Upload tokenizer
Browse files- merges.txt +0 -0
- tokenizer.json +0 -0
- tokenizer_config.json +0 -1
- vocab.json +0 -0
merges.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -4,7 +4,6 @@
|
|
4 |
"<|endoftext|>"
|
5 |
],
|
6 |
"bos_token": "<|endoftext|>",
|
7 |
-
"clean_up_tokenization_spaces": true,
|
8 |
"eos_token": "<|endoftext|>",
|
9 |
"model_max_length": 1000000000000000019884624838656,
|
10 |
"tokenizer_class": "GPT2Tokenizer",
|
|
|
4 |
"<|endoftext|>"
|
5 |
],
|
6 |
"bos_token": "<|endoftext|>",
|
|
|
7 |
"eos_token": "<|endoftext|>",
|
8 |
"model_max_length": 1000000000000000019884624838656,
|
9 |
"tokenizer_class": "GPT2Tokenizer",
|
vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|