César Trujillo commited on
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,20 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: unknown
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: unknown
|
| 3 |
+
---
|
| 4 |
+
pip install transformers
|
| 5 |
+
|
| 6 |
+
from transformers import GPT2Tokenizer
|
| 7 |
+
|
| 8 |
+
# Initialize the GPT-2 tokenizer
|
| 9 |
+
tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
|
| 10 |
+
|
| 11 |
+
# Text to tokenize
|
| 12 |
+
text = "Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua."
|
| 13 |
+
|
| 14 |
+
# Tokenizing the text
|
| 15 |
+
tokens = tokenizer.tokenize(text)
|
| 16 |
+
token_ids = tokenizer.convert_tokens_to_ids(tokens)
|
| 17 |
+
|
| 18 |
+
# Print tokens and token IDs
|
| 19 |
+
print(tokens)
|
| 20 |
+
print(token_ids)
|