qaihm-bot commited on
Commit
e9458f6
·
verified ·
1 Parent(s): 567d812

See https://github.com/qualcomm/ai-hub-models/releases/v0.61.0 for changelog.

Files changed (2) hide show
  1. README.md +112 -112
  2. release_assets.json +7 -7
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  library_name: pytorch
3
- license: other
4
  tags:
5
  - foundation
6
  - real_time
@@ -16,7 +16,7 @@ pipeline_tag: text-generation
16
  All-MiniLM-L6-v2 maps sentences to a 384-dimensional dense vector space. Trained on 1B+ sentence pairs, it excels at semantic search, clustering, and sentence similarity tasks while being small enough to run on mobile devices.
17
 
18
  This is based on the implementation of MiniLM-v2 found [here](https://github.com/UKPLab/sentence-transformers).
19
- This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/src/qai_hub_models/models/minilm_v2) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
20
 
21
  Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device.
22
 
@@ -29,26 +29,26 @@ Below are pre-exported model assets ready for deployment.
29
 
30
  | Runtime | Precision | Chipset | SDK Versions | Download |
31
  |---|---|---|---|---|
32
- | ONNX | float | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/minilm_v2/releases/v0.60.0/minilm_v2-onnx-float.zip)
33
- | ONNX | w8a8 | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/minilm_v2/releases/v0.60.0/minilm_v2-onnx-w8a8.zip)
34
- | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/minilm_v2/releases/v0.60.0/minilm_v2-qnn_dlc-float.zip)
35
- | QNN_DLC | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/minilm_v2/releases/v0.60.0/minilm_v2-qnn_dlc-w8a8.zip)
36
- | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/minilm_v2/releases/v0.60.0/minilm_v2-tflite-float.zip)
37
- | TFLITE | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/minilm_v2/releases/v0.60.0/minilm_v2-tflite-w8a8.zip)
38
 
39
  For more device-specific assets and performance metrics, visit **[MiniLM-v2 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/minilm_v2)**.
40
 
41
 
42
  ### Option 2: Export with Custom Configurations
43
 
44
- Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/src/qai_hub_models/models/minilm_v2) Python library to compile and export the model with your own:
45
  - Custom weights (e.g., fine-tuned checkpoints)
46
  - Custom input shapes
47
  - Target device and runtime configurations
48
 
49
  This option is ideal if you need to customize the model beyond the default configuration provided here.
50
 
51
- See our repository for [MiniLM-v2 on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/src/qai_hub_models/models/minilm_v2) for usage instructions.
52
 
