Hugging Face's logo

MinhNguyen2503
/
sentiment_model_phobert

Sentence Similarity
sentence-transformers
Safetensors
Transformers
English
bert
feature-extraction
text-embeddings-inference
Model card Files
xet
 Community
MinhNguyen2503 commited on
Commit
a806f6c
·
verified ·
1 Parent(s): 8b6b6a3

Upload tokenizer

Browse files
Files changed (5) hide show
  1. added_tokens.json +3 -0
  2. bpe.codes +0 -0
  3. special_tokens_map.json +7 -35
  4. tokenizer_config.json +18 -28
  5. vocab.txt +0 -0
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<mask>": 64000
3
+ }
bpe.codes ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json CHANGED
@@ -1,37 +1,9 @@
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
+ "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>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  }
tokenizer_config.json CHANGED
@@ -1,39 +1,39 @@
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,
@@ -41,25 +41,15 @@
41
  "special": true
42
  }
43
  },
 
44
  "clean_up_tokenization_spaces": false,
45
- "cls_token": "[CLS]",
46
- "do_basic_tokenize": true,
47
- "do_lower_case": true,
48
  "extra_special_tokens": {},
49
- "mask_token": "[MASK]",
50
- "max_length": 128,
51
- "model_max_length": 256,
52
- "never_split": null,
53
- "pad_to_multiple_of": null,
54
- "pad_token": "[PAD]",
55
- "pad_token_type_id": 0,
56
- "padding_side": "right",
57
- "sep_token": "[SEP]",
58
- "stride": 0,
59
- "strip_accents": null,
60
- "tokenize_chinese_chars": true,
61
- "tokenizer_class": "BertTokenizer",
62
- "truncation_side": "right",
63
- "truncation_strategy": "longest_first",
64
- "unk_token": "[UNK]"
65
  }
 
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
4
+ "content": "<s>",
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>",
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
+ "64000": {
36
+ "content": "<mask>",
37
  "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
 
41
  "special": true
42
  }
43
  },
44
+ "bos_token": "<s>",
45
  "clean_up_tokenization_spaces": false,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
 
48
  "extra_special_tokens": {},
49
+ "mask_token": "<mask>",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "pad_token": "<pad>",
52
+ "sep_token": "</s>",
53
+ "tokenizer_class": "PhobertTokenizer",
54
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
55
  }
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff