Upload tokenizer
Browse files- tokenizer_config.json +8 -0
tokenizer_config.json
CHANGED
@@ -102,11 +102,19 @@
|
|
102 |
"<extra_id_99>"
|
103 |
],
|
104 |
"clean_up_tokenization_spaces": true,
|
|
|
105 |
"eos_token": "</s>",
|
106 |
"extra_ids": 100,
|
|
|
107 |
"model_max_length": 512,
|
|
|
108 |
"pad_token": "<pad>",
|
|
|
|
|
109 |
"sp_model_kwargs": {},
|
|
|
110 |
"tokenizer_class": "T5Tokenizer",
|
|
|
|
|
111 |
"unk_token": "<unk>"
|
112 |
}
|
|
|
102 |
"<extra_id_99>"
|
103 |
],
|
104 |
"clean_up_tokenization_spaces": true,
|
105 |
+
"device_map": "auto",
|
106 |
"eos_token": "</s>",
|
107 |
"extra_ids": 100,
|
108 |
+
"max_length": 512,
|
109 |
"model_max_length": 512,
|
110 |
+
"pad_to_multiple_of": null,
|
111 |
"pad_token": "<pad>",
|
112 |
+
"pad_token_type_id": 0,
|
113 |
+
"padding_side": "right",
|
114 |
"sp_model_kwargs": {},
|
115 |
+
"stride": 0,
|
116 |
"tokenizer_class": "T5Tokenizer",
|
117 |
+
"truncation_side": "right",
|
118 |
+
"truncation_strategy": "longest_first",
|
119 |
"unk_token": "<unk>"
|
120 |
}
|