53
  ## Model Details
54
 
@@ -64,108 +64,108 @@ See our repository for [MiniLM-v2 on GitHub](https://github.com/qualcomm/ai-hub-
64
  ## Performance Summary
65
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
66
  |---|---|---|---|---|---|---
67
- | MiniLM-v2 | ONNX | float | Snapdragon® X2 Elite | 0.672 ms | 1 - 1 MB | NPU
68
- | MiniLM-v2 | ONNX | float | Snapdragon® X Elite | 1.676 ms | 44 - 44 MB | NPU
69
- | MiniLM-v2 | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 1.126 ms | 0 - 104 MB | NPU
70
- | MiniLM-v2 | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 2.357 ms | 0 - 107 MB | NPU
71
- | MiniLM-v2 | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 1.784 ms | 0 - 4 MB | NPU
72
- | MiniLM-v2 | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.615 ms | 0 - 50 MB | NPU
73
- | MiniLM-v2 | ONNX | float | Qualcomm® QCS8450 | 2.357 ms | 0 - 107 MB | NPU
74
- | MiniLM-v2 | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 2.437 ms | 0 - 3 MB | NPU
75
- | MiniLM-v2 | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 1.676 ms | 44 - 44 MB | NPU
76
- | MiniLM-v2 | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 0.79 ms | 0 - 59 MB | NPU
77
- | MiniLM-v2 | ONNX | float | Snapdragon® 8 Elite Mobile | 0.79 ms | 0 - 59 MB | NPU
78
- | MiniLM-v2 | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.643 ms | 0 - 61 MB | NPU
79
- | MiniLM-v2 | ONNX | w8a8 | Snapdragon® X2 Elite | 0.672 ms | 1 - 1 MB | NPU
80
- | MiniLM-v2 | ONNX | w8a8 | Snapdragon® X Elite | 1.783 ms | 23 - 23 MB | NPU
81
- | MiniLM-v2 | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 1.194 ms | 0 - 84 MB | NPU
82
- | MiniLM-v2 | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 1.98 ms | 0 - 87 MB | NPU
83
- | MiniLM-v2 | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 5.535 ms | 0 - 3 MB | NPU
84
- | MiniLM-v2 | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 1.67 ms | 0 - 4 MB | NPU
85
- | MiniLM-v2 | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.715 ms | 0 - 26 MB | NPU
86
- | MiniLM-v2 | ONNX | w8a8 | Qualcomm® QCS8450 | 1.98 ms | 0 - 87 MB | NPU
87
- | MiniLM-v2 | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 2.062 ms | 0 - 3 MB | NPU
88
- | MiniLM-v2 | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 1.783 ms | 23 - 23 MB | NPU
89
- | MiniLM-v2 | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 6.687 ms | 0 - 60 MB | NPU
90
- | MiniLM-v2 | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 1.95 ms | 0 - 54 MB | NPU
91
- | MiniLM-v2 | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.839 ms | 0 - 58 MB | NPU
92
- | MiniLM-v2 | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 0.839 ms | 0 - 58 MB | NPU
93
- | MiniLM-v2 | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.662 ms | 0 - 60 MB | NPU
94
- | MiniLM-v2 | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.95 ms | 0 - 54 MB | NPU
95
- | MiniLM-v2 | QNN_DLC | float | Snapdragon® X2 Elite | 0.65 ms | 1 - 1 MB | NPU
96
- | MiniLM-v2 | QNN_DLC | float | Snapdragon® X Elite | 1.303 ms | 1 - 1 MB | NPU
97
- | MiniLM-v2 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 0.793 ms | 0 - 99 MB | NPU
98
- | MiniLM-v2 | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 1.89 ms | 0 - 102 MB | NPU
99
- | MiniLM-v2 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 1.326 ms | 0 - 2 MB | NPU
100
- | MiniLM-v2 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 3.563 ms | 0 - 57 MB | NPU
101
- | MiniLM-v2 | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.124 ms | 0 - 3 MB | NPU
102
- | MiniLM-v2 | QNN_DLC | float | Qualcomm® SA8775P | 1.51 ms | 0 - 59 MB | NPU
103
- | MiniLM-v2 | QNN_DLC | float | Qualcomm® SA8650P | 1.51 ms | 0 - 59 MB | NPU
104
- | MiniLM-v2 | QNN_DLC | float | Qualcomm® SA8255P | 1.51 ms | 0 - 59 MB | NPU
105
- | MiniLM-v2 | QNN_DLC | float | Qualcomm® QCS8450 | 1.89 ms | 0 - 102 MB | NPU
106
- | MiniLM-v2 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 1.47 ms | 2 - 4 MB | NPU
107
- | MiniLM-v2 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 1.303 ms | 1 - 1 MB | NPU
108
- | MiniLM-v2 | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 0.568 ms | 0 - 60 MB | NPU
109
- | MiniLM-v2 | QNN_DLC | float | Qualcomm® SA7255P | 3.563 ms | 0 - 57 MB | NPU
110
- | MiniLM-v2 | QNN_DLC | float | Qualcomm® SA8295P | 2.281 ms | 0 - 57 MB | NPU
111
- | MiniLM-v2 | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 0.568 ms | 0 - 60 MB | NPU
112
- | MiniLM-v2 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.466 ms | 0 - 61 MB | NPU
113
- | MiniLM-v2 | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.806 ms | 1 - 1 MB | NPU
114
- | MiniLM-v2 | QNN_DLC | w8a8 | Snapdragon® X Elite | 1.909 ms | 0 - 0 MB | NPU
115
- | MiniLM-v2 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 1.205 ms | 0 - 74 MB | NPU
116
- | MiniLM-v2 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 1.943 ms | 0 - 72 MB | NPU
