Hugging Face's logo

KoichiYasuoka
/
roberta-base-serbian-upos

Token Classification
Transformers
PyTorch
Serbian
roberta
serbian
pos
dependency-parsing
Inference Endpoints
Model card Files Community
3
KoichiYasuoka commited on
Commit
8208c49
•
1 Parent(s): fac7ac1

model improved

Browse files
Files changed (5) hide show
  1. config.json +0 -0
  2. pytorch_model.bin +2 -2
  3. special_tokens_map.json +7 -1
  4. supar.model +2 -2
  5. tokenizer_config.json +64 -1
config.json CHANGED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6dd000b5c285446ada737f34e597cacd32c76e88635d618a112ad144ff9aa46c
3
- size 386365937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4474f77af6220ae75e94b7eecd6f81f61627fa0472cfcdc8bd20b3bf8bc4cfb8
3
+ size 391540646
special_tokens_map.json CHANGED
@@ -1 +1,7 @@
1
- {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
supar.model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb2c0bdcda63d436c2524669770e88100f33b8ad3b00acfc85cb0c60547c0441
3
- size 440059877
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7668fc9a1fe23e73afe45cf2510857c64bf77e1d1457436f9ea9c00f71c3e21
3
+ size 441902646
tokenizer_config.json CHANGED
@@ -1 +1,64 @@
1
- {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": false, "do_lowercase": true, "never_split": ["[UNK]", "[SEP]", "[PAD]", "[CLS]", "[MASK]"], "model_max_length": 512, "do_basic_tokenize": true, "tokenizer_class": "BertTokenizerFast"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[CLS]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[PAD]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
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
+ "do_lowercase": true,
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 512,
51
+ "never_split": [
52
+ "[UNK]",
53
+ "[SEP]",
54
+ "[PAD]",
55
+ "[CLS]",
56
+ "[MASK]"
57
+ ],
58
+ "pad_token": "[PAD]",
59
+ "sep_token": "[SEP]",
60
+ "strip_accents": false,
61
+ "tokenize_chinese_chars": true,
62
+ "tokenizer_class": "BertTokenizerFast",
63
+ "unk_token": "[UNK]"
64
+ }