Update README.md

README.md

@@ -9,4 +9,52 @@ tags:
 - mergekit
 - merge
 license: llama3
----
+---
+# merge
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the [DARE TIES](https://arxiv.org/abs/2311.03099) merge method using [TareksLab/Stylizer-V1-LLaMa-70B](https://huggingface.co/TareksLab/Stylizer-V1-LLaMa-70B) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [TareksLab/Wordsmith-V9-LLaMa-70B](https://huggingface.co/TareksLab/Wordsmith-V9-LLaMa-70B)
+* [TareksLab/Dungeons-and-Dragons-V1.2-LLaMa-70B](https://huggingface.co/TareksLab/Dungeons-and-Dragons-V1.2-LLaMa-70B)
+* [TareksLab/Malediction-V1-LLaMa-70B](https://huggingface.co/TareksLab/Malediction-V1-LLaMa-70B)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: TareksLab/Wordsmith-V9-LLaMa-70B
+    parameters:
+      weight: 0.25
+      density: 0.5
+  - model: TareksLab/Malediction-V1-LLaMa-70B
+    parameters:
+      weight: 0.25
+      density: 0.5
+  - model: TareksLab/Stylizer-V1-LLaMa-70B
+    parameters:
+      weight: 0.25
+      density: 0.5
+  - model: TareksLab/Dungeons-and-Dragons-V1.2-LLaMa-70B
+    parameters:
+      weight: 0.25
+      density: 0.5
+merge_method: dare_ties
+base_model: TareksLab/Stylizer-V1-LLaMa-70B
+parameters:
+  normalize: false
+out_dtype: bfloat16
+chat_template: llama3
+tokenizer:
+ source: base
+
+```