Skip to content

Commit 548cf15

Browse files
author
Roman Donchenko
authored
Merge pull request openvinotoolkit#1219 from vshampor/vs/update_bert_ops_
Update BERT-large ops number
2 parents f19cda1 + b2d5339 commit 548cf15

File tree

3 files changed

+4
-4
lines changed

3 files changed

+4
-4
lines changed

models/intel/bert-large-uncased-whole-word-masking-squad-fp32-onnx-0001/description/bert-large-uncased-whole-word-masking-squad-fp32-onnx-0001.md

+1-1
Original file line numberDiff line numberDiff line change
@@ -10,7 +10,7 @@ Tokenization occurs using the BERT tokenizer (see the demo code for implementati
1010

1111
| Metric | Value |
1212
|-------------------|-----------------------|
13-
| GOps | 16.25 |
13+
| GOps | 246.93 |
1414
| MParams | 333.96 |
1515
| Source framework | PyTorch\* |
1616

models/intel/bert-large-uncased-whole-word-masking-squad-int8-onnx-0001/description/bert-large-uncased-whole-word-masking-squad-int8-onnx-0001.md

+1-1
Original file line numberDiff line numberDiff line change
@@ -12,7 +12,7 @@ The model has been further quantized to INT8 precision using quantization-aware
1212

1313
| Metric | Value |
1414
|-------------------|-----------------------|
15-
| GOps | 16.25 |
15+
| GOps | 246.93 |
1616
| MParams | 333.96 |
1717
| Source framework | PyTorch\* |
1818

models/intel/index.md

+2-2
Original file line numberDiff line numberDiff line change
@@ -238,8 +238,8 @@ Deep Learning compressed models
238238

239239
| Model Name| Complexity (GFLOPs)|Size (Mp)|
240240
|-----------|--------------------|---------|
241-
| [bert-large-uncased-whole-word-masking-squad-fp32-onnx-0001](./bert-large-uncased-whole-word-masking-squad-fp32-onnx-0001/description/bert-large-uncased-whole-word-masking-squad-fp32-onnx-0001.md) | 16.25 | 333.96 |
242-
| [bert-large-uncased-whole-word-masking-squad-int8-onnx-0001](./bert-large-uncased-whole-word-masking-squad-int8-onnx-0001/description/bert-large-uncased-whole-word-masking-squad-int8-onnx-0001.md) | 16.25 | 333.96 |
241+
| [bert-large-uncased-whole-word-masking-squad-fp32-onnx-0001](./bert-large-uncased-whole-word-masking-squad-fp32-onnx-0001/description/bert-large-uncased-whole-word-masking-squad-fp32-onnx-0001.md) | 246.93 | 333.96 |
242+
| [bert-large-uncased-whole-word-masking-squad-int8-onnx-0001](./bert-large-uncased-whole-word-masking-squad-int8-onnx-0001/description/bert-large-uncased-whole-word-masking-squad-int8-onnx-0001.md) | 246.93 | 333.96 |
243243
| [bert-small-uncased-whole-word-masking-squad-0001](./bert-small-uncased-whole-word-masking-squad-0001/description/bert-small-uncased-whole-word-masking-squad-0001.md) | 23.9 | 57.94 |
244244

245245

0 commit comments

Comments
 (0)