117
- | MiniLM-v2 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 4.065 ms | 0 - 2 MB | NPU
118
- | MiniLM-v2 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 1.657 ms | 0 - 2 MB | NPU
119
- | MiniLM-v2 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 3.424 ms | 0 - 48 MB | NPU
120
- | MiniLM-v2 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.726 ms | 0 - 33 MB | NPU
121
- | MiniLM-v2 | QNN_DLC | w8a8 | Qualcomm® SA8775P | 1.941 ms | 0 - 52 MB | NPU
122
- | MiniLM-v2 | QNN_DLC | w8a8 | Qualcomm® SA8650P | 1.941 ms | 0 - 52 MB | NPU
123
- | MiniLM-v2 | QNN_DLC | w8a8 | Qualcomm® SA8255P | 1.941 ms | 0 - 52 MB | NPU
124
- | MiniLM-v2 | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 1.943 ms | 0 - 72 MB | NPU
125
- | MiniLM-v2 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 1.824 ms | 0 - 2 MB | NPU
126
- | MiniLM-v2 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 1.909 ms | 0 - 0 MB | NPU
127
- | MiniLM-v2 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 6.133 ms | 0 - 50 MB | NPU
128
- | MiniLM-v2 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 1.69 ms | 0 - 47 MB | NPU
129
- | MiniLM-v2 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.834 ms | 0 - 48 MB | NPU
130
- | MiniLM-v2 | QNN_DLC | w8a8 | Qualcomm® SA7255P | 3.424 ms | 0 - 48 MB | NPU
131
- | MiniLM-v2 | QNN_DLC | w8a8 | Qualcomm® SA8295P | 2.382 ms | 0 - 46 MB | NPU
132
- | MiniLM-v2 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 0.834 ms | 0 - 48 MB | NPU
133
- | MiniLM-v2 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.68 ms | 0 - 52 MB | NPU
134
- | MiniLM-v2 | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.69 ms | 0 - 47 MB | NPU
135
- | MiniLM-v2 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 0.832 ms | 0 - 105 MB | NPU
136
- | MiniLM-v2 | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 1.952 ms | 0 - 101 MB | NPU
137
- | MiniLM-v2 | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 1.401 ms | 0 - 46 MB | NPU
138
- | MiniLM-v2 | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 3.732 ms | 0 - 63 MB | NPU
139
- | MiniLM-v2 | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.127 ms | 0 - 2 MB | NPU
140
- | MiniLM-v2 | TFLITE | float | Qualcomm® SA8775P | 1.568 ms | 0 - 65 MB | NPU
141
- | MiniLM-v2 | TFLITE | float | Qualcomm® SA8650P | 1.568 ms | 0 - 65 MB | NPU
142
- | MiniLM-v2 | TFLITE | float | Qualcomm® SA8255P | 1.568 ms | 0 - 65 MB | NPU
143
- | MiniLM-v2 | TFLITE | float | Qualcomm® QCS8450 | 1.952 ms | 0 - 101 MB | NPU
144
- | MiniLM-v2 | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 1.414 ms | 0 - 45 MB | NPU
145
- | MiniLM-v2 | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 0.596 ms | 0 - 66 MB | NPU
146
- | MiniLM-v2 | TFLITE | float | Qualcomm® SA7255P | 3.732 ms | 0 - 63 MB | NPU
147
- | MiniLM-v2 | TFLITE | float | Qualcomm® SA8295P | 2.362 ms | 0 - 56 MB | NPU
148
- | MiniLM-v2 | TFLITE | float | Snapdragon® 8 Elite Mobile | 0.596 ms | 0 - 66 MB | NPU
149
- | MiniLM-v2 | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.488 ms | 0 - 60 MB | NPU
150
- | MiniLM-v2 | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 1.668 ms | 0 - 83 MB | NPU
151
- | MiniLM-v2 | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 2.608 ms | 0 - 82 MB | NPU
152
- | MiniLM-v2 | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 15.785 ms | 0 - 31 MB | NPU
153
- | MiniLM-v2 | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 2.26 ms | 0 - 25 MB | NPU
154
- | MiniLM-v2 | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 4.606 ms | 0 - 55 MB | NPU
155
- | MiniLM-v2 | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 2.361 ms | 0 - 5 MB | NPU
156
- | MiniLM-v2 | TFLITE | w8a8 | Qualcomm® SA8775P | 2.647 ms | 0 - 59 MB | NPU
157
- | MiniLM-v2 | TFLITE | w8a8 | Qualcomm® SA8650P | 2.647 ms | 0 - 59 MB | NPU
158
- | MiniLM-v2 | TFLITE | w8a8 | Qualcomm® SA8255P | 2.647 ms | 0 - 59 MB | NPU
159
- | MiniLM-v2 | TFLITE | w8a8 | Qualcomm® QCS8450 | 2.608 ms | 0 - 82 MB | NPU
160
- | MiniLM-v2 | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 2.499 ms | 0 - 24 MB | NPU
161
- | MiniLM-v2 | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 12.153 ms | 0 - 38 MB | NPU
162
- | MiniLM-v2 | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 5.059 ms | 0 - 35 MB | NPU
163
- | MiniLM-v2 | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 1.137 ms | 0 - 61 MB | NPU
164
- | MiniLM-v2 | TFLITE | w8a8 | Qualcomm® SA7255P | 4.606 ms | 0 - 55 MB | NPU
165
- | MiniLM-v2 | TFLITE | w8a8 | Qualcomm® SA8295P | 3.197 ms | 0 - 48 MB | NPU
166
- | MiniLM-v2 | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 1.137 ms | 0 - 61 MB | NPU
167
- | MiniLM-v2 | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.951 ms | 0 - 56 MB | NPU
168
- | MiniLM-v2 | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 5.059 ms | 0 - 35 MB | NPU
169
 
