Hugging Face's logo

Danieljacobsen
/
Helsinki-DA-SV-v2

Text2Text Generation
Transformers
Safetensors
marian
Inference Endpoints
Model card Files Community
Danieljacobsen commited on
Commit
10cee89
•
1 Parent(s): 7427535

Update tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +38 -38
tokenizer_config.json CHANGED
@@ -1,38 +1,38 @@
1
- {
2
- "added_tokens_decoder": {
3
- "0": {
4
- "content": "</s>",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "1": {
12
- "content": "<unk>",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "58011": {
20
- "content": "<pad>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- }
27
- },
28
- "clean_up_tokenization_spaces": true,
29
- "eos_token": "</s>",
30
- "model_max_length": 512,
31
- "pad_token": "<pad>",
32
- "separate_vocabs": false,
33
- "source_lang": "de+nl+fy+af+da+fo+is+no+nb+nn+sv",
34
- "sp_model_kwargs": {},
35
- "target_lang": "de+nl+fy+af+da+fo+is+no+nb+nn+sv",
36
- "tokenizer_class": "MarianTokenizer",
37
- "unk_token": "<unk>"
38
- }
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "</s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<unk>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "58011": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "clean_up_tokenization_spaces": true,
29
+ "eos_token": "</s>",
30
+ "model_max_length": 512,
31
+ "pad_token": "<pad>",
32
+ "separate_vocabs": false,
33
+ "source_lang": "da",
34
+ "sp_model_kwargs": {},
35
+ "target_lang": "sv",
36
+ "tokenizer_class": "MarianTokenizer",
37
+ "unk_token": "<unk>"
38
+ }