Upload tokenizer
Browse files- special_tokens_map.json +1 -1
- tokenizer.json +0 -0
- tokenizer_config.json +1 -1
- vocab.json +0 -0
special_tokens_map.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
"bos_token": "<|endoftext|>",
|
3 |
"eos_token": "<|endoftext|>",
|
4 |
-
"unk_token": "
|
5 |
}
|
|
|
1 |
{
|
2 |
"bos_token": "<|endoftext|>",
|
3 |
"eos_token": "<|endoftext|>",
|
4 |
+
"unk_token": "<unk>"
|
5 |
}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -5,5 +5,5 @@
|
|
5 |
"eos_token": "<|endoftext|>",
|
6 |
"model_max_length": 1024,
|
7 |
"tokenizer_class": "GPT2Tokenizer",
|
8 |
-
"unk_token": "
|
9 |
}
|
|
|
5 |
"eos_token": "<|endoftext|>",
|
6 |
"model_max_length": 1024,
|
7 |
"tokenizer_class": "GPT2Tokenizer",
|
8 |
+
"unk_token": "<unk>"
|
9 |
}
|
vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|