Hugging Face's logo

qualcomm
/
OpenAI-Clip

Image Classification
PyTorch
foundation
android
Model card Files
xet
Community
1
qaihm-bot commited on
Commit
cd0c65f
·
verified ·
1 Parent(s): 50089e6

v0.42.0

Browse files

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

Files changed (3) hide show
  1. OpenAI-Clip_float.dlc +2 -2
  2. OpenAI-Clip_float.onnx.zip +2 -2
  3. README.md +35 -36
OpenAI-Clip_float.dlc CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5fb0e364e64bd69965c262cf6a9a765b8727024b664b217e153f5a0180a964a8
3
- size 599175572
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a140ce8cd5ecebf9e1c9733e336012ee792b707ef167986a02296bd0496f3d66
3
+ size 599439284
OpenAI-Clip_float.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d6da35e52ac9e55f99379d28729e10561b401b24fd2a6a6b78daf4ce399c35a3
3
- size 406338278
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25b1a84b9b175045df4a31be57cdc613653cf0fa071dfd4f796c1f944fc47151
3
+ size 406345249
README.md CHANGED
@@ -37,36 +37,36 @@ More details on model performance across various devices, can be found
37
 
38
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
39
  |---|---|---|---|---|---|---|---|---|
40
- | OpenAI-Clip | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 63.06 ms | 0 - 494 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
41
- | OpenAI-Clip | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 59.944 ms | 1 - 568 MB | NPU | [OpenAI-Clip.dlc](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.dlc) |
42
- | OpenAI-Clip | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 25.379 ms | 0 - 502 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
43
- | OpenAI-Clip | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 26.32 ms | 0 - 528 MB | NPU | [OpenAI-Clip.dlc](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.dlc) |
44
- | OpenAI-Clip | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 22.346 ms | 0 - 29 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
45
- | OpenAI-Clip | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 21.443 ms | 0 - 43 MB | NPU | [OpenAI-Clip.dlc](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.dlc) |
46
- | OpenAI-Clip | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 22.001 ms | 1 - 29 MB | NPU | [OpenAI-Clip.onnx.zip](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.onnx.zip) |
47
- | OpenAI-Clip | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 25.238 ms | 0 - 493 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
48
- | OpenAI-Clip | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 24.111 ms | 1 - 568 MB | NPU | [OpenAI-Clip.dlc](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.dlc) |
49
- | OpenAI-Clip | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 63.06 ms | 0 - 494 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
50
- | OpenAI-Clip | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 59.944 ms | 1 - 568 MB | NPU | [OpenAI-Clip.dlc](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.dlc) |
51
- | OpenAI-Clip | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 22.107 ms | 0 - 28 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
52
- | OpenAI-Clip | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 21.238 ms | 0 - 39 MB | NPU | [OpenAI-Clip.dlc](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.dlc) |
53
- | OpenAI-Clip | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 28.421 ms | 0 - 485 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
54
- | OpenAI-Clip | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 26.825 ms | 1 - 558 MB | NPU | [OpenAI-Clip.dlc](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.dlc) |
55
- | OpenAI-Clip | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 22.106 ms | 0 - 34 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
56
- | OpenAI-Clip | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 21.328 ms | 0 - 40 MB | NPU | [OpenAI-Clip.dlc](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.dlc) |
57
- | OpenAI-Clip | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 25.238 ms | 0 - 493 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
58
- | OpenAI-Clip | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 24.111 ms | 1 - 568 MB | NPU | [OpenAI-Clip.dlc](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.dlc) |
59
- | OpenAI-Clip | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 15.323 ms | 0 - 500 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
60
- | OpenAI-Clip | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 15.354 ms | 1 - 575 MB | NPU | [OpenAI-Clip.dlc](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.dlc) |
61
- | OpenAI-Clip | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 15.187 ms | 15 - 585 MB | NPU | [OpenAI-Clip.onnx.zip](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.onnx.zip) |
62
- | OpenAI-Clip | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 12.309 ms | 0 - 493 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
63
- | OpenAI-Clip | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 11.779 ms | 0 - 549 MB | NPU | [OpenAI-Clip.dlc](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.dlc) |
64
- | OpenAI-Clip | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 12.223 ms | 0 - 550 MB | NPU | [OpenAI-Clip.onnx.zip](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.onnx.zip) |
65
- | OpenAI-Clip | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 9.957 ms | 0 - 491 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
66
- | OpenAI-Clip | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 9.625 ms | 0 - 497 MB | NPU | [OpenAI-Clip.dlc](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.dlc) |
67
- | OpenAI-Clip | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 10.125 ms | 0 - 498 MB | NPU | [OpenAI-Clip.onnx.zip](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.onnx.zip) |
68
- | OpenAI-Clip | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 21.948 ms | 1478 - 1478 MB | NPU | [OpenAI-Clip.dlc](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.dlc) |
69
- | OpenAI-Clip | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 22.605 ms | 295 - 295 MB | NPU | [OpenAI-Clip.onnx.zip](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.onnx.zip) |
70
 
71
 
72
 
@@ -76,14 +76,13 @@ More details on model performance across various devices, can be found
76
 
