Update README.md

README.md

@@ -1,59 +1,26 @@
 ---
 base_model:
 - unsloth/Mistral-Small-Instruct-2409
-- ToastyPigeon/mistral-small-springdragon-qlora
-- unsloth/Mistral-Small-Instruct-2409
-- unsloth/Mistral-Small-Instruct-2409
-- Alfitaria/mistral-small-fujin-qlora
-- nbeerbower/Mistral-Small-Gutenberg-Doppel-22B
 library_name: transformers
 tags:
 - mergekit
 - merge
 
 ---
-# ms-literarier-creativeflowerventure
-
-This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
-
-## Merge Details
-### Merge Method
+# MS-Meadowlark-22B
 
-This model was merged using the [task arithmetic](https://arxiv.org/abs/2212.04089) merge method using [unsloth/Mistral-Small-Instruct-2409](https://huggingface.co/unsloth/Mistral-Small-Instruct-2409) as a base.
+A roleplay and storywriting model based on Mistral Small 22B. 
 
-### Models Merged
+Datasets used in this model:
+- [Dampfinchen/Creative_Writing-Multiturn](https://huggingface.co/datasets/Dampfinchen/Creative_Writing_Multiturn) at 16k
+- [Fizzarolli/rosier-dataset](https://huggingface.co/datasets/Fizzarolli/rosier-dataset) + [Alfitaria/body-inflation-org](https://huggingface.co/datasets/Alfitaria/body-inflation-org) at 16k
+- [ToastyPigeon/SpringDragon](https://huggingface.co/datasets/ToastyPigeon/SpringDragon) at 8k
 
-The following models were included in the merge:
-* [unsloth/Mistral-Small-Instruct-2409](https://huggingface.co/unsloth/Mistral-Small-Instruct-2409) + [ToastyPigeon/mistral-small-springdragon-qlora](https://huggingface.co/ToastyPigeon/mistral-small-springdragon-qlora)
-* [unsloth/Mistral-Small-Instruct-2409](https://huggingface.co/unsloth/Mistral-Small-Instruct-2409) + [Alfitaria/mistral-small-fujin-qlora](https://huggingface.co/Alfitaria/mistral-small-fujin-qlora)
-* [nbeerbower/Mistral-Small-Gutenberg-Doppel-22B](https://huggingface.co/nbeerbower/Mistral-Small-Gutenberg-Doppel-22B)
-* output/ms-creative
+Each dataset was trained separately onto Mistral Small Instruct, and then the component models were merged along with [nbeerbower/Mistral-Small-Gutenberg-Doppel-22B](https://huggingface.co/nbeerbower/Mistral-Small-Gutenberg-Doppel-22B) to create Meadowlark. 
 
-### Configuration
+I tried different blends of the component models, and this one seems to be the most stable while retaining creativity and unpredictability added by the trained data. 
 
-The following YAML configuration was used to produce this model:
+# Instruct Format
+Rosier/bodyinf and SpringDragon were trained in completion format. This model should work with [Kobold Lite](https://lite.koboldai.net/) in Adventure Mode and Story Mode. 
 
-```yaml
-base_model: unsloth/Mistral-Small-Instruct-2409
-merge_method: task_arithmetic
-slices:
-- sources:
-  - layer_range: [0, 56]
-    model: output/ms-creative
-    parameters:
-      weight: 0.3
-  - layer_range: [0, 56]
-    model: nbeerbower/Mistral-Small-Gutenberg-Doppel-22B
-    parameters:
-      weight: 0.6
-  - layer_range: [0, 56]
-    model: unsloth/Mistral-Small-Instruct-2409+Alfitaria/mistral-small-fujin-qlora
-    parameters:
-      weight: 0.4
-  - layer_range: [0, 56]
-    model: unsloth/Mistral-Small-Instruct-2409+ToastyPigeon/mistral-small-springdragon-qlora
-    parameters:
-      weight: 0.1
-  - layer_range: [0, 56]
-    model: unsloth/Mistral-Small-Instruct-2409
-```
+Creative_Writing_Multiturn