="begins_ends" />
365
  <input>
366
  <port id="0" precision="U8">
@@ -379,13 +379,13 @@
379
  </port>
380
  </output>
381
  </layer>
382
- <layer id="26" name="Constant_98" type="Const" version="opset1">
383
  <data element_type="i32" shape="" offset="0" size="4" />
384
  <output>
385
  <port id="0" precision="I32" />
386
  </output>
387
  </layer>
388
- <layer id="27" name="Constant_92" type="Const" version="opset1">
389
  <data element_type="u8" shape="55" offset="4102348" size="55" />
390
  <output>
391
  <port id="0" precision="U8">
@@ -393,7 +393,7 @@
393
  </port>
394
  </output>
395
  </layer>
396
- <layer id="28" name="StringTensorUnpack_93" type="StringTensorUnpack" version="extension">
397
  <data mode="begins_ends" />
398
  <input>
399
  <port id="0" precision="U8">
@@ -412,7 +412,7 @@
412
  </port>
413
  </output>
414
  </layer>
415
- <layer id="29" name="ShapeOf_94" type="ShapeOf" version="opset3">
416
  <data output_type="i64" />
417
  <input>
418
  <port id="0" precision="I32">
@@ -425,19 +425,19 @@
425
  </port>
426
  </output>
427
  </layer>
428
- <layer id="30" name="Constant_95" type="Const" version="opset1">
429
  <data element_type="i32" shape="" offset="0" size="4" />
430
  <output>
431
  <port id="0" precision="I32" />
432
  </output>
433
  </layer>
434
- <layer id="31" name="Constant_96" type="Const" version="opset1">
435
  <data element_type="i32" shape="" offset="0" size="4" />
436
  <output>
437
  <port id="0" precision="I32" />
438
  </output>
439
  </layer>
440
- <layer id="32" name="Gather_97" type="Gather" version="opset8">
441
  <data batch_dims="0" />
442
  <input>
443
  <port id="0" precision="I64">
@@ -450,13 +450,13 @@
450
  <port id="3" precision="I64" />
451
  </output>
452
  </layer>
453
- <layer id="33" name="Constant_99" type="Const" version="opset1">
454
  <data element_type="i32" shape="" offset="4" size="4" />
455
  <output>
456
  <port id="0" precision="I32" />
457
  </output>
458
  </layer>
459
- <layer id="34" name="Range_100" type="Range" version="opset4">
460
  <data output_type="i32" />
461
  <input>
462
  <port id="0" precision="I32" />
@@ -469,19 +469,19 @@
469
  </port>
470
  </output>
471
  </layer>
472
- <layer id="35" name="Constant_102" type="Const" version="opset1">
473
  <data element_type="i32" shape="" offset="4" size="4" />
474
  <output>
475
  <port id="0" precision="I32" />
476
  </output>
477
  </layer>
478
- <layer id="36" name="Constant_103" type="Const" version="opset1">
479
  <data element_type="i64" shape="" offset="8" size="8" />
480
  <output>
481
  <port id="0" precision="I64" />
482
  </output>
483
  </layer>
484
- <layer id="37" name="Add_104" type="Add" version="opset1">
485
  <data auto_broadcast="numpy" />
486
  <input>
487
  <port id="0" precision="I64" />
@@ -491,13 +491,13 @@
491
  <port id="2" precision="I64" />
492
  </output>
493
  </layer>
494
- <layer id="38" name="Constant_105" type="Const" version="opset1">
495
  <data element_type="i32" shape="" offset="4" size="4" />
496
  <output>
497
  <port id="0" precision="I32" />
498
  </output>
499
  </layer>
500
- <layer id="39" name="Range_106" type="Range" version="opset4">
501
  <data output_type="i32" />
502
  <input>
503
  <port id="0" precision="I32" />
@@ -510,7 +510,7 @@
510
  </port>
511
  </output>
512
  </layer>
513
- <layer id="40" name="BytesToChars_168" type="BytesToChars" version="extension">
514
  <input>
515
  <port id="0" precision="I32">
516
  <dim>-1</dim>
@@ -546,7 +546,7 @@
546
  </port>
547
  </output>
548
  </layer>
549
- <layer id="41" name="Constant_172" type="Const" version="opset1">
550
  <data element_type="i32" shape="3" offset="4102403" size="12" />
551
  <output>
552
  <port id="0" precision="I32">
@@ -554,7 +554,7 @@
554
  </port>
555
  </output>
556
  </layer>
557
- <layer id="42" name="BPETokenizer_173" type="BPETokenizer" version="extension">
558
  <data unk_token="" fuse_unk="false" suffix_indicator="" end_suffix="" byte_fallback="false" cache_capacity="30328" />
559
  <input>
560
  <port id="0" precision="I32">
@@ -615,7 +615,7 @@
615
  </port>
616
  </output>
617
  </layer>
618
- <layer id="43" name="Subtract_174" type="Subtract" version="opset1">
