MUmairAB commited on
Commit
b7f335f
1 Parent(s): 05ae50e

Upload tokenizer

Browse files
Files changed (5) hide show
  1. source.spm +0 -0
  2. special_tokens_map.json +5 -0
  3. target.spm +0 -0
  4. tokenizer_config.json +13 -0
  5. vocab.json +0 -0
source.spm ADDED
Binary file (778 kB). View file
 
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "pad_token": "<pad>",
4
+ "unk_token": "<unk>"
5
+ }
target.spm ADDED
Binary file (802 kB). View file
 
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "eos_token": "</s>",
4
+ "model_max_length": 512,
5
+ "pad_token": "<pad>",
6
+ "return_tensor": "tf",
7
+ "separate_vocabs": false,
8
+ "source_lang": "en",
9
+ "sp_model_kwargs": {},
10
+ "target_lang": "fr",
11
+ "tokenizer_class": "MarianTokenizer",
12
+ "unk_token": "<unk>"
13
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff