Commit
•
0435e63
1
Parent(s):
256ddaa
Update README.md
Browse files
README.md
CHANGED
|
@@ -10,6 +10,8 @@ license_link: https://huggingface.co/Qwen/Qwen2-72B/blob/main/LICENSE
|
|
| 10 |
|
| 11 |
# Update:
|
| 12 |
|
|
|
|
|
|
|
| 13 |
I was testing a new feature with the Tess-v2.5 dataset. If you had used the model, you might have noticed that the model generations sometimes would end up with a follow-up question. This is intentional, and was created to provide more of a "natural" conversation.
|
| 14 |
|
| 15 |
What had happened earlier was that the stop token wasn't getting properly generated, so the model would go on to answer its own question.
|
|
|
|
| 10 |
|
| 11 |
# Update:
|
| 12 |
|
| 13 |
+
This is a fine-tune over the Tess-v2.5, with a changed learning rate and a subset of Tess-v2.5 dataset. The model is completely different to Tess-v2.5.
|
| 14 |
+
|
| 15 |
I was testing a new feature with the Tess-v2.5 dataset. If you had used the model, you might have noticed that the model generations sometimes would end up with a follow-up question. This is intentional, and was created to provide more of a "natural" conversation.
|
| 16 |
|
| 17 |
What had happened earlier was that the stop token wasn't getting properly generated, so the model would go on to answer its own question.
|