Hugging Face's logo

rippertnt
/
pibog_models

ONNX
Model card Files
xet
 Community
rippertnt commited on
Commit
d170e54
·
verified ·
1 Parent(s): 20d1e1e

Upload 146 files

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +42 -0
  2. FreeVC_ov/cmodel_ir.bin +3 -0
  3. FreeVC_ov/cmodel_ir.xml +0 -0
  4. FreeVC_ov/net_gir.bin +3 -0
  5. FreeVC_ov/net_gir.xml +0 -0
  6. FreeVC_ov/smodelir.bin +3 -0
  7. FreeVC_ov/smodelir.xml +1241 -0
  8. Qwen3-Embedding-0.6B-ov-int4/added_tokens.json +28 -0
  9. Qwen3-Embedding-0.6B-ov-int4/chat_template.jinja +85 -0
  10. Qwen3-Embedding-0.6B-ov-int4/config.json +60 -0
  11. Qwen3-Embedding-0.6B-ov-int4/merges.txt +0 -0
  12. Qwen3-Embedding-0.6B-ov-int4/model_cache/10398472748164076480.cl_cache +3 -0
  13. Qwen3-Embedding-0.6B-ov-int4/model_cache/11841033957157841238.cl_cache +3 -0
  14. Qwen3-Embedding-0.6B-ov-int4/model_cache/13100948868569734950.cl_cache +0 -0
  15. Qwen3-Embedding-0.6B-ov-int4/model_cache/14256774865286315154.cl_cache +3 -0
  16. Qwen3-Embedding-0.6B-ov-int4/model_cache/15972597138584836711.cl_cache +3 -0
  17. Qwen3-Embedding-0.6B-ov-int4/model_cache/17015111877664402134.cl_cache +3 -0
  18. Qwen3-Embedding-0.6B-ov-int4/model_cache/18358898440656323975.cl_cache +3 -0
  19. Qwen3-Embedding-0.6B-ov-int4/model_cache/18425769849181688742.cl_cache +3 -0
  20. Qwen3-Embedding-0.6B-ov-int4/model_cache/2084631378233982642.cl_cache +3 -0
  21. Qwen3-Embedding-0.6B-ov-int4/model_cache/2200953350652739583.cl_cache +3 -0
  22. Qwen3-Embedding-0.6B-ov-int4/model_cache/2467060138956266788.blob +3 -0
  23. Qwen3-Embedding-0.6B-ov-int4/model_cache/3006077353902421111.cl_cache +0 -0
  24. Qwen3-Embedding-0.6B-ov-int4/model_cache/4187937748300361869.cl_cache +3 -0
  25. Qwen3-Embedding-0.6B-ov-int4/model_cache/514085034797992975.cl_cache +3 -0
  26. Qwen3-Embedding-0.6B-ov-int4/model_cache/6367819844101748113.cl_cache +3 -0
  27. Qwen3-Embedding-0.6B-ov-int4/model_cache/6380654293821853377.cl_cache +3 -0
  28. Qwen3-Embedding-0.6B-ov-int4/model_cache/6417489891108773540.cl_cache +3 -0
  29. Qwen3-Embedding-0.6B-ov-int4/model_cache/8227443482036439551.cl_cache +3 -0
  30. Qwen3-Embedding-0.6B-ov-int4/model_cache/8233817952741756344.cl_cache +3 -0
  31. Qwen3-Embedding-0.6B-ov-int4/model_cache/8855579903425484800.cl_cache +3 -0
  32. Qwen3-Embedding-0.6B-ov-int4/model_cache/9546625216876219351.cl_cache +3 -0
  33. Qwen3-Embedding-0.6B-ov-int4/model_cache/9683605224545850666.cl_cache +3 -0
  34. Qwen3-Embedding-0.6B-ov-int4/openvino_config.json +46 -0
  35. Qwen3-Embedding-0.6B-ov-int4/openvino_detokenizer.bin +3 -0
  36. Qwen3-Embedding-0.6B-ov-int4/openvino_detokenizer.xml +219 -0
  37. Qwen3-Embedding-0.6B-ov-int4/openvino_model.bin +3 -0
  38. Qwen3-Embedding-0.6B-ov-int4/openvino_model.xml +0 -0
  39. Qwen3-Embedding-0.6B-ov-int4/openvino_tokenizer.bin +3 -0
  40. Qwen3-Embedding-0.6B-ov-int4/openvino_tokenizer.xml +799 -0
  41. Qwen3-Embedding-0.6B-ov-int4/special_tokens_map.json +31 -0
  42. Qwen3-Embedding-0.6B-ov-int4/tokenizer.json +3 -0
  43. Qwen3-Embedding-0.6B-ov-int4/tokenizer_config.json +239 -0
  44. Qwen3-Embedding-0.6B-ov-int4/vocab.json +0 -0
  45. Qwen3-Embedding-0.6B-ov-int8/added_tokens.json +28 -0
  46. Qwen3-Embedding-0.6B-ov-int8/chat_template.jinja +85 -0
  47. Qwen3-Embedding-0.6B-ov-int8/config.json +60 -0
  48. Qwen3-Embedding-0.6B-ov-int8/merges.txt +0 -0
  49. Qwen3-Embedding-0.6B-ov-int8/model_cache/10398472748164076480.cl_cache +3 -0
  50. Qwen3-Embedding-0.6B-ov-int8/model_cache/12113472825542766259.cl_cache +3 -0
.gitattributes CHANGED
@@ -33,3 +33,45 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ Qwen3-Embedding-0.6B-ov-int4/model_cache/10398472748164076480.cl_cache filter=lfs diff=lfs merge=lfs -text
37
+ Qwen3-Embedding-0.6B-ov-int4/model_cache/11841033957157841238.cl_cache filter=lfs diff=lfs merge=lfs -text
38
+ Qwen3-Embedding-0.6B-ov-int4/model_cache/14256774865286315154.cl_cache filter=lfs diff=lfs merge=lfs -text
39
+ Qwen3-Embedding-0.6B-ov-int4/model_cache/15972597138584836711.cl_cache filter=lfs diff=lfs merge=lfs -text
40
+ Qwen3-Embedding-0.6B-ov-int4/model_cache/17015111877664402134.cl_cache filter=lfs diff=lfs merge=lfs -text
41
+ Qwen3-Embedding-0.6B-ov-int4/model_cache/18358898440656323975.cl_cache filter=lfs diff=lfs merge=lfs -text
42
+ Qwen3-Embedding-0.6B-ov-int4/model_cache/18425769849181688742.cl_cache filter=lfs diff=lfs merge=lfs -text
43
+ Qwen3-Embedding-0.6B-ov-int4/model_cache/2084631378233982642.cl_cache filter=lfs diff=lfs merge=lfs -text
44
+ Qwen3-Embedding-0.6B-ov-int4/model_cache/2200953350652739583.cl_cache filter=lfs diff=lfs merge=lfs -text
45
+ Qwen3-Embedding-0.6B-ov-int4/model_cache/2467060138956266788.blob filter=lfs diff=lfs merge=lfs -text
46
+ Qwen3-Embedding-0.6B-ov-int4/model_cache/4187937748300361869.cl_cache filter=lfs diff=lfs merge=lfs -text
47
+ Qwen3-Embedding-0.6B-ov-int4/model_cache/514085034797992975.cl_cache filter=lfs diff=lfs merge=lfs -text
48
+ Qwen3-Embedding-0.6B-ov-int4/model_cache/6367819844101748113.cl_cache filter=lfs diff=lfs merge=lfs -text
49
+ Qwen3-Embedding-0.6B-ov-int4/model_cache/6380654293821853377.cl_cache filter=lfs diff=lfs merge=lfs -text
50
+ Qwen3-Embedding-0.6B-ov-int4/model_cache/6417489891108773540.cl_cache filter=lfs diff=lfs merge=lfs -text
51
+ Qwen3-Embedding-0.6B-ov-int4/model_cache/8227443482036439551.cl_cache filter=lfs diff=lfs merge=lfs -text
52
+ Qwen3-Embedding-0.6B-ov-int4/model_cache/8233817952741756344.cl_cache filter=lfs diff=lfs merge=lfs -text
53
+ Qwen3-Embedding-0.6B-ov-int4/model_cache/8855579903425484800.cl_cache filter=lfs diff=lfs merge=lfs -text
54
+ Qwen3-Embedding-0.6B-ov-int4/model_cache/9546625216876219351.cl_cache filter=lfs diff=lfs merge=lfs -text
55
+ Qwen3-Embedding-0.6B-ov-int4/model_cache/9683605224545850666.cl_cache filter=lfs diff=lfs merge=lfs -text
56
+ Qwen3-Embedding-0.6B-ov-int4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
57
+ Qwen3-Embedding-0.6B-ov-int8/model_cache/10398472748164076480.cl_cache filter=lfs diff=lfs merge=lfs -text
58
+ Qwen3-Embedding-0.6B-ov-int8/model_cache/12113472825542766259.cl_cache filter=lfs diff=lfs merge=lfs -text
59
+ Qwen3-Embedding-0.6B-ov-int8/model_cache/13904763665985950121.cl_cache filter=lfs diff=lfs merge=lfs -text
60
+ Qwen3-Embedding-0.6B-ov-int8/model_cache/14228004042234774058.cl_cache filter=lfs diff=lfs merge=lfs -text
61
+ Qwen3-Embedding-0.6B-ov-int8/model_cache/15452446039601008211.cl_cache filter=lfs diff=lfs merge=lfs -text
62
+ Qwen3-Embedding-0.6B-ov-int8/model_cache/15972597138584836711.cl_cache filter=lfs diff=lfs merge=lfs -text
63
+ Qwen3-Embedding-0.6B-ov-int8/model_cache/17015111877664402134.cl_cache filter=lfs diff=lfs merge=lfs -text
64
+ Qwen3-Embedding-0.6B-ov-int8/model_cache/17917053609886349368.blob filter=lfs diff=lfs merge=lfs -text
65
+ Qwen3-Embedding-0.6B-ov-int8/model_cache/18358898440656323975.cl_cache filter=lfs diff=lfs merge=lfs -text
66
+ Qwen3-Embedding-0.6B-ov-int8/model_cache/1897978825296495813.cl_cache filter=lfs diff=lfs merge=lfs -text
67
+ Qwen3-Embedding-0.6B-ov-int8/model_cache/2084631378233982642.cl_cache filter=lfs diff=lfs merge=lfs -text
68
+ Qwen3-Embedding-0.6B-ov-int8/model_cache/3535274234211186810.cl_cache filter=lfs diff=lfs merge=lfs -text
69
+ Qwen3-Embedding-0.6B-ov-int8/model_cache/3767622921309506184.cl_cache filter=lfs diff=lfs merge=lfs -text
70
+ Qwen3-Embedding-0.6B-ov-int8/model_cache/4083341330400695577.cl_cache filter=lfs diff=lfs merge=lfs -text
71
+ Qwen3-Embedding-0.6B-ov-int8/model_cache/7317836480131138323.cl_cache filter=lfs diff=lfs merge=lfs -text
72
+ Qwen3-Embedding-0.6B-ov-int8/model_cache/8855579903425484800.cl_cache filter=lfs diff=lfs merge=lfs -text
73
+ Qwen3-Embedding-0.6B-ov-int8/model_cache/9546625216876219351.cl_cache filter=lfs diff=lfs merge=lfs -text
74
+ Qwen3-Embedding-0.6B-ov-int8/tokenizer.json filter=lfs diff=lfs merge=lfs -text
75
+ Qwen3-Reranker-0.6B-ov-fp16/tokenizer.json filter=lfs diff=lfs merge=lfs -text
76
+ Qwen3-Reranker-0.6B-ov-int4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
77
+ Qwen3-Reranker-0.6B-ov-int8/tokenizer.json filter=lfs diff=lfs merge=lfs -text
FreeVC_ov/cmodel_ir.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a13c4b44223f28d5345c7094fa15e78ee6a71065dddae15cd8366a0277548c75
3
+ size 630904264
FreeVC_ov/cmodel_ir.xml ADDED
The diff for this file is too large to render. See raw diff
 
FreeVC_ov/net_gir.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd04b8833ecebd5cc5fab4b8541c7523b295154819e0180e924e9cfffd540ee4
3
+ size 60905382
FreeVC_ov/net_gir.xml ADDED
The diff for this file is too large to render. See raw diff
 
FreeVC_ov/smodelir.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b957d216cc4d2d167403b7cfb6705a76ef04d84a25d339718c0571497101f2a
3
+ size 2841174
FreeVC_ov/smodelir.xml ADDED
@@ -0,0 +1,1241 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="Model4" version="11">
3
+ <layers>
4
+ <layer id="0" name="mels" type="Parameter" version="opset1">
5
+ <data shape="?,?,?" element_type="f32" />
6
+ <output>
7
+ <port id="0" precision="FP32" names="mels">
8
+ <dim>-1</dim>
9
+ <dim>-1</dim>
10
+ <dim>-1</dim>
11
+ </port>
12
+ </output>
13
+ </layer>
14
+ <layer id="1" name="__module.lstm/aten::zeros/Convert_compressed" type="Const" version="opset1">
15
+ <data element_type="f16" shape="" offset="0" size="2" />
16
+ <output>
17
+ <port id="0" precision="FP16" />
18
+ </output>
19
+ </layer>
20
+ <layer id="2" name="__module.lstm/aten::zeros/Convert" type="Convert" version="opset1">
21
+ <data destination_type="f32" />
22
+ <rt_info>
23
+ <attribute name="decompression" version="0" />
24
+ </rt_info>
25
+ <input>
26
+ <port id="0" precision="FP16" />
27
+ </input>
28
+ <output>
29
+ <port id="1" precision="FP32" />
30
+ </output>
31
+ </layer>
32
+ <layer id="3" name="Constant_333313" type="Const" version="opset1">
33
+ <data element_type="i64" shape="1" offset="2" size="8" />
34
+ <rt_info>
35
+ <attribute name="precise" version="0" />
36
+ </rt_info>
37
+ <output>
38
+ <port id="0" precision="I64">
39
+ <dim>1</dim>
40
+ </port>
41
+ </output>
42
+ </layer>
43
+ <layer id="4" name="ShapeOf_335713" type="ShapeOf" version="opset3">
44
+ <data output_type="i64" />
45
+ <input>
46
+ <port id="0" precision="FP32">
47
+ <dim>-1</dim>
48
+ <dim>-1</dim>
49
+ <dim>-1</dim>
50
+ </port>
51
+ </input>
52
+ <output>
53
+ <port id="1" precision="I64">
54
+ <dim>3</dim>
55
+ </port>
56
+ </output>
57
+ </layer>
58
+ <layer id="5" name="Constant_335714" type="Const" version="opset1">
59
+ <data element_type="i64" shape="1" offset="10" size="8" />
60
+ <rt_info>
61
+ <attribute name="precise" version="0" />
62
+ </rt_info>
63
+ <output>
64
+ <port id="0" precision="I64">
65
+ <dim>1</dim>
66
+ </port>
67
+ </output>
68
+ </layer>
69
+ <layer id="6" name="Constant_335715" type="Const" version="opset1">
70
+ <data element_type="i64" shape="" offset="10" size="8" />
71
+ <rt_info>
72
+ <attribute name="precise" version="0" />
73
+ </rt_info>
74
+ <output>
75
+ <port id="0" precision="I64" />
76
+ </output>
77
+ </layer>
78
+ <layer id="7" name="Gather_335716" type="Gather" version="opset8">
79
+ <data batch_dims="0" />
80
+ <input>
81
+ <port id="0" precision="I64">
82
+ <dim>3</dim>
83
+ </port>
84
+ <port id="1" precision="I64">
85
+ <dim>1</dim>
86
+ </port>
87
+ <port id="2" precision="I64" />
88
+ </input>
89
+ <output>
90
+ <port id="3" precision="I64" names="39">
91
+ <dim>1</dim>
92
+ </port>
93
+ </output>
94
+ </layer>
95
+ <layer id="8" name="Constant_333314" type="Const" version="opset1">
96
+ <data element_type="i64" shape="1" offset="18" size="8" />
97
+ <rt_info>
98
+ <attribute name="precise" version="0" />
99
+ </rt_info>
100
+ <output>
101
+ <port id="0" precision="I64">
102
+ <dim>1</dim>
103
+ </port>
104
+ </output>
105
+ </layer>
106
+ <layer id="9" name="__module.lstm/prim::ListConstruct" type="Concat" version="opset1">
107
+ <data axis="0" />
108
+ <input>
109
+ <port id="0" precision="I64">
110
+ <dim>1</dim>
111
+ </port>
112
+ <port id="1" precision="I64">
113
+ <dim>1</dim>
114
+ </port>
115
+ <port id="2" precision="I64">
116
+ <dim>1</dim>
117
+ </port>
118
+ </input>
119
+ <output>
120
+ <port id="3" precision="I64">
121
+ <dim>3</dim>
122
+ </port>
123
+ </output>
124
+ </layer>
125
+ <layer id="10" name="__module.lstm/aten::zeros/Broadcast" type="Broadcast" version="opset3">
126
+ <data mode="numpy" />
127
+ <input>
128
+ <port id="0" precision="FP32" />
