Upload README.md
Browse files
README.md
CHANGED
@@ -29,7 +29,7 @@ The dataset encompasses a diverse range of topics, representing various aspects
|
|
29 |
This model can be utilized for various NLP tasks such as text generation, summarization, translation, and more. Due to its comprehensive training on a vast corpus, it promises accurate and contextually relevant outputs, especially for tasks related to the Serbian language.
|
30 |
|
31 |
|
32 |
-
|
33 |
|
34 |
from cryptography.fernet import Fernet
|
35 |
import torch
|
@@ -37,28 +37,25 @@ Loading the Model:
|
|
37 |
key = input("Enter the decryption key: ").encode()
|
38 |
cipher_suite = Fernet(key)
|
39 |
|
40 |
-
|
41 |
|
42 |
try:
|
43 |
-
with open(
|
44 |
encrypted_data = file.read()
|
45 |
|
46 |
decrypted_data = cipher_suite.decrypt(encrypted_data)
|
47 |
|
48 |
-
with open(
|
49 |
file.write(decrypted_data)
|
50 |
|
51 |
-
# Dodajte poziv za učitavanje modela
|
52 |
-
loaded_model = torch.load(model_path)
|
53 |
-
|
54 |
except:
|
55 |
print("You can decrypt the model by contacting the author of this model who will add the key, email: info@edukom.rs")
|
56 |
|
57 |
-
#
|
58 |
|
59 |
### Licensing:
|
60 |
|
61 |
-
The author of this model is the company **Edukom AI
|
62 |
|
63 |

|
64 |
|
|
|
29 |
This model can be utilized for various NLP tasks such as text generation, summarization, translation, and more. Due to its comprehensive training on a vast corpus, it promises accurate and contextually relevant outputs, especially for tasks related to the Serbian language.
|
30 |
|
31 |
|
32 |
+
### Decryption the Model:
|
33 |
|
34 |
from cryptography.fernet import Fernet
|
35 |
import torch
|
|
|
37 |
key = input("Enter the decryption key: ").encode()
|
38 |
cipher_suite = Fernet(key)
|
39 |
|
40 |
+
decryption_data = 'Serbian-GPT-2/pytorch_model.bin'
|
41 |
|
42 |
try:
|
43 |
+
with open(decryption_data, 'rb') as file:
|
44 |
encrypted_data = file.read()
|
45 |
|
46 |
decrypted_data = cipher_suite.decrypt(encrypted_data)
|
47 |
|
48 |
+
with open(decryption_data, 'wb') as file:
|
49 |
file.write(decrypted_data)
|
50 |
|
|
|
|
|
|
|
51 |
except:
|
52 |
print("You can decrypt the model by contacting the author of this model who will add the key, email: info@edukom.rs")
|
53 |
|
54 |
+
# Now you can use the Serbian-GPT-2 model for further operations...
|
55 |
|
56 |
### Licensing:
|
57 |
|
58 |
+
The author of this model is the company **Edukom AI**. The model is protected by encryption and its use requires a decryption key. Please check the licensing terms if you intend to use the model for commercial purposes. For any questions or if you need decryption keys, feel free to contact us at **info@edukom.rs**
|
59 |
|
60 |

|
61 |
|