619
  <data auto_broadcast="numpy" />
620
  <input>
621
  <port id="0" precision="I32">
@@ -631,13 +631,13 @@
631
  </port>
632
  </output>
633
  </layer>
634
- <layer id="44" name="Constant_175" type="Const" version="opset1">
635
  <data element_type="i32" shape="" offset="4102415" size="4" />
636
  <output>
637
  <port id="0" precision="I32" />
638
  </output>
639
  </layer>
640
- <layer id="45" name="Minimum_176" type="Minimum" version="opset1">
641
  <data auto_broadcast="numpy" />
642
  <input>
643
  <port id="0" precision="I32">
@@ -651,7 +651,7 @@
651
  </port>
652
  </output>
653
  </layer>
654
- <layer id="46" name="Add_177" type="Add" version="opset1">
655
  <data auto_broadcast="numpy" />
656
  <input>
657
  <port id="0" precision="I32">
@@ -667,7 +667,7 @@
667
  </port>
668
  </output>
669
  </layer>
670
- <layer id="47" name="Subtract_178" type="Subtract" version="opset1">
671
  <data auto_broadcast="numpy" />
672
  <input>
673
  <port id="0" precision="I32">
@@ -683,13 +683,13 @@
683
  </port>
684
  </output>
685
  </layer>
686
- <layer id="48" name="Constant_179" type="Const" version="opset1">
687
  <data element_type="i32" shape="" offset="0" size="4" />
688
  <output>
689
  <port id="0" precision="I32" />
690
  </output>
691
  </layer>
692
- <layer id="49" name="ReduceMax_180" type="ReduceMax" version="opset1">
693
  <data keep_dims="false" />
694
  <input>
695
  <port id="0" precision="I32">
@@ -701,14 +701,14 @@
701
  <port id="2" precision="I32" />
702
  </output>
703
  </layer>
704
- <layer id="50" name="Constant_181" type="Const" version="opset1">
705
  <data element_type="i32" shape="" offset="4102419" size="4" />
706
  <output>
707
  <port id="0" precision="I32" />
708
  </output>
709
  </layer>
710
- <layer id="51" name="RaggedToDense_182" type="RaggedToDense" version="extension">
711
- <data pad_right="true" />
712
  <input>
713
  <port id="0" precision="I32">
714
  <dim>-1</dim>
@@ -733,7 +733,7 @@
733
  </port>
734
  </output>
735
  </layer>
736
- <layer id="52" name="Convert_183" type="Convert" version="opset1">
737
  <data destination_type="i32" />
738
  <input>
739
  <port id="0" precision="BOOL">
@@ -748,7 +748,7 @@
748
  </port>
749
  </output>
750
  </layer>
751
- <layer id="53" name="Convert_183" type="Convert" version="opset1">
752
  <data destination_type="i64" />
753
  <input>
754
  <port id="0" precision="I32">
@@ -763,7 +763,7 @@
763
  </port>
764
  </output>
765
  </layer>
766
- <layer id="55" name="RaggedToDense_182.0" type="Convert" version="opset1">
767
  <data destination_type="i64" />
768
  <input>
769
  <port id="0" precision="I32">
@@ -778,7 +778,7 @@
778
  </port>
779
  </output>
780
  </layer>
781
- <layer id="56" name="Result_184" type="Result" version="opset1">
782
  <input>
783
  <port id="0" precision="I64">
784
  <dim>-1</dim>
@@ -786,7 +786,7 @@
786
  </port>
787
  </input>
788
  </layer>
789
- <layer id="54" name="Result_185" type="Result" version="opset1">
790
  <input>
791
  <port id="0" precision="I64">
792
  <dim>-1</dim>
@@ -870,15 +870,15 @@
870
  <edge from-layer="41" from-port="0" to-layer="42" to-port="14" />
871
  <edge from-layer="42" from-port="16" to-layer="43" to-port="0" />
872
  <edge from-layer="42" from-port="15" to-layer="43" to-port="1" />
873
- <edge from-layer="42" from-port="15" to-layer="46" to-port="0" />
874
- <edge from-layer="42" from-port="15" to-layer="47" to-port="1" />
875
- <edge from-layer="42" from-port="15" to-layer="51" to-port="0" />
876
  <edge from-layer="42" from-port="17" to-layer="51" to-port="2" />
877
  <edge from-layer="43" from-port="2" to-layer="45" to-port="0" />
878
  <edge from-layer="44" from-port="0" to-layer="45" to-port="1" />
879
  <edge from-layer="45" from-port="2" to-layer="46" to-port="1" />
880
- <edge from-layer="46" from-port="2" to-layer="47" to-port="0" />
881
- <edge from-layer="46" from-port="2" to-layer="51" to-port="1" />
882
  <edge from-layer="47" from-port="2" to-layer="49" to-port="0" />
883
  <edge from-layer="48" from-port="0" to-layer="49" to-port="1" />
884
  <edge from-layer="49" from-port="2" to-layer="51" to-port="3" />
 