129
+ <port id="1" precision="I64">
130
+ <dim>3</dim>
131
+ </port>
132
+ </input>
133
+ <output>
134
+ <port id="2" precision="FP32" names="41,43,hx,hx.1">
135
+ <dim>3</dim>
136
+ <dim>-1</dim>
137
+ <dim>256</dim>
138
+ </port>
139
+ </output>
140
+ </layer>
141
+ <layer id="11" name="Constant_333355" type="Const" version="opset1">
142
+ <data element_type="i32" shape="" offset="26" size="4" />
143
+ <output>
144
+ <port id="0" precision="I32" />
145
+ </output>
146
+ </layer>
147
+ <layer id="12" name="__module.lstm/aten::lstm/Split" type="Split" version="opset1">
148
+ <data num_splits="3" />
149
+ <input>
150
+ <port id="0" precision="FP32">
151
+ <dim>3</dim>
152
+ <dim>-1</dim>
153
+ <dim>256</dim>
154
+ </port>
155
+ <port id="1" precision="I32" />
156
+ </input>
157
+ <output>
158
+ <port id="2" precision="FP32">
159
+ <dim>1</dim>
160
+ <dim>-1</dim>
161
+ <dim>256</dim>
162
+ </port>
163
+ <port id="3" precision="FP32">
164
+ <dim>1</dim>
165
+ <dim>-1</dim>
166
+ <dim>256</dim>
167
+ </port>
168
+ <port id="4" precision="FP32">
169
+ <dim>1</dim>
170
+ <dim>-1</dim>
171
+ <dim>256</dim>
172
+ </port>
173
+ </output>
174
+ </layer>
175
+ <layer id="13" name="Constant_335522" type="Const" version="opset1">
176
+ <data element_type="i64" shape="3" offset="30" size="24" />
177
+ <rt_info>
178
+ <attribute name="precise" version="0" />
179
+ </rt_info>
180
+ <output>
181
+ <port id="0" precision="I64">
182
+ <dim>3</dim>
183
+ </port>
184
+ </output>
185
+ </layer>
186
+ <layer id="14" name="__module.lstm/aten::lstm/Transpose" type="Reshape" version="opset1">
187
+ <data special_zero="true" />
188
+ <input>
189
+ <port id="0" precision="FP32">
190
+ <dim>1</dim>
191
+ <dim>-1</dim>
192
+ <dim>256</dim>
193
+ </port>
194
+ <port id="1" precision="I64">
195
+ <dim>3</dim>
196
+ </port>
197
+ </input>
198
+ <output>
199
+ <port id="2" precision="FP32">
200
+ <dim>-1</dim>
201
+ <dim>1</dim>
202
+ <dim>256</dim>
203
+ </port>
204
+ </output>
205
+ </layer>
206
+ <layer id="15" name="Convert_335721" type="Convert" version="opset1">
207
+ <data destination_type="i32" />
208
+ <input>
209
+ <port id="0" precision="I64">
210
+ <dim>3</dim>
211
+ </port>
212
+ </input>
213
+ <output>
214
+ <port id="1" precision="I32">
215
+ <dim>3</dim>
216
+ </port>
217
+ </output>
218
+ </layer>
219
+ <layer id="16" name="Constant_333358" type="Const" version="opset1">
220
+ <data element_type="i32" shape="1" offset="54" size="4" />
221
+ <output>
222
+ <port id="0" precision="I32">
223
+ <dim>1</dim>
224
+ </port>
225
+ </output>
226
+ </layer>
227
+ <layer id="17" name="Constant_333379" type="Const" version="opset1">
228
+ <data element_type="i32" shape="1" offset="26" size="4" />
229
+ <output>
230
+ <port id="0" precision="I32">
231
+ <dim>1</dim>
232
+ </port>
233
+ </output>
234
+ </layer>
235
+ <layer id="18" name="__module.lstm/aten::lstm/Gather" type="Gather" version="opset8">
236
+ <data batch_dims="0" />
237
+ <input>
238
+ <port id="0" precision="I32">
239
+ <dim>3</dim>
240
+ </port>
241
+ <port id="1" precision="I32">
242
+ <dim>1</dim>
243
+ </port>
244
+ <port id="2" precision="I32">
245
+ <dim>1</dim>
246
+ </port>
247
+ </input>
248
+ <output>
249
+ <port id="3" precision="I32">
250
+ <dim>1</dim>
251
+ </port>
252
+ </output>
253
+ </layer>
254
+ <layer id="19" name="Convert_335722" type="Convert" version="opset1">
255
+ <data destination_type="i32" />
256
+ <input>
257
+ <port id="0" precision="I64">
258
+ <dim>1</dim>
259
+ </port>
260
+ </input>
261
+ <output>
262
+ <port id="1" precision="I32">
263
+ <dim>1</dim>
264
+ </port>
265
+ </output>
266
+ </layer>
267
+ <layer id="20" name="__module.lstm/aten::lstm/Broadcast" type="Broadcast" version="opset3">
268
+ <data mode="numpy" />
269
+ <input>
270
+ <port id="0" precision="I32">
271
+ <dim>1</dim>
272
+ </port>
273
+ <port id="1" precision="I32">
274
+ <dim>1</dim>
275
+ </port>
276
+ </input>
277
+ <output>
278
+ <port id="2" precision="I32">
279
+ <dim>-1</dim>
280
+ </port>
281
+ </output>
282
+ </layer>
283
+ <layer id="21" name="__module.lstm/aten::lstm/Unsqueeze_compressed" type="Const" version="opset1">
284
+ <data element_type="f16" shape="1, 1024, 40" offset="58" size="81920" />
285
+ <output>
286
+ <port id="0" precision="FP16">
287
+ <dim>1</dim>
288
+ <dim>1024</dim>
289
+ <dim>40</dim>
290
+ </port>
291
+ </output>
292
+ </layer>
293
+ <layer id="22" name="__module.lstm/aten::lstm/Unsqueeze" type="Convert" version="opset1">
294
+ <data destination_type="f32" />
295
+ <rt_info>
296
+ <attribute name="decompression" version="0" />
297
+ </rt_info>
298
+ <input>
299
+ <port id="0" precision="FP16">
300
+ <dim>1</dim>
301
+ <dim>1024</dim>
302
+ <dim>40</dim>
303
+ </port>
304
+ </input>
305
+ <output>
306
+ <port id="1" precision="FP32">
307
+ <dim>1</dim>
308
+ <dim>1024</dim>
309
+ <dim>40</dim>
310
+ </port>
311
+ </output>
312
+ </layer>
313
+ <layer id="23" name="__module.lstm/aten::lstm/Unsqueeze_1_compressed" type="Const" version="opset1">
314
+ <data element_type="f16" shape="1, 1024, 256" offset="81978" size="524288" />
315
+ <output>
316
+ <port id="0" precision="FP16">
317
+ <dim>1</dim>
318
+ <dim>1024</dim>
319
+ <dim>256</dim>
320
+ </port>
321
+ </output>
322
+ </layer>
323
+ <layer id="24" name="__module.lstm/aten::lstm/Unsqueeze_1" type="Convert" version="opset1">
324
+ <data destination_type="f32" />
325
+ <rt_info>
326
+ <attribute name="decompression" version="0" />
327
+ </rt_info>
328
+ <input>
329
+ <port id="0" precision="FP16">
330
+ <dim>1</dim>
331
+ <dim>1024</dim>
332
+ <dim>256</dim>
333
+ </port>
334
+ </input>
335
+ <output>
336
+ <port id="1" precision="FP32">
337
+ <dim>1</dim>
338
+ <dim>1024</dim>
339
+ <dim>256</dim>
340
+ </port>
341
+ </output>
342
+ </layer>
343
+ <layer id="25" name="__module.lstm/aten::lstm/Unsqueeze_2_compressed" type="Const" version="opset1">
344
+ <data element_type="f16" shape="1, 1024" offset="606266" size="2048" />
345
+ <output>
346
+ <port id="0" precision="FP16">
347
+ <dim>1</dim>
348
+ <dim>1024</dim>
349
+ </port>
350
+ </output>
351
+ </layer>
352
+ <layer id="26" name="__module.lstm/aten::lstm/Unsqueeze_2" type="Convert" version="opset1">
353
+ <data destination_type="f32" />
354
+ <rt_info>
355
+ <attribute name="decompression" version="0" />
356
+ </rt_info>
357
+ <input>
358
+ <port id="0" precision="FP16">
359
+ <dim>1</dim>
360
+ <dim>1024</dim>
361
+ </port>
362
+ </input>
363
+ <output>
364
+ <port id="1" precision="FP32">
365
+ <dim>1</dim>
366
+ <dim>1024</dim>
367
+ </port>
368
+ </output>
369
+ </layer>
370
+ <layer id="27" name="__module.lstm/aten::lstm/LSTMSequence" type="LSTMSequence" version="opset5">
371
+ <data direction="forward" hidden_size="256" activations="sigmoid, tanh, tanh" activations_alpha="" activations_beta="" clip="0" />
372
+ <input>
373
+ <port id="0" precision="FP32">
374
+ <dim>-1</dim>
375
+ <dim>-1</dim>
376
+ <dim>-1</dim>
377
+ </port>
378
+ <port id="1" precision="FP32">
379
+ <dim>-1</dim>
380
+ <dim>1</dim>
381
+ <dim>256</dim>
382
+ </port>
383
+ <port id="2" precision="FP32">
384
+ <dim>-1</dim>
385
+ <dim>1</dim>
386
+ <dim>256</dim>
387
+ </port>
388
+ <port id="3" precision="I32">
389
+ <dim>-1</dim>
390
+ </port>
391
+ <port id="4" precision="FP32">
392
+ <dim>1</dim>
393
+ <dim>1024</dim>
394
+ <dim>40</dim>
395
+ </port>
396
+ <port id="5" precision="FP32">
397
+ <dim>1</dim>
398
+ <dim>1024</dim>
399
+ <dim>256</dim>
400
+ </port>
401
+ <port id="6" precision="FP32">
402
+ <dim>1</dim>
403
+ <dim>1024</dim>
404
+ </port>
405
+ </input>
406
+ <output>
407
+ <port id="7" precision="FP32">
408
+ <dim>-1</dim>
409
+ <dim>1</dim>
410
+ <dim>-1</dim>
411
+ <dim>256</dim>
412
+ </port>
413
+ <port id="8" precision="FP32">
414
+ <dim>-1</dim>
415
+ <dim>1</dim>
416
+ <dim>256</dim>
417
+ </port>
418
+ <port id="9" precision="FP32">
419
+ <dim>-1</dim>
420
+ <dim>1</dim>
421
+ <dim>256</dim>
422
+ </port>
423
+ </output>
424
+ </layer>
425
+ <layer id="28" name="Constant_333357" type="Const" version="opset1">
426
+ <data element_type="i32" shape="" offset="54" size="4" />
427
+ <output>
428
+ <port id="0" precision="I32" />
429
+ </output>
430
+ </layer>
431
+ <layer id="29" name="__module.lstm/aten::lstm/Squeeze" type="Squeeze" version="opset1">
432
+ <input>
433
+ <port id="0" precision="FP32">
434
+ <dim>-1</dim>
435
+ <dim>1</dim>
436
+ <dim>-1</dim>
437
+ <dim>256</dim>
438
+ </port>
439
+ <port id="1" precision="I32" />
440
+ </input>
441
+ <output>
442
+ <port id="2" precision="FP32">
443
+ <dim>-1</dim>
444
+ <dim>-1</dim>
445
+ <dim>256</dim>
446
+ </port>
447
+ </output>
448
+ </layer>
449
+ <layer id="30" name="Constant_335524" type="Const" version="opset1">
450
+ <data element_type="i64" shape="3" offset="30" size="24" />
451
+ <rt_info>
452
+ <attribute name="precise" version="0" />
453
+ </rt_info>
454
+ <output>
455
+ <port id="0" precision="I64">
456
+ <dim>3</dim>
457
+ </port>
458
+ </output>
459
+ </layer>
460
+ <layer id="31" name="__module.lstm/aten::lstm/Transpose_2" type="Reshape" version="opset1">
461
+ <data special_zero="true" />
462
+ <input>
463
+ <port id="0" precision="FP32">
464
+ <dim>1</dim>
465
+ <dim>-1</dim>
466
+ <dim>256</dim>
467
+ </port>
468
+ <port id="1" precision="I64">
469
+ <dim>3</dim>
470
+ </port>
471
+ </input>
472
+ <output>
473
+ <port id="2" precision="FP32">
474
+ <dim>-1</dim>
475
+ <dim>1</dim>
476
+ <dim>256</dim>
477
+ </port>
478
+ </output>
479
+ </layer>
480
+ <layer id="32" name="__module.lstm/aten::lstm/Split_1" type="Split" version="opset1">
481
+ <data num_splits="3" />
482
+ <input>
483
+ <port id="0" precision="FP32">
484
+ <dim>3</dim>
485
+ <dim>-1</dim>
486
+ <dim>256</dim>
487
+ </port>
488
+ <port id="1" precision="I32" />
489
+ </input>
490
+ <output>
491
+ <port id="2" precision="FP32">
492
+ <dim>1</dim>
493
+ <dim>-1</dim>
494
+ <dim>256</dim>
495
+ </port>
496
+ <port id="3" precision="FP32">
497
+ <dim>1</dim>
498
+ <dim>-1</dim>
499
+ <dim>256</dim>
500
+ </port>
501
+ <port id="4" precision="FP32">
502
+ <dim>1</dim>
503
+ <dim>-1</dim>
504
+ <dim>256</dim>
505
+ </port>
506
+ </output>
507
+ </layer>
508
+ <layer id="33" name="Constant_335526" type="Const" version="opset1">
509
+ <data element_type="i64" shape="3" offset="30" size="24" />
510
+ <rt_info>
511
+ <attribute name="precise" version="0" />
512
+ </rt_info>
513
+ <output>
514
+ <port id="0" precision="I64">
515
+ <dim>3</dim>
516
+ </port>
517
+ </output>
518
+ </layer>
519
+ <layer id="34" name="__module.lstm/aten::lstm/Transpose_3" type="Reshape" version="opset1">
520
+ <data special_zero="true" />
521
+ <input>
522
+ <port id="0" precision="FP32">
523
+ <dim>1</dim>
524
+ <dim>-1</dim>
525
+ <dim>256</dim>
526
+ </port>
527
+ <port id="1" precision="I64">
528
+ <dim>3</dim>
529
+ </port>
530
+ </input>
531
+ <output>
532
+ <port id="2" precision="FP32">
533
+ <dim>-1</dim>
534
+ <dim>1</dim>
535
+ <dim>256</dim>
536
+ </port>
537
+ </output>
538
+ </layer>
539
+ <layer id="35" name="__module.lstm/aten::lstm/Unsqueeze_3_compressed" type="Const" version="opset1">
540
+ <data element_type="f16" shape="1, 1024, 256" offset="608314" size="524288" />
541
+ <output>
542
+ <port id="0" precision="FP16">
543
+ <dim>1</dim>
544
+ <dim>1024</dim>
545
+ <dim>256</dim>
546
+ </port>
547
+ </output>
548
+ </layer>
549
+ <layer id="36" name="__module.lstm/aten::lstm/Unsqueeze_3" type="Convert" version="opset1">
550
+ <data destination_type="f32" />
551
+ <rt_info>
552
+ <attribute name="decompression" version="0" />
553
+ </rt_info>
554
+ <input>
555
+ <port id="0" precision="FP16">
556
+ <dim>1</dim>
557
+ <dim>1024</dim>
558
+ <dim>256</dim>
559
+ </port>
560
+ </input>
561
+ <output>
562
+ <port id="1" precision="FP32">
563
+ <dim>1</dim>
564
+ <dim>1024</dim>
565
+ <dim>256</dim>
566
+ </port>
567
+ </output>
568
+ </layer>
569
+ <layer id="37" name="__module.lstm/aten::lstm/Unsqueeze_4_compressed" type="Const" version="opset1">
570
+ <data element_type="f16" shape="1, 1024, 256" offset="1132602" size="524288" />
571
+ <output>
572
+ <port id="0" precision="FP16">
573
+ <dim>1</dim>
574
+ <dim>1024</dim>
575
+ <dim>256</dim>
576
+ </port>
577
+ </output>
578
+ </layer>
579
+ <layer id="38" name="__module.lstm/aten::lstm/Unsqueeze_4" type="Convert" version="opset1">
580
+ <data destination_type="f32" />
581
+ <rt_info>
582
+ <attribute name="decompression" version="0" />
583
+ </rt_info>
584
+ <input>
585
+ <port id="0" precision="FP16">
586
+ <dim>1</dim>
