Hugging Face's logo

seanghay
/
albert-khmer-small

Fill-Mask
Transformers
Safetensors
Khmer
albert
Model card Files
xet
 Community
1
seanghay commited on
Commit
188f0d4
·
verified ·
1 Parent(s): 7d3c90d

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +2 -2
  2. spiece.model +2 -2
  3. tokenizer_config.json +14 -14
special_tokens_map.json CHANGED
@@ -28,7 +28,7 @@
28
  "single_word": false
29
  },
30
  "pad_token": {
31
- "content": "<pad>",
32
  "lstrip": false,
33
  "normalized": false,
34
  "rstrip": false,
@@ -42,7 +42,7 @@
42
  "single_word": false
43
  },
44
  "unk_token": {
45
- "content": "<unk>",
46
  "lstrip": false,
47
  "normalized": false,
48
  "rstrip": false,
 
28
  "single_word": false
29
  },
30
  "pad_token": {
31
+ "content": "[PAD]",
32
  "lstrip": false,
33
  "normalized": false,
34
  "rstrip": false,
 
42
  "single_word": false
43
  },
44
  "unk_token": {
45
+ "content": "[UNK]",
46
  "lstrip": false,
47
  "normalized": false,
48
  "rstrip": false,
spiece.model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:549e2ea1f37910e51f335a039b5fe2baaa1fa341f77f0ade4254cc0b06550cc4
3
- size 1373467
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:069733a699002399db1385d88d56d89557f459958b136063cc84a44cc18ea8f7
3
+ size 676662
tokenizer_config.json CHANGED
@@ -1,40 +1,40 @@
1
  {
2
  "added_tokens_decoder": {
3
- "2": {
4
- "content": "[CLS]",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
10
  },
11
- "3": {
12
- "content": "[SEP]",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
- "4": {
20
- "content": "[MASK]",
21
- "lstrip": true,
22
  "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  },
27
- "32000": {
28
- "content": "<unk>",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
- "32001": {
36
- "content": "<pad>",
37
- "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
@@ -50,10 +50,10 @@
50
  "keep_accents": true,
51
  "mask_token": "[MASK]",
52
  "model_max_length": 1000000000000000019884624838656,
53
- "pad_token": "<pad>",
54
  "remove_space": false,
55
  "sep_token": "[SEP]",
56
  "sp_model_kwargs": {},
57
  "tokenizer_class": "AlbertTokenizer",
58
- "unk_token": "<unk>"
59
  }
 
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
+ "1": {
12
+ "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "3": {
28
+ "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": true,
38
  "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
 
50
  "keep_accents": true,
51
  "mask_token": "[MASK]",
52
  "model_max_length": 1000000000000000019884624838656,
53
+ "pad_token": "[PAD]",
54
  "remove_space": false,
55
  "sep_token": "[SEP]",
56
  "sp_model_kwargs": {},
57
  "tokenizer_class": "AlbertTokenizer",
58
+ "unk_token": "[UNK]"
59
  }