Chua, Vui Seng
commited on
Commit
•
92be954
1
Parent(s):
51b709b
Add OpenVINO IR
Browse files
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ eval_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text
|
|
33 |
checkpoint-21750/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
|
34 |
checkpoint-21750/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
35 |
checkpoint-21750/optimizer.pt filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
checkpoint-21750/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
|
34 |
checkpoint-21750/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
35 |
checkpoint-21750/optimizer.pt filter=lfs diff=lfs merge=lfs -text
|
36 |
+
ir/*.bin filter=lfs diff=lfs merge=lfs -text
|
ir/bert-base-squadv1-block-pruning-hybrid-filled-lt-nncf-57.92sparse-qat-lt.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:396c6a21b573b86ab5926eeb59a820faffedfc989364ed2be45eeeb9506a45e5
|
3 |
+
size 44326840
|
ir/bert-base-squadv1-block-pruning-hybrid-filled-lt-nncf-57.92sparse-qat-lt.mapping
ADDED
The diff for this file is too large to render.
See raw diff
|
|
ir/bert-base-squadv1-block-pruning-hybrid-filled-lt-nncf-57.92sparse-qat-lt.xml
ADDED
The diff for this file is too large to render.
See raw diff
|
|
ir/mo.log
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
Model Optimizer arguments:
|
2 |
+
Common parameters:
|
3 |
+
- Path to the Input Model: /data1/vchua/tld-poc/repo/bert-base-squadv1-block-pruning-hybrid-filled-lt-nncf-57.92sparse-qat-lt/bert-base-squadv1-block-pruning-hybrid-filled-lt-nncf-57.92sparse-qat-lt.onnx
|
4 |
+
- Path for generated IR: /data1/vchua/tld-poc/repo/bert-base-squadv1-block-pruning-hybrid-filled-lt-nncf-57.92sparse-qat-lt/ir
|
5 |
+
- IR output name: bert-base-squadv1-block-pruning-hybrid-filled-lt-nncf-57.92sparse-qat-lt
|
6 |
+
- Log level: ERROR
|
7 |
+
- Batch: Not specified, inherited from the model
|
8 |
+
- Input layers: Not specified, inherited from the model
|
9 |
+
- Output layers: Not specified, inherited from the model
|
10 |
+
- Input shapes: Not specified, inherited from the model
|
11 |
+
- Mean values: Not specified
|
12 |
+
- Scale values: Not specified
|
13 |
+
- Scale factor: Not specified
|
14 |
+
- Precision of IR: FP32
|
15 |
+
- Enable fusing: True
|
16 |
+
- Enable grouped convolutions fusing: True
|
17 |
+
- Move mean values to preprocess section: None
|
18 |
+
- Reverse input channels: False
|
19 |
+
ONNX specific parameters:
|
20 |
+
- Inference Engine found in: /opt/intel/openvino/python/python3.6/openvino
|
21 |
+
Inference Engine version: 2021.4.2-3974-e2a469a3450-releases/2021/4
|
22 |
+
Model Optimizer version: 2021.4.2-3974-e2a469a3450-releases/2021/4
|
23 |
+
[ WARNING ] Convert data type of Parameter "input_ids" to int32
|
24 |
+
[ WARNING ] Convert data type of Parameter "attention_mask.1" to int32
|
25 |
+
[ WARNING ] Convert data type of Parameter "input.1" to int32
|
26 |
+
[ SUCCESS ] Generated IR version 10 model.
|
27 |
+
[ SUCCESS ] XML file: /data1/vchua/tld-poc/repo/bert-base-squadv1-block-pruning-hybrid-filled-lt-nncf-57.92sparse-qat-lt/ir/bert-base-squadv1-block-pruning-hybrid-filled-lt-nncf-57.92sparse-qat-lt.xml
|
28 |
+
[ SUCCESS ] BIN file: /data1/vchua/tld-poc/repo/bert-base-squadv1-block-pruning-hybrid-filled-lt-nncf-57.92sparse-qat-lt/ir/bert-base-squadv1-block-pruning-hybrid-filled-lt-nncf-57.92sparse-qat-lt.bin
|
29 |
+
[ SUCCESS ] Total execution time: 90.98 seconds.
|
30 |
+
[ SUCCESS ] Memory consumed: 1913 MB.
|