Upload tokenizer
Browse files- added_tokens.json +2 -4
- spiece.model +2 -2
- tokenizer_config.json +4 -4
added_tokens.json
CHANGED
|
@@ -1,6 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"<pad>":
|
| 3 |
-
"[
|
| 4 |
-
"[MASK]": 8003,
|
| 5 |
-
"[SEP]": 8001
|
| 6 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"<pad>": 8000,
|
| 3 |
+
"[MASK]": 8001
|
|
|
|
|
|
|
| 4 |
}
|
spiece.model
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 sha256:0c4c4de674e45ec7225358bce8cd211d2ce300f504e382c48f9cbca4f940d959
|
| 3 |
+
size 477508
|
tokenizer_config.json
CHANGED
|
@@ -8,7 +8,7 @@
|
|
| 8 |
"single_word": false,
|
| 9 |
"special": true
|
| 10 |
},
|
| 11 |
-
"
|
| 12 |
"content": "[CLS]",
|
| 13 |
"lstrip": false,
|
| 14 |
"normalized": false,
|
|
@@ -16,7 +16,7 @@
|
|
| 16 |
"single_word": false,
|
| 17 |
"special": true
|
| 18 |
},
|
| 19 |
-
"
|
| 20 |
"content": "[SEP]",
|
| 21 |
"lstrip": false,
|
| 22 |
"normalized": false,
|
|
@@ -24,7 +24,7 @@
|
|
| 24 |
"single_word": false,
|
| 25 |
"special": true
|
| 26 |
},
|
| 27 |
-
"
|
| 28 |
"content": "<pad>",
|
| 29 |
"lstrip": false,
|
| 30 |
"normalized": false,
|
|
@@ -32,7 +32,7 @@
|
|
| 32 |
"single_word": false,
|
| 33 |
"special": true
|
| 34 |
},
|
| 35 |
-
"
|
| 36 |
"content": "[MASK]",
|
| 37 |
"lstrip": true,
|
| 38 |
"normalized": false,
|
|
|
|
| 8 |
"single_word": false,
|
| 9 |
"special": true
|
| 10 |
},
|
| 11 |
+
"23": {
|
| 12 |
"content": "[CLS]",
|
| 13 |
"lstrip": false,
|
| 14 |
"normalized": false,
|
|
|
|
| 16 |
"single_word": false,
|
| 17 |
"special": true
|
| 18 |
},
|
| 19 |
+
"24": {
|
| 20 |
"content": "[SEP]",
|
| 21 |
"lstrip": false,
|
| 22 |
"normalized": false,
|
|
|
|
| 24 |
"single_word": false,
|
| 25 |
"special": true
|
| 26 |
},
|
| 27 |
+
"8000": {
|
| 28 |
"content": "<pad>",
|
| 29 |
"lstrip": false,
|
| 30 |
"normalized": false,
|
|
|
|
| 32 |
"single_word": false,
|
| 33 |
"special": true
|
| 34 |
},
|
| 35 |
+
"8001": {
|
| 36 |
"content": "[MASK]",
|
| 37 |
"lstrip": true,
|
| 38 |
"normalized": false,
|