Hugging Face's logo

desarrolloasesoreslocales
/
bert-leg-al-corpus

Fill-Mask
Transformers
TensorBoard
Safetensors
roberta
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
desarrolloasesoreslocales commited on
Commit
5866c00
•
1 Parent(s): 5bd941e

Upload tokenizer

Browse files
Files changed (4) hide show
  1. README.md +1 -1
  2. special_tokens_map.json +8 -8
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +18 -15
README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
  license: mit
3
- base_model: desarrolloasesoreslocales/bert-leg-al-corpus
4
  tags:
5
  - generated_from_trainer
 
6
  model-index:
7
  - name: bert-leg-al-corpus
8
  results: []
 
1
  ---
2
  license: mit
 
3
  tags:
4
  - generated_from_trainer
5
+ base_model: desarrolloasesoreslocales/bert-leg-al-corpus
6
  model-index:
7
  - name: bert-leg-al-corpus
8
  results: []
special_tokens_map.json CHANGED
@@ -2,49 +2,49 @@
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,
26
- "normalized": 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
  }
 
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": false,
26
+ "normalized": false,
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
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,18 +1,17 @@
1
  {
2
- "add_prefix_space": true,
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
@@ -20,7 +19,7 @@
20
  "2": {
21
  "content": "</s>",
22
  "lstrip": false,
23
- "normalized": true,
24
  "rstrip": false,
25
  "single_word": false,
26
  "special": true
@@ -28,15 +27,15 @@
28
  "3": {
29
  "content": "<unk>",
30
  "lstrip": false,
31
- "normalized": true,
32
  "rstrip": false,
33
  "single_word": false,
34
  "special": true
35
  },
36
- "51999": {
37
  "content": "<mask>",
38
- "lstrip": true,
39
- "normalized": true,
40
  "rstrip": false,
41
  "single_word": false,
42
  "special": true
@@ -46,13 +45,17 @@
46
  "clean_up_tokenization_spaces": true,
47
  "cls_token": "<s>",
48
  "eos_token": "</s>",
49
- "errors": "replace",
50
  "mask_token": "<mask>",
51
- "max_len": 512,
52
- "model_max_length": 4096,
 
53
  "pad_token": "<pad>",
 
 
54
  "sep_token": "</s>",
55
- "tokenizer_class": "RobertaTokenizer",
56
- "trim_offsets": true,
 
 
57
  "unk_token": "<unk>"
58
  }
 
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": "<s>",
13
  "lstrip": false,
14
+ "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
 
19
  "2": {
20
  "content": "</s>",
21
  "lstrip": false,
22
+ "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
 
27
  "3": {
28
  "content": "<unk>",
29
  "lstrip": false,
30
+ "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "4": {
36
  "content": "<mask>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
 
45
  "clean_up_tokenization_spaces": true,
46
  "cls_token": "<s>",
47
  "eos_token": "</s>",
 
48
  "mask_token": "<mask>",
49
+ "max_length": 512,
50
+ "model_max_length": 512,
51
+ "pad_to_multiple_of": null,
52
  "pad_token": "<pad>",
53
+ "pad_token_type_id": 0,
54
+ "padding_side": "right",
55
  "sep_token": "</s>",
56
+ "stride": 0,
57
+ "tokenizer_class": "PreTrainedTokenizerFast",
58
+ "truncation_side": "right",
59
+ "truncation_strategy": "longest_first",
60
  "unk_token": "<unk>"
61
  }