Update README.md

README.md

@@ -8,19 +8,17 @@ tags:
 - merge
 license: other
 ---
-![The Drummer turns into a Joshi Youchien](https://huggingface.co/knifeayumu/Lite-Cydonia-22B-v1.1/resolve/main/Lite-Cydonia-22B-v1.1.png)
+![The Drummer turns into a Joshi Youchien](https://huggingface.co/knifeayumu/Lite-Cydonia-22B-v1.1-75-25/resolve/main/Lite-Cydonia-22B-v1.1.png)
 
 # The Drummer turns into a Joshi Youchien
 
 This is a merge of pre-trained language models created using [mergekit](https://github.com/arcee-ai/mergekit).
 
-GGUF quants : [knifeayumu/Lite-Cydonia-22B-v1.1-GGUF](https://huggingface.co/knifeayumu/Lite-Cydonia-22B-v1.1-GGUF)
-
 ## Inspiration
 
 I thought both [BeaverAI/Cydonia-22B-v1f-GGUF](https://huggingface.co/TheDrummer/Cydonia-22B-v1.1) and [BeaverAI/Cydonia-22B-v1e-GGUF](https://huggingface.co/BeaverAI/Cydonia-22B-v1e-GGUF) versions were a bit too evil. The sense of morality was too screwed up, and it was quite deterministic (swipes didn't offer much variety) compared to the base model. Then an idea popped into my mind — why not merge it back with the base model? That way, we could give it a sense of "good" again, at least a little. Maybe this would also fix some of the deterministic generations.
 
-Quick testing shows... it works? Zero-shot evil Q&A no longer works, but with a bit of persuasion, it did answer. I've also tried combining both weights equally at 0.5, but it was too moral for my liking. Hence, I uploaded this version.
+Quick testing shows... it works? Zero-shot evil Q&A no longer works, but with a bit of persuasion, it did answer. But I think the model is a bit too dumb for my liking.
 
 Credits to [TheDrummer](https://huggingface.co/TheDrummer) and [BeaverAI](https://huggingface.co/BeaverAI) who makes such finetunes. "Lightly decensored" is a heavy understatement in this case.