v0.50.2
Browse filesSee https://github.com/qualcomm/ai-hub-models/releases/v0.50.2 for changelog.
- README.md +35 -54
- release_assets.json +1 -1
README.md
CHANGED
|
@@ -27,11 +27,9 @@ Below are pre-exported model assets ready for deployment.
|
|
| 27 |
|
| 28 |
| Runtime | Precision | Chipset | SDK Versions | Download |
|
| 29 |
|---|---|---|---|---|
|
| 30 |
-
| ONNX |
|
| 31 |
-
|
|
| 32 |
-
|
|
| 33 |
-
| QNN_DLC | w8a16 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/distil_bert_base_uncased_hf/releases/v0.50.1/distil_bert_base_uncased_hf-qnn_dlc-w8a16.zip)
|
| 34 |
-
| TFLITE | float | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/distil_bert_base_uncased_hf/releases/v0.50.1/distil_bert_base_uncased_hf-tflite-float.zip)
|
| 35 |
|
| 36 |
For more device-specific assets and performance metrics, visit **[Distil-Bert-Base-Uncased-Hf on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/distil_bert_base_uncased_hf)**.
|
| 37 |
|
|
@@ -60,55 +58,38 @@ See our repository for [Distil-Bert-Base-Uncased-Hf on GitHub](https://github.co
|
|
| 60 |
## Performance Summary
|
| 61 |
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|
| 62 |
|---|---|---|---|---|---|---
|
| 63 |
-
| Distil-Bert-Base-Uncased-Hf | ONNX |
|
| 64 |
-
| Distil-Bert-Base-Uncased-Hf | ONNX |
|
| 65 |
-
| Distil-Bert-Base-Uncased-Hf | ONNX |
|
| 66 |
-
| Distil-Bert-Base-Uncased-Hf | ONNX |
|
| 67 |
-
| Distil-Bert-Base-Uncased-Hf | ONNX |
|
| 68 |
-
| Distil-Bert-Base-Uncased-Hf | ONNX |
|
| 69 |
-
| Distil-Bert-Base-Uncased-Hf | ONNX |
|
| 70 |
-
| Distil-Bert-Base-Uncased-Hf | ONNX | w8a16 |
|
| 71 |
-
| Distil-Bert-Base-Uncased-Hf | ONNX | w8a16 | Snapdragon®
|
| 72 |
-
| Distil-Bert-Base-Uncased-Hf | ONNX | w8a16 | Snapdragon®
|
| 73 |
-
| Distil-Bert-Base-Uncased-Hf |
|
| 74 |
-
| Distil-Bert-Base-Uncased-Hf |
|
| 75 |
-
| Distil-Bert-Base-Uncased-Hf |
|
| 76 |
-
| Distil-Bert-Base-Uncased-Hf |
|
| 77 |
-
| Distil-Bert-Base-Uncased-Hf |
|
| 78 |
-
| Distil-Bert-Base-Uncased-Hf |
|
| 79 |
-
| Distil-Bert-Base-Uncased-Hf |
|
| 80 |
-
| Distil-Bert-Base-Uncased-Hf | QNN_DLC | float |
|
| 81 |
-
| Distil-Bert-Base-Uncased-Hf | QNN_DLC | float |
|
| 82 |
-
| Distil-Bert-Base-Uncased-Hf | QNN_DLC | float |
|
| 83 |
-
| Distil-Bert-Base-Uncased-Hf | QNN_DLC | float |
|
| 84 |
-
| Distil-Bert-Base-Uncased-Hf | QNN_DLC | float |
|
| 85 |
-
| Distil-Bert-Base-Uncased-Hf |
|
| 86 |
-
| Distil-Bert-Base-Uncased-Hf |
|
| 87 |
-
| Distil-Bert-Base-Uncased-Hf |
|
| 88 |
-
| Distil-Bert-Base-Uncased-Hf |
|
| 89 |
-
| Distil-Bert-Base-Uncased-Hf |
|
| 90 |
-
| Distil-Bert-Base-Uncased-Hf |
|
| 91 |
-
| Distil-Bert-Base-Uncased-Hf |
|
| 92 |
-
| Distil-Bert-Base-Uncased-Hf |
|
| 93 |
-
| Distil-Bert-Base-Uncased-Hf |
|
| 94 |
-
| Distil-Bert-Base-Uncased-Hf |
|
| 95 |
-
| Distil-Bert-Base-Uncased-Hf | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 5.228 ms | 0 - 357 MB | NPU
|
| 96 |
-
| Distil-Bert-Base-Uncased-Hf | QNN_DLC | w8a16 | Qualcomm® QCS8275 (Proxy) | 17.894 ms | 0 - 290 MB | NPU
|
| 97 |
-
| Distil-Bert-Base-Uncased-Hf | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 7.39 ms | 0 - 300 MB | NPU
|
| 98 |
-
| Distil-Bert-Base-Uncased-Hf | QNN_DLC | w8a16 | Qualcomm® SA8775P | 7.59 ms | 0 - 290 MB | NPU
|
| 99 |
-
| Distil-Bert-Base-Uncased-Hf | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 9.269 ms | 0 - 2 MB | NPU
|
| 100 |
-
| Distil-Bert-Base-Uncased-Hf | QNN_DLC | w8a16 | Qualcomm® SA7255P | 17.894 ms | 0 - 290 MB | NPU
|
| 101 |
-
| Distil-Bert-Base-Uncased-Hf | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 4.115 ms | 0 - 290 MB | NPU
