tarekziade
commited on
Commit
•
ea6e063
1
Parent(s):
524aa1b
use transformers.js converter
Browse files- config.json +9 -9
- onnx/model.onnx +2 -2
- onnx/model_quantized.onnx +2 -2
- quantize_config.json +31 -0
- special_tokens_map.json +35 -5
- tokenizer_config.json +51 -2
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"BertForSequenceClassification"
|
5 |
],
|
@@ -24,16 +24,16 @@
|
|
24 |
"initializer_range": 0.02,
|
25 |
"intermediate_size": 1024,
|
26 |
"label2id": {
|
27 |
-
"Society & Culture": 0,
|
28 |
-
"Science & Mathematics": 1,
|
29 |
-
"Health": 2,
|
30 |
-
"Education & Reference": 3,
|
31 |
-
"Computers & Internet": 4,
|
32 |
-
"Sports": 5,
|
33 |
"Business & Finance": 6,
|
|
|
|
|
34 |
"Entertainment & Music": 7,
|
35 |
"Family & Relationships": 8,
|
36 |
-
"
|
|
|
|
|
|
|
|
|
37 |
},
|
38 |
"layer_norm_eps": 1e-12,
|
39 |
"max_position_embeddings": 512,
|
@@ -43,7 +43,7 @@
|
|
43 |
"pad_token_id": 0,
|
44 |
"position_embedding_type": "absolute",
|
45 |
"problem_type": "multi_label_classification",
|
46 |
-
"transformers_version": "4.
|
47 |
"type_vocab_size": 2,
|
48 |
"use_cache": true,
|
49 |
"vocab_size": 30522
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "jonaskoenig/topic_classification_04",
|
3 |
"architectures": [
|
4 |
"BertForSequenceClassification"
|
5 |
],
|
|
|
24 |
"initializer_range": 0.02,
|
25 |
"intermediate_size": 1024,
|
26 |
"label2id": {
|
|
|
|
|
|
|
|
|
|
|
|
|
27 |
"Business & Finance": 6,
|
28 |
+
"Computers & Internet": 4,
|
29 |
+
"Education & Reference": 3,
|
30 |
"Entertainment & Music": 7,
|
31 |
"Family & Relationships": 8,
|
32 |
+
"Health": 2,
|
33 |
+
"Politics & Government": 9,
|
34 |
+
"Science & Mathematics": 1,
|
35 |
+
"Society & Culture": 0,
|
36 |
+
"Sports": 5
|
37 |
},
|
38 |
"layer_norm_eps": 1e-12,
|
39 |
"max_position_embeddings": 512,
|
|
|
43 |
"pad_token_id": 0,
|
44 |
"position_embedding_type": "absolute",
|
45 |
"problem_type": "multi_label_classification",
|
46 |
+
"transformers_version": "4.36.1",
|
47 |
"type_vocab_size": 2,
|
48 |
"use_cache": true,
|
49 |
"vocab_size": 30522
|
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 sha256:94e75119882aaaabebcd3abdf6ea9d3b84dac550a480bafe779e4feaf94cfa69
|
3 |
+
size 51233961
|
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:db08136f6794c723d017b22237cba58a2185fabb09d48e1710613850bedf08bd
|
3 |
+
size 13256259
|
quantize_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"per_channel": true,
|
3 |
+
"reduce_range": true,
|
4 |
+
"per_model_config": {
|
5 |
+
"model": {
|
6 |
+
"op_types": [
|
7 |
+
"Add",
|
8 |
+
"Gather",
|
9 |
+
"GlobalAveragePool",
|
10 |
+
"Tanh",
|
11 |
+
"MatMul",
|
12 |
+
"Reshape",
|
13 |
+
"Softmax",
|
14 |
+
"Slice",
|
15 |
+
"Reciprocal",
|
16 |
+
"Cast",
|
17 |
+
"Shape",
|
18 |
+
"Concat",
|
19 |
+
"Squeeze",
|
20 |
+
"Mul",
|
21 |
+
"Unsqueeze",
|
22 |
+
"Erf",
|
23 |
+
"Range",
|
24 |
+
"Transpose",
|
25 |
+
"Sqrt",
|
26 |
+
"Sub"
|
27 |
+
],
|
28 |
+
"weight_type": "QInt8"
|
29 |
+
}
|
30 |
+
}
|
31 |
+
}
|
special_tokens_map.json
CHANGED
@@ -1,7 +1,37 @@
|
|
1 |
{
|
2 |
-
"cls_token":
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
}
|
|
|
1 |
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
}
|
tokenizer_config.json
CHANGED
@@ -1,15 +1,64 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"cls_token": "[CLS]",
|
3 |
"do_basic_tokenize": true,
|
4 |
"do_lower_case": true,
|
5 |
"mask_token": "[MASK]",
|
6 |
-
"
|
|
|
7 |
"never_split": null,
|
|
|
8 |
"pad_token": "[PAD]",
|
|
|
|
|
9 |
"sep_token": "[SEP]",
|
10 |
-
"
|
11 |
"strip_accents": null,
|
12 |
"tokenize_chinese_chars": true,
|
13 |
"tokenizer_class": "BertTokenizer",
|
|
|
|
|
14 |
"unk_token": "[UNK]"
|
15 |
}
|
|
|
1 |
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
46 |
"do_basic_tokenize": true,
|
47 |
"do_lower_case": true,
|
48 |
"mask_token": "[MASK]",
|
49 |
+
"max_length": 64,
|
50 |
+
"model_max_length": 1000000000000000019884624838656,
|
51 |
"never_split": null,
|
52 |
+
"pad_to_multiple_of": null,
|
53 |
"pad_token": "[PAD]",
|
54 |
+
"pad_token_type_id": 0,
|
55 |
+
"padding_side": "right",
|
56 |
"sep_token": "[SEP]",
|
57 |
+
"stride": 0,
|
58 |
"strip_accents": null,
|
59 |
"tokenize_chinese_chars": true,
|
60 |
"tokenizer_class": "BertTokenizer",
|
61 |
+
"truncation_side": "right",
|
62 |
+
"truncation_strategy": "longest_first",
|
63 |
"unk_token": "[UNK]"
|
64 |
}
|