qaihm-bot commited on
Commit
94ed3da
·
verified ·
1 Parent(s): 1c898b6

See https://github.com/quic/ai-hub-models/releases/v0.31.0 for changelog.

Files changed (3) hide show
  1. .gitattributes +1 -0
  2. Beit.dlc +3 -0
  3. README.md +30 -30
.gitattributes CHANGED
@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  Beit.so filter=lfs diff=lfs merge=lfs -text
 
 
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  Beit.so filter=lfs diff=lfs merge=lfs -text
37
+ Beit.dlc filter=lfs diff=lfs merge=lfs -text
Beit.dlc ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a154bdfda0fa4763160ff4364935f60c6544d45a344cd3d19b1aedf2bebb623d
3
+ size 368435655
README.md CHANGED
@@ -35,35 +35,35 @@ More details on model performance across various devices, can be found
35
 
36
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
- | Beit | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 43.941 ms | 0 - 315 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
39
- | Beit | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 261.829 ms | 1 - 10 MB | NPU | Use Export Script |
40
- | Beit | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 18.2 ms | 0 - 324 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
41
- | Beit | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 26.7 ms | 1 - 309 MB | NPU | Use Export Script |
42
- | Beit | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 12.548 ms | 0 - 15 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
43
- | Beit | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 14.335 ms | 1 - 3 MB | NPU | Use Export Script |
44
- | Beit | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 15.588 ms | 0 - 315 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
45
- | Beit | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 17.043 ms | 1 - 10 MB | NPU | Use Export Script |
46
- | Beit | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 43.941 ms | 0 - 315 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
47
- | Beit | float | SA7255P ADP | Qualcomm® SA7255P | QNN | 261.829 ms | 1 - 10 MB | NPU | Use Export Script |
48
- | Beit | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 12.597 ms | 0 - 14 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
49
- | Beit | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN | 14.518 ms | 1 - 3 MB | NPU | Use Export Script |
50
- | Beit | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 20.447 ms | 0 - 307 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
51
- | Beit | float | SA8295P ADP | Qualcomm® SA8295P | QNN | 21.809 ms | 1 - 18 MB | NPU | Use Export Script |
52
- | Beit | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 12.188 ms | 0 - 18 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
53
- | Beit | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN | 14.352 ms | 1 - 3 MB | NPU | Use Export Script |
54
- | Beit | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 15.588 ms | 0 - 315 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
55
- | Beit | float | SA8775P ADP | Qualcomm® SA8775P | QNN | 17.043 ms | 1 - 10 MB | NPU | Use Export Script |
56
- | Beit | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 12.56 ms | 3 - 17 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
57
- | Beit | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 14.467 ms | 0 - 38 MB | NPU | Use Export Script |
58
- | Beit | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 14.91 ms | 0 - 429 MB | NPU | [Beit.onnx](https://huggingface.co/qualcomm/Beit/blob/main/Beit.onnx) |
59
- | Beit | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 8.581 ms | 0 - 339 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
60
- | Beit | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 9.855 ms | 1 - 342 MB | NPU | Use Export Script |
61
- | Beit | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 10.223 ms | 1 - 356 MB | NPU | [Beit.onnx](https://huggingface.co/qualcomm/Beit/blob/main/Beit.onnx) |
62
- | Beit | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 8.009 ms | 0 - 322 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
63
- | Beit | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 8.323 ms | 1 - 321 MB | NPU | Use Export Script |
64
- | Beit | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 8.308 ms | 1 - 326 MB | NPU | [Beit.onnx](https://huggingface.co/qualcomm/Beit/blob/main/Beit.onnx) |
65
- | Beit | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 14.895 ms | 1 - 1 MB | NPU | Use Export Script |
66
- | Beit | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 17.826 ms | 186 - 186 MB | NPU | [Beit.onnx](https://huggingface.co/qualcomm/Beit/blob/main/Beit.onnx) |
67
 
68
 
69
 
@@ -127,7 +127,7 @@ Profiling Results
127
  Beit
128
  Device : cs_8275 (ANDROID 14)
129
  Runtime : TFLITE
130
- Estimated inference time (ms) : 43.9
131
  Estimated peak memory usage (MB): [0, 315]
132
  Total # Ops : 569
133
  Compute Unit(s) : npu (569 ops) gpu (0 ops) cpu (0 ops)
 
