Hugging Face's logo

rrivera1849
/
LUAR-CRUD

Feature Extraction
Transformers
PyTorch
Safetensors
English
LUAR
custom_code
Model card Files Community
1
rrivera1849 commited on
Commit
b70dd34
·
verified ·
1 Parent(s): 56d1818

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +42 -6
  2. tokenizer.json +4 -4
  3. tokenizer_config.json +5 -4
special_tokens_map.json CHANGED
@@ -1,7 +1,25 @@
1
  {
2
- "bos_token": "<s>",
3
- "cls_token": "<s>",
4
- "eos_token": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "mask_token": {
6
  "content": "<mask>",
7
  "lstrip": true,
@@ -9,7 +27,25 @@
9
  "rstrip": false,
10
  "single_word": false
11
  },
12
- "pad_token": "<pad>",
13
- "sep_token": "</s>",
14
- "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
  }
 
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,
 
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
  }
tokenizer.json CHANGED
@@ -9,7 +9,7 @@
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
12
- "normalized": true,
13
  "special": true
14
  },
15
  {
@@ -18,7 +18,7 @@
18
  "single_word": false,
19
  "lstrip": false,
20
  "rstrip": false,
21
- "normalized": true,
22
  "special": true
23
  },
24
  {
@@ -27,7 +27,7 @@
27
  "single_word": false,
28
  "lstrip": false,
29
  "rstrip": false,
30
- "normalized": true,
31
  "special": true
32
  },
33
  {
@@ -36,7 +36,7 @@
36
  "single_word": false,
37
  "lstrip": false,
38
  "rstrip": false,
39
- "normalized": true,
40
  "special": true
41
  },
42
  {
 
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
12
+ "normalized": false,
13
  "special": true
14
  },
15
  {
 
18
  "single_word": false,
19
  "lstrip": false,
20
  "rstrip": false,
21
+ "normalized": false,
22
  "special": true
23
  },
24
  {
 
27
  "single_word": false,
28
  "lstrip": false,
29
  "rstrip": false,
30
+ "normalized": false,
31
  "special": true
32
  },
33
  {
 
36
  "single_word": false,
37
  "lstrip": false,
38
  "rstrip": false,
39
+ "normalized": false,
40
  "special": true
41
  },
42
  {
tokenizer_config.json CHANGED
@@ -4,7 +4,7 @@
4
  "0": {
5
  "content": "<s>",
6
  "lstrip": false,
7
- "normalized": true,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
@@ -12,7 +12,7 @@
12
  "1": {
13
  "content": "<pad>",
14
  "lstrip": false,
15
- "normalized": true,
16
  "rstrip": false,
17
  "single_word": false,
18
  "special": true
@@ -20,7 +20,7 @@
20
  "2": {
21
  "content": "</s>",
22
  "lstrip": false,
23
- "normalized": true,
24
  "rstrip": false,
25
  "single_word": false,
26
  "special": true
@@ -28,7 +28,7 @@
28
  "3": {
29
  "content": "<unk>",
30
  "lstrip": false,
31
- "normalized": true,
32
  "rstrip": false,
33
  "single_word": false,
34
  "special": true
@@ -47,6 +47,7 @@
47
  "cls_token": "<s>",
48
  "eos_token": "</s>",
49
  "errors": "replace",
 
50
  "mask_token": "<mask>",
51
  "model_max_length": 512,
52
  "pad_token": "<pad>",
 
4
  "0": {
5
  "content": "<s>",
6
  "lstrip": false,
7
+ "normalized": false,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
 
12
  "1": {
13
  "content": "<pad>",
14
  "lstrip": false,
15
+ "normalized": false,
16
  "rstrip": false,
17
  "single_word": false,
18
  "special": true
 
20
  "2": {
21
  "content": "</s>",
22
  "lstrip": false,
23
+ "normalized": false,
24
  "rstrip": false,
25
  "single_word": false,
26
  "special": true
 
28
  "3": {
29
  "content": "<unk>",
30
  "lstrip": false,
31
+ "normalized": false,
32
  "rstrip": false,
33
  "single_word": false,
34
  "special": true
 
47
  "cls_token": "<s>",
48
  "eos_token": "</s>",
49
  "errors": "replace",
50
+ "full_tokenizer_file": null,
51
  "mask_token": "<mask>",
52
  "model_max_length": 512,
53
  "pad_token": "<pad>",