yashvardhan7 commited on
Commit
fa6f14a
·
verified ·
1 Parent(s): c768534

Upload 6 files

Browse files
augmented_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6376b15341c165439d068b9e14830bc0c7aa28737eeb03eb250da9a9b35bceb6
3
+ size 440772657
model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c78e3293ec89445041a4626c3da4f87c4401b596f9f50578124bc80eca8d0ef
3
+ size 110934069
ort_config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "one_external_file": true,
3
+ "opset": null,
4
+ "optimization": {},
5
+ "optimum_version": "1.18.1",
6
+ "quantization": {
7
+ "activations_dtype": "QUInt8",
8
+ "activations_symmetric": false,
9
+ "format": "QDQ",
10
+ "is_static": true,
11
+ "mode": "QLinearOps",
12
+ "nodes_to_exclude": [],
13
+ "nodes_to_quantize": [],
14
+ "operators_to_quantize": [
15
+ "Conv",
16
+ "ConvTranspose",
17
+ "Gemm",
18
+ "Clip",
19
+ "Relu",
20
+ "Reshape",
21
+ "Transpose",
22
+ "Squeeze",
23
+ "Unsqueeze",
24
+ "Resize",
25
+ "MaxPool",
26
+ "AveragePool",
27
+ "MatMul",
28
+ "Split",
29
+ "Gather",
30
+ "Softmax",
31
+ "Where",
32
+ "InstanceNormalization",
33
+ "LayerNormalization"
34
+ ],
35
+ "per_channel": false,
36
+ "qdq_add_pair_to_weight": false,
37
+ "qdq_dedicated_pair": false,
38
+ "qdq_op_type_per_channel_support_to_axis": {
39
+ "MatMul": 1
40
+ },
41
+ "reduce_range": false,
42
+ "weights_dtype": "QInt8",
43
+ "weights_symmetric": true
44
+ },
45
+ "transformers_version": "4.38.2",
46
+ "use_external_data_format": false
47
+ }
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:988bc5a00281c6d210a5d34bd143d0363741a432fefe741bf71e61b1869d4314
3
+ size 810912
special_tokens_map.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s>NOTUSED",
4
+ "</s>NOTUSED"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<s>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "cls_token": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "eos_token": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "mask_token": {
28
+ "content": "<mask>",
29
+ "lstrip": true,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "pad_token": {
35
+ "content": "<pad>",
36
+ "lstrip": false,
37
+ "normalized": false,
38
+ "rstrip": false,
39
+ "single_word": false
40
+ },
41
+ "sep_token": {
42
+ "content": "</s>",
43
+ "lstrip": false,
44
+ "normalized": false,
45
+ "rstrip": false,
46
+ "single_word": false
47
+ },
48
+ "unk_token": {
49
+ "content": "<unk>",
50
+ "lstrip": false,
51
+ "normalized": false,
52
+ "rstrip": false,
53
+ "single_word": false
54
+ }
55
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff