Hugging Face's logo

qualcomm
/
Albert-Base-V2-Hf

Text Generation
PyTorch
backbone
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
d7ea96d
·
verified ·
1 Parent(s): 4c3417a

v0.58.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.58.0 for changelog.

Files changed (2) hide show
  1. README.md +36 -33
  2. release_assets.json +3 -3
README.md CHANGED
@@ -15,7 +15,7 @@ pipeline_tag: text-generation
15
  ALBERT is a lightweight BERT model designed for efficient self-supervised learning of language representations. It can be used for masked language modeling and as a backbone for various NLP tasks.
16
 
17
  This is based on the implementation of Albert-Base-V2-Hf found [here](https://github.com/google-research/albert).
18
- 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/v0.57.3/src/qai_hub_models/models/albert_base_v2_hf) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
19
 
20
  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.
21
 
@@ -28,22 +28,22 @@ Below are pre-exported model assets ready for deployment.
28
 
29
  | Runtime | Precision | Chipset | SDK Versions | Download |
30
  |---|---|---|---|---|
31
- | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/albert_base_v2_hf/releases/v0.57.3/albert_base_v2_hf-qnn_dlc-float.zip)
32
- | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/albert_base_v2_hf/releases/v0.57.3/albert_base_v2_hf-tflite-float.zip)
33
 
34
  For more device-specific assets and performance metrics, visit **[Albert-Base-V2-Hf on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/albert_base_v2_hf)**.
35
 
36
 
37
  ### Option 2: Export with Custom Configurations
38
 
39
- Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.57.3/src/qai_hub_models/models/albert_base_v2_hf) Python library to compile and export the model with your own:
40
  - Custom weights (e.g., fine-tuned checkpoints)
41
  - Custom input shapes
42
  - Target device and runtime configurations
43
 
44
  This option is ideal if you need to customize the model beyond the default configuration provided here.
45
 
46
- See our repository for [Albert-Base-V2-Hf on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.57.3/src/qai_hub_models/models/albert_base_v2_hf) for usage instructions.
47
 
48
  ## Model Details
49
 
@@ -58,34 +58,37 @@ See our repository for [Albert-Base-V2-Hf on GitHub](https://github.com/qualcomm
58
  ## Performance Summary
59
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
60
  |---|---|---|---|---|---|---
61
- | Albert-Base-V2-Hf | QNN_DLC | float | Snapdragon® X2 Elite | 9.324 ms | 1 - 1 MB | NPU
62
- | Albert-Base-V2-Hf | QNN_DLC | float | Snapdragon® X Elite | 20.942 ms | 1 - 1 MB | NPU
63
- | Albert-Base-V2-Hf | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 16.83 ms | 0 - 356 MB | NPU
64
- | Albert-Base-V2-Hf | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 34.107 ms | 0 - 423 MB | NPU
65
- | Albert-Base-V2-Hf | QNN_DLC | float | Qualcomm® QCS8275 | 72.564 ms | 0 - 308 MB | NPU
66
- | Albert-Base-V2-Hf | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 21.23 ms | 0 - 2 MB | NPU
67
- | Albert-Base-V2-Hf | QNN_DLC | float | Qualcomm® QCS8450 | 34.107 ms | 0 - 423 MB | NPU
68
- | Albert-Base-V2-Hf | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 11.226 ms | 0 - 398 MB | NPU
69
- | Albert-Base-V2-Hf | QNN_DLC | float | Qualcomm® SA8295P | 31.207 ms | 0 - 375 MB | NPU
70
- | Albert-Base-V2-Hf | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 8.184 ms | 0 - 397 MB | NPU
71
- | Albert-Base-V2-Hf | QNN_DLC | float | Qualcomm® SA7255P | 72.564 ms | 0 - 308 MB | NPU
72
- | Albert-Base-V2-Hf | QNN_DLC | float | Qualcomm® QCS9075 | 25.436 ms | 0 - 2 MB | NPU
73
- | Albert-Base-V2-Hf | QNN_DLC | float | Qualcomm® QCS8750 | 11.226 ms | 0 - 398 MB | NPU
74
- | Albert-Base-V2-Hf | QNN_DLC | float | Qualcomm® QCS7181 | 20.942 ms | 1 - 1 MB | NPU
75
- | Albert-Base-V2-Hf | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 16.996 ms | 0 - 370 MB | NPU
76
- | Albert-Base-V2-Hf | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 34.392 ms | 0 - 427 MB | NPU
77
- | Albert-Base-V2-Hf | TFLITE | float | Qualcomm® QCS8275 | 73.041 ms | 0 - 322 MB | NPU
78
- | Albert-Base-V2-Hf | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 21.406 ms | 0 - 3 MB | NPU
79
- | Albert-Base-V2-Hf | TFLITE | float | Qualcomm® SA8775P | 248.562 ms | 1 - 26 MB | GPU
80
- | Albert-Base-V2-Hf | TFLITE | float | Qualcomm® SA8650P | 248.562 ms | 1 - 26 MB | GPU
81
- | Albert-Base-V2-Hf | TFLITE | float | Qualcomm® SA8255P | 248.562 ms | 1 - 26 MB | GPU
82
- | Albert-Base-V2-Hf | TFLITE | float | Qualcomm® QCS8450 | 34.392 ms | 0 - 427 MB | NPU
83
- | Albert-Base-V2-Hf | TFLITE | float | Snapdragon® 8 Elite Mobile | 11.288 ms | 0 - 392 MB | NPU
84
- | Albert-Base-V2-Hf | TFLITE | float | Qualcomm® SA8295P | 31.541 ms | 0 - 376 MB | NPU
85
- | Albert-Base-V2-Hf | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 8.946 ms | 0 - 326 MB | NPU
86
- | Albert-Base-V2-Hf | TFLITE | float | Qualcomm® SA7255P | 73.041 ms | 0 - 322 MB | NPU
87
- | Albert-Base-V2-Hf | TFLITE | float | Qualcomm® QCS9075 | 25.622 ms | 0 - 32 MB | NPU
88
- | Albert-Base-V2-Hf | TFLITE | float | Qualcomm® QCS8750 | 11.288 ms | 0 - 392 MB | NPU
 