587
+ <dim>1024</dim>
588
+ <dim>256</dim>
589
+ </port>
590
+ </input>
591
+ <output>
592
+ <port id="1" precision="FP32">
593
+ <dim>1</dim>
594
+ <dim>1024</dim>
595
+ <dim>256</dim>
596
+ </port>
597
+ </output>
598
+ </layer>
599
+ <layer id="39" name="__module.lstm/aten::lstm/Unsqueeze_5_compressed" type="Const" version="opset1">
600
+ <data element_type="f16" shape="1, 1024" offset="1656890" size="2048" />
601
+ <output>
602
+ <port id="0" precision="FP16">
603
+ <dim>1</dim>
604
+ <dim>1024</dim>
605
+ </port>
606
+ </output>
607
+ </layer>
608
+ <layer id="40" name="__module.lstm/aten::lstm/Unsqueeze_5" type="Convert" version="opset1">
609
+ <data destination_type="f32" />
610
+ <rt_info>
611
+ <attribute name="decompression" version="0" />
612
+ </rt_info>
613
+ <input>
614
+ <port id="0" precision="FP16">
615
+ <dim>1</dim>
616
+ <dim>1024</dim>
617
+ </port>
618
+ </input>
619
+ <output>
620
+ <port id="1" precision="FP32">
621
+ <dim>1</dim>
622
+ <dim>1024</dim>
623
+ </port>
624
+ </output>
625
+ </layer>
626
+ <layer id="41" name="__module.lstm/aten::lstm/LSTMSequence_1" type="LSTMSequence" version="opset5">
627
+ <data direction="forward" hidden_size="256" activations="sigmoid, tanh, tanh" activations_alpha="" activations_beta="" clip="0" />
628
+ <input>
629
+ <port id="0" precision="FP32">
630
+ <dim>-1</dim>
631
+ <dim>-1</dim>
632
+ <dim>256</dim>
633
+ </port>
634
+ <port id="1" precision="FP32">
635
+ <dim>-1</dim>
636
+ <dim>1</dim>
637
+ <dim>256</dim>
638
+ </port>
639
+ <port id="2" precision="FP32">
640
+ <dim>-1</dim>
641
+ <dim>1</dim>
642
+ <dim>256</dim>
643
+ </port>
644
+ <port id="3" precision="I32">
645
+ <dim>-1</dim>
646
+ </port>
647
+ <port id="4" precision="FP32">
648
+ <dim>1</dim>
649
+ <dim>1024</dim>
650
+ <dim>256</dim>
651
+ </port>
652
+ <port id="5" precision="FP32">
653
+ <dim>1</dim>
654
+ <dim>1024</dim>
655
+ <dim>256</dim>
656
+ </port>
657
+ <port id="6" precision="FP32">
658
+ <dim>1</dim>
659
+ <dim>1024</dim>
660
+ </port>
661
+ </input>
662
+ <output>
663
+ <port id="7" precision="FP32">
664
+ <dim>-1</dim>
665
+ <dim>1</dim>
666
+ <dim>-1</dim>
667
+ <dim>256</dim>
668
+ </port>
669
+ <port id="8" precision="FP32">
670
+ <dim>-1</dim>
671
+ <dim>1</dim>
672
+ <dim>256</dim>
673
+ </port>
674
+ <port id="9" precision="FP32">
675
+ <dim>-1</dim>
676
+ <dim>1</dim>
677
+ <dim>256</dim>
678
+ </port>
679
+ </output>
680
+ </layer>
681
+ <layer id="42" name="__module.lstm/aten::lstm/Squeeze_1" type="Squeeze" version="opset1">
682
+ <input>
683
+ <port id="0" precision="FP32">
684
+ <dim>-1</dim>
685
+ <dim>1</dim>
686
+ <dim>-1</dim>
687
+ <dim>256</dim>
688
+ </port>
689
+ <port id="1" precision="I32" />
690
+ </input>
691
+ <output>
692
+ <port id="2" precision="FP32">
693
+ <dim>-1</dim>
694
+ <dim>-1</dim>
695
+ <dim>256</dim>
696
+ </port>
697
+ </output>
698
+ </layer>
699
+ <layer id="43" name="Constant_335528" type="Const" version="opset1">
700
+ <data element_type="i64" shape="3" offset="30" size="24" />
701
+ <rt_info>
702
+ <attribute name="precise" version="0" />
703
+ </rt_info>
704
+ <output>
705
+ <port id="0" precision="I64">
706
+ <dim>3</dim>
707
+ </port>
708
+ </output>
709
+ </layer>
710
+ <layer id="44" name="__module.lstm/aten::lstm/Transpose_4" type="Reshape" version="opset1">
711
+ <data special_zero="true" />
712
+ <input>
713
+ <port id="0" precision="FP32">
714
+ <dim>1</dim>
715
+ <dim>-1</dim>
716
+ <dim>256</dim>
717
+ </port>
718
+ <port id="1" precision="I64">
719
+ <dim>3</dim>
720
+ </port>
721
+ </input>
722
+ <output>
723
+ <port id="2" precision="FP32">
724
+ <dim>-1</dim>
725
+ <dim>1</dim>
726
+ <dim>256</dim>
727
+ </port>
728
+ </output>
729
+ </layer>
730
+ <layer id="45" name="Constant_335530" type="Const" version="opset1">
731
+ <data element_type="i64" shape="3" offset="30" size="24" />
732
+ <rt_info>
733
+ <attribute name="precise" version="0" />
734
+ </rt_info>
735
+ <output>
736
+ <port id="0" precision="I64">
737
+ <dim>3</dim>
738
+ </port>
739
+ </output>
740
+ </layer>
741
+ <layer id="46" name="__module.lstm/aten::lstm/Transpose_5" type="Reshape" version="opset1">
742
+ <data special_zero="true" />
743
+ <input>
744
+ <port id="0" precision="FP32">
745
+ <dim>1</dim>
746
+ <dim>-1</dim>
747
+ <dim>256</dim>
748
+ </port>
749
+ <port id="1" precision="I64">
750
+ <dim>3</dim>
751
+ </port>
752
+ </input>
753
+ <output>
754
+ <port id="2" precision="FP32">
755
+ <dim>-1</dim>
756
+ <dim>1</dim>
757
+ <dim>256</dim>
758
+ </port>
759
+ </output>
760
+ </layer>
761
+ <layer id="47" name="__module.lstm/aten::lstm/Unsqueeze_6_compressed" type="Const" version="opset1">
762
+ <data element_type="f16" shape="1, 1024, 256" offset="1658938" size="524288" />
763
+ <output>
764
+ <port id="0" precision="FP16">
765
+ <dim>1</dim>
766
+ <dim>1024</dim>
767
+ <dim>256</dim>
768
+ </port>
769
+ </output>
770
+ </layer>
771
+ <layer id="48" name="__module.lstm/aten::lstm/Unsqueeze_6" type="Convert" version="opset1">
772
+ <data destination_type="f32" />
773
+ <rt_info>
774
+ <attribute name="decompression" version="0" />
775
+ </rt_info>
776
+ <input>
777
+ <port id="0" precision="FP16">
778
+ <dim>1</dim>
779
+ <dim>1024</dim>
780
+ <dim>256</dim>
781
+ </port>
782
+ </input>
783
+ <output>
784
+ <port id="1" precision="FP32">
785
+ <dim>1</dim>
786
+ <dim>1024</dim>
787
+ <dim>256</dim>
788
+ </port>
789
+ </output>
790
+ </layer>
791
+ <layer id="49" name="__module.lstm/aten::lstm/Unsqueeze_7_compressed" type="Const" version="opset1">
792
+ <data element_type="f16" shape="1, 1024, 256" offset="2183226" size="524288" />
793
+ <output>
794
+ <port id="0" precision="FP16">
795
+ <dim>1</dim>
796
+ <dim>1024</dim>
797
+ <dim>256</dim>
798
+ </port>
799
+ </output>
800
+ </layer>
801
+ <layer id="50" name="__module.lstm/aten::lstm/Unsqueeze_7" type="Convert" version="opset1">
802
+ <data destination_type="f32" />
803
+ <rt_info>
804
+ <attribute name="decompression" version="0" />
805
+ </rt_info>
806
+ <input>
807
+ <port id="0" precision="FP16">
808
+ <dim>1</dim>
809
+ <dim>1024</dim>
810
+ <dim>256</dim>
811
+ </port>
812
+ </input>
813
+ <output>
814
+ <port id="1" precision="FP32">
815
+ <dim>1</dim>
816
+ <dim>1024</dim>
817
+ <dim>256</dim>
818
+ </port>
819
+ </output>
820
+ </layer>
821
+ <layer id="51" name="__module.lstm/aten::lstm/Unsqueeze_8_compressed" type="Const" version="opset1">
822
+ <data element_type="f16" shape="1, 1024" offset="2707514" size="2048" />
823
+ <output>
824
+ <port id="0" precision="FP16">
825
+ <dim>1</dim>
826
+ <dim>1024</dim>
827
+ </port>
828
+ </output>
829
+ </layer>
830
+ <layer id="52" name="__module.lstm/aten::lstm/Unsqueeze_8" type="Convert" version="opset1">
831
+ <data destination_type="f32" />
832
+ <rt_info>
833
+ <attribute name="decompression" version="0" />
834
+ </rt_info>
835
+ <input>
836
+ <port id="0" precision="FP16">
837
+ <dim>1</dim>
838
+ <dim>1024</dim>
839
+ </port>
840
+ </input>
841
+ <output>
842
+ <port id="1" precision="FP32">
843
+ <dim>1</dim>
844
+ <dim>1024</dim>
845
+ </port>
846
+ </output>
847
+ </layer>
848
+ <layer id="53" name="__module.lstm/aten::lstm/LSTMSequence_2" type="LSTMSequence" version="opset5">
849
+ <data direction="forward" hidden_size="256" activations="sigmoid, tanh, tanh" activations_alpha="" activations_beta="" clip="0" />
850
+ <input>
851
+ <port id="0" precision="FP32">
852
+ <dim>-1</dim>
853
+ <dim>-1</dim>
854
+ <dim>256</dim>
855
+ </port>
856
+ <port id="1" precision="FP32">
857
+ <dim>-1</dim>
858
+ <dim>1</dim>
859
+ <dim>256</dim>
860
+ </port>
861
+ <port id="2" precision="FP32">
862
+ <dim>-1</dim>
863
+ <dim>1</dim>
864
+ <dim>256</dim>
865
+ </port>
866
+ <port id="3" precision="I32">
867
+ <dim>-1</dim>
868
+ </port>
869
+ <port id="4" precision="FP32">
870
+ <dim>1</dim>
871
+ <dim>1024</dim>
872
+ <dim>256</dim>
873
+ </port>
874
+ <port id="5" precision="FP32">
875
+ <dim>1</dim>
876
+ <dim>1024</dim>
877
+ <dim>256</dim>
878
+ </port>
879
+ <port id="6" precision="FP32">
880
+ <dim>1</dim>
881
+ <dim>1024</dim>
882
+ </port>
883
+ </input>
884
+ <output>
885
+ <port id="7" precision="FP32">
886
+ <dim>-1</dim>
887
+ <dim>1</dim>
888
+ <dim>-1</dim>
889
+ <dim>256</dim>
890
+ </port>
891
+ <port id="8" precision="FP32">
892
+ <dim>-1</dim>
893
+ <dim>1</dim>
894
+ <dim>256</dim>
895
+ </port>
896
+ <port id="9" precision="FP32">
897
+ <dim>-1</dim>
898
+ <dim>1</dim>
899
+ <dim>256</dim>
900
+ </port>
901
+ </output>
902
+ </layer>
903
+ <layer id="54" name="__module.lstm/aten::lstm/Concat" type="Concat" version="opset1">
904
+ <data axis="1" />
905
+ <input>
906
+ <port id="0" precision="FP32">
907
+ <dim>-1</dim>
908
+ <dim>1</dim>
909
+ <dim>256</dim>
910
+ </port>
911
+ <port id="1" precision="FP32">
912
+ <dim>-1</dim>
913
+ <dim>1</dim>
914
+ <dim>256</dim>
915
+ </port>
916
+ <port id="2" precision="FP32">
917
+ <dim>-1</dim>
918
+ <dim>1</dim>
919
+ <dim>256</dim>
920
+ </port>
921
+ </input>
922
+ <output>
923
+ <port id="3" precision="FP32">
924
+ <dim>-1</dim>
925
+ <dim>3</dim>
926
+ <dim>256</dim>
927
+ </port>
928
+ </output>
929
+ </layer>
930
+ <layer id="55" name="Constant_333359" type="Const" version="opset1">
931
+ <data element_type="i32" shape="3" offset="2709562" size="12" />
932
+ <output>
933
+ <port id="0" precision="I32">
934
+ <dim>3</dim>
935
+ </port>
936
+ </output>
937
+ </layer>
938
+ <layer id="56" name="__module.lstm/aten::lstm/Transpose_6" type="Transpose" version="opset1">
939
+ <input>
940
+ <port id="0" precision="FP32">
941
+ <dim>-1</dim>
942
+ <dim>3</dim>
943
+ <dim>256</dim>
944
+ </port>
945
+ <port id="1" precision="I32">
946
+ <dim>3</dim>
947
+ </port>
948
+ </input>
949
+ <output>
950
+ <port id="2" precision="FP32" names="47,hidden">
951
+ <dim>3</dim>
952
+ <dim>-1</dim>
953
+ <dim>256</dim>
954
+ </port>
955
+ </output>
956
+ </layer>
957
+ <layer id="57" name="7" type="Const" version="opset1">
958
+ <data element_type="i64" shape="" offset="2709574" size="8" />
959
+ <output>
960
+ <port id="0" precision="I64" names="7" />
961
+ </output>
962
+ </layer>
963
+ <layer id="58" name="6" type="Const" version="opset1">
964
+ <data element_type="i64" shape="" offset="10" size="8" />
965
+ <output>
966
+ <port id="0" precision="I64" names="6" />
967
+ </output>
968
+ </layer>
969
+ <layer id="59" name="aten::select/Gather" type="Gather" version="opset8">
970
+ <data batch_dims="0" />
971
+ <input>
972
+ <port id="0" precision="FP32">
973
+ <dim>3</dim>
974
+ <dim>-1</dim>
975
+ <dim>256</dim>
976
+ </port>
977
+ <port id="1" precision="I64" />
978
+ <port id="2" precision="I64" />
979
+ </input>
980
+ <output>
981
+ <port id="3" precision="FP32" names="8,input.1">
982
+ <dim>-1</dim>
983
+ <dim>256</dim>
984
+ </port>
985
+ </output>
986
+ </layer>
987
+ <layer id="60" name="self.linear.weight_compressed" type="Const" version="opset1">
988
+ <data element_type="f16" shape="256, 256" offset="2709582" size="131072" />
989
+ <output>
990
+ <port id="0" precision="FP16" names="self.linear.weight">
991
+ <dim>256</dim>
992
+ <dim>256</dim>
993
+ </port>
994
+ </output>
995
+ </layer>
996
+ <layer id="61" name="self.linear.weight" type="Convert" version="opset1">
997
+ <data destination_type="f32" />
998
+ <rt_info>
999
+ <attribute name="decompression" version="0" />
1000
+ </rt_info>
1001
+ <input>
1002
+ <port id="0" precision="FP16">
1003
+ <dim>256</dim>
1004
+ <dim>256</dim>
1005
+ </port>
1006
+ </input>
1007
+ <output>
1008
+ <port id="1" precision="FP32">
1009
+ <dim>256</dim>
1010
+ <dim>256</dim>
1011
+ </port>
1012
+ </output>
1013
+ </layer>
1014
+ <layer id="62" name="__module.linear/aten::linear/MatMul" type="MatMul" version="opset1">
1015
+ <data transpose_a="false" transpose_b="true" />
1016
+ <input>
1017
+ <port id="0" precision="FP32">
1018
+ <dim>-1</dim>
1019
+ <dim>256</dim>
1020
+ </port>
1021
+ <port id="1" precision="FP32">
1022
+ <dim>256</dim>
1023
+ <dim>256</dim>
1024
+ </port>
1025
+ </input>
1026
+ <output>
1027
+ <port id="2" precision="FP32">
1028
+ <dim>-1</dim>
1029
+ <dim>256</dim>
1030
+ </port>
1031
+ </output>
1032
+ </layer>
1033
+ <layer id="63" name="Constant_335692_compressed" type="Const" version="opset1">
1034
+ <data element_type="f16" shape="1, 256" offset="2840654" size="512" />
1035
+ <output>
1036
+ <port id="0" precision="FP16">
1037
+ <dim>1</dim>
1038
+ <dim>256</dim>
1039
+ </port>
1040
+ </output>
1041
+ </layer>
1042
+ <layer id="64" name="Constant_335692" type="Convert" version="opset1">