|
| 102 |
-
| Distil-Bert-Base-Uncased-Hf | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 6.923 ms | 0 - 392 MB | NPU
|
| 103 |
-
| Distil-Bert-Base-Uncased-Hf | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 11.971 ms | 0 - 437 MB | NPU
|
| 104 |
-
| Distil-Bert-Base-Uncased-Hf | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 50.294 ms | 0 - 398 MB | NPU
|
| 105 |
-
| Distil-Bert-Base-Uncased-Hf | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 15.178 ms | 0 - 3 MB | NPU
|
| 106 |
-
| Distil-Bert-Base-Uncased-Hf | TFLITE | float | Qualcomm® SA8775P | 19.042 ms | 0 - 395 MB | NPU
|
| 107 |
-
| Distil-Bert-Base-Uncased-Hf | TFLITE | float | Qualcomm® QCS9075 | 19.533 ms | 0 - 176 MB | NPU
|
| 108 |
-
| Distil-Bert-Base-Uncased-Hf | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 36.857 ms | 0 - 408 MB | NPU
|
| 109 |
-
| Distil-Bert-Base-Uncased-Hf | TFLITE | float | Qualcomm® SA7255P | 50.294 ms | 0 - 398 MB | NPU
|
| 110 |
-
| Distil-Bert-Base-Uncased-Hf | TFLITE | float | Qualcomm® SA8295P | 23.576 ms | 0 - 368 MB | NPU
|
| 111 |
-
| Distil-Bert-Base-Uncased-Hf | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 8.635 ms | 0 - 388 MB | NPU
|
| 112 |
|
| 113 |
## License
|
| 114 |
* The license for the original implementation of Distil-Bert-Base-Uncased-Hf can be found
|
|
|
|
| 27 |
|
| 28 |
| Runtime | Precision | Chipset | SDK Versions | Download |
|
| 29 |
|---|---|---|---|---|
|
| 30 |
+
| ONNX | w8a16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/distil_bert_base_uncased_hf/releases/v0.50.2/distil_bert_base_uncased_hf-onnx-w8a16.zip)
|
| 31 |
+
| QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/distil_bert_base_uncased_hf/releases/v0.50.2/distil_bert_base_uncased_hf-qnn_dlc-float.zip)
|
| 32 |
+
| TFLITE | float | Universal | QAIRT 2.43, TFLite 2.19.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/distil_bert_base_uncased_hf/releases/v0.50.2/distil_bert_base_uncased_hf-tflite-float.zip)
|
|
|
|
|
|
|
| 33 |
|
| 34 |
For more device-specific assets and performance metrics, visit **[Distil-Bert-Base-Uncased-Hf on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/distil_bert_base_uncased_hf)**.
|
| 35 |
|
|
|
|
| 58 |
## Performance Summary
|
| 59 |
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|
| 60 |
|---|---|---|---|---|---|---
|
| 61 |
+
| Distil-Bert-Base-Uncased-Hf | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 5.028 ms | 0 - 304 MB | NPU
|
| 62 |
+
| Distil-Bert-Base-Uncased-Hf | ONNX | w8a16 | Snapdragon® X2 Elite | 5.049 ms | 111 - 111 MB | NPU
|
| 63 |
+
| Distil-Bert-Base-Uncased-Hf | ONNX | w8a16 | Snapdragon® X Elite | 12.018 ms | 112 - 112 MB | NPU
|
| 64 |
+
| Distil-Bert-Base-Uncased-Hf | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 8.395 ms | 0 - 401 MB | NPU
|
| 65 |
+
| Distil-Bert-Base-Uncased-Hf | ONNX | w8a16 | Qualcomm® QCS6490 | 1361.039 ms | 189 - 278 MB | CPU
|
| 66 |
+
| Distil-Bert-Base-Uncased-Hf | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 11.413 ms | 0 - 116 MB | NPU
|
| 67 |
+
| Distil-Bert-Base-Uncased-Hf | ONNX | w8a16 | Qualcomm® QCS9075 | 12.62 ms | 0 - 3 MB | NPU
|
| 68 |
+
| Distil-Bert-Base-Uncased-Hf | ONNX | w8a16 | Qualcomm® QCM6690 | 710.842 ms | 354 - 367 MB | CPU
|
| 69 |
+
| Distil-Bert-Base-Uncased-Hf | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 6.33 ms | 0 - 302 MB | NPU
|
| 70 |
+
| Distil-Bert-Base-Uncased-Hf | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 702.472 ms | 355 - 368 MB | CPU
|
| 71 |
+
