Create README.md

README.md

@@ -0,0 +1,51 @@
+---
+language:
+- en
+tags:
+- rp
+- erp
+- chat
+- storywriting
+---
+
+# Kitchen Sink 103b
+
+![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/65a531bc7ec6af0f95c707b1/NmlQi3OggdYF_Tyb_cs3D.jpeg)
+
+This model is a rotating-stack merge of three 70b models in a 103b (120 layer) configuration inspired by Venus 103b.  The result of 
+this "frankenmerge" is a large model that contains a little bit of everything.  RP, chat, storywriting, 
+and instruct are all well supported.  
+
+Component models for the rotating stack are 
+- miqudev/miqu-1-70b
+- royallab/Aetheria-L2-70B 
+- lizpreciatior/lzlv_70b_fp16_hf
+
+This model is *mostly* uncensored and is capable of generating objectionable material with a suitable prompt.  However it is not an explicitely-NSFW model, 
+and some remnants of Miqu's censoring do occasionally pop up.  As with any LLM, no factual claims 
+made by the model should be taken at face value.  You know that boilerplate safety disclaimer that most professional models have?  
+Assume this has it too.  This model is for entertainment purposes only. 
+
+
+FP16 and Q4_K_S GGUFs:
+
+
+# Sample output
+
+```
+{{[INPUT]}}
+Write a detailed and humorous story about a cute and fluffy bunny that goes to a Gwar concert.
+```
+
+
+
+# Prompt format
+Seems to have the strongest affinity for Alpaca prompts.  Others will work to some extent.
+
+
+# WTF is a rotating-stack merge?
+Inspired by Undi's experiments with stacked merges, Jeb Carter found that output quality and model initiative could be significantly 
+improved by reversing the model order in the stack, and then doing a linear merge between the original and reversed stacks.  That is 
+what I did here.  To preserve as much of the "smarts" and long-context-awareness from miqu as possible while still adding the flavor
+from the other models, there is effectively twice as much miqu as lzlv or aetheria.  The exact merge configs can be found in the 
+recipe.txt file.