aapot
commited on
Commit
•
4ebb03d
1
Parent(s):
c1f8001
Fix tokenizer
Browse files- special_tokens_map.json +3 -3
- tokenizer.json +3 -3
- tokenizer.model +0 -3
- tokenizer_config.json +3 -3
special_tokens_map.json
CHANGED
|
@@ -2,21 +2,21 @@
|
|
| 2 |
"bos_token": {
|
| 3 |
"content": "<s>",
|
| 4 |
"lstrip": false,
|
| 5 |
-
"normalized":
|
| 6 |
"rstrip": false,
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"eos_token": {
|
| 10 |
"content": "</s>",
|
| 11 |
"lstrip": false,
|
| 12 |
-
"normalized":
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
"unk_token": {
|
| 17 |
"content": "<unk>",
|
| 18 |
"lstrip": false,
|
| 19 |
-
"normalized":
|
| 20 |
"rstrip": false,
|
| 21 |
"single_word": false
|
| 22 |
}
|
|
|
|
| 2 |
"bos_token": {
|
| 3 |
"content": "<s>",
|
| 4 |
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
"rstrip": false,
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"eos_token": {
|
| 10 |
"content": "</s>",
|
| 11 |
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
"unk_token": {
|
| 17 |
"content": "<unk>",
|
| 18 |
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
"rstrip": false,
|
| 21 |
"single_word": false
|
| 22 |
}
|
tokenizer.json
CHANGED
|
@@ -9,7 +9,7 @@
|
|
| 9 |
"single_word": false,
|
| 10 |
"lstrip": false,
|
| 11 |
"rstrip": false,
|
| 12 |
-
"normalized":
|
| 13 |
"special": true
|
| 14 |
},
|
| 15 |
{
|
|
@@ -18,7 +18,7 @@
|
|
| 18 |
"single_word": false,
|
| 19 |
"lstrip": false,
|
| 20 |
"rstrip": false,
|
| 21 |
-
"normalized":
|
| 22 |
"special": true
|
| 23 |
},
|
| 24 |
{
|
|
@@ -27,7 +27,7 @@
|
|
| 27 |
"single_word": false,
|
| 28 |
"lstrip": false,
|
| 29 |
"rstrip": false,
|
| 30 |
-
"normalized":
|
| 31 |
"special": true
|
| 32 |
}
|
| 33 |
],
|
|
|
|
| 9 |
"single_word": false,
|
| 10 |
"lstrip": false,
|
| 11 |
"rstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
"special": true
|
| 14 |
},
|
| 15 |
{
|
|
|
|
| 18 |
"single_word": false,
|
| 19 |
"lstrip": false,
|
| 20 |
"rstrip": false,
|
| 21 |
+
"normalized": true,
|
| 22 |
"special": true
|
| 23 |
},
|
| 24 |
{
|
|
|
|
| 27 |
"single_word": false,
|
| 28 |
"lstrip": false,
|
| 29 |
"rstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
"special": true
|
| 32 |
}
|
| 33 |
],
|
tokenizer.model
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:ab1b681ec7fc02fed5edd3026687d7a692a918c4dd8e150ca2e3994a6229843b
|
| 3 |
-
size 534194
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer_config.json
CHANGED
|
@@ -5,7 +5,7 @@
|
|
| 5 |
"__type": "AddedToken",
|
| 6 |
"content": "<s>",
|
| 7 |
"lstrip": false,
|
| 8 |
-
"normalized":
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false
|
| 11 |
},
|
|
@@ -14,7 +14,7 @@
|
|
| 14 |
"__type": "AddedToken",
|
| 15 |
"content": "</s>",
|
| 16 |
"lstrip": false,
|
| 17 |
-
"normalized":
|
| 18 |
"rstrip": false,
|
| 19 |
"single_word": false
|
| 20 |
},
|
|
@@ -26,7 +26,7 @@
|
|
| 26 |
"__type": "AddedToken",
|
| 27 |
"content": "<unk>",
|
| 28 |
"lstrip": false,
|
| 29 |
-
"normalized":
|
| 30 |
"rstrip": false,
|
| 31 |
"single_word": false
|
| 32 |
}
|
|
|
|
| 5 |
"__type": "AddedToken",
|
| 6 |
"content": "<s>",
|
| 7 |
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false
|
| 11 |
},
|
|
|
|
| 14 |
"__type": "AddedToken",
|
| 15 |
"content": "</s>",
|
| 16 |
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
"rstrip": false,
|
| 19 |
"single_word": false
|
| 20 |
},
|
|
|
|
| 26 |
"__type": "AddedToken",
|
| 27 |
"content": "<unk>",
|
| 28 |
"lstrip": false,
|
| 29 |
+
"normalized": true,
|
| 30 |
"rstrip": false,
|
| 31 |
"single_word": false
|
| 32 |
}
|