| Distil-Bert-Base-Uncased-Hf | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 6.652 ms | 0 - 381 MB | NPU
|
| 72 |
+
| Distil-Bert-Base-Uncased-Hf | QNN_DLC | float | Snapdragon® X2 Elite | 7.364 ms | 0 - 0 MB | NPU
|
| 73 |
+
| Distil-Bert-Base-Uncased-Hf | QNN_DLC | float | Snapdragon® X Elite | 14.482 ms | 0 - 0 MB | NPU
|
| 74 |
+
| Distil-Bert-Base-Uncased-Hf | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 11.872 ms | 0 - 426 MB | NPU
|
| 75 |
+
| Distil-Bert-Base-Uncased-Hf | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 50.087 ms | 0 - 384 MB | NPU
|
| 76 |
+
| Distil-Bert-Base-Uncased-Hf | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 15.364 ms | 0 - 2 MB | NPU
|
| 77 |
+
| Distil-Bert-Base-Uncased-Hf | QNN_DLC | float | Qualcomm® SA8775P | 18.828 ms | 0 - 385 MB | NPU
|
| 78 |
+
| Distil-Bert-Base-Uncased-Hf | QNN_DLC | float | Qualcomm® QCS9075 | 19.163 ms | 2 - 4 MB | NPU
|
| 79 |
+
| Distil-Bert-Base-Uncased-Hf | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 21.112 ms | 0 - 408 MB | NPU
|
| 80 |
+
| Distil-Bert-Base-Uncased-Hf | QNN_DLC | float | Qualcomm® SA7255P | 50.087 ms | 0 - 384 MB | NPU
|
| 81 |
+
| Distil-Bert-Base-Uncased-Hf | QNN_DLC | float | Qualcomm® SA8295P | 23.647 ms | 0 - 363 MB | NPU
|
| 82 |
+
| Distil-Bert-Base-Uncased-Hf | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 8.194 ms | 0 - 382 MB | NPU
|
| 83 |
+
| Distil-Bert-Base-Uncased-Hf | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 6.935 ms | 0 - 393 MB | NPU
|
| 84 |
+
| Distil-Bert-Base-Uncased-Hf | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 11.944 ms | 0 - 434 MB | NPU
|
| 85 |
+
| Distil-Bert-Base-Uncased-Hf | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 50.388 ms | 0 - 398 MB | NPU
|
| 86 |
+
| Distil-Bert-Base-Uncased-Hf | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 15.202 ms | 0 - 3 MB | NPU
|
| 87 |
+
| Distil-Bert-Base-Uncased-Hf | TFLITE | float | Qualcomm® SA8775P | 19.1 ms | 0 - 396 MB | NPU
|
| 88 |
+
| Distil-Bert-Base-Uncased-Hf | TFLITE | float | Qualcomm® QCS9075 | 19.432 ms | 0 - 176 MB | NPU
|
| 89 |
+
| Distil-Bert-Base-Uncased-Hf | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 21.255 ms | 0 - 403 MB | NPU
|
| 90 |
+
| Distil-Bert-Base-Uncased-Hf | TFLITE | float | Qualcomm® SA7255P | 50.388 ms | 0 - 398 MB | NPU
|
| 91 |
+
| Distil-Bert-Base-Uncased-Hf | TFLITE | float | Qualcomm® SA8295P | 23.614 ms | 0 - 368 MB | NPU
|
| 92 |
+
| Distil-Bert-Base-Uncased-Hf | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 8.349 ms | 0 - 387 MB | NPU
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 93 |
|
| 94 |
## License
|
| 95 |
* The license for the original implementation of Distil-Bert-Base-Uncased-Hf can be found
|
release_assets.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"version":"0.50.
|
|
|
|
| 1 |
+
{"version":"0.50.2","precisions":{"float":{"universal_assets":{"qnn_dlc":{"tool_versions":{"qairt":"2.43.0.260127150333_193827"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/distil_bert_base_uncased_hf/releases/v0.50.2/distil_bert_base_uncased_hf-qnn_dlc-float.zip"},"tflite":{"tool_versions":{"qairt":"2.43.0.260127150333_193827","tflite":"2.19.1"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/distil_bert_base_uncased_hf/releases/v0.50.2/distil_bert_base_uncased_hf-tflite-float.zip"}}},"w8a16":{"universal_assets":{"onnx":{"tool_versions":{"qairt":"2.42.0.251225135753_193295","onnx_runtime":"1.24.3"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/distil_bert_base_uncased_hf/releases/v0.50.2/distil_bert_base_uncased_hf-onnx-w8a16.zip"}}}}}
|