Update README.md

README.md

@@ -8,53 +8,18 @@ library_name: transformers
 tags:
 - mergekit
 - merge
-
+- roleplay
+- experimental
+language:
+- ru
+- en
 ---
 # 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 [TIES](https://arxiv.org/abs/2306.01708) merge method using [Delta-Vector/Hamanasu-15B-Instruct](https://huggingface.co/Delta-Vector/Hamanasu-15B-Instruct) as a base.
-
-### Models Merged
-
-The following models were included in the merge:
-* [prithivMLmods/Phi-4-o1](https://huggingface.co/prithivMLmods/Phi-4-o1)
-* [prithivMLmods/Megatron-Opus-14B-2.0](https://huggingface.co/prithivMLmods/Megatron-Opus-14B-2.0)
-* [pankajmathur/orca_mini_phi-4](https://huggingface.co/pankajmathur/orca_mini_phi-4)
+This is a merge of pre-trained language models.
 
-### Configuration
+This merge was made to test how phi4 reacts to merging.
 
-The following YAML configuration was used to produce this model:
+Ii reacted good. Overall intellectual capabilities are good, rp language is rich, ERP is supported, but not as good as wanted. On ru it is better than it's parts, on eng it is good too.
 
-```yaml
-models:
-  - model: prithivMLmods/Phi-4-o1
-    parameters:
-      density: 0.5
-      weight: 0.5
-  - model: pankajmathur/orca_mini_phi-4
-    parameters:
-      density: 0.5
-      weight: 0.5
-  - model: prithivMLmods/Megatron-Opus-14B-2.0
-    parameters:
-      density: 0.5
-      weight: 0.5
-  - model: Delta-Vector/Hamanasu-15B-Instruct
-    parameters:
-      density: 0.7
-      weight: 0.7
-      
-merge_method: ties
-base_model: Delta-Vector/Hamanasu-15B-Instruct
-parameters:
-  normalize: false
-  int8_mask: true
-dtype: float16
-tokenizer:
- source: union 
-```
+Just remember, it is experimental, so tested on little amount of replies ~100