Upload tokenizer_config.json with huggingface_hub
Browse files- tokenizer_config.json +7 -0
tokenizer_config.json
CHANGED
|
@@ -47,9 +47,16 @@
|
|
| 47 |
"cls_token": "<s>",
|
| 48 |
"eos_token": "</s>",
|
| 49 |
"mask_token": "<mask>",
|
|
|
|
| 50 |
"model_max_length": 512,
|
|
|
|
| 51 |
"pad_token": "<pad>",
|
|
|
|
|
|
|
| 52 |
"sep_token": "</s>",
|
|
|
|
| 53 |
"tokenizer_class": "XLMRobertaTokenizer",
|
|
|
|
|
|
|
| 54 |
"unk_token": "<unk>"
|
| 55 |
}
|
|
|
|
| 47 |
"cls_token": "<s>",
|
| 48 |
"eos_token": "</s>",
|
| 49 |
"mask_token": "<mask>",
|
| 50 |
+
"max_length": 64,
|
| 51 |
"model_max_length": 512,
|
| 52 |
+
"pad_to_multiple_of": null,
|
| 53 |
"pad_token": "<pad>",
|
| 54 |
+
"pad_token_type_id": 0,
|
| 55 |
+
"padding_side": "right",
|
| 56 |
"sep_token": "</s>",
|
| 57 |
+
"stride": 0,
|
| 58 |
"tokenizer_class": "XLMRobertaTokenizer",
|
| 59 |
+
"truncation_side": "right",
|
| 60 |
+
"truncation_strategy": "longest_first",
|
| 61 |
"unk_token": "<unk>"
|
| 62 |
}
|