Commit
•
3e95818
1
Parent(s):
8852c40
Move <|endoftext|> from added_tokens.json to vocab.json
Browse files- added_tokens.json +0 -1
- tokenizer.json +2 -1
- vocab.json +1 -0
added_tokens.json
CHANGED
|
@@ -17,7 +17,6 @@
|
|
| 17 |
"<|da|>": 50285,
|
| 18 |
"<|de|>": 50261,
|
| 19 |
"<|el|>": 50281,
|
| 20 |
-
"<|endoftext|>": 50257,
|
| 21 |
"<|en|>": 50259,
|
| 22 |
"<|es|>": 50262,
|
| 23 |
"<|et|>": 50307,
|
|
|
|
| 17 |
"<|da|>": 50285,
|
| 18 |
"<|de|>": 50261,
|
| 19 |
"<|el|>": 50281,
|
|
|
|
| 20 |
"<|en|>": 50259,
|
| 21 |
"<|es|>": 50262,
|
| 22 |
"<|et|>": 50307,
|
tokenizer.json
CHANGED
|
@@ -51334,7 +51334,8 @@
|
|
| 51334 |
"ĠPakistani": 50253,
|
| 51335 |
"Ġ('": 50254,
|
| 51336 |
"åľº": 50255,
|
| 51337 |
-
"": 50256
|
|
|
|
| 51338 |
},
|
| 51339 |
"merges": [
|
| 51340 |
"Ġ a",
|
|
|
|
| 51334 |
"ĠPakistani": 50253,
|
| 51335 |
"Ġ('": 50254,
|
| 51336 |
"åľº": 50255,
|
| 51337 |
+
"": 50256,
|
| 51338 |
+
"<|endoftext|>": 50257
|
| 51339 |
},
|
| 51340 |
"merges": [
|
| 51341 |
"Ġ a",
|
vocab.json
CHANGED
|
@@ -1,5 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"": 50256,
|
|
|
|
| 3 |
"!": 0,
|
| 4 |
"!!": 1432,
|
| 5 |
"!!!": 4589,
|
|
|
|
| 1 |
{
|
| 2 |
"": 50256,
|
| 3 |
+
"<|endoftext|>": 50257,
|
| 4 |
"!": 0,
|
| 5 |
"!!": 1432,
|
| 6 |
"!!!": 4589,
|