Hugging Face's logo

Vedansh-Gupta
/
depression-distilbert

Text Classification
Transformers
Safetensors
distilbert
text-embeddings-inference
Model card Files
xet
 Community
Vedansh-Gupta commited on
Commit
c2e8763
·
verified ·
1 Parent(s): 18fce01

Upload tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer.json +2 -2
  2. tokenizer_config.json +8 -1
tokenizer.json CHANGED
@@ -2,13 +2,13 @@
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
- "max_length": 150,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
9
  "padding": {
10
  "strategy": {
11
- "Fixed": 150
12
  },
13
  "direction": "Right",
14
  "pad_to_multiple_of": null,
 
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
+ "max_length": 128,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
9
  "padding": {
10
  "strategy": {
11
+ "Fixed": 128
12
  },
13
  "direction": "Right",
14
  "pad_to_multiple_of": null,
tokenizer_config.json CHANGED
@@ -2,14 +2,21 @@
2
  "backend": "tokenizers",
3
  "cls_token": "[CLS]",
4
  "do_lower_case": true,
5
- "is_local": false,
6
  "local_files_only": false,
7
  "mask_token": "[MASK]",
 
8
  "model_max_length": 512,
 
9
  "pad_token": "[PAD]",
 
 
10
  "sep_token": "[SEP]",
 
11
  "strip_accents": null,
12
  "tokenize_chinese_chars": true,
13
  "tokenizer_class": "DistilBertTokenizer",
 
 
14
  "unk_token": "[UNK]"
15
  }
 
2
  "backend": "tokenizers",
3
  "cls_token": "[CLS]",
4
  "do_lower_case": true,
5
+ "is_local": true,
6
  "local_files_only": false,
7
  "mask_token": "[MASK]",
8
+ "max_length": 128,
9
  "model_max_length": 512,
10
+ "pad_to_multiple_of": null,
11
  "pad_token": "[PAD]",
12
+ "pad_token_type_id": 0,
13
+ "padding_side": "right",
14
  "sep_token": "[SEP]",
15
+ "stride": 0,
16
  "strip_accents": null,
17
  "tokenize_chinese_chars": true,
18
  "tokenizer_class": "DistilBertTokenizer",
19
+ "truncation_side": "right",
20
+ "truncation_strategy": "longest_first",
21
  "unk_token": "[UNK]"
22
  }