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
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
-
"
|
4 |
"content": "</s>",
|
5 |
"lstrip": false,
|
6 |
"normalized": false,
|
@@ -8,7 +8,7 @@
|
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
-
"
|
12 |
"content": "<unk>",
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
@@ -16,7 +16,7 @@
|
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
-
"
|
20 |
"content": "<pad>",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
+
"43741": {
|
4 |
"content": "</s>",
|
5 |
"lstrip": false,
|
6 |
"normalized": false,
|
|
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
+
"52508": {
|
12 |
"content": "<unk>",
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
|
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
+
"57059": {
|
20 |
"content": "<pad>",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|