Upload tokenizer
Browse files- tokenizer_config.json +10 -2
tokenizer_config.json
CHANGED
|
@@ -41,7 +41,15 @@
|
|
| 41 |
"special": true
|
| 42 |
}
|
| 43 |
},
|
| 44 |
-
"ambiguous_token_ids":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
"auto_map": {
|
| 46 |
"AutoTokenizer": [
|
| 47 |
"tokenizer.ProteinTokenizer",
|
|
@@ -69,5 +77,5 @@
|
|
| 69 |
"truncation_side": "right",
|
| 70 |
"unk_token": "<unk>",
|
| 71 |
"unk_token_id": 1,
|
| 72 |
-
"vocab_path": "
|
| 73 |
}
|
|
|
|
| 41 |
"special": true
|
| 42 |
}
|
| 43 |
},
|
| 44 |
+
"ambiguous_token_ids": [
|
| 45 |
+
1,
|
| 46 |
+
6,
|
| 47 |
+
7,
|
| 48 |
+
8,
|
| 49 |
+
9,
|
| 50 |
+
10,
|
| 51 |
+
11
|
| 52 |
+
],
|
| 53 |
"auto_map": {
|
| 54 |
"AutoTokenizer": [
|
| 55 |
"tokenizer.ProteinTokenizer",
|
|
|
|
| 77 |
"truncation_side": "right",
|
| 78 |
"unk_token": "<unk>",
|
| 79 |
"unk_token_id": 1,
|
| 80 |
+
"vocab_path": "conf/tokenizer/amplify_vocab.txt"
|
| 81 |
}
|