Upload tokenizer
Browse files- source.spm +2 -2
- target.spm +2 -2
- tokenizer_config.json +3 -3
- vocab.json +0 -0
source.spm
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c4a99ea3602b29fbf901ade8b93a45efa3d7c64eab8fc5fa812383efa327a87d
|
| 3 |
+
size 706917
|
target.spm
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6dce5fa58fcd7dde9e81e279b8c075bf42ee558278f73d6fb48e342029d7f19
|
| 3 |
+
size 791194
|
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 |
"model_max_length": 512,
|
| 32 |
"pad_token": "<pad>",
|
| 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 |
+
"64171": {
|
| 20 |
"content": "<pad>",
|
| 21 |
"lstrip": false,
|
| 22 |
"normalized": false,
|
|
|
|
| 31 |
"model_max_length": 512,
|
| 32 |
"pad_token": "<pad>",
|
| 33 |
"separate_vocabs": false,
|
| 34 |
+
"source_lang": "mul",
|
| 35 |
"sp_model_kwargs": {},
|
| 36 |
+
"target_lang": "eng",
|
| 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
|
|
|