Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
|
@@ -1,8 +1,11 @@
|
|
| 1 |
-
from
|
| 2 |
|
| 3 |
-
|
| 4 |
-
app = FastAPI()
|
| 5 |
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from tokenizers import models, trainers, Tokenizer
|
| 2 |
|
| 3 |
+
tokenizer = Tokenizer(model=models.WordPiece(unk_token="[UNK]"))
|
|
|
|
| 4 |
|
| 5 |
+
special_tokens = ["[UNK]", "[PAD]", "[CLS]", "[SEP]", "[MASK]"]
|
| 6 |
+
trainer = trainers.WordPieceTrainer(vocab_size=25000, special_tokens=special_tokens)
|
| 7 |
+
|
| 8 |
+
tokenizer.train(["wikitext-2.txt"], trainer=trainer)
|
| 9 |
+
|
| 10 |
+
encoding = tokenizer.encode("Let's test this tokenizer...", "on a pair of sentences.")
|
| 11 |
+
print(encoding.ids)
|