under-tree
commited on
Commit
•
5501486
1
Parent(s):
d723b15
End of training
Browse files- added_tokens.json +8 -0
- merges.txt +0 -0
- special_tokens_map.json +13 -0
- tokenizer.json +0 -0
- tokenizer_config.json +10 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|pad|>": 50257,
|
3 |
+
"answer: ": 50261,
|
4 |
+
"context: ": 50262,
|
5 |
+
"question: ": 50259,
|
6 |
+
"topic: ": 50258,
|
7 |
+
"variants: ": 50260
|
8 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"topic: ",
|
4 |
+
"question: ",
|
5 |
+
"variants: ",
|
6 |
+
"answer: ",
|
7 |
+
"context: "
|
8 |
+
],
|
9 |
+
"bos_token": "<|endoftext|>",
|
10 |
+
"eos_token": "<|endoftext|>",
|
11 |
+
"pad_token": "<|pad|>",
|
12 |
+
"unk_token": "<|endoftext|>"
|
13 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
4 |
+
"eos_token": "<|endoftext|>",
|
5 |
+
"model_max_length": 1024,
|
6 |
+
"pad_token": "<|pad|>",
|
7 |
+
"special_tokens_map_file": null,
|
8 |
+
"tokenizer_class": "GPT2Tokenizer",
|
9 |
+
"unk_token": "<|endoftext|>"
|
10 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|