Update README.md

README.md

@@ -8,42 +8,21 @@ library_name: transformers
 tags:
 - mergekit
 - merge
-
+license: apache-2.0
+datasets:
+- ResplendentAI/Synthetic_Soul_1k
+- Epiculous/Gnosis
+language:
+- en
 ---
 # Ashera
 
-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 SLERP merge method.
-
-### Models Merged
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/626dfb8786671a29c715f8a9/PwebDlwW-mPHC8yQwV2mF.png)
 
-The following models were included in the merge:
-* [jeiku/parttwo](https://huggingface.co/jeiku/parttwo) + [jeiku/Gnosis_Reformatted_Mistral](https://huggingface.co/jeiku/Gnosis_Reformatted_Mistral)
-* [jeiku/partone](https://huggingface.co/jeiku/partone) + [jeiku/Synthetic_Soul_1k_Mistral_128](https://huggingface.co/jeiku/Synthetic_Soul_1k_Mistral_128)
+Asherah, goddess of all creation according to ancient myth was a huge inspiration for this model. The model started with a merge of four of Sanji Watsuki's models using various methods. This merge was then finetuned on Gnosis and Synthetic Soul, two datasets penned by myself.It was then merged with Excalibur to impart multimodality. I consider this a great achievement.
 
-### Configuration
+You can use this as mmproj: https://huggingface.co/cjpais/llava-1.6-mistral-7b-gguf/blob/main/mmproj-model-f16.gguf
 
-The following YAML configuration was used to produce this model:
+I have also included a folder in the repo containing this file. It will be necessary for multimodal GGUF users. I recommend Koboldcpp.
 
-```yaml
-slices:
-  - sources:
-      - model: jeiku/partone+jeiku/Synthetic_Soul_1k_Mistral_128
-        layer_range: [0, 32]
-      - model: jeiku/parttwo+jeiku/Gnosis_Reformatted_Mistral
-        layer_range: [0, 32]
-merge_method: slerp
-base_model: jeiku/partone+jeiku/Synthetic_Soul_1k_Mistral_128
-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
-```
+Multimodal functionality is limited to GGUF users at this time. You can still use this model as a standard LLM.