eunyounglee
commited on
Commit
·
91ab4ad
1
Parent(s):
ae45374
Upload tokenizer
Browse files- special_tokens_map.json +12 -0
- tokenizer.json +0 -0
- tokenizer_config.json +8 -0
special_tokens_map.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|endoftext|>",
|
4 |
+
"<|sep|>",
|
5 |
+
"<|acc|>",
|
6 |
+
"<|tel|>",
|
7 |
+
"<|rrn|>"
|
8 |
+
],
|
9 |
+
"bos_token": "<|startoftext|>",
|
10 |
+
"eos_token": "<|endoftext|>",
|
11 |
+
"pad_token": "<|pad|>"
|
12 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|startoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"name_or_path": "EleutherAI/polyglot-ko-1.3b",
|
5 |
+
"pad_token": "<|pad|>",
|
6 |
+
"special_tokens_map_file": "C:\\Users\\User/.cache\\huggingface\\hub\\models--EleutherAI--polyglot-ko-1.3b\\snapshots\\711da2957fdae31202de86c51edbc0c7f433b9e5\\special_tokens_map.json",
|
7 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
8 |
+
}
|