Commit
•
48eee60
1
Parent(s):
2f0a925
Upload tokenizer
Browse files- special_tokens_map.json +41 -0
- tokenizer.json +0 -0
- tokenizer_config.json +0 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
">>TITLE<<",
|
| 4 |
+
">>ABSTRACT<<",
|
| 5 |
+
">>INTRODUCTION<<",
|
| 6 |
+
">>SUMMARY<<",
|
| 7 |
+
">>COMMENT<<",
|
| 8 |
+
">>ANSWER<<",
|
| 9 |
+
">>QUESTION<<",
|
| 10 |
+
">>DOMAIN<<",
|
| 11 |
+
">>EMAIL_ADDRESS<<",
|
| 12 |
+
">>IP_ADDRESS<<",
|
| 13 |
+
"<|startoftext|>",
|
| 14 |
+
">>IP_ADDRESS_0<<",
|
| 15 |
+
">>IP_ADDRESS_1<<",
|
| 16 |
+
">>IP_ADDRESS_2<<",
|
| 17 |
+
">>IP_ADDRESS_3<<",
|
| 18 |
+
">>IP_ADDRESS_4<<",
|
| 19 |
+
">>IP_ADDRESS_5<<",
|
| 20 |
+
">>IP_ADDRESS_6<<",
|
| 21 |
+
">>IP_ADDRESS_7<<",
|
| 22 |
+
">>IP_ADDRESS_8<<",
|
| 23 |
+
">>IP_ADDRESS_9<<",
|
| 24 |
+
">>PASSWORD<<",
|
| 25 |
+
">>KEY<<"
|
| 26 |
+
],
|
| 27 |
+
"eos_token": {
|
| 28 |
+
"content": "<|endoftext|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false
|
| 33 |
+
},
|
| 34 |
+
"pad_token": {
|
| 35 |
+
"content": "<|pad|>",
|
| 36 |
+
"lstrip": false,
|
| 37 |
+
"normalized": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"single_word": false
|
| 40 |
+
}
|
| 41 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|