35
 
36
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
+ | Beit | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 43.998 ms | 0 - 315 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
39
+ | Beit | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 44.762 ms | 0 - 326 MB | NPU | [Beit.dlc](https://huggingface.co/qualcomm/Beit/blob/main/Beit.dlc) |
40
+ | Beit | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 18.295 ms | 0 - 323 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
41
+ | Beit | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 26.778 ms | 0 - 310 MB | NPU | [Beit.dlc](https://huggingface.co/qualcomm/Beit/blob/main/Beit.dlc) |
42
+ | Beit | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 12.561 ms | 0 - 16 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
43
+ | Beit | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 14.594 ms | 0 - 34 MB | NPU | [Beit.dlc](https://huggingface.co/qualcomm/Beit/blob/main/Beit.dlc) |
44
+ | Beit | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 15.61 ms | 0 - 316 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
45
+ | Beit | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 17.202 ms | 0 - 327 MB | NPU | [Beit.dlc](https://huggingface.co/qualcomm/Beit/blob/main/Beit.dlc) |
46
+ | Beit | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 43.998 ms | 0 - 315 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
47
+ | Beit | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 44.762 ms | 0 - 326 MB | NPU | [Beit.dlc](https://huggingface.co/qualcomm/Beit/blob/main/Beit.dlc) |
48
+ | Beit | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 12.546 ms | 0 - 20 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
49
+ | Beit | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 14.563 ms | 0 - 32 MB | NPU | [Beit.dlc](https://huggingface.co/qualcomm/Beit/blob/main/Beit.dlc) |
50
+ | Beit | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 20.42 ms | 0 - 308 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
51
+ | Beit | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 21.8 ms | 1 - 315 MB | NPU | [Beit.dlc](https://huggingface.co/qualcomm/Beit/blob/main/Beit.dlc) |
52
+ | Beit | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 12.635 ms | 0 - 24 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
53
+ | Beit | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 14.634 ms | 0 - 33 MB | NPU | [Beit.dlc](https://huggingface.co/qualcomm/Beit/blob/main/Beit.dlc) |
54
+ | Beit | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 15.61 ms | 0 - 316 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
55
+ | Beit | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 17.202 ms | 0 - 327 MB | NPU | [Beit.dlc](https://huggingface.co/qualcomm/Beit/blob/main/Beit.dlc) |
56
+ | Beit | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 12.171 ms | 0 - 15 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
57
+ | Beit | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 14.571 ms | 0 - 33 MB | NPU | [Beit.dlc](https://huggingface.co/qualcomm/Beit/blob/main/Beit.dlc) |
58
+ | Beit | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 14.754 ms | 0 - 253 MB | NPU | [Beit.onnx](https://huggingface.co/qualcomm/Beit/blob/main/Beit.onnx) |
59
+ | Beit | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 8.649 ms | 0 - 337 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
60
+ | Beit | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 9.93 ms | 0 - 344 MB | NPU | [Beit.dlc](https://huggingface.co/qualcomm/Beit/blob/main/Beit.dlc) |
61
+ | Beit | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 10.261 ms | 1 - 354 MB | NPU | [Beit.onnx](https://huggingface.co/qualcomm/Beit/blob/main/Beit.onnx) |
62
+ | Beit | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 7.972 ms | 0 - 322 MB | NPU | [Beit.tflite](https://huggingface.co/qualcomm/Beit/blob/main/Beit.tflite) |
63
+ | Beit | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 9.398 ms | 1 - 320 MB | NPU | [Beit.dlc](https://huggingface.co/qualcomm/Beit/blob/main/Beit.dlc) |
64
+ | Beit | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 9.359 ms | 1 - 326 MB | NPU | [Beit.onnx](https://huggingface.co/qualcomm/Beit/blob/main/Beit.onnx) |
65
+ | Beit | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 18.125 ms | 1107 - 1107 MB | NPU | [Beit.dlc](https://huggingface.co/qualcomm/Beit/blob/main/Beit.dlc) |
66
+ | Beit | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 17.776 ms | 186 - 186 MB | NPU | [Beit.onnx](https://huggingface.co/qualcomm/Beit/blob/main/Beit.onnx) |
67
 
68
 
69
 
 
127
  Beit
128
  Device : cs_8275 (ANDROID 14)
129
  Runtime : TFLITE
130
+ Estimated inference time (ms) : 44.0
131
  Estimated peak memory usage (MB): [0, 315]
132
  Total # Ops : 569
133
  Compute Unit(s) : npu (569 ops) gpu (0 ops) cpu (0 ops)