Hugging Face's logo

hadifar
/
summarizer

Transformers
PyTorch
Safetensors
bart
text2text-generation
Model card Files
xet
Community
hadifar commited on
Commit
e288691
·
verified ·
1 Parent(s): 92ea124

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +42 -6
  2. tokenizer.json +18 -6
  3. tokenizer_config.json +51 -2
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": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
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": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
  }
tokenizer.json CHANGED
@@ -1,7 +1,19 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
4
- "padding": null,
 
 
 
 
 
 
 
 
 
 
 
 
5
  "added_tokens": [
6
  {
7
  "id": 0,
@@ -9,7 +21,7 @@
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
12
- "normalized": false,
13
  "special": true
14
  },
15
  {
@@ -18,7 +30,7 @@
18
  "single_word": false,
19
  "lstrip": false,
20
  "rstrip": false,
21
- "normalized": false,
22
  "special": true
23
  },
24
  {
@@ -27,7 +39,7 @@
27
  "single_word": false,
28
  "lstrip": false,
29
  "rstrip": false,
30
- "normalized": false,
31
  "special": true
32
  },
33
  {
@@ -36,7 +48,7 @@
36
  "single_word": false,
37
  "lstrip": false,
38
  "rstrip": false,
39
- "normalized": false,
40
  "special": true
41
  },
42
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 512,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": {
10
+ "strategy": "BatchLongest",
11
+ "direction": "Right",
12
+ "pad_to_multiple_of": null,
13
+ "pad_id": 1,
14
+ "pad_type_id": 0,
15
+ "pad_token": "<pad>"
16
+ },
17
  "added_tokens": [
18
  {
19
  "id": 0,
 
21
  "single_word": false,
22
  "lstrip": false,
23
  "rstrip": false,
24
+ "normalized": true,
25
  "special": true
26
  },
27
  {
 
30
  "single_word": false,
31
  "lstrip": false,
32
  "rstrip": false,
33
+ "normalized": true,
34
  "special": true
35
  },
36
  {
 
39
  "single_word": false,
40
  "lstrip": false,
41
  "rstrip": false,
42
+ "normalized": true,
43
  "special": true
44
  },
45
  {
 
48
  "single_word": false,
49
  "lstrip": false,
50
  "rstrip": false,
51
+ "normalized": true,
52
  "special": true
53
  },
54
  {
tokenizer_config.json CHANGED
@@ -1,15 +1,64 @@
1
  {
2
  "add_prefix_space": false,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "bos_token": "<s>",
4
  "clean_up_tokenization_spaces": true,
5
  "cls_token": "<s>",
6
  "eos_token": "</s>",
7
  "errors": "replace",
8
  "mask_token": "<mask>",
9
- "model_max_length": 1024,
 
 
10
  "pad_token": "<pad>",
 
 
11
  "sep_token": "</s>",
12
- "tokenizer_class": "BartTokenizer",
 
13
  "trim_offsets": true,
 
 
14
  "unk_token": "<unk>"
15
  }
 
1
  {
2
  "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
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
+ "max_length": 512,
52
+ "model_max_length": 512,
53
+ "pad_to_multiple_of": null,
54
  "pad_token": "<pad>",
55
+ "pad_token_type_id": 0,
56
+ "padding_side": "right",
57
  "sep_token": "</s>",
58
+ "stride": 0,
59
+ "tokenizer_class": "RobertaTokenizer",
60
  "trim_offsets": true,
61
+ "truncation_side": "right",
62
+ "truncation_strategy": "longest_first",
63
  "unk_token": "<unk>"
64
  }