1043
+ <data destination_type="f32" />
1044
+ <rt_info>
1045
+ <attribute name="decompression" version="0" />
1046
+ </rt_info>
1047
+ <input>
1048
+ <port id="0" precision="FP16">
1049
+ <dim>1</dim>
1050
+ <dim>256</dim>
1051
+ </port>
1052
+ </input>
1053
+ <output>
1054
+ <port id="1" precision="FP32">
1055
+ <dim>1</dim>
1056
+ <dim>256</dim>
1057
+ </port>
1058
+ </output>
1059
+ </layer>
1060
+ <layer id="65" name="__module.linear/aten::linear/Add" type="Add" version="opset1">
1061
+ <data auto_broadcast="numpy" />
1062
+ <input>
1063
+ <port id="0" precision="FP32">
1064
+ <dim>-1</dim>
1065
+ <dim>256</dim>
1066
+ </port>
1067
+ <port id="1" precision="FP32">
1068
+ <dim>1</dim>
1069
+ <dim>256</dim>
1070
+ </port>
1071
+ </input>
1072
+ <output>
1073
+ <port id="2" precision="FP32" names="51,input.3">
1074
+ <dim>-1</dim>
1075
+ <dim>256</dim>
1076
+ </port>
1077
+ </output>
1078
+ </layer>
1079
+ <layer id="66" name="__module.relu/aten::relu/Relu" type="ReLU" version="opset1">
1080
+ <input>
1081
+ <port id="0" precision="FP32">
1082
+ <dim>-1</dim>
1083
+ <dim>256</dim>
1084
+ </port>
1085
+ </input>
1086
+ <output>
1087
+ <port id="1" precision="FP32" names="52,input">
1088
+ <dim>-1</dim>
1089
+ <dim>256</dim>
1090
+ </port>
1091
+ </output>
1092
+ </layer>
1093
+ <layer id="67" name="Constant_333456" type="Const" version="opset1">
1094
+ <data element_type="i64" shape="1" offset="2841166" size="8" />
1095
+ <output>
1096
+ <port id="0" precision="I64" names="13">
1097
+ <dim>1</dim>
1098
+ </port>
1099
+ </output>
1100
+ </layer>
1101
+ <layer id="68" name="aten::linalg_vector_norm/ReduceL2" type="ReduceL2" version="opset4">
1102
+ <data keep_dims="true" />
1103
+ <input>
1104
+ <port id="0" precision="FP32">
1105
+ <dim>-1</dim>
1106
+ <dim>256</dim>
1107
+ </port>
1108
+ <port id="1" precision="I64">
1109
+ <dim>1</dim>
1110
+ </port>
1111
+ </input>
1112
+ <output>
1113
+ <port id="2" precision="FP32" names="16">
1114
+ <dim>-1</dim>
1115
+ <dim>1</dim>
1116
+ </port>
1117
+ </output>
1118
+ </layer>
1119
+ <layer id="69" name="aten::div/Divide" type="Divide" version="opset1">
1120
+ <data auto_broadcast="numpy" m_pythondiv="true" />
1121
+ <input>
1122
+ <port id="0" precision="FP32">
1123
+ <dim>-1</dim>
1124
+ <dim>256</dim>
1125
+ </port>
1126
+ <port id="1" precision="FP32">
1127
+ <dim>-1</dim>
1128
+ <dim>1</dim>
1129
+ </port>
1130
+ </input>
1131
+ <output>
1132
+ <port id="2" precision="FP32">
1133
+ <dim>-1</dim>
1134
+ <dim>256</dim>
1135
+ </port>
1136
+ </output>
1137
+ </layer>
1138
+ <layer id="70" name="Result_333464" type="Result" version="opset1">
1139
+ <input>
1140
+ <port id="0" precision="FP32">
1141
+ <dim>-1</dim>
1142
+ <dim>256</dim>
1143
+ </port>
1144
+ </input>
1145
+ </layer>
1146
+ </layers>
1147
+ <edges>
1148
+ <edge from-layer="0" from-port="0" to-layer="4" to-port="0" />
1149
+ <edge from-layer="0" from-port="0" to-layer="27" to-port="0" />
1150
+ <edge from-layer="1" from-port="0" to-layer="2" to-port="0" />
1151
+ <edge from-layer="2" from-port="1" to-layer="10" to-port="0" />
1152
+ <edge from-layer="3" from-port="0" to-layer="9" to-port="0" />
1153
+ <edge from-layer="4" from-port="1" to-layer="7" to-port="0" />
1154
+ <edge from-layer="4" from-port="1" to-layer="15" to-port="0" />
1155
+ <edge from-layer="5" from-port="0" to-layer="7" to-port="1" />
1156
+ <edge from-layer="6" from-port="0" to-layer="7" to-port="2" />
1157
+ <edge from-layer="7" from-port="3" to-layer="19" to-port="0" />
1158
+ <edge from-layer="7" from-port="3" to-layer="9" to-port="1" />
1159
+ <edge from-layer="8" from-port="0" to-layer="9" to-port="2" />
1160
+ <edge from-layer="9" from-port="3" to-layer="10" to-port="1" />
1161
+ <edge from-layer="10" from-port="2" to-layer="12" to-port="0" />
1162
+ <edge from-layer="10" from-port="2" to-layer="32" to-port="0" />
1163
+ <edge from-layer="11" from-port="0" to-layer="12" to-port="1" />
1164
+ <edge from-layer="11" from-port="0" to-layer="32" to-port="1" />
1165
+ <edge from-layer="12" from-port="3" to-layer="31" to-port="0" />
1166
+ <edge from-layer="12" from-port="2" to-layer="14" to-port="0" />
1167
+ <edge from-layer="12" from-port="4" to-layer="44" to-port="0" />
1168
+ <edge from-layer="13" from-port="0" to-layer="14" to-port="1" />
1169
+ <edge from-layer="14" from-port="2" to-layer="27" to-port="1" />
1170
+ <edge from-layer="14" from-port="2" to-layer="27" to-port="2" />
1171
+ <edge from-layer="15" from-port="1" to-layer="18" to-port="0" />
1172
+ <edge from-layer="16" from-port="0" to-layer="18" to-port="1" />
1173
+ <edge from-layer="17" from-port="0" to-layer="18" to-port="2" />
1174
+ <edge from-layer="18" from-port="3" to-layer="20" to-port="0" />
1175
+ <edge from-layer="19" from-port="1" to-layer="20" to-port="1" />
1176
+ <edge from-layer="20" from-port="2" to-layer="41" to-port="3" />
1177
+ <edge from-layer="20" from-port="2" to-layer="27" to-port="3" />
1178
+ <edge from-layer="20" from-port="2" to-layer="53" to-port="3" />
1179
+ <edge from-layer="21" from-port="0" to-layer="22" to-port="0" />
1180
+ <edge from-layer="22" from-port="1" to-layer="27" to-port="4" />
1181
+ <edge from-layer="23" from-port="0" to-layer="24" to-port="0" />
1182
+ <edge from-layer="24" from-port="1" to-layer="27" to-port="5" />
1183
+ <edge from-layer="25" from-port="0" to-layer="26" to-port="0" />
1184
+ <edge from-layer="26" from-port="1" to-layer="27" to-port="6" />
1185
+ <edge from-layer="27" from-port="8" to-layer="54" to-port="0" />
1186
+ <edge from-layer="27" from-port="7" to-layer="29" to-port="0" />
1187
+ <edge from-layer="28" from-port="0" to-layer="29" to-port="1" />
1188
+ <edge from-layer="28" from-port="0" to-layer="42" to-port="1" />
1189
+ <edge from-layer="29" from-port="2" to-layer="41" to-port="0" />
1190
+ <edge from-layer="30" from-port="0" to-layer="31" to-port="1" />
1191
+ <edge from-layer="31" from-port="2" to-layer="41" to-port="1" />
1192
+ <edge from-layer="32" from-port="4" to-layer="46" to-port="0" />
1193
+ <edge from-layer="32" from-port="3" to-layer="34" to-port="0" />
1194
+ <edge from-layer="33" from-port="0" to-layer="34" to-port="1" />
1195
+ <edge from-layer="34" from-port="2" to-layer="41" to-port="2" />
1196
+ <edge from-layer="35" from-port="0" to-layer="36" to-port="0" />
1197
+ <edge from-layer="36" from-port="1" to-layer="41" to-port="4" />
1198
+ <edge from-layer="37" from-port="0" to-layer="38" to-port="0" />
1199
+ <edge from-layer="38" from-port="1" to-layer="41" to-port="5" />
1200
+ <edge from-layer="39" from-port="0" to-layer="40" to-port="0" />
1201
+ <edge from-layer="40" from-port="1" to-layer="41" to-port="6" />
1202
+ <edge from-layer="41" from-port="7" to-layer="42" to-port="0" />
1203
+ <edge from-layer="41" from-port="8" to-layer="54" to-port="1" />
1204
+ <edge from-layer="42" from-port="2" to-layer="53" to-port="0" />
1205
+ <edge from-layer="43" from-port="0" to-layer="44" to-port="1" />
1206
+ <edge from-layer="44" from-port="2" to-layer="53" to-port="1" />
1207
+ <edge from-layer="45" from-port="0" to-layer="46" to-port="1" />
1208
+ <edge from-layer="46" from-port="2" to-layer="53" to-port="2" />
1209
+ <edge from-layer="47" from-port="0" to-layer="48" to-port="0" />
1210
+ <edge from-layer="48" from-port="1" to-layer="53" to-port="4" />
1211
+ <edge from-layer="49" from-port="0" to-layer="50" to-port="0" />
1212
+ <edge from-layer="50" from-port="1" to-layer="53" to-port="5" />
1213
+ <edge from-layer="51" from-port="0" to-layer="52" to-port="0" />
1214
+ <edge from-layer="52" from-port="1" to-layer="53" to-port="6" />
1215
+ <edge from-layer="53" from-port="8" to-layer="54" to-port="2" />
1216
+ <edge from-layer="54" from-port="3" to-layer="56" to-port="0" />
1217
+ <edge from-layer="55" from-port="0" to-layer="56" to-port="1" />
1218
+ <edge from-layer="56" from-port="2" to-layer="59" to-port="0" />
1219
+ <edge from-layer="57" from-port="0" to-layer="59" to-port="1" />
1220
+ <edge from-layer="58" from-port="0" to-layer="59" to-port="2" />
1221
+ <edge from-layer="59" from-port="3" to-layer="62" to-port="0" />
1222
+ <edge from-layer="60" from-port="0" to-layer="61" to-port="0" />
1223
+ <edge from-layer="61" from-port="1" to-layer="62" to-port="1" />
1224
+ <edge from-layer="62" from-port="2" to-layer="65" to-port="0" />
1225
+ <edge from-layer="63" from-port="0" to-layer="64" to-port="0" />
1226
+ <edge from-layer="64" from-port="1" to-layer="65" to-port="1" />
1227
+ <edge from-layer="65" from-port="2" to-layer="66" to-port="0" />
1228
+ <edge from-layer="66" from-port="1" to-layer="68" to-port="0" />
1229
+ <edge from-layer="66" from-port="1" to-layer="69" to-port="0" />
1230
+ <edge from-layer="67" from-port="0" to-layer="68" to-port="1" />
1231
+ <edge from-layer="68" from-port="2" to-layer="69" to-port="1" />
1232
+ <edge from-layer="69" from-port="2" to-layer="70" to-port="0" />
1233
+ </edges>
1234
+ <rt_info>
1235
+ <Runtime_version value="2025.4.1-20426-82bbf0292c5-releases/2025/4" />
1236
+ <conversion_parameters>
1237
+ <framework value="pytorch" />
1238
+ <is_python_object value="True" />
1239
+ </conversion_parameters>
1240
+ </rt_info>
1241
+ </net>
Qwen3-Embedding-0.6B-ov-int4/added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
Qwen3-Embedding-0.6B-ov-int4/chat_template.jinja ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for message in messages[::-1] %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
+ {%- set ns.multi_step_tool = false %}
22
+ {%- set ns.last_query_index = index %}
23
+ {%- endif %}
24
+ {%- endfor %}
25
+ {%- for message in messages %}
26
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
27
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
28
+ {%- elif message.role == "assistant" %}
29
+ {%- set content = message.content %}
30
+ {%- set reasoning_content = '' %}
31
+ {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
32
+ {%- set reasoning_content = message.reasoning_content %}
33
+ {%- else %}
34
+ {%- if '</think>' in message.content %}
35
+ {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
36
+ {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
37
+ {%- endif %}
38
+ {%- endif %}
39
+ {%- if loop.index0 > ns.last_query_index %}
40
+ {%- if loop.last or (not loop.last and reasoning_content) %}
41
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
42
+ {%- else %}
43
+ {{- '<|im_start|>' + message.role + '\n' + content }}
44
+ {%- endif %}
45
+ {%- else %}
46
+ {{- '<|im_start|>' + message.role + '\n' + content }}
47
+ {%- endif %}
48
+ {%- if message.tool_calls %}
49
+ {%- for tool_call in message.tool_calls %}
50
+ {%- if (loop.first and content) or (not loop.first) %}
51
+ {{- '\n' }}
52
+ {%- endif %}
53
+ {%- if tool_call.function %}
54
+ {%- set tool_call = tool_call.function %}
55
+ {%- endif %}
56
+ {{- '<tool_call>\n{"name": "' }}
57
+ {{- tool_call.name }}
58
+ {{- '", "arguments": ' }}
59
+ {%- if tool_call.arguments is string %}
60
+ {{- tool_call.arguments }}
61
+ {%- else %}
62
+ {{- tool_call.arguments | tojson }}
63
+ {%- endif %}
64
+ {{- '}\n</tool_call>' }}
65
+ {%- endfor %}
66
+ {%- endif %}
67
+ {{- '<|im_end|>\n' }}
68
+ {%- elif message.role == "tool" %}
69
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
70
+ {{- '<|im_start|>user' }}
71
+ {%- endif %}
72
+ {{- '\n<tool_response>\n' }}
73
+ {{- message.content }}
74
+ {{- '\n</tool_response>' }}
75
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
76
+ {{- '<|im_end|>\n' }}
77
+ {%- endif %}
78
+ {%- endif %}
79
+ {%- endfor %}
80
+ {%- if add_generation_prompt %}
81
+ {{- '<|im_start|>assistant\n' }}
82
+ {%- if enable_thinking is defined and enable_thinking is false %}
83
+ {{- '<think>\n\n</think>\n\n' }}
84
+ {%- endif %}
85
+ {%- endif %}
Qwen3-Embedding-0.6B-ov-int4/config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "dtype": "float32",
9
+ "eos_token_id": 151643,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 1024,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_types": [
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention"
44
+ ],
45
+ "max_position_embeddings": 32768,
46
+ "max_window_layers": 28,
47
+ "model_type": "qwen3",
48
+ "num_attention_heads": 16,
49
+ "num_hidden_layers": 28,
50
+ "num_key_value_heads": 8,
51
+ "rms_norm_eps": 1e-06,
52
+ "rope_scaling": null,
53
+ "rope_theta": 1000000,
54
+ "sliding_window": null,
55
+ "tie_word_embeddings": true,
56
+ "transformers_version": "4.57.3",
57