170
  ## License
171
  * The license for the original implementation of MiniLM-v2 can be found
 
1
  ---
2
  library_name: pytorch
3
+ license: apache-2.0
4
  tags:
5
  - foundation
6
  - real_time
 
16
  All-MiniLM-L6-v2 maps sentences to a 384-dimensional dense vector space. Trained on 1B+ sentence pairs, it excels at semantic search, clustering, and sentence similarity tasks while being small enough to run on mobile devices.
17
 
18
  This is based on the implementation of MiniLM-v2 found [here](https://github.com/UKPLab/sentence-transformers).
19
+ This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.61.0/src/qai_hub_models/models/minilm_v2) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
20
 
21
  Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device.
22
 
 
29
 
30
  | Runtime | Precision | Chipset | SDK Versions | Download |
31
  |---|---|---|---|---|
32
+ | ONNX | float | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/minilm_v2/releases/v0.61.0/minilm_v2-onnx-float.zip)
33
+ | ONNX | w8a8 | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/minilm_v2/releases/v0.61.0/minilm_v2-onnx-w8a8.zip)
34
+ | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/minilm_v2/releases/v0.61.0/minilm_v2-qnn_dlc-float.zip)
35
+ | QNN_DLC | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/minilm_v2/releases/v0.61.0/minilm_v2-qnn_dlc-w8a8.zip)
36
+ | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/minilm_v2/releases/v0.61.0/minilm_v2-tflite-float.zip)
37
+ | TFLITE | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/minilm_v2/releases/v0.61.0/minilm_v2-tflite-w8a8.zip)
38
 
