Update processor after resumed training
Browse files- special_tokens_map.json +28 -4
- vocab.json +5 -5
special_tokens_map.json
CHANGED
|
@@ -1,6 +1,30 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token":
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": true,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": true,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "[UNK]",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": true,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
}
|
vocab.json
CHANGED
|
@@ -1,4 +1,7 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
| 2 |
"ء": 0,
|
| 3 |
"ا": 1,
|
| 4 |
"ب": 2,
|
|
@@ -55,8 +58,5 @@
|
|
| 55 |
"ۃ": 53,
|
| 56 |
"ی": 54,
|
| 57 |
"ې": 55,
|
| 58 |
-
"ے": 56
|
| 59 |
-
|
| 60 |
-
"[UNK]": 58,
|
| 61 |
-
"[PAD]": 59
|
| 62 |
-
}
|
|
|
|
| 1 |
{
|
| 2 |
+
" ": 57,
|
| 3 |
+
"[PAD]": 59,
|
| 4 |
+
"[UNK]": 58,
|
| 5 |
"ء": 0,
|
| 6 |
"ا": 1,
|
| 7 |
"ب": 2,
|
|
|
|
| 58 |
"ۃ": 53,
|
| 59 |
"ی": 54,
|
| 60 |
"ې": 55,
|
| 61 |
+
"ے": 56
|
| 62 |
+
}
|
|
|
|
|
|
|
|
|