Hugging Face's logo

AnonymousSub
/
FPDM_Legal_RoBERTa

Feature Extraction
Transformers
PyTorch
Safetensors
roberta
Inference Endpoints
Model card Files Community
AnonymousSub commited on
Commit
1de616b
•
1 Parent(s): 474c866

Upload tokenizer

Browse files
Files changed (3) hide show
  1. merges.txt +1 -1
  2. tokenizer.json +5 -4
  3. tokenizer_config.json +49 -56
merges.txt CHANGED
@@ -1,4 +1,4 @@
1
- #version: 0.2 - Trained by `huggingface/tokenizers`
2
  Ġ t
3
  Ġ a
4
  h e
 
1
+ #version: 0.2
2
  Ġ t
3
  Ġ a
4
  h e
tokenizer.json CHANGED
@@ -9,7 +9,7 @@
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
12
- "normalized": false,
13
  "special": true
14
  },
15
  {
@@ -18,7 +18,7 @@
18
  "single_word": false,
19
  "lstrip": false,
20
  "rstrip": false,
21
- "normalized": false,
22
  "special": true
23
  },
24
  {
@@ -27,7 +27,7 @@
27
  "single_word": false,
28
  "lstrip": false,
29
  "rstrip": false,
30
- "normalized": false,
31
  "special": true
32
  },
33
  {
@@ -36,7 +36,7 @@
36
  "single_word": false,
37
  "lstrip": false,
38
  "rstrip": false,
39
- "normalized": false,
40
  "special": true
41
  },
42
  {
@@ -82,6 +82,7 @@
82
  "continuing_subword_prefix": "",
83
  "end_of_word_suffix": "",
84
  "fuse_unk": false,
 
85
  "vocab": {
86
  "<s>": 0,
87
  "<pad>": 1,
 
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
12
+ "normalized": true,
13
  "special": true
14
  },
15
  {
 
18
  "single_word": false,
19
  "lstrip": false,
20
  "rstrip": false,
21
+ "normalized": true,
22
  "special": true
23
  },
24
  {
 
27
  "single_word": false,
28
  "lstrip": false,
29
  "rstrip": false,
30
+ "normalized": true,
31
  "special": true
32
  },
33
  {
 
36
  "single_word": false,
37
  "lstrip": false,
38
  "rstrip": false,
39
+ "normalized": true,
40
  "special": true
41
  },
42
  {
 
82
  "continuing_subword_prefix": "",
83
  "end_of_word_suffix": "",
84
  "fuse_unk": false,
85
+ "byte_fallback": false,
86
  "vocab": {
87
  "<s>": 0,
88
  "<pad>": 1,
tokenizer_config.json CHANGED
@@ -1,64 +1,57 @@
1
  {
2
  "add_prefix_space": false,
3
- "bos_token": {
4
- "__type": "AddedToken",
5
- "content": "<s>",
6
- "lstrip": false,
7
- "normalized": true,
8
- "rstrip": false,
9
- "single_word": false
10
- },
11
- "cls_token": {
12
- "__type": "AddedToken",
13
- "content": "<s>",
14
- "lstrip": false,
15
- "normalized": true,
16
- "rstrip": false,
17
- "single_word": false
18
- },
19
- "eos_token": {
20
- "__type": "AddedToken",
21
- "content": "</s>",
22
- "lstrip": false,
23
- "normalized": true,
24
- "rstrip": false,
25
- "single_word": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
26
  },
 
 
 
 
27
  "errors": "replace",
28
- "mask_token": {
29
- "__type": "AddedToken",
30
- "content": "<mask>",
31
- "lstrip": true,
32
- "normalized": true,
33
- "rstrip": false,
34
- "single_word": false
35
- },
36
  "model_max_length": 512,
37
- "pad_token": {
38
- "__type": "AddedToken",
39
- "content": "<pad>",
40
- "lstrip": false,
41
- "normalized": true,
42
- "rstrip": false,
43
- "single_word": false
44
- },
45
- "sep_token": {
46
- "__type": "AddedToken",
47
- "content": "</s>",
48
- "lstrip": false,
49
- "normalized": true,
50
- "rstrip": false,
51
- "single_word": false
52
- },
53
- "special_tokens_map_file": null,
54
  "tokenizer_class": "RobertaTokenizer",
55
  "trim_offsets": true,
56
- "unk_token": {
57
- "__type": "AddedToken",
58
- "content": "<unk>",
59
- "lstrip": false,
60
- "normalized": true,
61
- "rstrip": false,
62
- "single_word": false
63
- }
64
  }
 
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
  "model_max_length": 512,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
54
  "tokenizer_class": "RobertaTokenizer",
55
  "trim_offsets": true,
56
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
57
  }