Hugging Face's logo

puettmann
/
Quadrifoglio-mt-it-en

Translation
Transformers
Safetensors
English
Italian
mt5
text2text-generation
seq2seq
Inference Endpoints
Model card Files Community
Leonard Püttmann commited on
Commit
cc2dac4
·
verified ·
1 Parent(s): d74cc3f

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +23 -23
  2. tokenizer.json +2 -2
  3. tokenizer_config.json +42 -38
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.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ee660ae764cd56ecac9dbe82d766502034efac119fc579414afcd68d4f6b922
3
- size 16315191
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c98f8344834558c781a4369f923c105460f69bb6c6cf3fe903893be98d76aab1
3
+ size 16315289
tokenizer_config.json CHANGED
@@ -1,38 +1,42 @@
1
- {
2
- "added_tokens_decoder": {
3
- "0": {
4
- "content": "<pad>",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "1": {
12
- "content": "</s>",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "2": {
20
- "content": "<unk>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- }
27
- },
28
- "additional_special_tokens": [],
29
- "clean_up_tokenization_spaces": false,
30
- "eos_token": "</s>",
31
- "extra_ids": 0,
32
- "extra_special_tokens": {},
33
- "model_max_length": 1000000000000000019884624838656,
34
- "pad_token": "<pad>",
35
- "sp_model_kwargs": {},
36
- "tokenizer_class": "T5Tokenizer",
37
- "unk_token": "<unk>"
38
- }
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "</s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<unk>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "additional_special_tokens": [],
29
+ "clean_up_tokenization_spaces": false,
30
+ "eos_token": "</s>",
31
+ "extra_ids": 0,
32
+ "extra_special_tokens": {},
33
+ "max_length": 256,
34
+ "model_max_length": 1000000000000000019884624838656,
35
+ "pad_token": "<pad>",
36
+ "sp_model_kwargs": {},
37
+ "stride": 0,
38
+ "tokenizer_class": "T5Tokenizer",
39
+ "truncation_side": "right",
40
+ "truncation_strategy": "longest_first",
41
+ "unk_token": "<unk>"
42
+ }