Update README.md
Browse files
README.md
CHANGED
|
@@ -1,8 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
| 1 |
This model was trained on the Zloss fork of Charles, and should fix issue the model had.
|
| 2 |
|
| 3 |
-
|
| 4 |
|
| 5 |
-
|
| 6 |
|
| 7 |
```
|
| 8 |
<|im_start|>system
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-nc-4.0
|
| 3 |
+
---
|
| 4 |
This model was trained on the Zloss fork of Charles, and should fix issue the model had.
|
| 5 |
|
| 6 |
+
Use Chatml prompt format, but not the special token.
|
| 7 |
|
| 8 |
+
The reason is that Axolotl merge the finetune with the base model at 1 weight basically, but this is too much, so I use another script available [HERE](https://github.com/DocShotgun/LLM-notebooks/blob/main/weighted-lora-merge.ipynb) to merge with less weight, sadly, it don't take the special chatml token.
|
| 9 |
|
| 10 |
```
|
| 11 |
<|im_start|>system
|