 
 
89
 
90
  ## License
91
  * The license for the original implementation of Albert-Base-V2-Hf can be found
 
15
  ALBERT is a lightweight BERT model designed for efficient self-supervised learning of language representations. It can be used for masked language modeling and as a backbone for various NLP tasks.
16
 
17
  This is based on the implementation of Albert-Base-V2-Hf found [here](https://github.com/google-research/albert).
18
+ 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/v0.58.0/src/qai_hub_models/models/albert_base_v2_hf) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
19
 
20
  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.
21
 
 
28
 
29
  | Runtime | Precision | Chipset | SDK Versions | Download |
30
  |---|---|---|---|---|
31
+ | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/albert_base_v2_hf/releases/v0.58.0/albert_base_v2_hf-qnn_dlc-float.zip)
32
+ | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/albert_base_v2_hf/releases/v0.58.0/albert_base_v2_hf-tflite-float.zip)
33
 
34
  For more device-specific assets and performance metrics, visit **[Albert-Base-V2-Hf on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/albert_base_v2_hf)**.
35
 
36
 
37
  ### Option 2: Export with Custom Configurations
38
 
39
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.58.0/src/qai_hub_models/models/albert_base_v2_hf) Python library to compile and export the model with your own:
40
  - Custom weights (e.g., fine-tuned checkpoints)
41
  - Custom input shapes
42
  - Target device and runtime configurations
43
 
44
  This option is ideal if you need to customize the model beyond the default configuration provided here.
45
 
46
+ See our repository for [Albert-Base-V2-Hf on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.58.0/src/qai_hub_models/models/albert_base_v2_hf) for usage instructions.
47
 
