andreaskoepf
commited on
Commit
•
cfc2629
1
Parent(s):
a0c7912
Upload tokenizer
Browse files- special_tokens_map.json +18 -0
- tokenizer.json +0 -0
- tokenizer_config.json +7 -0
special_tokens_map.json
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"<|im_start|>",
|
15 |
+
"<|im_end|>"
|
16 |
+
],
|
17 |
+
"eos_token": "<|endoftext|>"
|
18 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
}
|