Chua, Vui Seng
commited on
Commit
•
8ff860f
1
Parent(s):
92be954
Add tile-aligned pytorch_model, onnx, ir
Browse files- bert-base-squadv1-block-pruning-hybrid-filled-lt-nncf-57.92sparse-qat-lt-tilealigned.onnx +3 -0
- checkpoint-21750-tilealigned/config.json +115 -0
- checkpoint-21750-tilealigned/optimizer.pt +3 -0
- checkpoint-21750-tilealigned/pytorch_model.bin +3 -0
- checkpoint-21750-tilealigned/rng_state.pth +3 -0
- checkpoint-21750-tilealigned/scheduler.pt +3 -0
- checkpoint-21750-tilealigned/special_tokens_map.json +1 -0
- checkpoint-21750-tilealigned/tokenizer.json +0 -0
- checkpoint-21750-tilealigned/tokenizer_config.json +1 -0
- checkpoint-21750-tilealigned/trainer_state.json +3 -0
- checkpoint-21750-tilealigned/training_args.bin +3 -0
- checkpoint-21750-tilealigned/vocab.txt +0 -0
- ir-tilealigned/bert-base-squadv1-block-pruning-hybrid-filled-lt-nncf-57.92sparse-qat-lt-tilealigned.bin +3 -0
- ir-tilealigned/bert-base-squadv1-block-pruning-hybrid-filled-lt-nncf-57.92sparse-qat-lt-tilealigned.mapping +0 -0
- ir-tilealigned/bert-base-squadv1-block-pruning-hybrid-filled-lt-nncf-57.92sparse-qat-lt-tilealigned.xml +0 -0
- ir-tilealigned/mo.log +30 -0
bert-base-squadv1-block-pruning-hybrid-filled-lt-nncf-57.92sparse-qat-lt-tilealigned.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41efed3c2f85e7d71d619c8f80b39b88eac754472d792bc52b1c59e33d5273e7
|
3 |
+
size 177575143
|
checkpoint-21750-tilealigned/config.json
ADDED
@@ -0,0 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/data1/vchua/tld-poc/bert-base-squadv1-local-hybrid-compiled",
|
3 |
+
"architectures": [
|
4 |
+
"NNCFNetwork"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"pruned_heads": {
|
22 |
+
"0": [
|
23 |
+
0,
|
24 |
+
2,
|
25 |
+
4,
|
26 |
+
5,
|
27 |
+
6,
|
28 |
+
7,
|
29 |
+
11
|
30 |
+
],
|
31 |
+
"1": [
|
32 |
+
0,
|
33 |
+
2,
|
34 |
+
3,
|
35 |
+
5,
|
36 |
+
6,
|
37 |
+
7,
|
38 |
+
8
|
39 |
+
],
|
40 |
+
"2": [
|
41 |
+
8,
|
42 |
+
4,
|
43 |
+
7
|
44 |
+
],
|
45 |
+
"3": [
|
46 |
+
2,
|
47 |
+
4,
|
48 |
+
6
|
49 |
+
],
|
50 |
+
"4": [
|
51 |
+
1,
|
52 |
+
2,
|
53 |
+
11
|
54 |
+
],
|
55 |
+
"5": [
|
56 |
+
1,
|
57 |
+
2,
|
58 |
+
5,
|
59 |
+
6,
|
60 |
+
7,
|
61 |
+
11
|
62 |
+
],
|
63 |
+
"6": [
|
64 |
+
0,
|
65 |
+
2,
|
66 |
+
3,
|
67 |
+
7,
|
68 |
+
10
|
69 |
+
],
|
70 |
+
"7": [
|
71 |
+
1,
|
72 |
+
3,
|
73 |
+
6,
|
74 |
+
7,
|
75 |
+
11
|
76 |
+
],
|
77 |
+
"8": [
|
78 |
+
0,
|
79 |
+
3,
|
80 |
+
4,
|
81 |
+
5,
|
82 |
+
8
|
83 |
+
],
|
84 |
+
"9": [
|
85 |
+
1,
|
86 |
+
3,
|
87 |
+
4,
|
88 |
+
5,
|
89 |
+
7,
|
90 |
+
9,
|
91 |
+
10
|
92 |
+
],
|
93 |
+
"10": [
|
94 |
+
1,
|
95 |
+
4,
|
96 |
+
5,
|
97 |
+
6,
|
98 |
+
7,
|
99 |
+
8
|
100 |
+
],
|
101 |
+
"11": [
|
102 |
+
4,
|
103 |
+
5,
|
104 |
+
7,
|
105 |
+
8,
|
106 |
+
10,
|
107 |
+
11
|
108 |
+
]
|
109 |
+
},
|
110 |
+
"torch_dtype": "float32",
|
111 |
+
"transformers_version": "4.9.1",
|
112 |
+
"type_vocab_size": 2,
|
113 |
+
"use_cache": true,
|
114 |
+
"vocab_size": 30522
|
115 |
+
}
|
