Commit
•
cffc94b
1
Parent(s):
920f1d9
Upload 3 files
Browse files- special_tokens_map.json +8 -2
- tokenizer.json +0 -0
- tokenizer_config.json +3 -6
special_tokens_map.json
CHANGED
|
@@ -1,5 +1,11 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"eos_token": "<|endoftext|>",
|
| 4 |
-
"
|
| 5 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|endoftext|>",
|
| 4 |
+
"<|sep|>",
|
| 5 |
+
"<|acc|>",
|
| 6 |
+
"<|tel|>",
|
| 7 |
+
"<|rrn|>"
|
| 8 |
+
],
|
| 9 |
"eos_token": "<|endoftext|>",
|
| 10 |
+
"pad_token": "<|endoftext|>"
|
| 11 |
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,9 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"bos_token": "<|endoftext|>",
|
| 4 |
"eos_token": "<|endoftext|>",
|
| 5 |
-
"
|
| 6 |
-
"
|
| 7 |
-
"tokenizer_class": "GPTNeoXTokenizer",
|
| 8 |
-
"unk_token": "<|endoftext|>"
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"name_or_path": "EleutherAI/polyglot-ko-1.3b",
|
|
|
|
| 3 |
"eos_token": "<|endoftext|>",
|
| 4 |
+
"pad_token": "<|endoftext|>",
|
| 5 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
|
|
|
|
|
|
| 6 |
}
|