Update README.md
Browse files
README.md
CHANGED
|
@@ -14,6 +14,18 @@ I personally think this mogs Euryale 1.3, but ymmv.
|
|
| 14 |
|
| 15 |
***
|
| 16 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
Prompt Format - Alpaca
|
| 18 |
|
| 19 |
|
|
|
|
| 14 |
|
| 15 |
***
|
| 16 |
|
| 17 |
+
For Transparency's Sake:
|
| 18 |
+
|
| 19 |
+
Models Used:
|
| 20 |
+
<br> Platypus2-70B-instruct
|
| 21 |
+
<br> Lila-70B
|
| 22 |
+
<br> SunsetBoulevard (at roughly 0.1 weight, boosting coherency)
|
| 23 |
+
<br> Private De-alignment LoRA on top.
|
| 24 |
+
|
| 25 |
+
why does it show mergekit in the safetensors.index metadata? -> I used DARE method to merge the 3 models. Then Axolotl qLoRA. then used lora-merge, copying the files of the base merged model because they didn't save to the new one, only the .safetensor files got saved.
|
| 26 |
+
|
| 27 |
+
***
|
| 28 |
+
|
| 29 |
Prompt Format - Alpaca
|
| 30 |
|
| 31 |
|