Upload tokenizer
Browse files- special_tokens_map.json +14 -3
- tokenizer.json +0 -0
- tokenizer_config.json +1 -3
special_tokens_map.json
CHANGED
@@ -1,5 +1,16 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
|
4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
}
|
|
|
1 |
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
">>TITLE<<",
|
4 |
+
">>ABSTRACT<<",
|
5 |
+
">>INTRODUCTION<<",
|
6 |
+
">>SUMMARY<<",
|
7 |
+
">>COMMENT<<",
|
8 |
+
">>ANSWER<<",
|
9 |
+
">>QUESTION<<",
|
10 |
+
">>DOMAIN<<",
|
11 |
+
">>PREFIX<<",
|
12 |
+
">>SUFFIX<<",
|
13 |
+
">>MIDDLE<<"
|
14 |
+
],
|
15 |
+
"eos_token": "<|endoftext|>"
|
16 |
}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,9 +1,7 @@
|
|
1 |
{
|
2 |
"add_prefix_space": false,
|
3 |
-
"bos_token": "<|endoftext|>",
|
4 |
"clean_up_tokenization_spaces": true,
|
5 |
"eos_token": "<|endoftext|>",
|
6 |
"model_max_length": 2048,
|
7 |
-
"tokenizer_class": "
|
8 |
-
"unk_token": "<|endoftext|>"
|
9 |
}
|
|
|
1 |
{
|
2 |
"add_prefix_space": false,
|
|
|
3 |
"clean_up_tokenization_spaces": true,
|
4 |
"eos_token": "<|endoftext|>",
|
5 |
"model_max_length": 2048,
|
6 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
|
|
7 |
}
|