commit files to HF hub
Browse files- compressed_graph.dot +0 -0
- openvino_config.json +60 -0
- original_graph.dot +0 -0
compressed_graph.dot
ADDED
The diff for this file is too large to render.
See raw diff
|
|
openvino_config.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"compression": {
|
3 |
+
"algorithm": "quantization",
|
4 |
+
"export_to_onnx_standard_ops": false,
|
5 |
+
"ignored_scopes": [
|
6 |
+
"{re}.*Embedding*",
|
7 |
+
"{re}.*__add___[0-1]",
|
8 |
+
"{re}.*layer_norm_0",
|
9 |
+
"{re}.*matmul_1",
|
10 |
+
"{re}.*__truediv__*"
|
11 |
+
],
|
12 |
+
"initializer": {
|
13 |
+
"batchnorm_adaptation": {
|
14 |
+
"num_bn_adaptation_samples": 0
|
15 |
+
},
|
16 |
+
"range": {
|
17 |
+
"num_init_samples": 300,
|
18 |
+
"type": "mean_min_max"
|
19 |
+
}
|
20 |
+
},
|
21 |
+
"overflow_fix": "disable",
|
22 |
+
"preset": "mixed",
|
23 |
+
"scope_overrides": {
|
24 |
+
"activations": {
|
25 |
+
"{re}.*matmul_0": {
|
26 |
+
"mode": "symmetric"
|
27 |
+
}
|
28 |
+
}
|
29 |
+
}
|
30 |
+
},
|
31 |
+
"input_info": [
|
32 |
+
{
|
33 |
+
"keyword": "input_ids",
|
34 |
+
"sample_size": [
|
35 |
+
8,
|
36 |
+
160
|
37 |
+
],
|
38 |
+
"type": "long"
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"keyword": "token_type_ids",
|
42 |
+
"sample_size": [
|
43 |
+
8,
|
44 |
+
160
|
45 |
+
],
|
46 |
+
"type": "long"
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"keyword": "attention_mask",
|
50 |
+
"sample_size": [
|
51 |
+
8,
|
52 |
+
160
|
53 |
+
],
|
54 |
+
"type": "long"
|
55 |
+
}
|
56 |
+
],
|
57 |
+
"optimum_version": "1.8.3.dev0",
|
58 |
+
"save_onnx_model": false,
|
59 |
+
"transformers_version": "4.27.4"
|
60 |
+
}
|
original_graph.dot
ADDED
The diff for this file is too large to render.
See raw diff
|
|