Hugging Face's logo

team-lucid
/
layoutlmv3-base-ko

Feature Extraction
Transformers
PyTorch
JAX
Safetensors
layoutlmv3
Inference Endpoints
Model card Files Community
hyunwoo3235 commited on
Commit
9840888
•
1 Parent(s): 7cbd997

Upload 10 files

Browse files
Files changed (10) hide show
  1. added_tokens.json +3 -0
  2. config.json +1 -1
  3. flax_model.msgpack +2 -2
  4. merges.txt +0 -0
  5. model.safetensors +2 -2
  6. pytorch_model.bin +3 -0
  7. special_tokens_map.json +38 -51
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +69 -57
  10. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<mask>": 50432
3
+ }
config.json CHANGED
@@ -34,5 +34,5 @@
34
  "transformers_version": "4.37.2",
35
  "type_vocab_size": 1,
36
  "visual_embed": true,
37
- "vocab_size": 38400
38
  }
 
34
  "transformers_version": "4.37.2",
35
  "type_vocab_size": 1,
36
  "visual_embed": true,
37
+ "vocab_size": 50560
38
  }
flax_model.msgpack CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:23dffca1ec9e6b7f8fbfef1ab459fe46b953c765a2e90c861b71c559da9ffd7f
3
- size 472129029
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99c74e24b38a1525786cea8c6f47ba38944363b717701bca158300610fd4288a
3
+ size 509533189
merges.txt CHANGED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:975894eae17a878f95412db50ca6ed5bcc214bedcf5a1de153fe80afd52715f5
3
- size 464882232
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:771ba50977acef08d385892f20552ea34ec332c8236568d9c921274e5116e239
3
+ size 502237752
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f42ded82d6a3aed8ae5af2667d1885a3719d3ae9b4c97ce8df31062f20433b7
3
+ size 502282586
special_tokens_map.json CHANGED
@@ -1,51 +1,38 @@
1
- {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "cls_token": {
10
- "content": "<s>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "eos_token": {
17
- "content": "</s>",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
- "mask_token": {
24
- "content": "<mask>",
25
- "lstrip": true,
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": "</s>",
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
- }
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": "<mask>",
24
+ "pad_token": {
25
+ "content": "<pad>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ "sep_token": {
32
+ "content": "</s>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ }
38
+ }
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,57 +1,69 @@
1
- {
2
- "add_prefix_space": false,
3
- "added_tokens_decoder": {
4
- "0": {
5
- "content": "<pad>",
6
- "lstrip": false,
7
- "normalized": false,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- },
12
- "1": {
13
- "content": "<s>",
14
- "lstrip": false,
15
- "normalized": false,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": true
19
- },
20
- "2": {
21
- "content": "</s>",
22
- "lstrip": false,
23
- "normalized": false,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": true
27
- },
28
- "3": {
29
- "content": "<unk>",
30
- "lstrip": false,
31
- "normalized": false,
32
- "rstrip": false,
33
- "single_word": false,
34
- "special": true
35
- },
36
- "4": {
37
- "content": "<mask>",
38
- "lstrip": true,
39
- "normalized": false,
40
- "rstrip": false,
41
- "single_word": false,
42
- "special": true
43
- }
44
- },
45
- "bos_token": "<s>",
46
- "clean_up_tokenization_spaces": true,
47
- "cls_token": "<s>",
48
- "eos_token": "</s>",
49
- "errors": "replace",
50
- "mask_token": "<mask>",
51
- "model_max_length": 1000000000000000019884624838656,
52
- "pad_token": "<pad>",
53
- "sep_token": "</s>",
54
- "tokenizer_class": "RobertaTokenizer",
55
- "trim_offsets": true,
56
- "unk_token": "<unk>"
57
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "50432": {
29
+ "content": "<mask>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ }
36
+ },
37
+ "bos_token": "<s>",
38
+ "clean_up_tokenization_spaces": true,
39
+ "cls_token": "<s>",
40
+ "cls_token_box": [
41
+ 0,
42
+ 0,
43
+ 0,
44
+ 0
45
+ ],
46
+ "eos_token": "</s>",
47
+ "errors": "replace",
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 512,
50
+ "only_label_first_subword": true,
51
+ "pad_token": "<pad>",
52
+ "pad_token_box": [
53
+ 0,
54
+ 0,
55
+ 0,
56
+ 0
57
+ ],
58
+ "pad_token_label": -100,
59
+ "sep_token": "</s>",
60
+ "sep_token_box": [
61
+ 0,
62
+ 0,
63
+ 0,
64
+ 0
65
+ ],
66
+ "tokenizer_class": "LayoutLMv3Tokenizer",
67
+ "trim_offsets": true,
68
+ "unk_token": null
69
+ }
vocab.json CHANGED
The diff for this file is too large to render. See raw diff