1
  <?xml version="1.0"?>
2
  <net name="tokenizer" version="11">
3
  <layers>
4
+ <layer id="0" name="Parameter_322512" type="Parameter" version="opset1">
5
  <data shape="?" element_type="string" />
6
  <output>
7
+ <port id="0" precision="STRING" names="Parameter_322512">
8
  <dim>-1</dim>
9
  </port>
10
  </output>
11
  </layer>
12
+ <layer id="1" name="Constant_322519" 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_322513" type="StringTensorUnpack" version="extension">
19
  <data mode="begins_ends" />
20
  <input>
21
  <port id="0" precision="STRING">
 
34
  </port>
35
  </output>
36
  </layer>
37
+ <layer id="3" name="NormalizeUnicode_322514" type="NormalizeUnicode" version="extension">
38
  <data normalization_form="NFC" />
39
  <input>
40
  <port id="0" precision="I32">
 
59
  </port>
60
  </output>
61
  </layer>
62
+ <layer id="4" name="ShapeOf_322515" type="ShapeOf" version="opset3">
63
  <data output_type="i64" />
64
  <input>
65
  <port id="0" precision="I32">
 
72
  </port>
73
  </output>
74
  </layer>
75
+ <layer id="5" name="Constant_322516" type="Const" version="opset1">
76
  <data element_type="i32" shape="" offset="0" size="4" />
77
  <output>
78
  <port id="0" precision="I32" />
79
  </output>
80
  </layer>
81
+ <layer id="6" name="Constant_322517" type="Const" version="opset1">
82
  <data element_type="i32" shape="" offset="0" size="4" />
83
  <output>
84
  <port id="0" precision="I32" />
85
  </output>
86
  </layer>
87
+ <layer id="7" name="Gather_322518" type="Gather" version="opset8">
88
  <data batch_dims="0" />
89
  <input>
90
  <port id="0" precision="I64">
 
97
  <port id="3" precision="I64" />
98
  </output>
99
  </layer>
100
+ <layer id="8" name="Constant_322520" type="Const" version="opset1">
101
  <data element_type="i32" shape="" offset="4" size="4" />
102
  <output>
103
  <port id="0" precision="I32" />
104
  </output>
105
  </layer>
106
+ <layer id="9" name="Range_322521" type="Range" version="opset4">
107
  <data output_type="i32" />
108
  <input>
109
  <port id="0" precision="I32" />
 
116
  </port>
117
  </output>
118
  </layer>
119
+ <layer id="10" name="Constant_322523" type="Const" version="opset1">
120
  <data element_type="i32" shape="" offset="4" size="4" />
121
  <output>
122
  <port id="0" precision="I32" />
123
  </output>
124
  </layer>
125
+ <layer id="11" name="Constant_322524" type="Const" version="opset1">
126
  <data element_type="i64" shape="" offset="8" size="8" />
127
  <output>
128
  <port id="0" precision="I64" />
129
  </output>
130
  </layer>
131
+ <layer id="12" name="Add_322525" type="Add" version="opset1">
132
  <data auto_broadcast="numpy" />
133
  <input>
134
  <port id="0" precision="I64" />
 
