shadowlilac
commited on
Commit
•
603a23f
1
Parent(s):
f6e929f
Upload processor
Browse files- preprocessor_config.json +2 -2
- tokenizer.json +10 -1
- tokenizer_config.json +42 -0
preprocessor_config.json
CHANGED
@@ -19,8 +19,8 @@
|
|
19 |
"resample": 3,
|
20 |
"rescale_factor": 0.00392156862745098,
|
21 |
"size": {
|
22 |
-
"height":
|
23 |
-
"width":
|
24 |
},
|
25 |
"size_divisor": 32
|
26 |
}
|
|
|
19 |
"resample": 3,
|
20 |
"rescale_factor": 0.00392156862745098,
|
21 |
"size": {
|
22 |
+
"height": 384,
|
23 |
+
"width": 384
|
24 |
},
|
25 |
"size_divisor": 32
|
26 |
}
|
tokenizer.json
CHANGED
@@ -1,7 +1,16 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
"truncation": null,
|
4 |
-
"padding":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 0,
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
"truncation": null,
|
4 |
+
"padding": {
|
5 |
+
"strategy": {
|
6 |
+
"Fixed": 512
|
7 |
+
},
|
8 |
+
"direction": "Right",
|
9 |
+
"pad_to_multiple_of": null,
|
10 |
+
"pad_id": 0,
|
11 |
+
"pad_type_id": 0,
|
12 |
+
"pad_token": "[PAD]"
|
13 |
+
},
|
14 |
"added_tokens": [
|
15 |
{
|
16 |
"id": 0,
|
tokenizer_config.json
CHANGED
@@ -1,4 +1,46 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"clean_up_tokenization_spaces": true,
|
3 |
"cls_token": "[CLS]",
|
4 |
"do_basic_tokenize": true,
|
|
|
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,
|