39
  For more device-specific assets and performance metrics, visit **[MiniLM-v2 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/minilm_v2)**.
40
 
41
 
42
  ### Option 2: Export with Custom Configurations
43
 
44
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.61.0/src/qai_hub_models/models/minilm_v2) Python library to compile and export the model with your own:
45
  - Custom weights (e.g., fine-tuned checkpoints)
46
  - Custom input shapes
47
  - Target device and runtime configurations
48
 
49
  This option is ideal if you need to customize the model beyond the default configuration provided here.
50
 
51
+ See our repository for [MiniLM-v2 on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.61.0/src/qai_hub_models/models/minilm_v2) for usage instructions.
52
 
53
  ## Model Details
54
 
 
64
  ## Performance Summary
65
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
66
  |---|---|---|---|---|---|---
67
+ | MiniLM-v2 | ONNX | float | Snapdragon® X2 Elite | 0.671 ms | 1 - 1 MB | NPU
68
+ | MiniLM-v2 | ONNX | float | Snapdragon® X Elite | 1.673 ms | 44 - 44 MB | NPU
69
+ | MiniLM-v2 | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 1.128 ms | 0 - 102 MB | NPU
70
+ | MiniLM-v2 | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 2.35 ms | 0 - 107 MB | NPU
71
+ | MiniLM-v2 | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 1.785 ms | 0 - 4 MB | NPU
72
+ | MiniLM-v2 | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.621 ms | 0 - 50 MB | NPU
73
+ | MiniLM-v2 | ONNX | float | Qualcomm® QCS8450 | 2.35 ms | 0 - 107 MB | NPU
74
+ | MiniLM-v2 | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 2.004 ms | 0 - 3 MB | NPU
75
+ | MiniLM-v2 | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 1.673 ms | 44 - 44 MB | NPU
76
+ | MiniLM-v2 | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 0.789 ms | 0 - 60 MB | NPU
77
+ | MiniLM-v2 | ONNX | float | Snapdragon® 8 Elite Mobile | 0.789 ms | 0 - 60 MB | NPU
78
+ | MiniLM-v2 | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.643 ms | 0 - 62 MB | NPU
79
+ | MiniLM-v2 | ONNX | w8a8 | Snapdragon® X2 Elite | 0.671 ms | 1 - 1 MB | NPU
80
+ | MiniLM-v2 | ONNX | w8a8 | Snapdragon® X Elite | 1.782 ms | 23 - 23 MB | NPU
81
+ | MiniLM-v2 | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 1.207 ms | 0 - 87 MB | NPU
82
+ | MiniLM-v2 | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 1.964 ms | 0 - 87 MB | NPU
83
+ | MiniLM-v2 | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 5.267 ms | 0 - 3 MB | NPU
84
+ | MiniLM-v2 | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 1.673 ms | 0 - 4 MB | NPU
85
+ | MiniLM-v2 | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.707 ms | 0 - 26 MB | NPU
86
+ | MiniLM-v2 | ONNX | w8a8 | Qualcomm® QCS8450 | 1.964 ms | 0 - 87 MB | NPU
87
+ | MiniLM-v2 | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 1.797 ms | 0 - 3 MB | NPU
88
+ | MiniLM-v2 | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 1.782 ms | 23 - 23 MB | NPU
89
+ | MiniLM-v2 | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 6.704 ms | 0 - 60 MB | NPU
90
+ | MiniLM-v2 | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 1.953 ms | 0 - 54 MB | NPU
91
+ | MiniLM-v2 | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.843 ms | 0 - 60 MB | NPU
92
+ | MiniLM-v2 | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 0.843 ms | 0 - 60 MB | NPU
93
+ | MiniLM-v2 | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.665 ms | 0 - 57 MB | NPU
94
+ | MiniLM-v2 | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.953 ms | 0 - 54 MB | NPU
95
+ | MiniLM-v2 | QNN_DLC | float | Snapdragon® X2 Elite | 0.677 ms | 1 - 1 MB | NPU
96
+ | MiniLM-v2 | QNN_DLC | float | Snapdragon® X Elite | 1.288 ms | 1 - 1 MB | NPU
97
+ | MiniLM-v2 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 0.788 ms | 0 - 99 MB | NPU
98
+ | MiniLM-v2 | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 1.895 ms | 0 - 101 MB | NPU
99
+ | MiniLM-v2 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 1.323 ms | 0 - 2 MB | NPU
100
+ | MiniLM-v2 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 3.572 ms | 0 - 58 MB | NPU
101
+ | MiniLM-v2 | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.115 ms | 0 - 7 MB | NPU
102
+ | MiniLM-v2 | QNN_DLC | float | Qualcomm® SA8775P | 1.521 ms | 0 - 60 MB | NPU
103
+ | MiniLM-v2 | QNN_DLC | float | Qualcomm® SA8650P | 1.521 ms | 0 - 60 MB | NPU
104
+ | MiniLM-v2 | QNN_DLC | float | Qualcomm® SA8255P | 1.521 ms | 0 - 60 MB | NPU
105
+ | MiniLM-v2 | QNN_DLC | float | Qualcomm® QCS8450 | 1.895 ms | 0 - 101 MB | NPU
106
+ | MiniLM-v2 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 1.39 ms | 2 - 4 MB | NPU
107
+ | MiniLM-v2 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 1.288 ms | 1 - 1 MB | NPU
108
+ | MiniLM-v2 | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 0.565 ms | 0 - 59 MB | NPU
109
+ | MiniLM-v2 | QNN_DLC | float | Qualcomm® SA7255P | 3.572 ms | 0 - 58 MB | NPU
110
+ | MiniLM-v2 | QNN_DLC | float | Qualcomm® SA8295P | 2.286 ms | 0 - 57 MB | NPU
111
+ | MiniLM-v2 | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 0.565 ms | 0 - 59 MB | NPU
112
+ | MiniLM-v2 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.464 ms | 0 - 61 MB | NPU
113
