Commit
·
9e42b96
1
Parent(s):
c41548d
Upload tokenizer
Browse files- added_tokens.json +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +11 -2
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<sep>": 32100
|
3 |
+
}
|
special_tokens_map.json
CHANGED
@@ -103,5 +103,6 @@
|
|
103 |
],
|
104 |
"eos_token": "</s>",
|
105 |
"pad_token": "<pad>",
|
|
|
106 |
"unk_token": "<unk>"
|
107 |
}
|
|
|
103 |
],
|
104 |
"eos_token": "</s>",
|
105 |
"pad_token": "<pad>",
|
106 |
+
"sep_token": "<sep>",
|
107 |
"unk_token": "<unk>"
|
108 |
}
|
tokenizer.json
CHANGED
@@ -2,13 +2,13 @@
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
-
"max_length":
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
9 |
"padding": {
|
10 |
"strategy": {
|
11 |
-
"Fixed":
|
12 |
},
|
13 |
"direction": "Right",
|
14 |
"pad_to_multiple_of": null,
|
@@ -943,6 +943,15 @@
|
|
943 |
"rstrip": false,
|
944 |
"normalized": false,
|
945 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
946 |
}
|
947 |
],
|
948 |
"normalizer": {
|
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
+
"max_length": 256,
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
9 |
"padding": {
|
10 |
"strategy": {
|
11 |
+
"Fixed": 256
|
12 |
},
|
13 |
"direction": "Right",
|
14 |
"pad_to_multiple_of": null,
|
|
|
943 |
"rstrip": false,
|
944 |
"normalized": false,
|
945 |
"special": true
|
946 |
+
},
|
947 |
+
{
|
948 |
+
"id": 32100,
|
949 |
+
"content": "<sep>",
|
950 |
+
"single_word": false,
|
951 |
+
"lstrip": false,
|
952 |
+
"rstrip": false,
|
953 |
+
"normalized": true,
|
954 |
+
"special": false
|
955 |
}
|
956 |
],
|
957 |
"normalizer": {
|