checkpoint-21750-tilealigned/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:502d61b24766935d2d0b196d147d27f1f98bb63acb74c00544ff492f201d0276
|
3 |
+
size 353016429
|
checkpoint-21750-tilealigned/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8521138bce93eb71a564b5d4200616bc005419839e62416c0efced9b4ae30cda
|
3 |
+
size 259744785
|
checkpoint-21750-tilealigned/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a94692d497d62f266652bbbc4a1a07abeff70560b00b87755fc4710f1be4ee3f
|
3 |
+
size 14503
|
checkpoint-21750-tilealigned/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e602f6bb85fa11ee4dd91991bfc4d199ca92f7b80f61a8a792f4315172ceab0b
|
3 |
+
size 623
|
checkpoint-21750-tilealigned/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
checkpoint-21750-tilealigned/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-21750-tilealigned/tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "/data1/vchua/tld-poc/bert-base-squadv1-local-hybrid-compiled", "tokenizer_class": "BertTokenizer"}
|
checkpoint-21750-tilealigned/trainer_state.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08d9f173574b7831a17f3e025503da75a134a1ea02db1d3b657468f835161f03
|
3 |
+
size 11398921
|
checkpoint-21750-tilealigned/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75b97d5ad5c00837e2ab0e008d14c563eb384f79123ee707c385a7929abfb8d9
|
3 |
+
size 3439
|
checkpoint-21750-tilealigned/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
ir-tilealigned/bert-base-squadv1-block-pruning-hybrid-filled-lt-nncf-57.92sparse-qat-lt-tilealigned.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:07454e37766e40482ab3f0207c80233686ec934c4e8b7161e5164ef6df430eee
|
3 |
+
size 44591720
|
ir-tilealigned/bert-base-squadv1-block-pruning-hybrid-filled-lt-nncf-57.92sparse-qat-lt-tilealigned.mapping
ADDED
The diff for this file is too large to render.
See raw diff
|
|
ir-tilealigned/bert-base-squadv1-block-pruning-hybrid-filled-lt-nncf-57.92sparse-qat-lt-tilealigned.xml
ADDED
The diff for this file is too large to render.
See raw diff
|
|
ir-tilealigned/mo.log
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
Model Optimizer arguments:
|
2 |
+
Common parameters:
|
3 |
+
- Path to the Input Model: /home/openvino/tile/hybrid-tile-aligned-int8-eval/bert-base-squadv1-block-pruning-hybrid-filled-lt-nncf-57.92sparse-qat-lt-tilealigned.onnx
|
4 |
+
- Path for generated IR: /home/openvino/tile/hybrid-tile-aligned-int8-eval/ir
|
5 |
+
- IR output name: bert-base-squadv1-block-pruning-hybrid-filled-lt-nncf-57.92sparse-qat-lt-tilealigned
|
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: /home/openvino/tile/hybrid-tile-aligned-int8-eval/ir/bert-base-squadv1-block-pruning-hybrid-filled-lt-nncf-57.92sparse-qat-lt-tilealigned.xml
|
28 |
+
[ SUCCESS ] BIN file: /home/openvino/tile/hybrid-tile-aligned-int8-eval/ir/bert-base-squadv1-block-pruning-hybrid-filled-lt-nncf-57.92sparse-qat-lt-tilealigned.bin
|
29 |
+
[ SUCCESS ] Total execution time: 78.71 seconds.
|
30 |
+
[ SUCCESS ] Memory consumed: 1920 MB.
|