Update README.md

README.md

@@ -10,41 +10,13 @@ tags:
 - merge
 
 ---
-# out
 
-This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+Merge of Lumimaid and Magnum as requested by somes.
 
-## Merge Details
-### Merge Method
+I used the new DELLA merge method in mergekit and added a finetune of Nemo only on Claude input, trained on 16k ctx, in the mix.
 
-This model was merged using the della merge method using [mistralai/Mistral-Nemo-Instruct-2407](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407) as a base.
+# Prompt template: Mistral
 
-### Models Merged
-
-The following models were included in the merge:
-* [NeverSleep/Lumimaid-v0.2-12B](https://huggingface.co/NeverSleep/Lumimaid-v0.2-12B)
-* [Undi95/LocalC-12B-e2.0](https://huggingface.co/Undi95/LocalC-12B-e2.0)
-* [intervitens/mini-magnum-12b-v1.1](https://huggingface.co/intervitens/mini-magnum-12b-v1.1)
-
-### Configuration
-
-The following YAML configuration was used to produce this model:
-
-```yaml
-base_model: mistralai/Mistral-Nemo-Instruct-2407
-merge_method: della
-dtype: bfloat16
-models:
-  - model: intervitens/mini-magnum-12b-v1.1
-    parameters:
-      weight: 1.0
-  - model: Undi95/LocalC-12B-e2.0
-    parameters:
-      weight: 1.0
-  - model: NeverSleep/Lumimaid-v0.2-12B
-    parameters:
-      weight: 1.0
-  - model: mistralai/Mistral-Nemo-Instruct-2407
-    parameters:
-      weight: 1.0
 ```
+<s>[INST] {input} [/INST] {output}</s>
+```