77
  Install the package via pip:
78
  ```bash
79
- # NOTE: 3.10 <= PYTHON_VERSION < 3.14 is supported.
80
- pip install "qai-hub-models[openai-clip]"
81
  ```
82
 
83
 
84
- ## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
85
 
86
- Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your
87
  Qualcomm® ID. Once signed in navigate to `Account -> Settings -> API Token`.
88
 
89
  With this API token, you can configure your client to run models on the cloud
@@ -91,7 +90,7 @@ hosted devices.
91
  ```bash
92
  qai-hub configure --api_token API_TOKEN
93
  ```
94
- Navigate to [docs](https://app.aihub.qualcomm.com/docs/) for more information.
95
 
96
 
97
 
@@ -202,7 +201,7 @@ With the output of the model, you can compute like PSNR, relative errors or
202
  spot check the output with expected output.
203
 
204
  **Note**: This on-device profiling and inference requires access to Qualcomm®
205
- AI Hub. [Sign up for access](https://myaccount.qualcomm.com/signup).
206
 
207
 
208
 
 
37
 
38
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
39
  |---|---|---|---|---|---|---|---|---|
40
+ | OpenAI-Clip | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 62.355 ms | 0 - 495 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
41
+ | OpenAI-Clip | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 59.235 ms | 1 - 569 MB | NPU | [OpenAI-Clip.dlc](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.dlc) |
42
+ | OpenAI-Clip | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 24.652 ms | 0 - 499 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
43
+ | OpenAI-Clip | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 25.491 ms | 0 - 527 MB | NPU | [OpenAI-Clip.dlc](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.dlc) |
44
+ | OpenAI-Clip | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 21.786 ms | 0 - 29 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
45
+ | OpenAI-Clip | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 20.629 ms | 0 - 33 MB | NPU | [OpenAI-Clip.dlc](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.dlc) |
46
+ | OpenAI-Clip | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 22.4 ms | 1 - 37 MB | NPU | [OpenAI-Clip.onnx.zip](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.onnx.zip) |
47
+ | OpenAI-Clip | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 24.838 ms | 0 - 495 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
48
+ | OpenAI-Clip | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 108.559 ms | 1 - 569 MB | NPU | [OpenAI-Clip.dlc](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.dlc) |
49
+ | OpenAI-Clip | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 62.355 ms | 0 - 495 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
50
+ | OpenAI-Clip | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 59.235 ms | 1 - 569 MB | NPU | [OpenAI-Clip.dlc](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.dlc) |
51
+ | OpenAI-Clip | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 21.79 ms | 0 - 35 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
52
+ | OpenAI-Clip | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 20.713 ms | 0 - 39 MB | NPU | [OpenAI-Clip.dlc](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.dlc) |
53
+ | OpenAI-Clip | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 28.129 ms | 0 - 487 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
54
+ | OpenAI-Clip | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 26.41 ms | 0 - 556 MB | NPU | [OpenAI-Clip.dlc](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.dlc) |
55
+ | OpenAI-Clip | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 21.69 ms | 0 - 27 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
56
+ | OpenAI-Clip | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 20.779 ms | 0 - 28 MB | NPU | [OpenAI-Clip.dlc](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.dlc) |
57
+ | OpenAI-Clip | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 24.838 ms | 0 - 495 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
58
+ | OpenAI-Clip | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 108.559 ms | 1 - 569 MB | NPU | [OpenAI-Clip.dlc](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.dlc) |
59
+ | OpenAI-Clip | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 14.964 ms | 0 - 501 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
60
+ | OpenAI-Clip | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 14.6 ms | 1 - 575 MB | NPU | [OpenAI-Clip.dlc](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.dlc) |
61
+ | OpenAI-Clip | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 15.743 ms | 0 - 574 MB | NPU | [OpenAI-Clip.onnx.zip](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.onnx.zip) |
62
+ | OpenAI-Clip | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 11.878 ms | 0 - 496 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
63
+ | OpenAI-Clip | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 11.455 ms | 0 - 551 MB | NPU | [OpenAI-Clip.dlc](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.dlc) |
64
+ | OpenAI-Clip | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 12.296 ms | 0 - 551 MB | NPU | [OpenAI-Clip.onnx.zip](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.onnx.zip) |
65
+ | OpenAI-Clip | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 9.267 ms | 0 - 493 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
66
+ | OpenAI-Clip | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 9.309 ms | 0 - 496 MB | NPU | [OpenAI-Clip.dlc](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.dlc) |
67
+ | OpenAI-Clip | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 10.107 ms | 0 - 499 MB | NPU | [OpenAI-Clip.onnx.zip](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.onnx.zip) |
68
+ | OpenAI-Clip | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 21.684 ms | 1443 - 1443 MB | NPU | [OpenAI-Clip.dlc](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.dlc) |
69
+ | OpenAI-Clip | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 22.723 ms | 295 - 295 MB | NPU | [OpenAI-Clip.onnx.zip](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.onnx.zip) |
70
 
71
 
72
 
 
76
 
77
  Install the package via pip:
78
  ```bash
79
+ pip install qai-hub-models
 
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