+ "use_cache": true,
58
+ "use_sliding_window": false,
59
+ "vocab_size": 151669
60
+ }
Qwen3-Embedding-0.6B-ov-int4/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
Qwen3-Embedding-0.6B-ov-int4/model_cache/10398472748164076480.cl_cache ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cea6db01e75c76d8eb37b65365b63d200e1ae11d54f2aa98fc0d030563288286
3
+ size 144120
Qwen3-Embedding-0.6B-ov-int4/model_cache/11841033957157841238.cl_cache ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba18121c4cb32a9ff895d34d6b5111f3256f6b20e479b981852f6f0817b84799
3
+ size 196864
Qwen3-Embedding-0.6B-ov-int4/model_cache/13100948868569734950.cl_cache ADDED
Binary file (2.69 kB). View file
 
Qwen3-Embedding-0.6B-ov-int4/model_cache/14256774865286315154.cl_cache ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bf7c69f1b0d4cf0e90c0dbb5c276c2c87a65dcb652c4f924ebb6b6b2f18dae3
3
+ size 202680
Qwen3-Embedding-0.6B-ov-int4/model_cache/15972597138584836711.cl_cache ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d585dce7cabf849f6f0a52f96158ce040a2e7c6408076e94fefbda137b8e1f12
3
+ size 140304
Qwen3-Embedding-0.6B-ov-int4/model_cache/17015111877664402134.cl_cache ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2358c4686d9148d5f9238614998149bc1c4a57bccdc30e52461fad619d3eedc3
3
+ size 144120
Qwen3-Embedding-0.6B-ov-int4/model_cache/18358898440656323975.cl_cache ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45fb211dd0e70a8b269ee10d36b86a282a7cb5474e51433348e5c17c76407392
3
+ size 126216
Qwen3-Embedding-0.6B-ov-int4/model_cache/18425769849181688742.cl_cache ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89842033af13feede454073afef7be45b11f0b1419bfef8db6e277ca84292bff
3
+ size 179656
Qwen3-Embedding-0.6B-ov-int4/model_cache/2084631378233982642.cl_cache ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33de7bc7919011d58cf8cb7f28b4c13b53ba8d5b0bbcf69441c4553326025627
3
+ size 140304
Qwen3-Embedding-0.6B-ov-int4/model_cache/2200953350652739583.cl_cache ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2226cbd37e84f43622a9a84b14fb04abf29da04b15d70afc2ef1e4e1ec60bfcd
3
+ size 212296
Qwen3-Embedding-0.6B-ov-int4/model_cache/2467060138956266788.blob ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76130c2ab64f3c5b3d171c09edd495703fe2fd87cb2934f35b657dff2688d5eb
3
+ size 447155799
Qwen3-Embedding-0.6B-ov-int4/model_cache/3006077353902421111.cl_cache ADDED
Binary file (38.2 kB). View file
 
Qwen3-Embedding-0.6B-ov-int4/model_cache/4187937748300361869.cl_cache ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea0cdf6c13d684f18085a8e1361cf39e913119382b1a67089cc24f7fa69f9354
3
+ size 184912
Qwen3-Embedding-0.6B-ov-int4/model_cache/514085034797992975.cl_cache ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64f722825a5b3a126a7ee63df47b557f21c349dc651e43c10dec0b870984e98e
3
+ size 178624
Qwen3-Embedding-0.6B-ov-int4/model_cache/6367819844101748113.cl_cache ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a711f37f299098d17587e90513954bc09ce6b2b6cdea23f8dc7768a1230b6811
3
+ size 160160
Qwen3-Embedding-0.6B-ov-int4/model_cache/6380654293821853377.cl_cache ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e52f40efcc8aa1ffcba8a0f16bf2ce481cd2f73ab282701a141c1343058970b
3
+ size 178952
Qwen3-Embedding-0.6B-ov-int4/model_cache/6417489891108773540.cl_cache ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9340776db61a96c28e5f6a15848926eaa5998f9d17a9f26885991c91f4865f3
3
+ size 160040
Qwen3-Embedding-0.6B-ov-int4/model_cache/8227443482036439551.cl_cache ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f027e9c953607f3c8c5caf63c753f72b278372d83ff7ade832540a00058106a
3
+ size 187632
Qwen3-Embedding-0.6B-ov-int4/model_cache/8233817952741756344.cl_cache ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d97e1ff59b3f5317e538db6a9412d578854d37bfc9471e5ed0f8fa8d290add64
3
+ size 176840
Qwen3-Embedding-0.6B-ov-int4/model_cache/8855579903425484800.cl_cache ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2fcf4faf78e75192ce7a673938aa8532a63bd78ffa7dfb2ecc08f765a89d7e3
3
+ size 264552
Qwen3-Embedding-0.6B-ov-int4/model_cache/9546625216876219351.cl_cache ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b415353495ccd5593725f4aaad4a90be7ab03b5c4cdc6cfbc0dd1a3f57f1319
3
+ size 429248
Qwen3-Embedding-0.6B-ov-int4/model_cache/9683605224545850666.cl_cache ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c525e13bfaeab6561d6210f3c0604eb1042068182614b6d987e946ba5da7141
3
+ size 160216
Qwen3-Embedding-0.6B-ov-int4/openvino_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dtype": "int4",
3
+ "input_info": null,
4
+ "optimum_version": "2.1.0",
5
+ "output_attentions": false,
6
+ "quantization_config": {
7
+ "dataset": null,
8
+ "default_config": {
9
+ "quant_method": "default"
10
+ },
11
+ "ignored_scope": null,
12
+ "num_samples": null,
13
+ "processor": null,
14
+ "quantization_configs": {
15
+ "model": {
16
+ "all_layers": null,
17
+ "backup_precision": null,
18
+ "bits": 4,
19
+ "dataset": null,
20
+ "dtype": "int4",
21
+ "gptq": null,
22
+ "group_size": null,
23
+ "group_size_fallback": null,
24
+ "ignored_scope": {
25
+ "names": [
26
+ "__module.layers.27.mlp.up_proj/aten::linear/MatMul",
27
+ "__module.layers.27.mlp.gate_proj/aten::linear/MatMul"
28
+ ]
29
+ },
30
+ "lora_correction": null,
31
+ "num_samples": null,
32
+ "processor": null,
33
+ "quant_method": "default",
34
+ "ratio": 0.8,
35
+ "scale_estimation": null,
36
+ "sensitivity_metric": null,
37
+ "statistics_path": null,
38
+ "sym": false,
39
+ "tokenizer": "Qwen/Qwen3-Embedding-0.6B"
40
+ }
41
+ },
42
+ "tokenizer": "Qwen/Qwen3-Embedding-0.6B"
43
+ },
44
+ "save_onnx_model": false,
45
+ "transformers_version": "4.57.3"
46
+ }
Qwen3-Embedding-0.6B-ov-int4/openvino_detokenizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d73093f72c80ebcaffb76a192727170ecd3c6a06c4df52df0e76b3f70ad9d7f7
3
+ size 2189717
Qwen3-Embedding-0.6B-ov-int4/openvino_detokenizer.xml ADDED
@@ -0,0 +1,219 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="detokenizer" version="11">
3
+ <layers>
4
+ <layer id="0" name="Parameter_73346" type="Parameter" version="opset1">
5
+ <data shape="?,?" element_type="i64" />
6
+ <output>
7
+ <port id="0" precision="I64" names="Parameter_73346">
8
+ <dim>-1</dim>
9
+ <dim>-1</dim>
10
+ </port>
11
+ </output>
12
+ </layer>
13
+ <layer id="1" name="Convert_73545" 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_73348" type="Const" version="opset1">
29
+ <data element_type="i32" shape="151669" offset="0" size="606676" />
30
+ <output>
31
+ <port id="0" precision="I32">
32
+ <dim>151669</dim>
33
+ </port>
34
+ </output>
35
+ </layer>
36
+ <layer id="3" name="Constant_73350" type="Const" version="opset1">
37
+ <data element_type="i32" shape="151669" offset="606676" size="606676" />
38
+ <output>
39
+ <port id="0" precision="I32">
40
+ <dim>151669</dim>
41
+ </port>
42
+ </output>
43
+ </layer>
44
+ <layer id="4" name="Constant_73352" type="Const" version="opset1">
45
+ <data element_type="u8" shape="976309" offset="1213352" size="976309" />
46
+ <output>
47
+ <port id="0" precision="U8">
48
+ <dim>976309</dim>
49
+ </port>
50
+ </output>
51
+ </layer>
52
+ <layer id="5" name="Slice_73357" type="Const" version="opset1">
53
+ <data element_type="i32" shape="14" offset="2189661" size="56" />
54
+ <output>
55
+ <port id="0" precision="I32">
56
+ <dim>14</dim>
57
+ </port>
58
+ </output>
59
+ </layer>
60
+ <layer id="6" name="VocabDecoder_73359" 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>151669</dim>
69
+ </port>
70
+ <port id="2" precision="I32">
71
+ <dim>151669</dim>
72
+ </port>
73
+ <port id="3" precision="U8">
74
+ <dim>976309</dim>
75
+ </port>
76
+ <port id="4" precision="I32">
77
+ <dim>14</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="FuzeRagged_73360" type="FuzeRagged" version="extension">
99
+ <input>
100
+ <port id="0" precision="I32">
101
+ <dim>-1</dim>
102
+ </port>
103
+ <port id="1" precision="I32">
104
+ <dim>-1</dim>
105
+ </port>
106
+ <port id="2" precision="I32">
107
+ <dim>-1</dim>
108
+ </port>
109
+ <port id="3" precision="I32">
110
+ <dim>-1</dim>
111
+ </port>
112
+ </input>
113
+ <output>
114
+ <port id="4" precision="I32">
115
+ <dim>-1</dim>
116
+ </port>
117
+ <port id="5" precision="I32">
118
+ <dim>-1</dim>
119
+ </port>
120
+ </output>
121
+ </layer>
122
+ <layer id="8" name="UTF8Validate_73361" type="UTF8Validate" version="extension">
123
+ <data replace_mode="true" />
124
+ <input>
125
+ <port id="0" precision="I32">
126
+ <dim>-1</dim>
127
+ </port>
128
+ <port id="1" precision="I32">
129
+ <dim>-1</dim>
130
+ </port>
131
+ <port id="2" precision="U8">
132
+ <dim>-1</dim>
133
+ </port>
134
+ </input>
135
+ <output>
136
+ <port id="3" precision="I32">
137
+ <dim>-1</dim>
138
+ </port>
139
+ <port id="4" precision="I32">
140
+ <dim>-1</dim>
141
+ </port>
142
+ <port id="5" precision="U8">
143
+ <dim>-1</dim>
144
+ </port>
145
+ </output>
146
+ </layer>
147
+ <layer id="9" name="StringTensorPack_73362" type="StringTensorPack" version="opset15">
148
+ <input>
149
+ <port id="0" precision="I32">
150
+ <dim>-1</dim>
151
+ </port>
152
+ <port id="1" precision="I32">
153
+ <dim>-1</dim>
154
+ </port>
155
+ <port id="2" precision="U8">
156
+ <dim>-1</dim>
157
+ </port>
158
+ </input>
159
+ <output>
160
+ <port id="3" precision="STRING" names="Result_73363,string_output">
161
+ <dim>-1</dim>
162
+ </port>
163
+ </output>
164
+ </layer>
165
+ <layer id="10" name="Result_73363" type="Result" version="opset1" output_names="Result_73363,string_output">
166
+ <input>
167
+ <port id="0" precision="STRING">
168
+ <dim>-1</dim>
169
+ </port>
170
+ </input>
171
+ </layer>
172
+ </layers>
173
+ <edges>
174
+ <edge from-layer="0" from-port="0" to-layer="1" to-port="0" />
175
+ <edge from-layer="1" from-port="1" to-layer="6" to-port="0" />
176
+ <edge from-layer="2" from-port="0" to-layer="6" to-port="1" />
177
+ <edge from-layer="3" from-port="0" to-layer="6" to-port="2" />
178
+ <edge from-layer="4" from-port="0" to-layer="6" to-port="3" />
179
+ <edge from-layer="5" from-port="0" to-layer="6" to-port="4" />
180
+ <edge from-layer="6" from-port="7" to-layer="7" to-port="2" />
181
+ <edge from-layer="6" from-port="9" to-layer="8" to-port="2" />
182
+ <edge from-layer="6" from-port="8" to-layer="7" to-port="3" />
183
+ <edge from-layer="6" from-port="6" to-layer="7" to-port="1" />
184
+ <edge from-layer="6" from-port="5" to-layer="7" to-port="0" />
185
+ <edge from-layer="7" from-port="4" to-layer="8" to-port="0" />
186
+ <edge from-layer="7" from-port="5" to-layer="8" to-port="1" />
187
+ <edge from-layer="8" from-port="3" to-layer="9" to-port="0" />
188
+ <edge from-layer="8" from-port="4" to-layer="9" to-port="1" />
189
+ <edge from-layer="8" from-port="5" to-layer="9" to-port="2" />
190
+ <edge from-layer="9" from-port="3" to-layer="10" to-port="0" />
191
+ </edges>
192
+ <rt_info>
193
+ <add_attention_mask value="True" />
194
+ <add_prefix_space />
195
+ <add_special_tokens value="True" />
196
