Upload 8 files
Browse files- config.json +1 -2
- onnx/model.onnx +3 -0
- onnx/model_quantized.onnx +3 -0
- quantize_config.json +30 -0
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"BertModel"
|
5 |
],
|
@@ -23,7 +23,6 @@
|
|
23 |
"num_hidden_layers": 3,
|
24 |
"pad_token_id": 0,
|
25 |
"position_embedding_type": "absolute",
|
26 |
-
"torch_dtype": "float32",
|
27 |
"transformers_version": "4.40.1",
|
28 |
"type_vocab_size": 2,
|
29 |
"use_cache": true,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "Mihaiii/Giratina",
|
3 |
"architectures": [
|
4 |
"BertModel"
|
5 |
],
|
|
|
23 |
"num_hidden_layers": 3,
|
24 |
"pad_token_id": 0,
|
25 |
"position_embedding_type": "absolute",
|
|
|
26 |
"transformers_version": "4.40.1",
|
27 |
"type_vocab_size": 2,
|
28 |
"use_cache": true,
|
onnx/model.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9d0840ab8b1ff2dab8c6f6252a2a6c07a43701746e78d7f079b47acdf36bdd2
|
3 |
+
size 69035106
|
onnx/model_quantized.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d6e2f18e53d9566d208023e362b0b59e0b2b7b1496cda0003c925b7860f05db5
|
3 |
+
size 17452600
|
quantize_config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"per_channel": true,
|
3 |
+
"reduce_range": true,
|
4 |
+
"per_model_config": {
|
5 |
+
"model": {
|
6 |
+
"op_types": [
|
7 |
+
"Shape",
|
8 |
+
"Unsqueeze",
|
9 |
+
"Concat",
|
10 |
+
"Mul",
|
11 |
+
"Transpose",
|
12 |
+
"Reshape",
|
13 |
+
"Add",
|
14 |
+
"Erf",
|
15 |
+
"Sqrt",
|
16 |
+
"MatMul",
|
17 |
+
"Pow",
|
18 |
+
"Constant",
|
19 |
+
"Slice",
|
20 |
+
"Sub",
|
21 |
+
"Div",
|
22 |
+
"ReduceMean",
|
23 |
+
"Gather",
|
24 |
+
"Cast",
|
25 |
+
"Softmax"
|
26 |
+
],
|
27 |
+
"weight_type": "QInt8"
|
28 |
+
}
|
29 |
+
}
|
30 |
+
}
|