+ | MiniLM-v2 | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.815 ms | 1 - 1 MB | NPU
114
+ | MiniLM-v2 | QNN_DLC | w8a8 | Snapdragon® X Elite | 1.909 ms | 1 - 1 MB | NPU
115
+ | MiniLM-v2 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 1.208 ms | 0 - 73 MB | NPU
116
+ | MiniLM-v2 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 1.954 ms | 0 - 72 MB | NPU
117
+ | MiniLM-v2 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 4.003 ms | 2 - 4 MB | NPU
118
+ | MiniLM-v2 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 1.647 ms | 0 - 2 MB | NPU
119
+ | MiniLM-v2 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 3.449 ms | 0 - 48 MB | NPU
120
+ | MiniLM-v2 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.717 ms | 0 - 2 MB | NPU
121
+ | MiniLM-v2 | QNN_DLC | w8a8 | Qualcomm® SA8775P | 1.931 ms | 0 - 50 MB | NPU
122
+ | MiniLM-v2 | QNN_DLC | w8a8 | Qualcomm® SA8650P | 1.931 ms | 0 - 50 MB | NPU
123
+ | MiniLM-v2 | QNN_DLC | w8a8 | Qualcomm® SA8255P | 1.931 ms | 0 - 50 MB | NPU
124
+ | MiniLM-v2 | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 1.954 ms | 0 - 72 MB | NPU
125
+ | MiniLM-v2 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 1.994 ms | 0 - 2 MB | NPU
126
+ | MiniLM-v2 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 1.909 ms | 1 - 1 MB | NPU
127
+ | MiniLM-v2 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 6.135 ms | 0 - 50 MB | NPU
128
+ | MiniLM-v2 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 1.699 ms | 0 - 47 MB | NPU
129
+ | MiniLM-v2 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.833 ms | 0 - 48 MB | NPU
130
+ | MiniLM-v2 | QNN_DLC | w8a8 | Qualcomm® SA7255P | 3.449 ms | 0 - 48 MB | NPU
131
+ | MiniLM-v2 | QNN_DLC | w8a8 | Qualcomm® SA8295P | 2.371 ms | 0 - 46 MB | NPU
132
+ | MiniLM-v2 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 0.833 ms | 0 - 48 MB | NPU
133
+ | MiniLM-v2 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.671 ms | 0 - 51 MB | NPU
134
+ | MiniLM-v2 | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.699 ms | 0 - 47 MB | NPU
135
+ | MiniLM-v2 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 0.829 ms | 0 - 103 MB | NPU
136
+ | MiniLM-v2 | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 1.96 ms | 0 - 104 MB | NPU
137
+ | MiniLM-v2 | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 1.383 ms | 0 - 46 MB | NPU
138
+ | MiniLM-v2 | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 3.674 ms | 0 - 63 MB | NPU
139
+ | MiniLM-v2 | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.132 ms | 0 - 6 MB | NPU
140
+ | MiniLM-v2 | TFLITE | float | Qualcomm® SA8775P | 1.556 ms | 0 - 65 MB | NPU
141
+ | MiniLM-v2 | TFLITE | float | Qualcomm® SA8650P | 1.556 ms | 0 - 65 MB | NPU
142
+ | MiniLM-v2 | TFLITE | float | Qualcomm® SA8255P | 1.556 ms | 0 - 65 MB | NPU
143
+ | MiniLM-v2 | TFLITE | float | Qualcomm® QCS8450 | 1.96 ms | 0 - 104 MB | NPU
144
+ | MiniLM-v2 | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 1.402 ms | 0 - 45 MB | NPU
145
+ | MiniLM-v2 | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 0.593 ms | 0 - 58 MB | NPU
146
+ | MiniLM-v2 | TFLITE | float | Qualcomm® SA7255P | 3.674 ms | 0 - 63 MB | NPU
147
+ | MiniLM-v2 | TFLITE | float | Qualcomm® SA8295P | 2.375 ms | 0 - 56 MB | NPU
148
+ | MiniLM-v2 | TFLITE | float | Snapdragon® 8 Elite Mobile | 0.593 ms | 0 - 58 MB | NPU
149
+ | MiniLM-v2 | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.485 ms | 0 - 58 MB | NPU
150
+ | MiniLM-v2 | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 1.666 ms | 0 - 82 MB | NPU
151
+ | MiniLM-v2 | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 2.604 ms | 0 - 79 MB | NPU
152
+ | MiniLM-v2 | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 15.688 ms | 0 - 31 MB | NPU
153
+ | MiniLM-v2 | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 2.268 ms | 0 - 25 MB | NPU
154
+ | MiniLM-v2 | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 4.64 ms | 0 - 55 MB | NPU
155
+ | MiniLM-v2 | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 2.376 ms | 0 - 2 MB | NPU
156
+ | MiniLM-v2 | TFLITE | w8a8 | Qualcomm® SA8775P | 2.681 ms | 0 - 59 MB | NPU
157
+ | MiniLM-v2 | TFLITE | w8a8 | Qualcomm® SA8650P | 2.681 ms | 0 - 59 MB | NPU
158
+ | MiniLM-v2 | TFLITE | w8a8 | Qualcomm® SA8255P | 2.681 ms | 0 - 59 MB | NPU
159
+ | MiniLM-v2 | TFLITE | w8a8 | Qualcomm® QCS8450 | 2.604 ms | 0 - 79 MB | NPU
160
+ | MiniLM-v2 | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 2.502 ms | 0 - 24 MB | NPU
161
+ | MiniLM-v2 | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 12.098 ms | 0 - 36 MB | NPU
162
+ | MiniLM-v2 | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 5.046 ms | 0 - 35 MB | NPU
163
+ | MiniLM-v2 | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 1.134 ms | 0 - 62 MB | NPU
164
+ | MiniLM-v2 | TFLITE | w8a8 | Qualcomm® SA7255P | 4.64 ms | 0 - 55 MB | NPU
165
+ | MiniLM-v2 | TFLITE | w8a8 | Qualcomm® SA8295P | 3.21 ms | 0 - 48 MB | NPU
166
+ | MiniLM-v2 | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 1.134 ms | 0 - 62 MB | NPU
167
+ | MiniLM-v2 | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.95 ms | 0 - 56 MB | NPU
168
+ | MiniLM-v2 | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 5.046 ms | 0 - 35 MB | NPU
169
 