+ <chat_template value="{%- if tools %}&#10; {{- '&lt;|im_start|>system\n' }}&#10; {%- if messages[0].role == 'system' %}&#10; {{- messages[0].content + '\n\n' }}&#10; {%- endif %}&#10; {{- &quot;# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within &lt;tools>&lt;/tools> XML tags:\n&lt;tools>&quot; }}&#10; {%- for tool in tools %}&#10; {{- &quot;\n&quot; }}&#10; {{- tool | tojson }}&#10; {%- endfor %}&#10; {{- &quot;\n&lt;/tools>\n\nFor each function call, return a json object with function name and arguments within &lt;tool_call>&lt;/tool_call> XML tags:\n&lt;tool_call>\n{\&quot;name\&quot;: &lt;function-name>, \&quot;arguments\&quot;: &lt;args-json-object>}\n&lt;/tool_call>&lt;|im_end|>\n&quot; }}&#10;{%- else %}&#10; {%- if messages[0].role == 'system' %}&#10; {{- '&lt;|im_start|>system\n' + messages[0].content + '&lt;|im_end|>\n' }}&#10; {%- endif %}&#10;{%- endif %}&#10;{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}&#10;{%- for message in messages[::-1] %}&#10; {%- set index = (messages|length - 1) - loop.index0 %}&#10; {%- if ns.multi_step_tool and message.role == &quot;user&quot; and not(message.content.startswith('&lt;tool_response>') and message.content.endswith('&lt;/tool_response>')) %}&#10; {%- set ns.multi_step_tool = false %}&#10; {%- set ns.last_query_index = index %}&#10; {%- endif %}&#10;{%- endfor %}&#10;{%- for message in messages %}&#10; {%- if (message.role == &quot;user&quot;) or (message.role == &quot;system&quot; and not loop.first) %}&#10; {{- '&lt;|im_start|>' + message.role + '\n' + message.content + '&lt;|im_end|>' + '\n' }}&#10; {%- elif message.role == &quot;assistant&quot; %}&#10; {%- set content = message.content %}&#10; {%- set reasoning_content = '' %}&#10; {%- if message.reasoning_content is defined and message.reasoning_content is not none %}&#10; {%- set reasoning_content = message.reasoning_content %}&#10; {%- else %}&#10; {%- if '&lt;/think>' in message.content %}&#10; {%- set content = message.content.split('&lt;/think>')[-1].lstrip('\n') %}&#10; {%- set reasoning_content = message.content.split('&lt;/think>')[0].rstrip('\n').split('&lt;think>')[-1].lstrip('\n') %}&#10; {%- endif %}&#10; {%- endif %}&#10; {%- if loop.index0 > ns.last_query_index %}&#10; {%- if loop.last or (not loop.last and reasoning_content) %}&#10; {{- '&lt;|im_start|>' + message.role + '\n&lt;think>\n' + reasoning_content.strip('\n') + '\n&lt;/think>\n\n' + content.lstrip('\n') }}&#10; {%- else %}&#10; {{- '&lt;|im_start|>' + message.role + '\n' + content }}&#10; {%- endif %}&#10; {%- else %}&#10; {{- '&lt;|im_start|>' + message.role + '\n' + content }}&#10; {%- endif %}&#10; {%- if message.tool_calls %}&#10; {%- for tool_call in message.tool_calls %}&#10; {%- if (loop.first and content) or (not loop.first) %}&#10; {{- '\n' }}&#10; {%- endif %}&#10; {%- if tool_call.function %}&#10; {%- set tool_call = tool_call.function %}&#10; {%- endif %}&#10; {{- '&lt;tool_call>\n{&quot;name&quot;: &quot;' }}&#10; {{- tool_call.name }}&#10; {{- '&quot;, &quot;arguments&quot;: ' }}&#10; {%- if tool_call.arguments is string %}&#10; {{- tool_call.arguments }}&#10; {%- else %}&#10; {{- tool_call.arguments | tojson }}&#10; {%- endif %}&#10; {{- '}\n&lt;/tool_call>' }}&#10; {%- endfor %}&#10; {%- endif %}&#10; {{- '&lt;|im_end|>\n' }}&#10; {%- elif message.role == &quot;tool&quot; %}&#10; {%- if loop.first or (messages[loop.index0 - 1].role != &quot;tool&quot;) %}&#10; {{- '&lt;|im_start|>user' }}&#10; {%- endif %}&#10; {{- '\n&lt;tool_response>\n' }}&#10; {{- message.content }}&#10; {{- '\n&lt;/tool_response>' }}&#10; {%- if loop.last or (messages[loop.index0 + 1].role != &quot;tool&quot;) %}&#10; {{- '&lt;|im_end|>\n' }}&#10; {%- endif %}&#10; {%- endif %}&#10;{%- endfor %}&#10;{%- if add_generation_prompt %}&#10; {{- '&lt;|im_start|>assistant\n' }}&#10; {%- if enable_thinking is defined and enable_thinking is false %}&#10; {{- '&lt;think>\n\n&lt;/think>\n\n' }}&#10; {%- endif %}&#10;{%- endif %}" />
197
+ <clean_up_tokenization_spaces />
198
+ <detokenizer_input_type value="i64" />
199
+ <eos_token_id value="151645" />
200
+ <handle_special_tokens_with_re />
201
+ <max_length />
202
+ <number_of_inputs value="1" />
203
+ <openvino_tokenizers_version value="2025.4.1.0-627-e79796a77f3" />
204
+ <openvino_version value="2025.4.1-20426-82bbf0292c5-releases/2025/4" />
205
+ <original_post_processor_template value="{&quot;type&quot;: &quot;Sequence&quot;, &quot;processors&quot;: [{&quot;type&quot;: &quot;ByteLevel&quot;, &quot;add_prefix_space&quot;: false, &quot;trim_offsets&quot;: false, &quot;use_regex&quot;: false}, {&quot;type&quot;: &quot;TemplateProcessing&quot;, &quot;single&quot;: [{&quot;Sequence&quot;: {&quot;id&quot;: &quot;A&quot;, &quot;type_id&quot;: 0}}, {&quot;SpecialToken&quot;: {&quot;id&quot;: &quot;&lt;|endoftext|>&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;: 0}}, {&quot;SpecialToken&quot;: {&quot;id&quot;: &quot;&lt;|endoftext|>&quot;, &quot;type_id&quot;: 0}}], &quot;special_tokens&quot;: {&quot;&lt;|endoftext|>&quot;: {&quot;id&quot;: &quot;&lt;|endoftext|>&quot;, &quot;ids&quot;: [151643], &quot;tokens&quot;: [&quot;&lt;|endoftext|>&quot;]}}}]}" />
206
+ <original_tokenizer_class value="&lt;class 'transformers.models.qwen2.tokenization_qwen2_fast.Qwen2TokenizerFast'>" />
207
+ <pad_token_id value="151643" />
208
+ <processed_post_processor_template value="{&quot;single&quot;: {&quot;ids&quot;: [-1, 151643], &quot;type_ids&quot;: [0, 0]}, &quot;pair&quot;: {&quot;ids&quot;: [-1, -2, 151643], &quot;type_ids&quot;: [0, 0, 0]}}" />
209
+ <skip_special_tokens value="True" />
210
+ <streaming_detokenizer value="False" />
211
+ <tokenizer_output_type value="i64" />
212
+ <tokenizers_version value="0.22.1" />
213
+ <transformers_version value="4.57.3" />
214
+ <use_max_padding value="False" />
215
+ <use_sentencepiece_backend value="False" />
216
+ <utf8_replace_mode value="replace" />
217
+ <with_detokenizer value="True" />
218
+ </rt_info>
219
+ </net>
Qwen3-Embedding-0.6B-ov-int4/openvino_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21e1c79ff7a134a63b0cdcfae29d37032a33763891de9ac4845aee108cac23a3
3
+ size 450782132
Qwen3-Embedding-0.6B-ov-int4/openvino_model.xml ADDED
The diff for this file is too large to render. See raw diff
 
Qwen3-Embedding-0.6B-ov-int4/openvino_tokenizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c7f757b411ea311555082721b54f4519d4127f4907674390a3ebd5fc40bc8d6
3
+ size 5588840
Qwen3-Embedding-0.6B-ov-int4/openvino_tokenizer.xml ADDED
@@ -0,0 +1,799 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="tokenizer" version="11">
3
+ <layers>
4
+ <layer id="0" name="Parameter_73215" type="Parameter" version="opset1">
5
+ <data shape="?" element_type="string" />
6
+ <output>
7
+ <port id="0" precision="STRING" names="Parameter_73215">
8
+ <dim>-1</dim>
9
+ </port>
10
+ </output>
11
+ </layer>
12
+ <layer id="1" name="Constant_73221" 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_73216" 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_73217" 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_73218" 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_73219" 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_73220" 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_73222" 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_73223" 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_73224" 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_73225" 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_73226" 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_73227" 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_73228" 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_73292" type="Const" version="opset1">
135
+ <data element_type="u8" shape="462" offset="16" size="462" />
136
+ <output>
137
+ <port id="0" precision="U8">
138
+ <dim>462</dim>
139
+ </port>
140
+ </output>
141
+ </layer>
142
+ <layer id="15" name="SpecialTokensSplit_73293" 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>462</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="CharsMapNormalization_73294" type="CharsMapNormalization" version="extension">
185
+ <data add_dummy_prefix="false" remove_extra_whitespaces="false" escape_whitespaces="false" normalization_form="nfc" case_fold="false" nmt="false" />
186
+ <input>
187
+ <port id="0" precision="I32">
188
+ <dim>-1</dim>
189
+ </port>
190
+ <port id="1" precision="I32">
191
+ <dim>-1</dim>
192
+ </port>
193
+ <port id="2" precision="U8">
194
+ <dim>-1</dim>
195
+ </port>
196
+ <port id="3" precision="BOOL">
197
+ <dim>-1</dim>
198
+ </port>
199
+ </input>
200
+ <output>
201
+ <port id="4" precision="I32">
202
+ <dim>-1</dim>
203
+ </port>
204
+ <port id="5" precision="I32">
205
+ <dim>-1</dim>
206
+ </port>
207
+ <port id="6" precision="U8">
208
+ <dim>-1</dim>
209
+ </port>
210
+ <port id="7" precision="BOOL">
211
+ <dim>-1</dim>
212
+ </port>
213
+ </output>
214
+ </layer>
215
+ <layer id="17" name="Constant_73296" type="Const" version="opset1">
216
+ <data element_type="u8" shape="110" offset="478" size="110" />
217
+ <output>
218
+ <port id="0" precision="U8">
219
+ <dim>110</dim>
220
+ </port>
221
+ </output>
222
+ </layer>
223
+ <layer id="18" name="RegexSplit_73297" type="RegexSplit" version="extension">
224
+ <data behaviour="isolate" invert="false" max_splits="-1" />
225
+ <input>
226
+ <port id="0" precision="I32">
227
+ <dim>-1</dim>
228
+ </port>
229
+ <port id="1" precision="I32">
230
+ <dim>-1</dim>
231
+ </port>
232
+ <port id="2" precision="I32">
233
+ <dim>-1</dim>
234
+ </port>
235
+ <port id="3" precision="I32">
236
+ <dim>-1</dim>
237
+ </port>
238
+ <port id="4" precision="U8">
239
+ <dim>-1</dim>
240
+ </port>
241
+ <port id="5" precision="BOOL">
242
+ <dim>-1</dim>
243
+ </port>
244
+ <port id="6" precision="U8">
245
+ <dim>110</dim>
246
+ </port>
247
+ </input>
248
+ <output>
249
+ <port id="7" precision="I32">
250
+ <dim>-1</dim>
251
+ </port>
252
+ <port id="8" precision="I32">
253
+ <dim>-1</dim>
254
+ </port>
255
+ <port id="9" precision="I32">
256
+ <dim>-1</dim>
257
+ </port>
258
+ <port id="10" precision="I32">
259
+ <dim>-1</dim>
260
+ </port>
261
+ <port id="11" precision="U8">
262
+ <dim>-1</dim>
263
+ </port>
264
+ <port id="12" precision="BOOL">
265
+ <dim>-1</dim>
266
+ </port>
267
+ </output>
268
+ </layer>
269
+ <layer id="19" name="Constant_73299" type="Const" version="opset1">
270
+ <data element_type="i32" shape="151669" offset="588" size="606676" />
271
+ <output>
272
+ <port id="0" precision="I32">
273
+ <dim>151669</dim>
274
+ </port>
275
+ </output>
276
+ </layer>
277
+ <layer id="20" name="Constant_73301" type="Const" version="opset1">
278
+ <data element_type="i32" shape="151669" offset="607264" size="606676" />
279
+ <output>
280
+ <port id="0" precision="I32">
281
+ <dim>151669</dim>
282
+ </port>
283
+ </output>
284
+ </layer>
285
+ <layer id="21" name="Constant_73303" type="Const" version="opset1">
286
+ <data element_type="u8" shape="976309" offset="1213940" size="976309" />
287
+ <output>
288
+ <port id="0" precision="U8">
289
+ <dim>976309</dim>
290
+ </port>
291
+ </output>
292
+ </layer>
293
+ <layer id="22" name="Constant_73311" type="Const" version="opset1">
294
+ <data element_type="i32" shape="151387" offset="2190249" size="605548" />
295
+ <output>
296
+ <port id="0" precision="I32">
297
+ <dim>151387</dim>
298
+ </port>
299
+ </output>
300
+ </layer>
301
+ <layer id="23" name="Constant_73313" type="Const" version="opset1">
302
+ <data element_type="i32" shape="151387" offset="2795797" size="605548" />
303
+ <output>
304
+ <port id="0" precision="I32">
305
+ <dim>151387</dim>
306
+ </port>
307
+ </output>
308
+ </layer>
309
+ <layer id="24" name="Constant_73315" type="Const" version="opset1">
310
+ <data element_type="u8" shape="491359" offset="3401345" size="491359" />
311
+ <output>
312
+ <port id="0" precision="U8">
313
+ <dim>491359</dim>
314
+ </port>
315
+ </output>
316
+ </layer>
317
+ <layer id="25" name="Constant_73317" type="Const" version="opset1">
318
+ <data element_type="i32" shape="151387" offset="3892704" size="605548" />
319
+ <output>
320
+ <port id="0" precision="I32">
321
+ <dim>151387</dim>
322
+ </port>
323
+ </output>
324
+ </layer>
325
+ <layer id="26" name="Constant_73319" type="Const" version="opset1">
326
+ <data element_type="i32" shape="151387" offset="4498252" size="605548" />
327
+ <output>
328
+ <port id="0" precision="I32">
329
+ <dim>151387</dim>
330
+ </port>
331
+ </output>
332
+ </layer>
333
+ <layer id="27" name="Constant_73321" type="Const" version="opset1">
334
+ <data element_type="u8" shape="484354" offset="5103800" size="484354" />
335
+ <output>
336
+ <port id="0" precision="U8">
337
+ <dim>484354</dim>
338
+ </port>
339
+ </output>
340
+ </layer>
341
+ <layer id="28" name="Constant_73305" type="Const" version="opset1">
342
+ <data element_type="i32" shape="26" offset="5588154" size="104" />
343
+ <output>
344
+ <port id="0" precision="I32">
345
+ <dim>26</dim>
346
+ </port>
347
+ </output>
348
+ </layer>
349
+ <layer id="29" name="Constant_73307" type="Const" version="opset1">
350
+ <data element_type="i32" shape="26" offset="5588258" size="104" />
351
+ <output>
352
+ <port id="0" precision="I32">
353
+ <dim>26</dim>
354
+ </port>
355
+ </output>
356
+ </layer>
357
+ <layer id="30" name="Constant_73309" type="Const" version="opset1">
358
+ <data element_type="u8" shape="340" offset="5588362" size="340" />
359
+ <output>
360
+ <port id="0" precision="U8">
361
+ <dim>340</dim>
362
+ </port>
363
+ </output>
364
+ </layer>
365
+ <layer id="31" name="Constant_73322" type="Const" version="opset1">
366
+ <data element_type="i32" shape="26" offset="5588702" size="104" />
367
+ <output>
368
+ <port id="0" precision="I32">
369
+ <dim>26</dim>
370
+ </port>
371
+ </output>
372
+ </layer>
373
+ <layer id="32" name="BPETokenizer_73323" type="BPETokenizer" version="extension">
374
+ <data unk_token="" fuse_unk="false" suffix_indicator="" end_suffix="" byte_fallback="false" cache_capacity="30328" />
375
+ <input>
376
+ <port id="0" precision="I32">
377
+ <dim>-1</dim>
378
+ </port>
379
+ <port id="1" precision="I32">
380
+ <dim>-1</dim>
381
+ </port>
382
+ <port id="2" precision="I32">
383
+ <dim>-1</dim>
384
+ </port>
385
+ <port id="3" precision="I32">
386
+ <dim>-1</dim>
387
+ </port>
388
+ <port id="4" precision="U8">
389
+ <dim>-1</dim>
390
+ </port>
391
+ <port id="5" precision="I32">
392
+ <dim>151669</dim>
393
+ </port>
394
+ <port id="6" precision="I32">
395
+ <dim>151669</dim>
396
+ </port>
397
+ <port id="7" precision="U8">
398
+ <dim>976309</dim>
399
+ </port>
400
+ <port id="8" precision="I32">
401
+ <dim>151387</dim>
402
+ </port>
403
+ <port id="9" precision="I32">
404
+ <dim>151387</dim>
405
+ </port>
406
+ <port id="10" precision="U8">
407
+ <dim>491359</dim>
408
+ </port>
409
+ <port id="11" precision="I32">
410
+ <dim>151387</dim>
411
+ </port>
412
+ <port id="12" precision="I32">
413
+ <dim>151387</dim>
414
+ </port>
415
+ <port id="13" precision="U8">
416
+ <dim>484354</dim>
417
+ </port>
418
+ <port id="14" precision="I32">
419
+ <dim>26</dim>
420
+ </port>
421
+ <port id="15" precision="I32">
422
+ <dim>26</dim>
423
+ </port>
424
+ <port id="16" precision="U8">
425
+ <dim>340</dim>
426
+ </port>
427
+ <port id="17" precision="I32">
428
+ <dim>26</dim>
429
+ </port>
430
+ </input>
431
+ <output>
432
+ <port id="18" precision="I32">
433
+ <dim>-1</dim>
434
+ </port>
435
+ <port id="19" precision="I32">
436
+ <dim>-1</dim>
437
+ </port>
438
+ <port id="20" precision="I32">
439
+ <dim>-1</dim>
440
+ </port>
441
+ </output>
442
+ </layer>
443
+ <layer id="33" name="Constant_73324" type="Const" version="opset1">
444
+ <data element_type="i32" shape="" offset="5588806" size="4" />
445
+ <output>
446
+ <port id="0" precision="I32" />
447
+ </output>
448
+ </layer>
449
+ <layer id="34" name="Constant_73326" type="Const" version="opset1">
450
+ <data element_type="u8" shape="5" offset="5588810" size="5" />
451
+ <output>
452
+ <port id="0" precision="U8">
453
+ <dim>5</dim>
454
+ </port>
455
+ </output>
456
+ </layer>
457
+ <layer id="35" name="Constant_73328" type="Const" version="opset1">
458
+ <data element_type="u8" shape="13" offset="5588815" size="13" />
459
+ <output>
460
+ <port id="0" precision="U8">
461
+ <dim>13</dim>
462
+ </port>
463
+ </output>
464
+ </layer>
465
+ <layer id="36" name="Truncate_73329" type="Truncate" version="extension">
466
+ <data m_num_inputs="1" />
467
+ <input>
468
+ <port id="0" precision="I32">
469
+ <dim>-1</dim>
470
+ </port>
471
+ <port id="1" precision="I32">
472
+ <dim>-1</dim>
473
+ </port>
474
+ <port id="2" precision="I32">
475
+ <dim>-1</dim>
476
+ </port>
477
+ <port id="3" precision="I32" />
478
+ <port id="4" precision="U8">
479
+ <dim>5</dim>
480
+ </port>
481
+ <port id="5" precision="U8">
482
+ <dim>13</dim>
483
+ </port>
484
+ </input>
485
+ <output>
486
+ <port id="6" precision="I32">
487
+ <dim>-1</dim>
488
+ </port>
489
+ <port id="7" precision="I32">
490
+ <dim>-1</dim>
491
+ </port>
492
+ <port id="8" precision="I32">
493
+ <dim>-1</dim>
494
+ </port>
495
+ </output>
496
+ </layer>
497
+ <layer id="37" name="Constant_73330" type="Const" version="opset1">
498
+ <data element_type="i32" shape="" offset="5588828" size="4" />
499
+ <output>
500
+ <port id="0" precision="I32" />
501
+ </output>
502
+ </layer>
503
+ <layer id="38" name="Constant_73331" type="Const" version="opset1">
504
+ <data element_type="i32" shape="" offset="5588832" size="4" />
505
+ <output>
506
+ <port id="0" precision="I32" />
507
+ </output>
508
+ </layer>
509
+ <layer id="39" name="Constant_73332" type="Const" version="opset1">
510
+ <data element_type="i32" shape="1" offset="5588836" size="4" />
511
+ <output>
512
+ <port id="0" precision="I32">
513
+ <dim>1</dim>
514
+ </port>
515
+ </output>
516
+ </layer>
517
+ <layer id="40" name="Constant_73333" type="Const" version="opset1">
518
+ <data element_type="i32" shape="2" offset="0" size="8" />
519
+ <output>
520
+ <port id="0" precision="I32">
521
+ <dim>2</dim>
522
+ </port>
523
+ </output>
524
+ </layer>
525
+ <layer id="41" name="CombineSegments_73334" type="CombineSegments" version="extension">
526
+ <input>
527
+ <port id="0" precision="I32">
528
+ <dim>-1</dim>
529
+ </port>
530
+ <port id="1" precision="I32">
531
+ <dim>-1</dim>
532
+ </port>
533
+ <port id="2" precision="I32">
534
+ <dim>-1</dim>
535
+ </port>
536
+ <port id="3" precision="I32" />
537
+ <port id="4" precision="I32" />
538
+ <port id="5" precision="I32">
539
+ <dim>1</dim>
540
+ </port>
541
+ <port id="6" precision="I32">
542
+ <dim>2</dim>
543
+ </port>
544
+ </input>
545
+ <output>
546
+ <port id="7" precision="I32">
547
+ <dim>-1</dim>
548
+ </port>
549
+ <port id="8" precision="I32">
550
+ <dim>-1</dim>
551
+ </port>
552
+ <port id="9" precision="I32">
553
+ <dim>-1</dim>
554
+ </port>
555
+ <port id="10" precision="I32">
556
+ <dim>-1</dim>
557
+ </port>
558
+ <port id="11" precision="I32">
559
+ <dim>-1</dim>
560
+ </port>
561
+ <port id="12" precision="I32">
562
+ <dim>-1</dim>
563
+ </port>
564
+ </output>
565
+ </layer>
566
+ <layer id="42" name="Subtract_73335" type="Subtract" version="opset1">
567
+ <data auto_broadcast="numpy" />
568
+ <input>
569
+ <port id="0" precision="I32">
570
+ <dim>-1</dim>
571
+ </port>
572
+ <port id="1" precision="I32">
573
+ <dim>-1</dim>
574
+ </port>
575
+ </input>
576
+ <output>
577
+ <port id="2" precision="I32">
578
+ <dim>-1</dim>
579
+ </port>
580
+ </output>
581
+ </layer>
582
+ <layer id="43" name="Constant_73336" type="Const" version="opset1">
583
+ <data element_type="i32" shape="" offset="5588828" size="4" />
584
+ <output>
585
+ <port id="0" precision="I32" />
586
+ </output>
587
+ </layer>
588
+ <layer id="44" name="ReduceMax_73337" type="ReduceMax" version="opset1">
589
+ <data keep_dims="false" />
590
+ <input>
591
+ <port id="0" precision="I32">
592
+ <dim>-1</dim>
593
+ </port>
594
+ <port id="1" precision="I32" />
595
+ </input>
596
+ <output>
597
+ <port id="2" precision="I32" />
598
+ </output>
599
+ </layer>
600
+ <layer id="45" name="Constant_73338" type="Const" version="opset1">
601
+ <data element_type="i32" shape="" offset="5588836" size="4" />
602
+ <output>
603
+ <port id="0" precision="I32" />
604
+ </output>
605
+ </layer>
606
+ <layer id="46" name="RaggedToDense_73339" type="RaggedToDense" version="extension">
607
+ <data pad_right="true" m_pad_max_length="false" />
608
+ <input>
609
+ <port id="0" precision="I32">
610
+ <dim>-1</dim>
611
+ </port>
612
+ <port id="1" precision="I32">
613
+ <dim>-1</dim>
614
+ </port>
615
+ <port id="2" precision="I32">
616
+ <dim>-1</dim>
617
+ </port>
618
+ <port id="3" precision="I32" />
619
+ <port id="4" precision="I32" />
620
+ </input>
621
+ <output>
622
+ <port id="5" precision="I32">
623
+ <dim>-1</dim>
624
+ <dim>-1</dim>
625
+ </port>
626
+ <port id="6" precision="BOOL">
627
+ <dim>-1</dim>
628
+ <dim>-1</dim>
629
+ </port>
630
+ </output>
631
+ </layer>
632
+ <layer id="47" name="Convert_73340" type="Convert" version="opset1">
633
+ <data destination_type="i32" />
634
+ <input>
635
+ <port id="0" precision="BOOL">
636
+ <dim>-1</dim>
637
+ <dim>-1</dim>
638
+ </port>
639
+ </input>
640
+ <output>
641
+ <port id="1" precision="I32">
642
+ <dim>-1</dim>
643
+ <dim>-1</dim>
644
+ </port>
645
+ </output>
646
+ </layer>
647
+ <layer id="48" name="Convert_73340.0" type="Convert" version="opset1">
648
+ <data destination_type="i64" />
649
+ <input>
650
+ <port id="0" precision="I32">
651
+ <dim>-1</dim>
652
+ <dim>-1</dim>
653
+ </port>
654
+ </input>
655
+ <output>
656
+ <port id="1" precision="I64" names="attention_mask">
657
+ <dim>-1</dim>
658
+ <dim>-1</dim>
659
+ </port>
660
+ </output>
661
+ </layer>
662
+ <layer id="50" name="RaggedToDense_73339.0" type="Convert" version="opset1">
663
+ <data destination_type="i64" />
664
+ <input>
665
+ <port id="0" precision="I32">
666
+ <dim>-1</dim>
667
+ <dim>-1</dim>
668
+ </port>
669
+ </input>
670
+ <output>
671
+ <port id="1" precision="I64" names="input_ids">
672
+ <dim>-1</dim>
673
+ <dim>-1</dim>
674
+ </port>
675
+ </output>
676
+ </layer>
677
+ <layer id="51" name="Result_73343" type="Result" version="opset1" output_names="input_ids">
678
+ <input>
679
+ <port id="0" precision="I64">
680
+ <dim>-1</dim>
681
+ <dim>-1</dim>
682
+ </port>
683
+ </input>
684
+ </layer>
685
+ <layer id="49" name="Result_73345" type="Result" version="opset1" output_names="attention_mask">
686
+ <input>
687
+ <port id="0" precision="I64">
688
+ <dim>-1</dim>
689
+ <dim>-1</dim>
690
+ </port>
691
+ </input>
692
+ </layer>
693
+ </layers>
694
+ <edges>
695
+ <edge from-layer="0" from-port="0" to-layer="2" to-port="0" />
696
+ <edge from-layer="1" from-port="0" to-layer="8" to-port="0" />
697
+ <edge from-layer="2" from-port="1" to-layer="3" to-port="0" />
698
+ <edge from-layer="2" from-port="3" to-layer="15" to-port="4" />
699
+ <edge from-layer="2" from-port="2" to-layer="15" to-port="3" />
700
+ <edge from-layer="2" from-port="1" to-layer="15" to-port="2" />
701
+ <edge from-layer="3" from-port="1" to-layer="6" to-port="0" />
702
+ <edge from-layer="4" from-port="0" to-layer="6" to-port="1" />
703
+ <edge from-layer="5" from-port="0" to-layer="6" to-port="2" />
704
+ <edge from-layer="6" from-port="3" to-layer="11" to-port="0" />
705
+ <edge from-layer="6" from-port="3" to-layer="8" to-port="1" />
706
+ <edge from-layer="7" from-port="0" to-layer="8" to-port="2" />
707
+ <edge from-layer="8" from-port="3" to-layer="15" to-port="0" />
708
+ <edge from-layer="9" from-port="0" to-layer="13" to-port="0" />
709
+ <edge from-layer="10" from-port="0" to-layer="11" to-port="1" />
710
+ <edge from-layer="11" from-port="2" to-layer="13" to-port="1" />
711
+ <edge from-layer="12" from-port="0" to-layer="13" to-port="2" />
712
+ <edge from-layer="13" from-port="3" to-layer="15" to-port="1" />
713
+ <edge from-layer="14" from-port="0" to-layer="15" to-port="5" />
714
+ <edge from-layer="15" from-port="11" to-layer="16" to-port="3" />
715
+ <edge from-layer="15" from-port="7" to-layer="18" to-port="1" />
716
+ <edge from-layer="15" from-port="6" to-layer="18" to-port="0" />
717
+ <edge from-layer="15" from-port="10" to-layer="16" to-port="2" />
718
+ <edge from-layer="15" from-port="9" to-layer="16" to-port="1" />
719
+ <edge from-layer="15" from-port="8" to-layer="16" to-port="0" />
720
+ <edge from-layer="16" from-port="4" to-layer="18" to-port="2" />
721
+ <edge from-layer="16" from-port="5" to-layer="18" to-port="3" />
722
+ <edge from-layer="16" from-port="6" to-layer="18" to-port="4" />
723
+ <edge from-layer="16" from-port="7" to-layer="18" to-port="5" />
724
+ <edge from-layer="17" from-port="0" to-layer="18" to-port="6" />
725
+ <edge from-layer="18" from-port="7" to-layer="32" to-port="0" />
726
+ <edge from-layer="18" from-port="8" to-layer="32" to-port="1" />
727
+ <edge from-layer="18" from-port="9" to-layer="32" to-port="2" />
728
+ <edge from-layer="18" from-port="10" to-layer="32" to-port="3" />
729
+ <edge from-layer="18" from-port="11" to-layer="32" to-port="4" />
730
+ <edge from-layer="19" from-port="0" to-layer="32" to-port="5" />
731
+ <edge from-layer="20" from-port="0" to-layer="32" to-port="6" />
732
+ <edge from-layer="21" from-port="0" to-layer="32" to-port="7" />
733
+ <edge from-layer="22" from-port="0" to-layer="32" to-port="8" />
734
+ <edge from-layer="23" from-port="0" to-layer="32" to-port="9" />
735
+ <edge from-layer="24" from-port="0" to-layer="32" to-port="10" />
736
+ <edge from-layer="25" from-port="0" to-layer="32" to-port="11" />
737
+ <edge from-layer="26" from-port="0" to-layer="32" to-port="12" />
738
+ <edge from-layer="27" from-port="0" to-layer="32" to-port="13" />
739
+ <edge from-layer="28" from-port="0" to-layer="32" to-port="14" />
740
+ <edge from-layer="29" from-port="0" to-layer="32" to-port="15" />
741
+ <edge from-layer="30" from-port="0" to-layer="32" to-port="16" />
742
+ <edge from-layer="31" from-port="0" to-layer="32" to-port="17" />
743
+ <edge from-layer="32" from-port="18" to-layer="36" to-port="0" />
744
+ <edge from-layer="32" from-port="19" to-layer="36" to-port="1" />
745
+ <edge from-layer="32" from-port="20" to-layer="36" to-port="2" />
746
+ <edge from-layer="33" from-port="0" to-layer="36" to-port="3" />
747
+ <edge from-layer="34" from-port="0" to-layer="36" to-port="4" />
748
+ <edge from-layer="35" from-port="0" to-layer="36" to-port="5" />
