AlexWortega
commited on
Commit
•
ea01343
1
Parent(s):
04e1087
Upload tokenizer
Browse files- added_tokens.json +3 -0
- special_tokens_map.json +4 -1
- tokenizer.json +27 -0
added_tokens.json
CHANGED
@@ -1,5 +1,8 @@
|
|
1 |
{
|
2 |
"</code>": 50259,
|
3 |
"<code>": 50258,
|
|
|
|
|
|
|
4 |
"<|endoftext|>": 50257
|
5 |
}
|
|
|
1 |
{
|
2 |
"</code>": 50259,
|
3 |
"<code>": 50258,
|
4 |
+
"<instructionE>": 50261,
|
5 |
+
"<instructionS>": 50260,
|
6 |
+
"<next>": 50262,
|
7 |
"<|endoftext|>": 50257
|
8 |
}
|
special_tokens_map.json
CHANGED
@@ -1,7 +1,10 @@
|
|
1 |
{
|
2 |
"additional_special_tokens": [
|
3 |
"<code>",
|
4 |
-
"</code>"
|
|
|
|
|
|
|
5 |
],
|
6 |
"bos_token": {
|
7 |
"content": "<|endoftext|>",
|
|
|
1 |
{
|
2 |
"additional_special_tokens": [
|
3 |
"<code>",
|
4 |
+
"</code>",
|
5 |
+
"<instructionS>",
|
6 |
+
"<instructionE>",
|
7 |
+
"<next>"
|
8 |
],
|
9 |
"bos_token": {
|
10 |
"content": "<|endoftext|>",
|
tokenizer.json
CHANGED
@@ -29,6 +29,33 @@
|
|
29 |
"rstrip": false,
|
30 |
"normalized": false,
|
31 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
}
|
33 |
],
|
34 |
"normalizer": null,
|
|
|
29 |
"rstrip": false,
|
30 |
"normalized": false,
|
31 |
"special": true
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"id": 50260,
|
35 |
+
"content": "<instructionS>",
|
36 |
+
"single_word": false,
|
37 |
+
"lstrip": false,
|
38 |
+
"rstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"special": true
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"id": 50261,
|
44 |
+
"content": "<instructionE>",
|
45 |
+
"single_word": false,
|
46 |
+
"lstrip": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"id": 50262,
|
53 |
+
"content": "<next>",
|
54 |
+
"single_word": false,
|
55 |
+
"lstrip": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"special": true
|
59 |
}
|
60 |
],
|
61 |
"normalizer": null,
|