Upload tokenizer
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +2 -1
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -11,8 +11,9 @@
|
|
| 11 |
}
|
| 12 |
},
|
| 13 |
"bos_token": "<|endoftext|>",
|
| 14 |
-
"clean_up_tokenization_spaces":
|
| 15 |
"eos_token": "<|endoftext|>",
|
|
|
|
| 16 |
"model_max_length": 1024,
|
| 17 |
"pad_token": "<|endoftext|>",
|
| 18 |
"tokenizer_class": "GPT2Tokenizer",
|
|
|
|
| 11 |
}
|
| 12 |
},
|
| 13 |
"bos_token": "<|endoftext|>",
|
| 14 |
+
"clean_up_tokenization_spaces": false,
|
| 15 |
"eos_token": "<|endoftext|>",
|
| 16 |
+
"extra_special_tokens": {},
|
| 17 |
"model_max_length": 1024,
|
| 18 |
"pad_token": "<|endoftext|>",
|
| 19 |
"tokenizer_class": "GPT2Tokenizer",
|