한국어위키, 나무위키, aihub 구어 웹데이터 1%만 사용해서 8k 토크나이저 학습
Browse files- merges.txt +0 -0
- tokenizer_config.json +1 -1
- vocab.json +0 -0
merges.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -18,7 +18,7 @@
|
|
18 |
"single_word": false
|
19 |
},
|
20 |
"errors": "replace",
|
21 |
-
"name_or_path": "tokenizer-8k
|
22 |
"pad_token": null,
|
23 |
"special_tokens_map_file": null,
|
24 |
"tokenizer_class": "GPT2Tokenizer",
|
|
|
18 |
"single_word": false
|
19 |
},
|
20 |
"errors": "replace",
|
21 |
+
"name_or_path": "tokenizer-8k",
|
22 |
"pad_token": null,
|
23 |
"special_tokens_map_file": null,
|
24 |
"tokenizer_class": "GPT2Tokenizer",
|
vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|