Update README.md

README.md

@@ -1,3 +1,38 @@
-This version was initially on the **#experimental** side, but, performance seems to be solid. <br>
+This version was initially on the **#experimental** side, but, quality and character card adherence seem to be solid. <br>
 Let's try to make Eris smarter _and cuter_. <br>
-Thanks for the solid work, [@Nitral-AI](https://huggingface.co/Nitral-AI/).
+Thanks for the solid work, [@Nitral-AI](https://huggingface.co/Nitral-AI/).
+
+# Original model information:
+
+Model outputs are solid in quality, and relevant to given cards. 
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/642265bc01c62c1e4102dc36/gvC9qywRvyYk1KzDUw1zZ.png)
+
+### Models Merged
+
+The following models were included in the merge:
+* [ChaoticNeutrals/Prima-LelantaclesV7-experimental-7b](https://huggingface.co/ChaoticNeutrals/Prima-LelantaclesV7-experimental-7b)
+* [ChaoticNeutrals/Eris_PrimeV3-Vision-7B](https://huggingface.co/ChaoticNeutrals/Eris_PrimeV3-Vision-7B)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+  - sources:
+      - model: ChaoticNeutrals/Eris_PrimeV3-Vision-7B
+        layer_range: [0, 32]
+      - model: ChaoticNeutrals/Prima-LelantaclesV7-experimental-7b
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: ChaoticNeutrals/Eris_PrimeV3-Vision-7B
+parameters:
+  t:
+    - filter: self_attn
+      value: [0.5, 0.5, 0.5, 0.5, 0.5]
+    - filter: mlp
+      value: [0.5, 0.5, 0.5, 0.5, 0.5]
+    - value: 0.5
+dtype: bfloat16
+```