170
  ## License
171
  * The license for the original implementation of MiniLM-v2 can be found
release_assets.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "version": "0.60.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
@@ -8,19 +8,19 @@
8
  "qairt": "2.45.0.260326154327",
9
  "onnx_runtime": "1.27.1"
10
  },
11
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/minilm_v2/releases/v0.60.0/minilm_v2-onnx-float.zip"
12
  },
13
  "qnn_dlc": {
14
  "tool_versions": {
15
  "qairt": "2.45.0.260326154327"
16
  },
17
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/minilm_v2/releases/v0.60.0/minilm_v2-qnn_dlc-float.zip"
18
  },
19
  "tflite": {
20
  "tool_versions": {
21
  "qairt": "2.45.0.260326154327"
22
  },
23
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/minilm_v2/releases/v0.60.0/minilm_v2-tflite-float.zip"
24
  }
25
  }
26
  },
@@ -31,19 +31,19 @@
31
  "qairt": "2.45.0.260326154327",
32
  "onnx_runtime": "1.27.1"
33
  },
34
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/minilm_v2/releases/v0.60.0/minilm_v2-onnx-w8a8.zip"
35
  },
36
  "qnn_dlc": {
37
  "tool_versions": {
38
  "qairt": "2.45.0.260326154327"
39
  },
40
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/minilm_v2/releases/v0.60.0/minilm_v2-qnn_dlc-w8a8.zip"
41
  },
42
  "tflite": {
43
  "tool_versions": {
44
  "qairt": "2.45.0.260326154327"
45
  },
46
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/minilm_v2/releases/v0.60.0/minilm_v2-tflite-w8a8.zip"
47
  }
48
  }
49
  }
 
