Add trained tokenizer
Browse files- tokenizer/tokenizer.json +0 -0
- tokenizer/tokenizer_config.json +10 -0
tokenizer/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer/tokenizer_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"vocab_size": 32000,
|
| 3 |
+
"max_seq_len": 128,
|
| 4 |
+
"pad_id": 0,
|
| 5 |
+
"cls_id": 2,
|
| 6 |
+
"sep_id": 3,
|
| 7 |
+
"pad_token": "[PAD]",
|
| 8 |
+
"cls_token": "[CLS]",
|
| 9 |
+
"sep_token": "[SEP]"
|
| 10 |
+
}
|