qaihm-bot commited on
Commit
4cd79a1
·
verified ·
1 Parent(s): 30d6253

See https://github.com/quic/ai-hub-models/releases/v0.42.0 for changelog.

Files changed (3) hide show
  1. Beit_float.dlc +2 -2
  2. Beit_float.onnx.zip +2 -2
  3. README.md +33 -33
Beit_float.dlc CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:47903c4e7d97aa5231f916ddf2968f2877728470745b5f6729fd5e996414c11d
3
- size 368438300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10b98e408d0ea137c4dd4c716917e5af4ee66563da26d2931aa810d9f8a2c3fd
3
+ size 368438420
Beit_float.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:428ccca31e43036a099008ba34f6c4e6a86bd21ea603850c105e6a808b4812e1
3
- size 218716832
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ec824a83d481525f1bd89bd9d971f8b5ad95a9e27cd93cdf944efcccf5f75c5
3
+ size 218717146
README.md CHANGED
@@ -36,36 +36,36 @@ More details on model performance across various devices, can be found
36
 
37
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
39
- | Beit | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 40.298 ms | 0 - 310 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
40
- | Beit | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 42.538 ms | 0 - 320 MB | NPU | [Beit.dlc](https://huggingface.co/qualcomm/Beit/blob/main/Beit.dlc) |
41
- | Beit | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 15.224 ms | 0 - 320 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
42
- | Beit | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 23.477 ms | 1 - 318 MB | NPU | [Beit.dlc](https://huggingface.co/qualcomm/Beit/blob/main/Beit.dlc) |
43
- | Beit | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 9.978 ms | 0 - 17 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
44
- | Beit | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 12.341 ms | 0 - 26 MB | NPU | [Beit.dlc](https://huggingface.co/qualcomm/Beit/blob/main/Beit.dlc) |
45
- | Beit | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 13.632 ms | 1 - 31 MB | NPU | [Beit.onnx.zip](https://huggingface.co/qualcomm/Beit/blob/main/Beit.onnx.zip) |
46
- | Beit | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 13.345 ms | 0 - 310 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
47
- | Beit | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 14.956 ms | 1 - 322 MB | NPU | [Beit.dlc](https://huggingface.co/qualcomm/Beit/blob/main/Beit.dlc) |
48
- | Beit | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 40.298 ms | 0 - 310 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
49
- | Beit | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 42.538 ms | 0 - 320 MB | NPU | [Beit.dlc](https://huggingface.co/qualcomm/Beit/blob/main/Beit.dlc) |
50
- | Beit | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 9.992 ms | 0 - 18 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
51
- | Beit | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 12.354 ms | 0 - 30 MB | NPU | [Beit.dlc](https://huggingface.co/qualcomm/Beit/blob/main/Beit.dlc) |
52
- | Beit | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 17.33 ms | 0 - 304 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
53
- | Beit | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 19.507 ms | 1 - 318 MB | NPU | [Beit.dlc](https://huggingface.co/qualcomm/Beit/blob/main/Beit.dlc) |
54
- | Beit | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 9.965 ms | 0 - 15 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
55
- | Beit | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 12.348 ms | 0 - 31 MB | NPU | [Beit.dlc](https://huggingface.co/qualcomm/Beit/blob/main/Beit.dlc) |
56
- | Beit | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 13.345 ms | 0 - 310 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
57
- | Beit | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 14.956 ms | 1 - 322 MB | NPU | [Beit.dlc](https://huggingface.co/qualcomm/Beit/blob/main/Beit.dlc) |
58
- | Beit | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 7.083 ms | 0 - 324 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
59
- | Beit | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 8.278 ms | 1 - 331 MB | NPU | [Beit.dlc](https://huggingface.co/qualcomm/Beit/blob/main/Beit.dlc) |
60
- | Beit | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 9.853 ms | 0 - 351 MB | NPU | [Beit.onnx.zip](https://huggingface.co/qualcomm/Beit/blob/main/Beit.onnx.zip) |
61
- | Beit | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 5.098 ms | 0 - 312 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
62
- | Beit | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 6.42 ms | 1 - 311 MB | NPU | [Beit.dlc](https://huggingface.co/qualcomm/Beit/blob/main/Beit.dlc) |
63
- | Beit | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 7.141 ms | 0 - 326 MB | NPU | [Beit.onnx.zip](https://huggingface.co/qualcomm/Beit/blob/main/Beit.onnx.zip) |
64
- | Beit | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 4.428 ms | 0 - 309 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
65
- | Beit | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 5.17 ms | 1 - 308 MB | NPU | [Beit.dlc](https://huggingface.co/qualcomm/Beit/blob/main/Beit.dlc) |
66
  | Beit | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 5.988 ms | 1 - 317 MB | NPU | [Beit.onnx.zip](https://huggingface.co/qualcomm/Beit/blob/main/Beit.onnx.zip) |
67
- | Beit | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 13.066 ms | 1075 - 1075 MB | NPU | [Beit.dlc](https://huggingface.co/qualcomm/Beit/blob/main/Beit.dlc) |
68
- | Beit | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 14.824 ms | 186 - 186 MB | NPU | [Beit.onnx.zip](https://huggingface.co/qualcomm/Beit/blob/main/Beit.onnx.zip) |
69
 
