Upload tokenizer
Browse files- source.spm +0 -0
- target.spm +0 -0
- tokenizer_config.json +3 -3
- vocab.json +0 -0
source.spm
CHANGED
|
Binary files a/source.spm and b/source.spm differ
|
|
|
target.spm
CHANGED
|
Binary files a/target.spm and b/target.spm differ
|
|
|
tokenizer_config.json
CHANGED
|
@@ -16,7 +16,7 @@
|
|
| 16 |
"single_word": false,
|
| 17 |
"special": true
|
| 18 |
},
|
| 19 |
-
"
|
| 20 |
"content": "<pad>",
|
| 21 |
"lstrip": false,
|
| 22 |
"normalized": false,
|
|
@@ -31,9 +31,9 @@
|
|
| 31 |
"pad_token": "<pad>",
|
| 32 |
"return_tensors": "pt",
|
| 33 |
"separate_vocabs": false,
|
| 34 |
-
"source_lang": "
|
| 35 |
"sp_model_kwargs": {},
|
| 36 |
-
"target_lang": "
|
| 37 |
"tokenizer_class": "MarianTokenizer",
|
| 38 |
"unk_token": "<unk>"
|
| 39 |
}
|
|
|
|
| 16 |
"single_word": false,
|
| 17 |
"special": true
|
| 18 |
},
|
| 19 |
+
"62388": {
|
| 20 |
"content": "<pad>",
|
| 21 |
"lstrip": false,
|
| 22 |
"normalized": false,
|
|
|
|
| 31 |
"pad_token": "<pad>",
|
| 32 |
"return_tensors": "pt",
|
| 33 |
"separate_vocabs": false,
|
| 34 |
+
"source_lang": "tr",
|
| 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
|
|
|