nik kon
commited on
Commit
·
d76abfb
1
Parent(s):
6225dbe
Update README.md
Browse files
README.md
CHANGED
|
@@ -6,4 +6,4 @@ A variant of the Persona-Chat dataset was used, which contains 19319 short dialo
|
|
| 6 |
Using the pre-trained gpt2-greek (https://huggingface.co/nikokons/gpt2-greek) model, we fine-tune the model on this Greek version of translated Persona-Chat dataset for 3 epochs until there is no progress in validation loss. The model's input is customized to the Greek version of the PERSONA-CHAT dataset to perform the fine-tuning procedure. A batch size of 4 is used, and gradients are accumulated over 8 iterations, resulting in a total batch size of 32. The Adam optimization scheme is used, with a learning rate of 5.7e-5.
|
| 7 |
|
| 8 |
## Interact with the Chatbot:
|
| 9 |
-
You can interact with the chatbot using the code in this repository: https://github.com/Nkonstan/chatbot
|
|
|
|
| 6 |
Using the pre-trained gpt2-greek (https://huggingface.co/nikokons/gpt2-greek) model, we fine-tune the model on this Greek version of translated Persona-Chat dataset for 3 epochs until there is no progress in validation loss. The model's input is customized to the Greek version of the PERSONA-CHAT dataset to perform the fine-tuning procedure. A batch size of 4 is used, and gradients are accumulated over 8 iterations, resulting in a total batch size of 32. The Adam optimization scheme is used, with a learning rate of 5.7e-5.
|
| 7 |
|
| 8 |
## Interact with the Chatbot:
|
| 9 |
+
You can interact with the chatbot in Greek using the code in this repository: https://github.com/Nkonstan/chatbot
|