luzalbaposse commited on
Commit
0aa90f4
·
verified ·
1 Parent(s): 2510bde

Upload folder using huggingface_hub

Browse files
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "HelloBERT",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
 
1
  {
2
+ "_name_or_path": "bert-base-uncased",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7cf76a2a145a83c17538dc0d85c5aa7524fd7b5af5eff8d3045562c861f52f53
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51f026d67abac6b1b30e4da47a1a4ec0f62b299fc8786b9536d5a6c8a5cc7d32
3
  size 437958648
special_tokens_map.json CHANGED
@@ -1,37 +1,7 @@
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
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
tokenizer.json CHANGED
@@ -1,7 +1,21 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
4
- "padding": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "added_tokens": [
6
  {
7
  "id": 0,
 
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": {
11
+ "Fixed": 512
12
+ },
13
+ "direction": "Right",
14
+ "pad_to_multiple_of": null,
15
+ "pad_id": 0,
16
+ "pad_type_id": 0,
17
+ "pad_token": "[PAD]"
18
+ },
19
  "added_tokens": [
20
  {
21
  "id": 0,
tokenizer_config.json CHANGED
@@ -45,18 +45,11 @@
45
  "cls_token": "[CLS]",
46
  "do_lower_case": true,
47
  "mask_token": "[MASK]",
48
- "max_length": 512,
49
  "model_max_length": 512,
50
- "pad_to_multiple_of": null,
51
  "pad_token": "[PAD]",
52
- "pad_token_type_id": 0,
53
- "padding_side": "right",
54
  "sep_token": "[SEP]",
55
- "stride": 0,
56
  "strip_accents": null,
57
  "tokenize_chinese_chars": true,
58
  "tokenizer_class": "BertTokenizer",
59
- "truncation_side": "right",
60
- "truncation_strategy": "longest_first",
61
  "unk_token": "[UNK]"
62
  }
 
45
  "cls_token": "[CLS]",
46
  "do_lower_case": true,
47
  "mask_token": "[MASK]",
 
48
  "model_max_length": 512,
 
49
  "pad_token": "[PAD]",
 
 
50
  "sep_token": "[SEP]",
 
51
  "strip_accents": null,
52
  "tokenize_chinese_chars": true,
53
  "tokenizer_class": "BertTokenizer",
 
 
54
  "unk_token": "[UNK]"
55
  }