749
+ <edge from-layer="36" from-port="8" to-layer="41" to-port="2" />
750
+ <edge from-layer="36" from-port="6" to-layer="41" to-port="0" />
751
+ <edge from-layer="36" from-port="7" to-layer="41" to-port="1" />
752
+ <edge from-layer="37" from-port="0" to-layer="41" to-port="3" />
753
+ <edge from-layer="38" from-port="0" to-layer="41" to-port="4" />
754
+ <edge from-layer="39" from-port="0" to-layer="41" to-port="5" />
755
+ <edge from-layer="40" from-port="0" to-layer="41" to-port="6" />
756
+ <edge from-layer="41" from-port="7" to-layer="46" to-port="0" />
757
+ <edge from-layer="41" from-port="9" to-layer="46" to-port="2" />
758
+ <edge from-layer="41" from-port="8" to-layer="46" to-port="1" />
759
+ <edge from-layer="41" from-port="7" to-layer="42" to-port="1" />
760
+ <edge from-layer="41" from-port="8" to-layer="42" to-port="0" />
761
+ <edge from-layer="42" from-port="2" to-layer="44" to-port="0" />
762
+ <edge from-layer="43" from-port="0" to-layer="44" to-port="1" />
763
+ <edge from-layer="44" from-port="2" to-layer="46" to-port="3" />
764
+ <edge from-layer="45" from-port="0" to-layer="46" to-port="4" />
765
+ <edge from-layer="46" from-port="6" to-layer="47" to-port="0" />
766
+ <edge from-layer="46" from-port="5" to-layer="50" to-port="0" />
767
+ <edge from-layer="47" from-port="1" to-layer="48" to-port="0" />
768
+ <edge from-layer="48" from-port="1" to-layer="49" to-port="0" />
769
+ <edge from-layer="50" from-port="1" to-layer="51" to-port="0" />
770
+ </edges>
771
+ <rt_info>
772
+ <add_attention_mask value="True" />
773
+ <add_prefix_space />
774
+ <add_special_tokens value="True" />
775
+ <chat_template value="{%- if tools %}&#10; {{- '&lt;|im_start|>system\n' }}&#10; {%- if messages[0].role == 'system' %}&#10; {{- messages[0].content + '\n\n' }}&#10; {%- endif %}&#10; {{- &quot;# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within &lt;tools>&lt;/tools> XML tags:\n&lt;tools>&quot; }}&#10; {%- for tool in tools %}&#10; {{- &quot;\n&quot; }}&#10; {{- tool | tojson }}&#10; {%- endfor %}&#10; {{- &quot;\n&lt;/tools>\n\nFor each function call, return a json object with function name and arguments within &lt;tool_call>&lt;/tool_call> XML tags:\n&lt;tool_call>\n{\&quot;name\&quot;: &lt;function-name>, \&quot;arguments\&quot;: &lt;args-json-object>}\n&lt;/tool_call>&lt;|im_end|>\n&quot; }}&#10;{%- else %}&#10; {%- if messages[0].role == 'system' %}&#10; {{- '&lt;|im_start|>system\n' + messages[0].content + '&lt;|im_end|>\n' }}&#10; {%- endif %}&#10;{%- endif %}&#10;{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}&#10;{%- for message in messages[::-1] %}&#10; {%- set index = (messages|length - 1) - loop.index0 %}&#10; {%- if ns.multi_step_tool and message.role == &quot;user&quot; and not(message.content.startswith('&lt;tool_response>') and message.content.endswith('&lt;/tool_response>')) %}&#10; {%- set ns.multi_step_tool = false %}&#10; {%- set ns.last_query_index = index %}&#10; {%- endif %}&#10;{%- endfor %}&#10;{%- for message in messages %}&#10; {%- if (message.role == &quot;user&quot;) or (message.role == &quot;system&quot; and not loop.first) %}&#10; {{- '&lt;|im_start|>' + message.role + '\n' + message.content + '&lt;|im_end|>' + '\n' }}&#10; {%- elif message.role == &quot;assistant&quot; %}&#10; {%- set content = message.content %}&#10; {%- set reasoning_content = '' %}&#10; {%- if message.reasoning_content is defined and message.reasoning_content is not none %}&#10; {%- set reasoning_content = message.reasoning_content %}&#10; {%- else %}&#10; {%- if '&lt;/think>' in message.content %}&#10; {%- set content = message.content.split('&lt;/think>')[-1].lstrip('\n') %}&#10; {%- set reasoning_content = message.content.split('&lt;/think>')[0].rstrip('\n').split('&lt;think>')[-1].lstrip('\n') %}&#10; {%- endif %}&#10; {%- endif %}&#10; {%- if loop.index0 > ns.last_query_index %}&#10; {%- if loop.last or (not loop.last and reasoning_content) %}&#10; {{- '&lt;|im_start|>' + message.role + '\n&lt;think>\n' + reasoning_content.strip('\n') + '\n&lt;/think>\n\n' + content.lstrip('\n') }}&#10; {%- else %}&#10; {{- '&lt;|im_start|>' + message.role + '\n' + content }}&#10; {%- endif %}&#10; {%- else %}&#10; {{- '&lt;|im_start|>' + message.role + '\n' + content }}&#10; {%- endif %}&#10; {%- if message.tool_calls %}&#10; {%- for tool_call in message.tool_calls %}&#10; {%- if (loop.first and content) or (not loop.first) %}&#10; {{- '\n' }}&#10; {%- endif %}&#10; {%- if tool_call.function %}&#10; {%- set tool_call = tool_call.function %}&#10; {%- endif %}&#10; {{- '&lt;tool_call>\n{&quot;name&quot;: &quot;' }}&#10; {{- tool_call.name }}&#10; {{- '&quot;, &quot;arguments&quot;: ' }}&#10; {%- if tool_call.arguments is string %}&#10; {{- tool_call.arguments }}&#10; {%- else %}&#10; {{- tool_call.arguments | tojson }}&#10; {%- endif %}&#10; {{- '}\n&lt;/tool_call>' }}&#10; {%- endfor %}&#10; {%- endif %}&#10; {{- '&lt;|im_end|>\n' }}&#10; {%- elif message.role == &quot;tool&quot; %}&#10; {%- if loop.first or (messages[loop.index0 - 1].role != &quot;tool&quot;) %}&#10; {{- '&lt;|im_start|>user' }}&#10; {%- endif %}&#10; {{- '\n&lt;tool_response>\n' }}&#10; {{- message.content }}&#10; {{- '\n&lt;/tool_response>' }}&#10; {%- if loop.last or (messages[loop.index0 + 1].role != &quot;tool&quot;) %}&#10; {{- '&lt;|im_end|>\n' }}&#10; {%- endif %}&#10; {%- endif %}&#10;{%- endfor %}&#10;{%- if add_generation_prompt %}&#10; {{- '&lt;|im_start|>assistant\n' }}&#10; {%- if enable_thinking is defined and enable_thinking is false %}&#10; {{- '&lt;think>\n\n&lt;/think>\n\n' }}&#10; {%- endif %}&#10;{%- endif %}" />
776
+ <clean_up_tokenization_spaces />
777
+ <detokenizer_input_type value="i64" />
778
+ <eos_token_id value="151645" />
779
+ <handle_special_tokens_with_re />
780
+ <max_length />
781
+ <number_of_inputs value="1" />
782
+ <openvino_tokenizers_version value="2025.4.1.0-627-e79796a77f3" />
783
+ <openvino_version value="2025.4.1-20426-82bbf0292c5-releases/2025/4" />
784
+ <original_post_processor_template value="{&quot;type&quot;: &quot;Sequence&quot;, &quot;processors&quot;: [{&quot;type&quot;: &quot;ByteLevel&quot;, &quot;add_prefix_space&quot;: false, &quot;trim_offsets&quot;: false, &quot;use_regex&quot;: false}, {&quot;type&quot;: &quot;TemplateProcessing&quot;, &quot;single&quot;: [{&quot;Sequence&quot;: {&quot;id&quot;: &quot;A&quot;, &quot;type_id&quot;: 0}}, {&quot;SpecialToken&quot;: {&quot;id&quot;: &quot;&lt;|endoftext|>&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;: 0}}, {&quot;SpecialToken&quot;: {&quot;id&quot;: &quot;&lt;|endoftext|>&quot;, &quot;type_id&quot;: 0}}], &quot;special_tokens&quot;: {&quot;&lt;|endoftext|>&quot;: {&quot;id&quot;: &quot;&lt;|endoftext|>&quot;, &quot;ids&quot;: [151643], &quot;tokens&quot;: [&quot;&lt;|endoftext|>&quot;]}}}]}" />
785
+ <original_tokenizer_class value="&lt;class 'transformers.models.qwen2.tokenization_qwen2_fast.Qwen2TokenizerFast'>" />
786
+ <pad_token_id value="151643" />
787
+ <processed_post_processor_template value="{&quot;single&quot;: {&quot;ids&quot;: [-1, 151643], &quot;type_ids&quot;: [0, 0]}, &quot;pair&quot;: {&quot;ids&quot;: [-1, -2, 151643], &quot;type_ids&quot;: [0, 0, 0]}}" />
788
+ <simplified_chat_template value="{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '&lt;|im_start|>system&#10;You are a helpful assistant.&lt;|im_end|>&#10;' }}{% endif %}{{'&lt;|im_start|>' + message['role'] + '&#10;' + message['content'] + '&lt;|im_end|>' + '&#10;'}}{% endfor %}{% if add_generation_prompt %}{{ '&lt;|im_start|>assistant&#10;' }}{% endif %}" />
789
+ <skip_special_tokens value="True" />
790
+ <streaming_detokenizer value="False" />
791
+ <tokenizer_output_type value="i64" />
792
+ <tokenizers_version value="0.22.1" />
793
+ <transformers_version value="4.57.3" />
794
+ <use_max_padding value="False" />
795
+ <use_sentencepiece_backend value="False" />
796
+ <utf8_replace_mode value="replace" />
797
+ <with_detokenizer value="True" />
798
+ </rt_info>
799
+ </net>
Qwen3-Embedding-0.6B-ov-int4/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
Qwen3-Embedding-0.6B-ov-int4/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:def76fb086971c7867b829c23a26261e38d9d74e02139253b38aeb9df8b4b50a
3
+ size 11423705
Qwen3-Embedding-0.6B-ov-int4/tokenizer_config.json ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 131072,
235
+ "pad_token": "<|endoftext|>",
236
+ "split_special_tokens": false,
237
+ "tokenizer_class": "Qwen2Tokenizer",
238
+ "unk_token": null
239
+ }
Qwen3-Embedding-0.6B-ov-int4/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
Qwen3-Embedding-0.6B-ov-int8/added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
Qwen3-Embedding-0.6B-ov-int8/chat_template.jinja ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for message in messages[::-1] %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
+ {%- set ns.multi_step_tool = false %}
22
+ {%- set ns.last_query_index = index %}
23
+ {%- endif %}
24
+ {%- endfor %}
25
+ {%- for message in messages %}
26
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
27
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
28
+ {%- elif message.role == "assistant" %}
29
+ {%- set content = message.content %}
30
+ {%- set reasoning_content = '' %}
31
+ {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
32
+ {%- set reasoning_content = message.reasoning_content %}
33
+ {%- else %}
34
+ {%- if '</think>' in message.content %}
35
+ {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
36
+ {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
37
+ {%- endif %}
38
+ {%- endif %}
39
+ {%- if loop.index0 > ns.last_query_index %}
40
+ {%- if loop.last or (not loop.last and reasoning_content) %}
41
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
42
+ {%- else %}
43
+ {{- '<|im_start|>' + message.role + '\n' + content }}
44
+ {%- endif %}
45
+ {%- else %}
46
+ {{- '<|im_start|>' + message.role + '\n' + content }}
47
+ {%- endif %}
48
+ {%- if message.tool_calls %}
49
+ {%- for tool_call in message.tool_calls %}
50
+ {%- if (loop.first and content) or (not loop.first) %}
51
+ {{- '\n' }}
52
+ {%- endif %}
53
+ {%- if tool_call.function %}
54
+ {%- set tool_call = tool_call.function %}
55
+ {%- endif %}
56
+ {{- '<tool_call>\n{"name": "' }}
57
+ {{- tool_call.name }}
58
+ {{- '", "arguments": ' }}
59
+ {%- if tool_call.arguments is string %}
60
+ {{- tool_call.arguments }}
61
+ {%- else %}
62
+ {{- tool_call.arguments | tojson }}
63
+ {%- endif %}
64
+ {{- '}\n</tool_call>' }}
65
+ {%- endfor %}
66
+ {%- endif %}
67
+ {{- '<|im_end|>\n' }}
68
+ {%- elif message.role == "tool" %}
69
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
70
+ {{- '<|im_start|>user' }}
71
+ {%- endif %}
72
+ {{- '\n<tool_response>\n' }}
73
+ {{- message.content }}
74
+ {{- '\n</tool_response>' }}
75
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
76
+ {{- '<|im_end|>\n' }}
77
+ {%- endif %}
78
+ {%- endif %}
79
+ {%- endfor %}
80
+ {%- if add_generation_prompt %}
81
+ {{- '<|im_start|>assistant\n' }}
82
+ {%- if enable_thinking is defined and enable_thinking is false %}
83
+ {{- '<think>\n\n</think>\n\n' }}
84
+ {%- endif %}
85
+ {%- endif %}
Qwen3-Embedding-0.6B-ov-int8/config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "dtype": "float32",
9
+ "eos_token_id": 151643,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 1024,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_types": [
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention"
44
+ ],
45
+ "max_position_embeddings": 32768,
46
+ "max_window_layers": 28,
47
+ "model_type": "qwen3",
48
+ "num_attention_heads": 16,
49
+ "num_hidden_layers": 28,
50
+ "num_key_value_heads": 8,
51
+ "rms_norm_eps": 1e-06,
52
+ "rope_scaling": null,
53
+ "rope_theta": 1000000,
54
+ "sliding_window": null,
55
+ "tie_word_embeddings": true,
56
+ "transformers_version": "4.57.3",
57
+ "use_cache": true,
58
+ "use_sliding_window": false,
59
+ "vocab_size": 151669
60
+ }
Qwen3-Embedding-0.6B-ov-int8/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
Qwen3-Embedding-0.6B-ov-int8/model_cache/10398472748164076480.cl_cache ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cea6db01e75c76d8eb37b65365b63d200e1ae11d54f2aa98fc0d030563288286
3
+ size 144120
Qwen3-Embedding-0.6B-ov-int8/model_cache/12113472825542766259.cl_cache ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a8553d33a68b2fd75160e85a9932a5a70317cd4f73e6aa56929e57dd1ef6aef
3
+ size 177552