Text Classification
Transformers
Safetensors
modernbert
mmbert
sentiment-analysis
twitter
multilingual
text-embeddings-inference
Ido-shraga commited on
Commit
acae0f2
·
verified ·
1 Parent(s): 9c17773

Make config and tokenizer loadable by transformers v4

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +7 -10
tokenizer_config.json CHANGED
@@ -1,15 +1,8 @@
1
  {
2
- "backend": "tokenizers",
3
  "bos_token": "<bos>",
4
  "clean_up_tokenization_spaces": false,
5
  "cls_token": "<bos>",
6
  "eos_token": "<eos>",
7
- "extra_special_tokens": [
8
- "<start_of_turn>",
9
- "<end_of_turn>"
10
- ],
11
- "is_local": false,
12
- "local_files_only": false,
13
  "mask_token": "<mask>",
14
  "model_input_names": [
15
  "input_ids",
@@ -20,6 +13,10 @@
20
  "padding_side": "right",
21
  "sep_token": "<eos>",
22
  "spaces_between_special_tokens": false,
23
- "tokenizer_class": "TokenizersBackend",
24
- "unk_token": "<unk>"
25
- }
 
 
 
 
 
1
  {
 
2
  "bos_token": "<bos>",
3
  "clean_up_tokenization_spaces": false,
4
  "cls_token": "<bos>",
5
  "eos_token": "<eos>",
 
 
 
 
 
 
6
  "mask_token": "<mask>",
7
  "model_input_names": [
8
  "input_ids",
 
13
  "padding_side": "right",
14
  "sep_token": "<eos>",
15
  "spaces_between_special_tokens": false,
16
+ "tokenizer_class": "PreTrainedTokenizerFast",
17
+ "unk_token": "<unk>",
18
+ "additional_special_tokens": [
19
+ "<start_of_turn>",
20
+ "<end_of_turn>"
21
+ ]
22
+ }