Update README.md

README.md

@@ -1,25 +1,27 @@
 ---
-base_model: []
+license: cc-by-nc-4.0
+base_model:
+- NousResearch/Hermes-3-Llama-3.1-70B
+- Sao10K/L3.1-70B-Hanami-x1
 library_name: transformers
 tags:
 - mergekit
 - merge
-
 ---
-# hanamixv3
 
-This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+# Hanames-90B-L3.1
+It's a stack merge meme model made from Hermes 3 and Hanami-x1. Uses a similar formula to my previous stack merge, but updates to Hanami-x1 and includes some mild slerping of the slices. Coherence seems to be improved as a result while remaining fun to use. You should use it for roleplay and creative writing AND PROBABLY NOTHING ELSE (but hey, it's your funeral)
 
-## Merge Details
-### Merge Method
+## STACK MERGE DISCLAIMER
+yes it's just a stack merge, no I didn't do any additional pretraining, no stack merges don't make the model smarter, yes they harm its ability to do complex logical tasks, yes they introduce some weird behaviors and unexpected mistakes, no they don't make the model sentient, no you shouldn't post on twitter about how adding a few layers turned it into agi, etc. etc.
 
-This model was merged using the SLERP merge method.
+That said, it does feel unique and fun to use. If you're the type of person who's drowning in VRAM would rather have some more variety at the expense of needing to make a few manual edits to clean up mistakes, give it a try.
 
-### Models Merged
+## Format
+ChatML
 
-The following models were included in the merge:
-* ../L3.1-70B-Hanami-x1
-* ../Hermes-3-Llama-3.1-70B
+## Samplers
+Because stack merges introduce some unexpected noise to the model, I recommend higher min p than normal. I've been getting good results with min_p 0.1 -> temp 1 (I usually prefer something like min_p 0.03-0.05 -> temp 0.7-0.9, adjust according to taste). Add your favorite anti-repetition sampler as needed.
 
 ### Configuration
 
@@ -66,5 +68,12 @@ merge_method: slerp
 base_model: ../Hermes-3-Llama-3.1-70B
 idtype: bfloat16
 tokenizer_source: ../Hermes-3-Llama-3.1-70B
-
 ```
+
+This is an 
+
+---
+
+All credit goes to the original finetuners, I'm just some dummy who can write mergekit configs.
+
+:*