Hugging Face's logo

simoneprete
/
mbert-lstm-sentiment-analysis

Text Classification
Transformers
Safetensors
camembert
Inference Endpoints
Model card Files Community
simoneprete commited on
Commit
49a8dd9
·
verified ·
1 Parent(s): 32788cb

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +3 -0
  2. sentencepiece.bpe.model +3 -0
  3. special_tokens_map.json +13 -30
  4. tokenizer_config.json +48 -21
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<mask>": 32004
3
+ }
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:988bc5a00281c6d210a5d34bd143d0363741a432fefe741bf71e61b1869d4314
3
+ size 810912
special_tokens_map.json CHANGED
@@ -1,37 +1,20 @@
1
  {
2
- "cls_token": {
3
- "content": "[CLS]",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
 
9
  "mask_token": {
10
- "content": "[MASK]",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": {
17
- "content": "[PAD]",
18
- "lstrip": false,
19
  "normalized": false,
20
  "rstrip": false,
21
  "single_word": false
22
  },
23
- "sep_token": {
24
- "content": "[SEP]",
25
- "lstrip": false,
26
- "normalized": false,
27
- "rstrip": false,
28
- "single_word": false
29
- },
30
- "unk_token": {
31
- "content": "[UNK]",
32
- "lstrip": false,
33
- "normalized": false,
34
- "rstrip": false,
35
- "single_word": false
36
- }
37
  }
 
1
  {
2
+ "additional_special_tokens": [
3
+ "<s>NOTUSED",
4
+ "</s>NOTUSED",
5
+ "<unk>NOTUSED"
6
+ ],
7
+ "bos_token": "<s>",
8
+ "cls_token": "<s>",
9
+ "eos_token": "</s>",
10
  "mask_token": {
11
+ "content": "<mask>",
12
+ "lstrip": true,
 
 
 
 
 
 
 
13
  "normalized": false,
14
  "rstrip": false,
15
  "single_word": false
16
  },
17
+ "pad_token": "<pad>",
18
+ "sep_token": "</s>",
19
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
20
  }
tokenizer_config.json CHANGED
@@ -1,57 +1,84 @@
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
- "100": {
12
- "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
- "101": {
20
- "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  },
27
- "102": {
28
- "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
- "103": {
36
- "content": "[MASK]",
37
  "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
42
  }
43
  },
44
- "clean_up_tokenization_spaces": true,
45
- "cls_token": "[CLS]",
46
- "do_basic_tokenize": true,
47
- "do_lower_case": false,
48
- "mask_token": "[MASK]",
 
 
 
 
 
49
  "model_max_length": 512,
50
- "never_split": null,
51
- "pad_token": "[PAD]",
52
- "sep_token": "[SEP]",
53
- "strip_accents": null,
54
- "tokenize_chinese_chars": true,
55
- "tokenizer_class": "BertTokenizer",
56
- "unk_token": "[UNK]"
57
  }
 
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
4
+ "content": "<s>NOTUSED",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
10
  },
11
+ "1": {
12
+ "content": "<pad>",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
+ "2": {
20
+ "content": "</s>NOTUSED",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  },
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": "<unk>NOTUSED",
37
  "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
42
+ },
43
+ "5": {
44
+ "content": "<s>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "</s>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "32004": {
60
+ "content": "<mask>",
61
+ "lstrip": true,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
  }
67
  },
68
+ "additional_special_tokens": [
69
+ "<s>NOTUSED",
70
+ "</s>NOTUSED",
71
+ "<unk>NOTUSED"
72
+ ],
73
+ "bos_token": "<s>",
74
+ "clean_up_tokenization_spaces": false,
75
+ "cls_token": "<s>",
76
+ "eos_token": "</s>",
77
+ "mask_token": "<mask>",
78
  "model_max_length": 512,
79
+ "pad_token": "<pad>",
80
+ "sep_token": "</s>",
81
+ "sp_model_kwargs": {},
82
+ "tokenizer_class": "CamembertTokenizer",
83
+ "unk_token": "<unk>"
 
 
84
  }