Create tokenizer.json
Browse files- tokenizer.json +25 -0
tokenizer.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
| 5 |
+
"added_tokens": [
|
| 6 |
+
],
|
| 7 |
+
"normalizer": null,
|
| 8 |
+
"pre_tokenizer": {
|
| 9 |
+
"type": "Whitespace"
|
| 10 |
+
},
|
| 11 |
+
"post_processor": null,
|
| 12 |
+
"decoder": null,
|
| 13 |
+
"model": {
|
| 14 |
+
"type": "WordPiece",
|
| 15 |
+
"unk_token": "[UNK]",
|
| 16 |
+
"continuing_subword_prefix": "##",
|
| 17 |
+
"max_input_chars_per_word": 100,
|
| 18 |
+
"vocab": {
|
| 19 |
+
"[PAD]": 0,
|
| 20 |
+
"[UNK]": 1,
|
| 21 |
+
"[CLS]": 2,
|
| 22 |
+
"[SEP]": 3
|
| 23 |
+
}
|
| 24 |
+
}
|
| 25 |
+
}
|