Spaces:
Sleeping
Sleeping
Update README.md
Browse files
README.md
CHANGED
|
@@ -92,4 +92,11 @@ Using the data with additional tokens, I generated two datasets for Rachel in En
|
|
| 92 |
|
| 93 |
2. Raw dialogues - a dataset that contains the pairs "NON-Friend's cue - HERO's response", separated by a line break character \n. The dialogue dataset is needed because we want our model to be able to maintain a Friends-style conversation with the user, not just generate text.
|
| 94 |
|
| 95 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 92 |
|
| 93 |
2. Raw dialogues - a dataset that contains the pairs "NON-Friend's cue - HERO's response", separated by a line break character \n. The dialogue dataset is needed because we want our model to be able to maintain a Friends-style conversation with the user, not just generate text.
|
| 94 |
|
| 95 |
+
|
| 96 |
+
|
| 97 |
+
# Training
|
| 98 |
+
For training the model to transfer style of Rachel to chatbot I used several models.
|
| 99 |
+
1. First one is GPT2. For datasets I used TextDataset by PyTorch and library transformers by huggingface.
|
| 100 |
+
The results are shown on the image below
|
| 101 |
+
|
| 102 |
+
|