Update README.md
Browse files
README.md
CHANGED
|
@@ -21,6 +21,8 @@ This LoRA uses the 1000B checkpoint.
|
|
| 21 |
|
| 22 |
Trained for 1 epoch with 2048 token context, LoRA Rank 256, Alpha 512.
|
| 23 |
|
|
|
|
|
|
|
| 24 |
# Uploaded model
|
| 25 |
|
| 26 |
- **Developed by:** mpasila
|
|
|
|
| 21 |
|
| 22 |
Trained for 1 epoch with 2048 token context, LoRA Rank 256, Alpha 512.
|
| 23 |
|
| 24 |
+
As a proof of concept it seems to work fairly well. Though I should generate the rest of the dataset which should hopefully work a lot better.
|
| 25 |
+
|
| 26 |
# Uploaded model
|
| 27 |
|
| 28 |
- **Developed by:** mpasila
|