finnvoorhees commited on
Commit
2d48714
·
verified ·
1 Parent(s): a9e2cd4

Upload folder using huggingface_hub

Browse files
Qwen2.5-0.5B-Instruct-4bit.mlmodelc/analytics/coremldata.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:210c0f7ff77fa09981711357deae56c918e91a53ad0d2f830dad341a57e2643b
3
+ size 243
Qwen2.5-0.5B-Instruct-4bit.mlmodelc/coremldata.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23ec629302c11a3e880fd1c885cb542b89c4a89f2fc8a608dabf4c362e28256a
3
+ size 445
Qwen2.5-0.5B-Instruct-4bit.mlmodelc/metadata.json ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "metadataOutputVersion" : "3.0",
4
+ "storagePrecision" : "Mixed (Float16, Int4)",
5
+ "outputSchema" : [
6
+ {
7
+ "hasShapeFlexibility" : "0",
8
+ "isOptional" : "0",
9
+ "dataType" : "Float16",
10
+ "formattedType" : "MultiArray (Float16)",
11
+ "shortDescription" : "",
12
+ "shape" : "[]",
13
+ "name" : "logits",
14
+ "type" : "MultiArray"
15
+ }
16
+ ],
17
+ "modelParameters" : [
18
+
19
+ ],
20
+ "specificationVersion" : 9,
21
+ "mlProgramOperationTypeHistogram" : {
22
+ "Ios18.expandDims" : 54,
23
+ "Range1d" : 1,
24
+ "Ios18.cos" : 1,
25
+ "Ios18.mul" : 266,
26
+ "Ios18.matmul" : 1,
27
+ "Ios18.rsqrt" : 49,
28
+ "Ios16.reduceMean" : 49,
29
+ "Ios18.realDiv" : 48,
30
+ "Ios18.scaledDotProductAttention" : 24,
31
+ "Ios18.sin" : 1,
32
+ "Ios18.readState" : 50,
33
+ "Tile" : 48,
34
+ "Ios18.gather" : 77,
35
+ "Ios18.add" : 147,
36
+ "Ios18.writeState" : 48,
37
+ "Ios18.sliceUpdate" : 48,
38
+ "Ios18.reshape" : 144,
39
+ "Shape" : 124,
40
+ "Ios18.linear" : 169,
41
+ "Ios18.concat" : 147,
42
+ "Ios18.transpose" : 97,
43
+ "Ios18.sub" : 1,
44
+ "Ios18.pow" : 49,
45
+ "Ios18.cast" : 153,
46
+ "Ios18.silu" : 24,
47
+ "Ios18.sliceByIndex" : 216,
48
+ "Ios18.constexprBlockwiseShiftScale" : 169
49
+ },
50
+ "computePrecision" : "Mixed (Float16, Float32, Int16, Int32, UInt16)",
51
+ "isUpdatable" : "0",
52
+ "stateSchema" : [
53
+ {
54
+ "dataType" : "Float16",
55
+ "isOptional" : "0",
56
+ "formattedType" : "State (Float16 24 × 1 × 2 × 2048 × 64)",
57
+ "shortDescription" : "",
58
+ "shape" : "[24, 1, 2, 2048, 64]",
59
+ "name" : "key_cache",
60
+ "type" : "State"
61
+ },
62
+ {
63
+ "dataType" : "Float16",
64
+ "isOptional" : "0",
65
+ "formattedType" : "State (Float16 24 × 1 × 2 × 2048 × 64)",
66
+ "shortDescription" : "",
67
+ "shape" : "[24, 1, 2, 2048, 64]",
68
+ "name" : "value_cache",
69
+ "type" : "State"
70
+ }
71
+ ],
72
+ "availability" : {
73
+ "macOS" : "15.0",
74
+ "tvOS" : "18.0",
75
+ "visionOS" : "2.0",
76
+ "watchOS" : "11.0",
77
+ "iOS" : "18.0",
78
+ "macCatalyst" : "18.0"
79
+ },
80
+ "modelType" : {
81
+ "name" : "MLModelType_mlProgram"
82
+ },
83
+ "userDefinedMetadata" : {
84
+ "com.github.apple.coremltools.source_dialect" : "TorchScript",
85
+ "com.github.apple.coremltools.source" : "torch==2.5.1",
86
+ "com.github.apple.coremltools.version" : "8.1"
87
+ },
88
+ "inputSchema" : [
89
+ {
90
+ "dataType" : "Int32",
91
+ "hasShapeFlexibility" : "1",
92
+ "isOptional" : "0",
93
+ "shapeFlexibility" : "1 × 1...2048",
94
+ "shapeRange" : "[[1, 1], [1, 2048]]",
95
+ "formattedType" : "MultiArray (Int32 1 × 1)",
96
+ "type" : "MultiArray",
97
+ "shape" : "[1, 1]",
98
+ "name" : "input_ids",
99
+ "shortDescription" : ""
100
+ },
101
+ {
102
+ "dataType" : "Float16",
103
+ "hasShapeFlexibility" : "1",
104
+ "isOptional" : "0",
105
+ "shapeFlexibility" : "1 × 1 × 1...2048 × 1...2048",
106
+ "shapeRange" : "[[1, 1], [1, 1], [1, 2048], [1, 2048]]",
107
+ "formattedType" : "MultiArray (Float16 1 × 1 × 1 × 1)",
108
+ "type" : "MultiArray",
109
+ "shape" : "[1, 1, 1, 1]",
110
+ "name" : "causal_mask",
111
+ "shortDescription" : ""
112
+ }
113
+ ],
114
+ "generatedClassName" : "Qwen2_5_0_5B_Instruct_4bit",
115
+ "method" : "predict"
116
+ }
117
+ ]
Qwen2.5-0.5B-Instruct-4bit.mlmodelc/model.mil ADDED
The diff for this file is too large to render. See raw diff
 
Qwen2.5-0.5B-Instruct-4bit.mlmodelc/weights/weight.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ffda57e39c0f0dddc9db9d10d0122e8954f64562545b18394160a27d45cec0b
3
+ size 278341440