Upload tokenizer
Browse files- tokenizer_config.json +4 -0
tokenizer_config.json
CHANGED
|
@@ -160,9 +160,13 @@
|
|
| 160 |
"bos_token": "<|endoftext|>",
|
| 161 |
"clean_up_tokenization_spaces": false,
|
| 162 |
"eos_token": "<|endoftext|>",
|
|
|
|
| 163 |
"model_max_length": 8192,
|
| 164 |
"pad_token": "<|endoftext|>",
|
|
|
|
| 165 |
"tokenizer_class": "GPT2Tokenizer",
|
|
|
|
|
|
|
| 166 |
"unk_token": "<|endoftext|>",
|
| 167 |
"vocab_size": 49152
|
| 168 |
}
|
|
|
|
| 160 |
"bos_token": "<|endoftext|>",
|
| 161 |
"clean_up_tokenization_spaces": false,
|
| 162 |
"eos_token": "<|endoftext|>",
|
| 163 |
+
"max_length": 512,
|
| 164 |
"model_max_length": 8192,
|
| 165 |
"pad_token": "<|endoftext|>",
|
| 166 |
+
"stride": 0,
|
| 167 |
"tokenizer_class": "GPT2Tokenizer",
|
| 168 |
+
"truncation_side": "right",
|
| 169 |
+
"truncation_strategy": "longest_first",
|
| 170 |
"unk_token": "<|endoftext|>",
|
| 171 |
"vocab_size": 49152
|
| 172 |
}
|