Upload tokenizer
Browse files- added_tokens.json +1 -1
- tokenizer_config.json +17 -1
- vocab.json +2 -2
added_tokens.json
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
{
|
2 |
"</s>": 58,
|
3 |
-
"
|
4 |
}
|
|
|
1 |
{
|
2 |
"</s>": 58,
|
3 |
+
"<s>": 57
|
4 |
}
|
tokenizer_config.json
CHANGED
@@ -1,6 +1,14 @@
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
"content": "[PAD]",
|
5 |
"lstrip": true,
|
6 |
"normalized": false,
|
@@ -8,6 +16,14 @@
|
|
8 |
"single_word": false,
|
9 |
"special": false
|
10 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
"58": {
|
12 |
"content": "</s>",
|
13 |
"lstrip": false,
|
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
+
"55": {
|
4 |
+
"content": "[UNK]",
|
5 |
+
"lstrip": true,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": true,
|
8 |
+
"single_word": false,
|
9 |
+
"special": false
|
10 |
+
},
|
11 |
+
"56": {
|
12 |
"content": "[PAD]",
|
13 |
"lstrip": true,
|
14 |
"normalized": false,
|
|
|
16 |
"single_word": false,
|
17 |
"special": false
|
18 |
},
|
19 |
+
"57": {
|
20 |
+
"content": "<s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
"58": {
|
28 |
"content": "</s>",
|
29 |
"lstrip": false,
|
vocab.json
CHANGED
@@ -9,8 +9,8 @@
|
|
9 |
"7": 8,
|
10 |
"8": 9,
|
11 |
"9": 10,
|
12 |
-
"[PAD]":
|
13 |
-
"[UNK]":
|
14 |
"a": 11,
|
15 |
"b": 12,
|
16 |
"c": 13,
|
|
|
9 |
"7": 8,
|
10 |
"8": 9,
|
11 |
"9": 10,
|
12 |
+
"[PAD]": 56,
|
13 |
+
"[UNK]": 55,
|
14 |
"a": 11,
|
15 |
"b": 12,
|
16 |
"c": 13,
|