48
  ## Model Details
49
 
 
58
  ## Performance Summary
59
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
60
  |---|---|---|---|---|---|---
61
+ | Albert-Base-V2-Hf | QNN_DLC | float | Snapdragon® X2 Elite | 9.203 ms | 1 - 1 MB | NPU
62
+ | Albert-Base-V2-Hf | QNN_DLC | float | Snapdragon® X Elite | 21.081 ms | 1 - 1 MB | NPU
63
+ | Albert-Base-V2-Hf | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 16.715 ms | 0 - 355 MB | NPU
64
+ | Albert-Base-V2-Hf | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 34.139 ms | 0 - 422 MB | NPU
65
+ | Albert-Base-V2-Hf | QNN_DLC | float | Qualcomm® QCS8275 | 72.498 ms | 0 - 307 MB | NPU
66
+ | Albert-Base-V2-Hf | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 21.654 ms | 0 - 23 MB | NPU
67
+ | Albert-Base-V2-Hf | QNN_DLC | float | Qualcomm® SA8775P | 25.858 ms | 0 - 307 MB | NPU
68
+ | Albert-Base-V2-Hf | QNN_DLC | float | Qualcomm® SA8650P | 25.858 ms | 0 - 307 MB | NPU
69
+ | Albert-Base-V2-Hf | QNN_DLC | float | Qualcomm® SA8255P | 25.858 ms | 0 - 307 MB | NPU
70
+ | Albert-Base-V2-Hf | QNN_DLC | float | Qualcomm® QCS8450 | 34.139 ms | 0 - 422 MB | NPU
71
+ | Albert-Base-V2-Hf | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 25.445 ms | 0 - 2 MB | NPU
72
+ | Albert-Base-V2-Hf | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 8.2 ms | 0 - 397 MB | NPU
73
+ | Albert-Base-V2-Hf | QNN_DLC | float | Qualcomm® SA7255P | 72.498 ms | 0 - 307 MB | NPU
74
+ | Albert-Base-V2-Hf | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 11.298 ms | 0 - 399 MB | NPU
75
+ | Albert-Base-V2-Hf | QNN_DLC | float | Qualcomm® SA8295P | 31.276 ms | 0 - 374 MB | NPU
76
+ | Albert-Base-V2-Hf | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 11.298 ms | 0 - 399 MB | NPU
77
+ | Albert-Base-V2-Hf | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 21.081 ms | 1 - 1 MB | NPU
78
+ | Albert-Base-V2-Hf | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 16.909 ms | 0 - 366 MB | NPU
79
+ | Albert-Base-V2-Hf | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 34.224 ms | 0 - 425 MB | NPU
80
+ | Albert-Base-V2-Hf | TFLITE | float | Qualcomm® QCS8275 | 72.947 ms | 0 - 322 MB | NPU
81
+ | Albert-Base-V2-Hf | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 21.983 ms | 0 - 13 MB | NPU
82
+ | Albert-Base-V2-Hf | TFLITE | float | Qualcomm® SA8775P | 26.157 ms | 0 - 322 MB | NPU
83
+ | Albert-Base-V2-Hf | TFLITE | float | Qualcomm® SA8650P | 26.157 ms | 0 - 322 MB | NPU
84
+ | Albert-Base-V2-Hf | TFLITE | float | Qualcomm® SA8255P | 26.157 ms | 0 - 322 MB | NPU
85
+ | Albert-Base-V2-Hf | TFLITE | float | Qualcomm® QCS8450 | 34.224 ms | 0 - 425 MB | NPU
86
+ | Albert-Base-V2-Hf | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 26.102 ms | 0 - 32 MB | NPU
87
+ | Albert-Base-V2-Hf | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 8.96 ms | 0 - 324 MB | NPU
88
+ | Albert-Base-V2-Hf | TFLITE | float | Qualcomm® SA7255P | 72.947 ms | 0 - 322 MB | NPU
89
+ | Albert-Base-V2-Hf | TFLITE | float | Snapdragon® 8 Elite Mobile | 11.286 ms | 0 - 391 MB | NPU
90
+ | Albert-Base-V2-Hf | TFLITE | float | Qualcomm® SA8295P | 31.619 ms | 0 - 376 MB | NPU
91
+ | Albert-Base-V2-Hf | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 11.286 ms | 0 - 391 MB | NPU
92
 
93
  ## License
94
  * The license for the original implementation of Albert-Base-V2-Hf can be found
release_assets.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "version": "0.57.3",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
@@ -8,13 +8,13 @@
8
  "qairt": "2.45.0.260326154327",
9
  "litert": "1.4.4"
10
  },
11
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/albert_base_v2_hf/releases/v0.57.3/albert_base_v2_hf-tflite-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/albert_base_v2_hf/releases/v0.57.3/albert_base_v2_hf-qnn_dlc-float.zip"
18
  }
19
  }
20
  }
 
1
  {
2
+ "version": "0.58.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
 
8
  "qairt": "2.45.0.260326154327",
9
  "litert": "1.4.4"
10
  },
11
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/albert_base_v2_hf/releases/v0.58.0/albert_base_v2_hf-tflite-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/albert_base_v2_hf/releases/v0.58.0/albert_base_v2_hf-qnn_dlc-float.zip"
18
  }
19
  }
20
  }