Upload tokenizer
#2
by
ouasdg
- opened
- merges.txt +0 -0
- tokenizer.json +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.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -3,7 +3,7 @@
|
|
| 3 |
"bos_token": "<|endoftext|>",
|
| 4 |
"clean_up_tokenization_spaces": true,
|
| 5 |
"eos_token": "<|endoftext|>",
|
| 6 |
-
"model_max_length":
|
| 7 |
"tokenizer_class": "GPT2Tokenizer",
|
| 8 |
"unk_token": "<|endoftext|>"
|
| 9 |
}
|
|
|
|
| 3 |
"bos_token": "<|endoftext|>",
|
| 4 |
"clean_up_tokenization_spaces": true,
|
| 5 |
"eos_token": "<|endoftext|>",
|
| 6 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 7 |
"tokenizer_class": "GPT2Tokenizer",
|
| 8 |
"unk_token": "<|endoftext|>"
|
| 9 |
}
|
vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|