Upload tokenizer_config.json
Browse files- tokenizer_config.json +12 -0
tokenizer_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_tokenize_postprocess": false,
|
| 3 |
+
"sep_token": "[SEP]",
|
| 4 |
+
"cls_token": "[CLS]",
|
| 5 |
+
"unk_token": "[UNK]",
|
| 6 |
+
"pad_token": "[PAD]",
|
| 7 |
+
"mask_token": "[MASK]",
|
| 8 |
+
"do_lower_case": true,
|
| 9 |
+
"model_max_length": 512,
|
| 10 |
+
"vocab_file": "/home/ysocr/data/pretrain/ernie-layoutx-base-uncased/torch_version/vocab.txt",
|
| 11 |
+
"sentencepiece_model_file": "/home/ysocr/data/pretrain/ernie-layoutx-base-uncased/torch_version/sentencepiece.bpe.model"
|
| 12 |
+
}
|