Commit
•
e964d9b
1
Parent(s):
a916ca4
Upload tokenizer
Browse files- tokenizer_config.json +4 -0
tokenizer_config.json
CHANGED
|
@@ -13,8 +13,12 @@
|
|
| 13 |
"bos_token": "<|endoftext|>",
|
| 14 |
"clean_up_tokenization_spaces": true,
|
| 15 |
"eos_token": "<|endoftext|>",
|
|
|
|
| 16 |
"model_max_length": 1024,
|
| 17 |
"pad_token": "<|endoftext|>",
|
|
|
|
| 18 |
"tokenizer_class": "GPT2Tokenizer",
|
|
|
|
|
|
|
| 19 |
"unk_token": "<|endoftext|>"
|
| 20 |
}
|
|
|
|
| 13 |
"bos_token": "<|endoftext|>",
|
| 14 |
"clean_up_tokenization_spaces": true,
|
| 15 |
"eos_token": "<|endoftext|>",
|
| 16 |
+
"max_length": 512,
|
| 17 |
"model_max_length": 1024,
|
| 18 |
"pad_token": "<|endoftext|>",
|
| 19 |
+
"stride": 0,
|
| 20 |
"tokenizer_class": "GPT2Tokenizer",
|
| 21 |
+
"truncation_side": "right",
|
| 22 |
+
"truncation_strategy": "longest_first",
|
| 23 |
"unk_token": "<|endoftext|>"
|
| 24 |
}
|