Upload folder using huggingface_hub
Browse files- config.json +2 -2
- onnx/model.onnx +3 -0
- onnx/model_quantized.onnx +2 -2
- tokenizer.json +10 -10
- tokenizer_config.json +1 -2
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"BertModel"
|
5 |
],
|
@@ -18,7 +18,7 @@
|
|
18 |
"num_hidden_layers": 6,
|
19 |
"pad_token_id": 0,
|
20 |
"position_embedding_type": "absolute",
|
21 |
-
"transformers_version": "4.
|
22 |
"type_vocab_size": 2,
|
23 |
"use_cache": true,
|
24 |
"vocab_size": 30522
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "sentence-transformers/all-MiniLM-L6-v2",
|
3 |
"architectures": [
|
4 |
"BertModel"
|
5 |
],
|
|
|
18 |
"num_hidden_layers": 6,
|
19 |
"pad_token_id": 0,
|
20 |
"position_embedding_type": "absolute",
|
21 |
+
"transformers_version": "4.29.2",
|
22 |
"type_vocab_size": 2,
|
23 |
"use_cache": true,
|
24 |
"vocab_size": 30522
|
onnx/model.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:759c3cd2b7fe7e93933ad23c4c9181b7396442a2ed746ec7c1d46192c469c46e
|
3 |
+
size 90387606
|
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 sha256:2f9a2cd8a5955f62908d5087be47516e9d91849f50579c3e47c73fd2c563b224
|
3 |
+
size 22868510
|
tokenizer.json
CHANGED
@@ -19,48 +19,48 @@
|
|
19 |
"added_tokens": [
|
20 |
{
|
21 |
"id": 0,
|
22 |
-
"special": true,
|
23 |
"content": "[PAD]",
|
24 |
"single_word": false,
|
25 |
"lstrip": false,
|
26 |
"rstrip": false,
|
27 |
-
"normalized": false
|
|
|
28 |
},
|
29 |
{
|
30 |
"id": 100,
|
31 |
-
"special": true,
|
32 |
"content": "[UNK]",
|
33 |
"single_word": false,
|
34 |
"lstrip": false,
|
35 |
"rstrip": false,
|
36 |
-
"normalized": false
|
|
|
37 |
},
|
38 |
{
|
39 |
"id": 101,
|
40 |
-
"special": true,
|
41 |
"content": "[CLS]",
|
42 |
"single_word": false,
|
43 |
"lstrip": false,
|
44 |
"rstrip": false,
|
45 |
-
"normalized": false
|
|
|
46 |
},
|
47 |
{
|
48 |
"id": 102,
|
49 |
-
"special": true,
|
50 |
"content": "[SEP]",
|
51 |
"single_word": false,
|
52 |
"lstrip": false,
|
53 |
"rstrip": false,
|
54 |
-
"normalized": false
|
|
|
55 |
},
|
56 |
{
|
57 |
"id": 103,
|
58 |
-
"special": true,
|
59 |
"content": "[MASK]",
|
60 |
"single_word": false,
|
61 |
"lstrip": false,
|
62 |
"rstrip": false,
|
63 |
-
"normalized": false
|
|
|
64 |
}
|
65 |
],
|
66 |
"normalizer": {
|
|
|
19 |
"added_tokens": [
|
20 |
{
|
21 |
"id": 0,
|
|
|
22 |
"content": "[PAD]",
|
23 |
"single_word": false,
|
24 |
"lstrip": false,
|
25 |
"rstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"special": true
|
28 |
},
|
29 |
{
|
30 |
"id": 100,
|
|
|
31 |
"content": "[UNK]",
|
32 |
"single_word": false,
|
33 |
"lstrip": false,
|
34 |
"rstrip": false,
|
35 |
+
"normalized": false,
|
36 |
+
"special": true
|
37 |
},
|
38 |
{
|
39 |
"id": 101,
|
|
|
40 |
"content": "[CLS]",
|
41 |
"single_word": false,
|
42 |
"lstrip": false,
|
43 |
"rstrip": false,
|
44 |
+
"normalized": false,
|
45 |
+
"special": true
|
46 |
},
|
47 |
{
|
48 |
"id": 102,
|
|
|
49 |
"content": "[SEP]",
|
50 |
"single_word": false,
|
51 |
"lstrip": false,
|
52 |
"rstrip": false,
|
53 |
+
"normalized": false,
|
54 |
+
"special": true
|
55 |
},
|
56 |
{
|
57 |
"id": 103,
|
|
|
58 |
"content": "[MASK]",
|
59 |
"single_word": false,
|
60 |
"lstrip": false,
|
61 |
"rstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"special": true
|
64 |
}
|
65 |
],
|
66 |
"normalizer": {
|
tokenizer_config.json
CHANGED
@@ -1,14 +1,13 @@
|
|
1 |
{
|
|
|
2 |
"cls_token": "[CLS]",
|
3 |
"do_basic_tokenize": true,
|
4 |
"do_lower_case": true,
|
5 |
"mask_token": "[MASK]",
|
6 |
"model_max_length": 512,
|
7 |
-
"name_or_path": "./models/pytorch/all-MiniLM-L6-v2",
|
8 |
"never_split": null,
|
9 |
"pad_token": "[PAD]",
|
10 |
"sep_token": "[SEP]",
|
11 |
-
"special_tokens_map_file": null,
|
12 |
"strip_accents": null,
|
13 |
"tokenize_chinese_chars": true,
|
14 |
"tokenizer_class": "BertTokenizer",
|
|
|
1 |
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
"cls_token": "[CLS]",
|
4 |
"do_basic_tokenize": true,
|
5 |
"do_lower_case": true,
|
6 |
"mask_token": "[MASK]",
|
7 |
"model_max_length": 512,
|
|
|
8 |
"never_split": null,
|
9 |
"pad_token": "[PAD]",
|
10 |
"sep_token": "[SEP]",
|
|
|
11 |
"strip_accents": null,
|
12 |
"tokenize_chinese_chars": true,
|
13 |
"tokenizer_class": "BertTokenizer",
|