Statuo commited on
Commit
beecf06
1 Parent(s): 714506a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -1
README.md CHANGED
@@ -1,7 +1,14 @@
 
 
 
1
  # Lemon Kunoichi Wizard - 7b
2
 
3
  ![LemonKunoichiWizard](https://files.catbox.moe/eivabp.png)
4
 
 
 
 
 
5
  A merge of three models, LemonadeRP-4.5.3, Kunoichi-DPO-v2, and WizardLM-2. I used Lemonade as a base with Kunoichi being the second biggest influence and WizardLM-2 for logic capabilities.
6
 
7
  The end result is a Roleplay-focused model with great character card inference. I ran 4 merges at varying values to see which provided the most accurate output to a character cards quirk, with this v3 version being the winner out of the four.
@@ -59,4 +66,4 @@ models:
59
  weight: 0.6
60
  merge_method: linear
61
  dtype: float16
62
- ```
 
1
+ ---
2
+ {}
3
+ ---
4
  # Lemon Kunoichi Wizard - 7b
5
 
6
  ![LemonKunoichiWizard](https://files.catbox.moe/eivabp.png)
7
 
8
+ [Base Model](https://huggingface.co/Statuo/LemonKunoichiWizardV3/), [4bpw](https://huggingface.co/Statuo/LemonKunoichiWizardv3_4bpw), [6bpw](https://huggingface.co/Statuo/LemonKunoichiWizardv3_6bpw), [8bpw](https://huggingface.co/Statuo/LemonKunoichiWizardv3_8bpw)
9
+
10
+ The Quanted versions come with the measurement files in case you want to do your own quants.
11
+
12
  A merge of three models, LemonadeRP-4.5.3, Kunoichi-DPO-v2, and WizardLM-2. I used Lemonade as a base with Kunoichi being the second biggest influence and WizardLM-2 for logic capabilities.
13
 
14
  The end result is a Roleplay-focused model with great character card inference. I ran 4 merges at varying values to see which provided the most accurate output to a character cards quirk, with this v3 version being the winner out of the four.
 
66
  weight: 0.6
67
  merge_method: linear
68
  dtype: float16
69
+ ```