Upload 6 files
Browse files- tokenizer_config.json +7 -0
- vocab.json +0 -0
tokenizer_config.json
CHANGED
@@ -1050,8 +1050,15 @@
|
|
1050 |
"clean_up_tokenization_spaces": true,
|
1051 |
"eos_token": "</s>",
|
1052 |
"extra_ids": 100,
|
|
|
1053 |
"model_max_length": 512,
|
|
|
1054 |
"pad_token": "<pad>",
|
|
|
|
|
|
|
1055 |
"tokenizer_class": "T5Tokenizer",
|
|
|
|
|
1056 |
"unk_token": "<unk>"
|
1057 |
}
|
|
|
1050 |
"clean_up_tokenization_spaces": true,
|
1051 |
"eos_token": "</s>",
|
1052 |
"extra_ids": 100,
|
1053 |
+
"max_length": 512,
|
1054 |
"model_max_length": 512,
|
1055 |
+
"pad_to_multiple_of": null,
|
1056 |
"pad_token": "<pad>",
|
1057 |
+
"pad_token_type_id": 0,
|
1058 |
+
"padding_side": "right",
|
1059 |
+
"stride": 0,
|
1060 |
"tokenizer_class": "T5Tokenizer",
|
1061 |
+
"truncation_side": "right",
|
1062 |
+
"truncation_strategy": "longest_first",
|
1063 |
"unk_token": "<unk>"
|
1064 |
}
|
vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|