Update README.md
Browse files
README.md
CHANGED
|
@@ -20,4 +20,15 @@ datasets:
|
|
| 20 |
This is polish fast tokenizer.
|
| 21 |
|
| 22 |
Number of documents used to train tokenizer:
|
| 23 |
-
- 25 088 398
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
This is polish fast tokenizer.
|
| 21 |
|
| 22 |
Number of documents used to train tokenizer:
|
| 23 |
+
- 25 088 398
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
Sample usge with transformers:
|
| 27 |
+
|
| 28 |
+
```[python]
|
| 29 |
+
from transformers import AutoTokenizer
|
| 30 |
+
|
| 31 |
+
tokenizer = AutoTokenizer.from_pretrained('radlab/polish-fast-tokenizer')
|
| 32 |
+
tokenizer.decode(tokenizer("Ala ma kota i psa").input_ids)
|
| 33 |
+
|
| 34 |
+
```
|