Hugging Face's logo

TheophileCA
/
distilroberta_trainedOnCACatalogue

Fill-Mask
Transformers
TensorFlow
roberta
generated_from_keras_callback
Inference Endpoints
Model card Files Community
TheophileCA commited on
Commit
798831a
•
1 Parent(s): 6e219bf

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +7 -0
  2. special_tokens_map.json +1 -7
  3. tokenizer.json +4 -5
  4. tokenizer_config.json +5 -4
added_tokens.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<mask>": 50264,
4
+ "<pad>": 1,
5
+ "<s>": 0,
6
+ "<unk>": 3
7
+ }
special_tokens_map.json CHANGED
@@ -2,13 +2,7 @@
2
  "bos_token": "<s>",
3
  "cls_token": "<s>",
4
  "eos_token": "</s>",
5
- "mask_token": {
6
- "content": "<mask>",
7
- "lstrip": true,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false
11
- },
12
  "pad_token": "<pad>",
13
  "sep_token": "</s>",
14
  "unk_token": "<unk>"
 
2
  "bos_token": "<s>",
3
  "cls_token": "<s>",
4
  "eos_token": "</s>",
5
+ "mask_token": "<mask>",
 
 
 
 
 
 
6
  "pad_token": "<pad>",
7
  "sep_token": "</s>",
8
  "unk_token": "<unk>"
tokenizer.json CHANGED
@@ -14,7 +14,7 @@
14
  "single_word": false,
15
  "lstrip": false,
16
  "rstrip": false,
17
- "normalized": true,
18
  "special": true
19
  },
20
  {
@@ -23,7 +23,7 @@
23
  "single_word": false,
24
  "lstrip": false,
25
  "rstrip": false,
26
- "normalized": true,
27
  "special": true
28
  },
29
  {
@@ -32,7 +32,7 @@
32
  "single_word": false,
33
  "lstrip": false,
34
  "rstrip": false,
35
- "normalized": true,
36
  "special": true
37
  },
38
  {
@@ -41,7 +41,7 @@
41
  "single_word": false,
42
  "lstrip": false,
43
  "rstrip": false,
44
- "normalized": true,
45
  "special": true
46
  },
47
  {
@@ -88,7 +88,6 @@
88
  "end_of_word_suffix": "",
89
  "fuse_unk": false,
90
  "byte_fallback": false,
91
- "ignore_merges": false,
92
  "vocab": {
93
  "<s>": 0,
94
  "<pad>": 1,
 
14
  "single_word": false,
15
  "lstrip": false,
16
  "rstrip": false,
17
+ "normalized": false,
18
  "special": true
19
  },
20
  {
 
23
  "single_word": false,
24
  "lstrip": false,
25
  "rstrip": false,
26
+ "normalized": false,
27
  "special": true
28
  },
29
  {
 
32
  "single_word": false,
33
  "lstrip": false,
34
  "rstrip": false,
35
+ "normalized": false,
36
  "special": true
37
  },
38
  {
 
41
  "single_word": false,
42
  "lstrip": false,
43
  "rstrip": false,
44
+ "normalized": false,
45
  "special": true
46
  },
47
  {
 
88
  "end_of_word_suffix": "",
89
  "fuse_unk": false,
90
  "byte_fallback": false,
 
91
  "vocab": {
92
  "<s>": 0,
93
  "<pad>": 1,
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
@@ -42,6 +42,7 @@
42
  "special": true
43
  }
44
  },
 
45
  "bos_token": "<s>",
46
  "clean_up_tokenization_spaces": true,
47
  "cls_token": "<s>",
 
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
 
42
  "special": true
43
  }
44
  },
45
+ "additional_special_tokens": [],
46
  "bos_token": "<s>",
47
  "clean_up_tokenization_spaces": true,
48
  "cls_token": "<s>",