Upload tokenizer
Browse files- special_tokens_map.json +4 -28
- tokenizer.json +5 -2
special_tokens_map.json
CHANGED
|
@@ -1,30 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token":
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 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": false,
|
| 19 |
-
"normalized": false,
|
| 20 |
-
"rstrip": false,
|
| 21 |
-
"single_word": false
|
| 22 |
-
},
|
| 23 |
-
"unk_token": {
|
| 24 |
-
"content": "<unk>",
|
| 25 |
-
"lstrip": false,
|
| 26 |
-
"normalized": false,
|
| 27 |
-
"rstrip": false,
|
| 28 |
-
"single_word": false
|
| 29 |
-
}
|
| 30 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"pad_token": "<pad>",
|
| 5 |
+
"unk_token": "<unk>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
}
|
tokenizer.json
CHANGED
|
@@ -71,9 +71,12 @@
|
|
| 71 |
"7": 19,
|
| 72 |
"8": 20,
|
| 73 |
"9": 21,
|
| 74 |
-
"
|
| 75 |
"EQUALS": 23,
|
| 76 |
-
"END": 24
|
|
|
|
|
|
|
|
|
|
| 77 |
},
|
| 78 |
"unk_token": "<unk>"
|
| 79 |
}
|
|
|
|
| 71 |
"7": 19,
|
| 72 |
"8": 20,
|
| 73 |
"9": 21,
|
| 74 |
+
"MOD_2": 22,
|
| 75 |
"EQUALS": 23,
|
| 76 |
+
"END": 24,
|
| 77 |
+
"MOD_3": 25,
|
| 78 |
+
"MOD_5": 26,
|
| 79 |
+
"MOD_7": 27
|
| 80 |
},
|
| 81 |
"unk_token": "<unk>"
|
| 82 |
}
|