Hugging Face's logo

MrFrijo
/
LiAPI

Translation
Transformers
Safetensors
Lingala
French
marian
text2text-generation
traduction
Model card Files Community
MrFrijo commited on
Commit
55bf22a
·
verified ·
1 Parent(s): 37ae045

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +23 -23
  2. tokenizer_config.json +39 -38
  3. vocab.json +0 -0
special_tokens_map.json CHANGED
@@ -1,23 +1,23 @@
1
- {
2
- "eos_token": {
3
- "content": "</s>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "pad_token": {
10
- "content": "<pad>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "unk_token": {
17
- "content": "<unk>",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- }
23
- }
 
1
+ {
2
+ "eos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<pad>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer_config.json CHANGED
@@ -1,38 +1,39 @@
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
- "59513": {
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": "fr",
34
- "sp_model_kwargs": {},
35
- "target_lang": "en",
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
+ "59513": {
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
+ "extra_special_tokens": {},
31
+ "model_max_length": 512,
32
+ "pad_token": "<pad>",
33
+ "separate_vocabs": false,
34
+ "source_lang": "fr",
35
+ "sp_model_kwargs": {},
36
+ "target_lang": "en",
37
+ "tokenizer_class": "MarianTokenizer",
38
+ "unk_token": "<unk>"
39
+ }
vocab.json CHANGED
The diff for this file is too large to render. See raw diff