Upload tokenizer
Browse files- tokenizer_config.json +4 -0
tokenizer_config.json
CHANGED
@@ -11,9 +11,13 @@
|
|
11 |
"rstrip": false,
|
12 |
"single_word": false
|
13 |
},
|
|
|
14 |
"model_max_length": 512,
|
15 |
"pad_token": "<pad>",
|
16 |
"sep_token": "</s>",
|
|
|
17 |
"tokenizer_class": "XLMRobertaTokenizer",
|
|
|
|
|
18 |
"unk_token": "<unk>"
|
19 |
}
|
|
|
11 |
"rstrip": false,
|
12 |
"single_word": false
|
13 |
},
|
14 |
+
"max_length": 256,
|
15 |
"model_max_length": 512,
|
16 |
"pad_token": "<pad>",
|
17 |
"sep_token": "</s>",
|
18 |
+
"stride": 0,
|
19 |
"tokenizer_class": "XLMRobertaTokenizer",
|
20 |
+
"truncation_side": "right",
|
21 |
+
"truncation_strategy": "longest_first",
|
22 |
"unk_token": "<unk>"
|
23 |
}
|