138
  <port id="2" precision="I64" />
139
  </output>
140
  </layer>
141
+ <layer id="13" name="Constant_322526" type="Const" version="opset1">
142
  <data element_type="i32" shape="" offset="4" size="4" />
143
  <output>
144
  <port id="0" precision="I32" />
145
  </output>
146
  </layer>
147
+ <layer id="14" name="Range_322527" type="Range" version="opset4">
148
  <data output_type="i32" />
149
  <input>
150
  <port id="0" precision="I32" />
 
157
  </port>
158
  </output>
159
  </layer>
160
+ <layer id="15" name="Constant_322590" type="Const" version="opset1">
161
  <data element_type="u8" shape="49" offset="16" size="49" />
162
  <output>
163
  <port id="0" precision="U8">
 
165
  </port>
166
  </output>
167
  </layer>
168
+ <layer id="16" name="RegexSplit_322591" type="RegexSplit" version="extension">
169
  <data behaviour="isolate" invert="false" max_splits="-1" />
170
  <input>
171
  <port id="0" precision="I32">
 
205
  </port>
206
  </output>
207
  </layer>
208
+ <layer id="17" name="Constant_322596" type="Const" version="opset1">
209
  <data element_type="u8" shape="110" offset="65" size="110" />
210
  <output>
211
  <port id="0" precision="U8">
 
213
  </port>
214
  </output>
215
  </layer>
216
+ <layer id="18" name="Constant_322593" type="Const" version="opset1">
217
  <data element_type="u8" shape="55" offset="175" size="55" />
218
  <output>
219
  <port id="0" precision="U8">
 
221
  </port>
222
  </output>
223
  </layer>
224
+ <layer id="19" name="StringTensorUnpack_322594" type="StringTensorUnpack" version="extension">
225
  <data mode="begins_ends" />
226
  <input>
227
  <port id="0" precision="U8">
 
240
  </port>
241
  </output>
242
  </layer>
243
+ <layer id="20" name="RegexSplit_322597" type="RegexSplit" version="extension">
244
  <data behaviour="isolate" invert="false" max_splits="-1" />
245
  <input>
246
  <port id="0" precision="I32">
 
289
  </port>
290
  </output>
291
  </layer>
292
+ <layer id="21" name="BytesToChars_322598" type="BytesToChars" version="extension">
293
  <input>
294
  <port id="0" precision="I32">
295
  <dim>-1</dim>
 
325
  </port>
326
  </output>
327
  </layer>
328
+ <layer id="22" name="Constant_322600" type="Const" version="opset1">
329
  <data element_type="u8" shape="1976110" offset="230" size="1976110" />
330
  <output>
331
  <port id="0" precision="U8">
 
333
  </port>
334
  </output>
335
  </layer>
336
+ <layer id="23" name="StringTensorUnpack_322601" type="StringTensorUnpack" version="extension">
337
  <data mode="begins_ends" />
338
  <input>
339
  <port id="0" precision="U8">
 
352
  </port>
353
  </output>
354
  </layer>
355
+ <layer id="24" name="Constant_322681" type="Const" version="opset1">
356
  <data element_type="u8" shape="2126008" offset="1976340" size="2126008" />
357
  <output>
358
  <port id="0" precision="U8">
 
360
  </port>
361
  </output>
362
  </layer>
363
+ <layer id="25" name="StringTensorUnpack_322682" type="StringTensorUnpack" version="extension">
364
  <data mode="begins_ends" />
365
  <input>
366
  <port id="0" precision="U8">
 
379
  </port>
380
  </output>
381
  </layer>
382
+ <layer id="26" name="Constant_322609" type="Const" version="opset1">
383
  <data element_type="i32" shape="" offset="0" size="4" />
384
  <output>
385
  <port id="0" precision="I32" />
386
  </output>
387
  </layer>
388
+ <layer id="27" name="Constant_322603" type="Const" version="opset1">
389
  <data element_type="u8" shape="55" offset="4102348" size="55" />
390
  <output>
391
  <port id="0" precision="U8">
 
393
  </port>
394
  </output>
395
  </layer>
396
+ <layer id="28" name="StringTensorUnpack_322604" type="StringTensorUnpack" version="extension">
397
  <data mode="begins_ends" />
398
  <input>
399
  <port id="0" precision="U8">
 
412
  </port>
413
  </output>
414
  </layer>
415
+ <layer id="29" name="ShapeOf_322605" type="ShapeOf" version="opset3">
416
  <data output_type="i64" />
417
  <input>
418
  <port id="0" precision="I32">
 
