Tom9358 commited on
Commit
7c48c34
·
verified ·
1 Parent(s): f50cb0a

Upload tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer.json +2 -2
  2. tokenizer_config.json +28 -27
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d8596f068fc4cb0aaee6a18903cd59ef84828f48c785ae8f1e9e59a84ddc036
3
- size 32240574
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3853a3e4573223cc64959f90644e4157d315789d434c479c28079f9bb8f95c41
3
+ size 32240584
tokenizer_config.json CHANGED
@@ -1,27 +1,28 @@
1
- {
2
- "backend": "tokenizers",
3
- "bos_token": "<s>",
4
- "cls_token": "<s>",
5
- "eos_token": "</s>",
6
- "extra_special_tokens": [
7
- "gos_Latn"
8
- ],
9
- "is_local": true,
10
- "legacy_behaviour": false,
11
- "mask_token": "<mask>",
12
- "max_length": 43,
13
- "model_max_length": 1024,
14
- "pad_to_multiple_of": null,
15
- "pad_token": "<pad>",
16
- "pad_token_type_id": 0,
17
- "padding_side": "right",
18
- "sep_token": "</s>",
19
- "sp_model_kwargs": {},
20
- "src_lang": "nld_Latn",
21
- "stride": 0,
22
- "tgt_lang": "gos_Latn",
23
- "tokenizer_class": "NllbTokenizer",
24
- "truncation_side": "right",
25
- "truncation_strategy": "longest_first",
26
- "unk_token": "<unk>"
27
- }
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "extra_special_tokens": [
7
+ "gos_Latn"
8
+ ],
9
+ "is_local": true,
10
+ "legacy_behaviour": false,
11
+ "local_files_only": false,
12
+ "mask_token": "<mask>",
13
+ "max_length": 47,
14
+ "model_max_length": 1024,
15
+ "pad_to_multiple_of": null,
16
+ "pad_token": "<pad>",
17
+ "pad_token_type_id": 0,
18
+ "padding_side": "right",
19
+ "sep_token": "</s>",
20
+ "sp_model_kwargs": {},
21
+ "src_lang": "nld_Latn",
22
+ "stride": 0,
23
+ "tgt_lang": null,
24
+ "tokenizer_class": "NllbTokenizer",
25
+ "truncation_side": "right",
26
+ "truncation_strategy": "longest_first",
27
+ "unk_token": "<unk>"
28
+ }