Update README.md
Browse files
README.md
CHANGED
|
@@ -5,6 +5,8 @@ license: cc-by-nc-4.0
|
|
| 5 |
I'm honestly too tired to write out a whole model page. I retrained the model using a cleaner dataset and then ran KTO using a previous dataset.
|
| 6 |
Probably can improve performance by generating a KTO set off the same base model.
|
| 7 |
|
|
|
|
|
|
|
| 8 |
## Chat Format: ChatML with System Prompt
|
| 9 |
|
| 10 |
```
|
|
|
|
| 5 |
I'm honestly too tired to write out a whole model page. I retrained the model using a cleaner dataset and then ran KTO using a previous dataset.
|
| 6 |
Probably can improve performance by generating a KTO set off the same base model.
|
| 7 |
|
| 8 |
+
Next major version I plan to pretrain -> SFT -> KTO which should improve things further.
|
| 9 |
+
|
| 10 |
## Chat Format: ChatML with System Prompt
|
| 11 |
|
| 12 |
```
|