425
  </port>
426
  </output>
427
  </layer>
428
+ <layer id="30" name="Constant_322606" type="Const" version="opset1">
429
  <data element_type="i32" shape="" offset="0" size="4" />
430
  <output>
431
  <port id="0" precision="I32" />
432
  </output>
433
  </layer>
434
+ <layer id="31" name="Constant_322607" type="Const" version="opset1">
435
  <data element_type="i32" shape="" offset="0" size="4" />
436
  <output>
437
  <port id="0" precision="I32" />
438
  </output>
439
  </layer>
440
+ <layer id="32" name="Gather_322608" type="Gather" version="opset8">
441
  <data batch_dims="0" />
442
  <input>
443
  <port id="0" precision="I64">
 
450
  <port id="3" precision="I64" />
451
  </output>
452
  </layer>
453
+ <layer id="33" name="Constant_322610" type="Const" version="opset1">
454
  <data element_type="i32" shape="" offset="4" size="4" />
455
  <output>
456
  <port id="0" precision="I32" />
457
  </output>
458
  </layer>
459
+ <layer id="34" name="Range_322611" type="Range" version="opset4">
460
  <data output_type="i32" />
461
  <input>
462
  <port id="0" precision="I32" />
 
469
  </port>
470
  </output>
471
  </layer>
472
+ <layer id="35" name="Constant_322613" type="Const" version="opset1">
473
  <data element_type="i32" shape="" offset="4" size="4" />
474
  <output>
475
  <port id="0" precision="I32" />
476
  </output>
477
  </layer>
478
+ <layer id="36" name="Constant_322614" type="Const" version="opset1">
479
  <data element_type="i64" shape="" offset="8" size="8" />
480
  <output>
481
  <port id="0" precision="I64" />
482
  </output>
483
  </layer>
484
+ <layer id="37" name="Add_322615" type="Add" version="opset1">
485
  <data auto_broadcast="numpy" />
486
  <input>
487
  <port id="0" precision="I64" />
 
491
  <port id="2" precision="I64" />
492
  </output>
493
  </layer>
494
+ <layer id="38" name="Constant_322616" type="Const" version="opset1">
495
  <data element_type="i32" shape="" offset="4" size="4" />
496
  <output>
497
  <port id="0" precision="I32" />
498
  </output>
499
  </layer>
500
+ <layer id="39" name="Range_322617" type="Range" version="opset4">
501
  <data output_type="i32" />
502
  <input>
503
  <port id="0" precision="I32" />
 
510
  </port>
511
  </output>
512
  </layer>
513
+ <layer id="40" name="BytesToChars_322679" type="BytesToChars" version="extension">
514
  <input>
515
  <port id="0" precision="I32">
516
  <dim>-1</dim>
 
546
  </port>
547
  </output>
548
  </layer>
549
+ <layer id="41" name="Constant_322683" type="Const" version="opset1">
550
  <data element_type="i32" shape="3" offset="4102403" size="12" />
551
  <output>
552
  <port id="0" precision="I32">
 
554
  </port>
555
  </output>
556
  </layer>
557
+ <layer id="42" name="BPETokenizer_322684" type="BPETokenizer" version="extension">
558
  <data unk_token="" fuse_unk="false" suffix_indicator="" end_suffix="" byte_fallback="false" cache_capacity="30328" />
559
  <input>
560
  <port id="0" precision="I32">
 
615
  </port>
616
  </output>
617
  </layer>
618
+ <layer id="43" name="Subtract_322685" type="Subtract" version="opset1">
619
  <data auto_broadcast="numpy" />
620
  <input>
621
  <port id="0" precision="I32">
 
631
  </port>
632
  </output>
633
  </layer>
634
+ <layer id="44" name="Constant_322686" type="Const" version="opset1">
635
  <data element_type="i32" shape="" offset="4102415" size="4" />
636
  <output>
637
  <port id="0" precision="I32" />
638
  </output>
639
  </layer>
640
+ <layer id="45" name="Minimum_322687" type="Minimum" version="opset1">
641
  <data auto_broadcast="numpy" />
642
  <input>
643
  <port id="0" precision="I32">
 
651
  </port>
652
  </output>
653
  </layer>
654
+ <layer id="46" name="Subtract_322688" type="Subtract" version="opset1">
655
  <data auto_broadcast="numpy" />
656
  <input>
657
  <port id="0" precision="I32">
 
