Upload 4 files
Browse files- special_tokens_map.json +24 -0
- tokenizer.json +9 -12
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<unk>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": true,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.json
CHANGED
@@ -9,7 +9,7 @@
|
|
9 |
"single_word": false,
|
10 |
"lstrip": false,
|
11 |
"rstrip": false,
|
12 |
-
"normalized":
|
13 |
"special": true
|
14 |
},
|
15 |
{
|
@@ -27,16 +27,7 @@
|
|
27 |
"single_word": false,
|
28 |
"lstrip": false,
|
29 |
"rstrip": false,
|
30 |
-
"normalized":
|
31 |
-
"special": true
|
32 |
-
},
|
33 |
-
{
|
34 |
-
"id": 32000,
|
35 |
-
"content": "[PAD]",
|
36 |
-
"single_word": false,
|
37 |
-
"lstrip": false,
|
38 |
-
"rstrip": false,
|
39 |
-
"normalized": false,
|
40 |
"special": true
|
41 |
}
|
42 |
],
|
@@ -86,10 +77,16 @@
|
|
86 |
"type_id": 0
|
87 |
}
|
88 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
89 |
{
|
90 |
"Sequence": {
|
91 |
"id": "B",
|
92 |
-
"type_id":
|
93 |
}
|
94 |
}
|
95 |
],
|
|
|
9 |
"single_word": false,
|
10 |
"lstrip": false,
|
11 |
"rstrip": false,
|
12 |
+
"normalized": false,
|
13 |
"special": true
|
14 |
},
|
15 |
{
|
|
|
27 |
"single_word": false,
|
28 |
"lstrip": false,
|
29 |
"rstrip": false,
|
30 |
+
"normalized": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
31 |
"special": true
|
32 |
}
|
33 |
],
|
|
|
77 |
"type_id": 0
|
78 |
}
|
79 |
},
|
80 |
+
{
|
81 |
+
"SpecialToken": {
|
82 |
+
"id": "<s>",
|
83 |
+
"type_id": 1
|
84 |
+
}
|
85 |
+
},
|
86 |
{
|
87 |
"Sequence": {
|
88 |
"id": "B",
|
89 |
+
"type_id": 1
|
90 |
}
|
91 |
}
|
92 |
],
|