Hugging Face's logo

livinNector
/
IndicBERTv2-MLM-Sam-TLM-NER

Token Classification
Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
livinNector commited on
Commit
1d08d6b
•
1 Parent(s): 2bd4ec8

Upload tokenizer

Browse files
Files changed (4) hide show
  1. .gitattributes +1 -0
  2. tokenizer.json +2 -2
  3. tokenizer_config.json +10 -2
  4. vocab.txt +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
36
+ vocab.txt filter=lfs diff=lfs merge=lfs -text
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6af22a5c4bc890322c365fcb77dd77c06cbb9b088ffa50db1892d5220313c495
3
- size 7749482
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25857a4e12214c69418001835c3661376f03811a2739abd29a1488bd1574bf8a
3
+ size 7749568
tokenizer_config.json CHANGED
@@ -1,5 +1,13 @@
1
  {
2
  "clean_up_tokenization_spaces": true,
3
- "model_max_length": 1000000000000000019884624838656,
4
- "tokenizer_class": "PreTrainedTokenizerFast"
 
 
 
 
 
 
 
 
5
  }
 
1
  {
2
  "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "strip_accents": null,
10
+ "tokenize_chinese_chars": true,
11
+ "tokenizer_class": "BertTokenizer",
12
+ "unk_token": "[UNK]"
13
  }
vocab.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24f7ce20f8093552a0a750b322a1cf99c65558f81c57ff0d58e8253c39ca7ceb
3
+ size 3603559