Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-nc-4.0
|
3 |
+
tags:
|
4 |
+
- not-for-all-audiences
|
5 |
+
- nsfw
|
6 |
+
---
|
7 |
+
[HIGHLY EXPERIMENTAL]
|
8 |
+
|
9 |
+
Just try it for a good laugh. Need testing.
|
10 |
+
```shell
|
11 |
+
The plan :
|
12 |
+
Open-Orca/OpenOrcaxOpenChat-Preview2-13B
|
13 |
+
PygmalionAI/pygmalion-2-13b
|
14 |
+
|
15 |
+
Undi95/MLewd-L2-13B-v2-3
|
16 |
+
jondurbin/spicyboros-13b-2.2
|
17 |
+
|
18 |
+
lemonilia/limarp-llama2-v2
|
19 |
+
|
20 |
+
Step 1: Merge OpenOrcaxOpenChat-Preview2-13B with pygmalion-2-13b
|
21 |
+
=> OpenOrcaPyg2
|
22 |
+
Step 2: Merge MLewd with Spicyboros
|
23 |
+
=> MLewdBorosPlus
|
24 |
+
Step 3: In the layer side, replace the layer 0 to 8 with MLewd, and the layer 16 to 20 with Spicyboros of the first merge
|
25 |
+
=> OpenOrcaPyg2-Layered
|
26 |
+
Step 4: In the layer side, replace the layer 0 to 8 with MLewd, and the layer 16 to 20 with Spicyboros of the second merge
|
27 |
+
=> MLewdBorosPlus-Layered
|
28 |
+
Step 5: Merge OpenOrcaPyg2-Layered with MLewdBorosPlus-Layered
|
29 |
+
=> OpenRPBase
|
30 |
+
Step 6: Apply Limarp2 at 0.5 weight at the end
|
31 |
+
=> OpenRP
|
32 |
+
|
33 |
+
Goal: making Orca a RP model with Pyg2 dataset and MLewd+Spicyboros 100% layer accross the merge and avoid censoring
|
34 |
+
It will be diluted to ~25% in other layer, SLERP do the dirty job
|
35 |
+
The LoRA is here to redirect to RP writing
|
36 |
+
```
|
37 |
+
|
38 |
+
Don't ask me why this model work. I'm a blind scientist. It seems a little obsessed with the game "Garry's mod" tho. Be patient with him.
|