Hugging Face's logo

KoichiYasuoka
/
roberta-large-korean-morph-upos

Token Classification
Transformers
PyTorch
Korean
roberta
korean
pos
dependency-parsing
Inference Endpoints
Model card Files Community
1
KoichiYasuoka commited on
Commit
05bddf4
•
1 Parent(s): 0b447fc

model improved

Browse files
Files changed (5) hide show
  1. config.json +1 -1
  2. pytorch_model.bin +1 -1
  3. special_tokens_map.json +49 -7
  4. supar.model +1 -1
  5. tokenizer_config.json +43 -0
config.json CHANGED
@@ -34674,7 +34674,7 @@
34674
  },
34675
  "tokenizer_class": "BertTokenizerFast",
34676
  "torch_dtype": "float32",
34677
- "transformers_version": "4.22.1",
34678
  "type_vocab_size": 1,
34679
  "use_cache": true,
34680
  "vocab_size": 39255
 
34674
  },
34675
  "tokenizer_class": "BertTokenizerFast",
34676
  "torch_dtype": "float32",
34677
+ "transformers_version": "4.27.1",
34678
  "type_vocab_size": 1,
34679
  "use_cache": true,
34680
  "vocab_size": 39255
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d3da39446cb1f074ebfd48a6eabfed615255d15d86ed90111da997a8ad4a92b6
3
  size 1375937329
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46d7f6122b3ea59b89a1868d633d4c76dabc33a4d3d24a6a67b53468e3fd76a9
3
  size 1375937329
special_tokens_map.json CHANGED
@@ -1,9 +1,51 @@
1
  {
2
- "bos_token": "[CLS]",
3
- "cls_token": "[CLS]",
4
- "eos_token": "[SEP]",
5
- "mask_token": "[MASK]",
6
- "pad_token": "[PAD]",
7
- "sep_token": "[SEP]",
8
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
  }
supar.model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:492d018e593f542e7948cc19312dc6339882298a4ef4196d3318544fa5f6d83a
3
  size 1424807269
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d9048f0daa4a92be98699c315566dc08e2c86962cd0a816b7df8aafb7e4355f
3
  size 1424807269
tokenizer_config.json CHANGED
@@ -1,5 +1,48 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "bos_token": "[CLS]",
 
3
  "cls_token": "[CLS]",
4
  "do_basic_tokenize": true,
5
  "do_lower_case": false,
 
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
  "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": true,
46
  "cls_token": "[CLS]",
47
  "do_basic_tokenize": true,
48
  "do_lower_case": false,