70
 
71
 
@@ -80,9 +80,9 @@ pip install "qai-hub-models[beit]"
80
  ```
81
 
82
 
83
- ## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
84
 
85
- Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your
86
  Qualcomm® ID. Once signed in navigate to `Account -> Settings -> API Token`.
87
 
88
  With this API token, you can configure your client to run models on the cloud
@@ -90,7 +90,7 @@ hosted devices.
90
  ```bash
91
  qai-hub configure --api_token API_TOKEN
92
  ```
93
- Navigate to [docs](https://app.aihub.qualcomm.com/docs/) for more information.
94
 
95
 
96
 
@@ -201,7 +201,7 @@ With the output of the model, you can compute like PSNR, relative errors or
201
  spot check the output with expected output.
202
 
203
  **Note**: This on-device profiling and inference requires access to Qualcomm®
204
- AI Hub. [Sign up for access](https://myaccount.qualcomm.com/signup).
205
 
206
 
207
 
 
36
 
37
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
39
+ | Beit | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 40.315 ms | 0 - 309 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
40
+ | Beit | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 42.174 ms | 0 - 320 MB | NPU | [Beit.dlc](https://huggingface.co/qualcomm/Beit/blob/main/Beit.dlc) |
41
+ | Beit | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 15.332 ms | 0 - 320 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
42
+ | Beit | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 23.28 ms | 1 - 316 MB | NPU | [Beit.dlc](https://huggingface.co/qualcomm/Beit/blob/main/Beit.dlc) |
43
+ | Beit | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 9.969 ms | 0 - 16 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
44
+ | Beit | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 11.989 ms | 0 - 29 MB | NPU | [Beit.dlc](https://huggingface.co/qualcomm/Beit/blob/main/Beit.dlc) |
45
+ | Beit | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 13.594 ms | 1 - 25 MB | NPU | [Beit.onnx.zip](https://huggingface.co/qualcomm/Beit/blob/main/Beit.onnx.zip) |
46
+ | Beit | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 13.434 ms | 0 - 311 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
47
+ | Beit | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 14.918 ms | 1 - 321 MB | NPU | [Beit.dlc](https://huggingface.co/qualcomm/Beit/blob/main/Beit.dlc) |
48
+ | Beit | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 40.315 ms | 0 - 309 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
49
+ | Beit | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 42.174 ms | 0 - 320 MB | NPU | [Beit.dlc](https://huggingface.co/qualcomm/Beit/blob/main/Beit.dlc) |
50
+ | Beit | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 9.974 ms | 0 - 15 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
51
+ | Beit | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 12.007 ms | 0 - 30 MB | NPU | [Beit.dlc](https://huggingface.co/qualcomm/Beit/blob/main/Beit.dlc) |
52
+ | Beit | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 17.349 ms | 0 - 305 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
53
+ | Beit | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 19.762 ms | 1 - 322 MB | NPU | [Beit.dlc](https://huggingface.co/qualcomm/Beit/blob/main/Beit.dlc) |
54
+ | Beit | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 10.42 ms | 0 - 16 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
55
+ | Beit | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 12.026 ms | 0 - 30 MB | NPU | [Beit.dlc](https://huggingface.co/qualcomm/Beit/blob/main/Beit.dlc) |
56
+ | Beit | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 13.434 ms | 0 - 311 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
57
+ | Beit | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 14.918 ms | 1 - 321 MB | NPU | [Beit.dlc](https://huggingface.co/qualcomm/Beit/blob/main/Beit.dlc) |
58
+ | Beit | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 7.099 ms | 0 - 327 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
59
+ | Beit | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 8.181 ms | 0 - 338 MB | NPU | [Beit.dlc](https://huggingface.co/qualcomm/Beit/blob/main/Beit.dlc) |
60
+ | Beit | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 9.838 ms | 0 - 350 MB | NPU | [Beit.onnx.zip](https://huggingface.co/qualcomm/Beit/blob/main/Beit.onnx.zip) |
61
+ | Beit | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 5.167 ms | 0 - 311 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
62
+ | Beit | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 6.962 ms | 1 - 314 MB | NPU | [Beit.dlc](https://huggingface.co/qualcomm/Beit/blob/main/Beit.dlc) |
63
+ | Beit | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 7.1 ms | 0 - 325 MB | NPU | [Beit.onnx.zip](https://huggingface.co/qualcomm/Beit/blob/main/Beit.onnx.zip) |
64
+ | Beit | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 4.436 ms | 0 - 310 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
65
+ | Beit | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 5.229 ms | 1 - 311 MB | NPU | [Beit.dlc](https://huggingface.co/qualcomm/Beit/blob/main/Beit.dlc) |
66
  | Beit | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 5.988 ms | 1 - 317 MB | NPU | [Beit.onnx.zip](https://huggingface.co/qualcomm/Beit/blob/main/Beit.onnx.zip) |
67
+ | Beit | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 12.694 ms | 1129 - 1129 MB | NPU | [Beit.dlc](https://huggingface.co/qualcomm/Beit/blob/main/Beit.dlc) |
68
+ | Beit | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 14.808 ms | 186 - 186 MB | NPU | [Beit.onnx.zip](https://huggingface.co/qualcomm/Beit/blob/main/Beit.onnx.zip) |
69
 
70
 
71
 
 
80
  ```
81
 
82
 
83
+ ## Configure Qualcomm® AI Hub Workbench to run this model on a cloud-hosted device
84
 
85
+ Sign-in to [Qualcomm® AI Hub Workbench](https://workbench.aihub.qualcomm.com/) with your
86
  Qualcomm® ID. Once signed in navigate to `Account -> Settings -> API Token`.
87
 
88
  With this API token, you can configure your client to run models on the cloud
 
90
  ```bash
91
  qai-hub configure --api_token API_TOKEN
92
  ```
93
+ Navigate to [docs](https://workbench.aihub.qualcomm.com/docs/) for more information.
94
 
95
 
96
 
 
201
  spot check the output with expected output.
202
 
203
  **Note**: This on-device profiling and inference requires access to Qualcomm®
204
+ AI Hub Workbench. [Sign up for access](https://myaccount.qualcomm.com/signup).
205
 
206
 
207