Upload folder using huggingface_hub
Browse files- config.json +1 -1
- generation_config.json +1 -1
- onnx/model.onnx +2 -2
- onnx/model_quantized.onnx +2 -2
- quantize_config.json +30 -0
config.json
CHANGED
@@ -23,7 +23,7 @@
|
|
23 |
"pooler_size_per_head": 128,
|
24 |
"pooler_type": "first_token_transform",
|
25 |
"position_embedding_type": "absolute",
|
26 |
-
"transformers_version": "4.
|
27 |
"type_vocab_size": 2,
|
28 |
"use_cache": true,
|
29 |
"vocab_size": 119547
|
|
|
23 |
"pooler_size_per_head": 128,
|
24 |
"pooler_type": "first_token_transform",
|
25 |
"position_embedding_type": "absolute",
|
26 |
+
"transformers_version": "4.33.0.dev0",
|
27 |
"type_vocab_size": 2,
|
28 |
"use_cache": true,
|
29 |
"vocab_size": 119547
|
generation_config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
"pad_token_id": 0,
|
4 |
-
"transformers_version": "4.
|
5 |
}
|
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
"pad_token_id": 0,
|
4 |
+
"transformers_version": "4.33.0.dev0"
|
5 |
}
|
onnx/model.onnx
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50b9295fd51d23948cf0dc652c478eccfdc62e28aef115c4ffdec60bbd168903
|
3 |
+
size 712168690
|
onnx/model_quantized.onnx
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:42d4a69e276e04bffeec2ec3830e9f43bf057f6f364c6481986dcc4705c46f30
|
3 |
+
size 179575879
|
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 |
+
"Sqrt",
|
9 |
+
"Erf",
|
10 |
+
"Slice",
|
11 |
+
"MatMul",
|
12 |
+
"Concat",
|
13 |
+
"ReduceMean",
|
14 |
+
"Add",
|
15 |
+
"Softmax",
|
16 |
+
"Div",
|
17 |
+
"Reshape",
|
18 |
+
"Mul",
|
19 |
+
"Gather",
|
20 |
+
"Sub",
|
21 |
+
"Cast",
|
22 |
+
"Constant",
|
23 |
+
"Unsqueeze",
|
24 |
+
"Transpose",
|
25 |
+
"Pow"
|
26 |
+
],
|
27 |
+
"weight_type": "QInt8"
|
28 |
+
}
|
29 |
+
}
|
30 |
+
}
|