1
  {
2
+ "version": "0.61.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
 
8
  "qairt": "2.45.0.260326154327",
9
  "onnx_runtime": "1.27.1"
10
  },
11
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/minilm_v2/releases/v0.61.0/minilm_v2-onnx-float.zip"
12
  },
13
  "qnn_dlc": {
14
  "tool_versions": {
15
  "qairt": "2.45.0.260326154327"
16
  },
17
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/minilm_v2/releases/v0.61.0/minilm_v2-qnn_dlc-float.zip"
18
  },
19
  "tflite": {
20
  "tool_versions": {
21
  "qairt": "2.45.0.260326154327"
22
  },
23
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/minilm_v2/releases/v0.61.0/minilm_v2-tflite-float.zip"
24
  }
25
  }
26
  },
 
31
  "qairt": "2.45.0.260326154327",
32
  "onnx_runtime": "1.27.1"
33
  },
34
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/minilm_v2/releases/v0.61.0/minilm_v2-onnx-w8a8.zip"
35
  },
36
  "qnn_dlc": {
37
  "tool_versions": {
38
  "qairt": "2.45.0.260326154327"
39
  },
40
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/minilm_v2/releases/v0.61.0/minilm_v2-qnn_dlc-w8a8.zip"
41
  },
42
  "tflite": {
43
  "tool_versions": {
44
  "qairt": "2.45.0.260326154327"
45
  },
46
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/minilm_v2/releases/v0.61.0/minilm_v2-tflite-w8a8.zip"
47
  }
48
  }
49
  }