Update README.md

README.md

@@ -8,34 +8,21 @@ tags:
 - merge
 
 ---
+![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/642265bc01c62c1e4102dc36/xnDxqMZRVOAUfTSerDFJB.jpeg)
 
-This model was merged using the SLERP merge method.
+# Eris Prime: Version 4.0 32k
+After many trials and tribulations we have a winner: A more coherent, format stable version of Eris Prime v4 with better long context handling.
 
-### Models Merged
+Quants Available Here Tahnks to Lewdiculus: https://huggingface.co/Lewdiculous/Eris_PrimeV4-Vision-7B-GGUF-IQ-Imatrix
+# Vision/multimodal capabilities:
 
-The following models were included in the merge:
-* [Nitral-AI/EPV3.075xMI-0.2-32k-7B](https://huggingface.co/Nitral-AI/EPV3.075xMI-0.2-32k-7B)
-* [Nitral-AI/EPV3.05xMI-0.2-32k-7B](https://huggingface.co/Nitral-AI/EPV3.05xMI-0.2-32k-7B)
+ If you want to use vision functionality:
 
-### Configuration
+ * You must use the latest versions of [Koboldcpp](https://github.com/LostRuins/koboldcpp).
+ 
+To use the multimodal capabilities of this model and use **vision** you need to load the specified **mmproj** file, this can be found inside this model repo.
+ 
+ * You can load the **mmproj** by using the corresponding section in the interface:
 
-The following YAML configuration was used to produce this model:
-
-```yaml
-slices:
-  - sources:
-      - model: Nitral-AI/EPV3.075xMI-0.2-32k-7B
-        layer_range: [0, 32]
-      - model: Nitral-AI/EPV3.05xMI-0.2-32k-7B
-        layer_range: [0, 32]
-merge_method: slerp
-base_model: Nitral-AI/EPV3.075xMI-0.2-32k-7B
-parameters:
-  t:
-    - filter: self_attn
-      value: [0, 0.5, 0.3, 0.7, 1]
-    - filter: mlp
-      value: [1, 0.5, 0.7, 0.3, 0]
-    - value: 0.5
-dtype: bfloat16
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/UX6Ubss2EPNAT3SKGMLe0.png)
 ```