667
  </port>
668
  </output>
669
  </layer>
670
+ <layer id="47" name="Subtract_322689" type="Subtract" version="opset1">
671
  <data auto_broadcast="numpy" />
672
  <input>
673
  <port id="0" precision="I32">
 
683
  </port>
684
  </output>
685
  </layer>
686
+ <layer id="48" name="Constant_322690" type="Const" version="opset1">
687
  <data element_type="i32" shape="" offset="0" size="4" />
688
  <output>
689
  <port id="0" precision="I32" />
690
  </output>
691
  </layer>
692
+ <layer id="49" name="ReduceMax_322691" type="ReduceMax" version="opset1">
693
  <data keep_dims="false" />
694
  <input>
695
  <port id="0" precision="I32">
 
701
  <port id="2" precision="I32" />
702
  </output>
703
  </layer>
704
+ <layer id="50" name="Constant_322692" type="Const" version="opset1">
705
  <data element_type="i32" shape="" offset="4102419" size="4" />
706
  <output>
707
  <port id="0" precision="I32" />
708
  </output>
709
  </layer>
710
+ <layer id="51" name="RaggedToDense_322693" type="RaggedToDense" version="extension">
711
+ <data pad_right="false" />
712
  <input>
713
  <port id="0" precision="I32">
714
  <dim>-1</dim>
 
733
  </port>
734
  </output>
735
  </layer>
736
+ <layer id="52" name="Convert_322694" type="Convert" version="opset1">
737
  <data destination_type="i32" />
738
  <input>
739
  <port id="0" precision="BOOL">
 
748
  </port>
749
  </output>
750
  </layer>
751
+ <layer id="53" name="Convert_322694" type="Convert" version="opset1">
752
  <data destination_type="i64" />
753
  <input>
754
  <port id="0" precision="I32">
 
763
  </port>
764
  </output>
765
  </layer>
766
+ <layer id="55" name="RaggedToDense_322693.0" type="Convert" version="opset1">
767
  <data destination_type="i64" />
768
  <input>
769
  <port id="0" precision="I32">
 
778
  </port>
779
  </output>
780
  </layer>
781
+ <layer id="56" name="Result_322695" type="Result" version="opset1">
782
  <input>
783
  <port id="0" precision="I64">
784
  <dim>-1</dim>
 
786
  </port>
787
  </input>
788
  </layer>
789
+ <layer id="54" name="Result_322696" type="Result" version="opset1">
790
  <input>
791
  <port id="0" precision="I64">
792
  <dim>-1</dim>
 
870
  <edge from-layer="41" from-port="0" to-layer="42" to-port="14" />
871
  <edge from-layer="42" from-port="16" to-layer="43" to-port="0" />
872
  <edge from-layer="42" from-port="15" to-layer="43" to-port="1" />
873
+ <edge from-layer="42" from-port="16" to-layer="46" to-port="0" />
874
+ <edge from-layer="42" from-port="16" to-layer="47" to-port="0" />
875
+ <edge from-layer="42" from-port="16" to-layer="51" to-port="1" />
876
  <edge from-layer="42" from-port="17" to-layer="51" to-port="2" />
877
  <edge from-layer="43" from-port="2" to-layer="45" to-port="0" />
878
  <edge from-layer="44" from-port="0" to-layer="45" to-port="1" />
879
  <edge from-layer="45" from-port="2" to-layer="46" to-port="1" />
880
+ <edge from-layer="46" from-port="2" to-layer="47" to-port="1" />
881
+ <edge from-layer="46" from-port="2" to-layer="51" to-port="0" />
882
  <edge from-layer="47" from-port="2" to-layer="49" to-port="0" />
883
  <edge from-layer="48" from-port="0" to-layer="49" to-port="1" />
884
  <edge from-layer="49" from-port="2" to-layer="51" to-port="3" />
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ }
20
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [
30
+ "<|im_start|>",
31
+ "<|im_end|>"
32
+ ],
33
+ "bos_token": null,
34
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
35
+ "clean_up_tokenization_spaces": false,
36
+ "eos_token": "<|endoftext|>",
37
+ "errors": "replace",
38
+ "model_max_length": 32768,
39
+ "pad_token": "<|endoftext|>",
40
+ "split_special_tokens": false,
41
+ "tokenizer_class": "Qwen2Tokenizer",
42
+ "unk_token": null
43
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff