Update README.md

README.md

@@ -7,42 +7,32 @@ library_name: transformers
 tags:
 - mergekit
 - merge
-
+- roleplay
+- creative
+language:
+- en
+- ru
 ---
-# merge
+# Core
+
+This is a merge of pretrained language models 
+
+With new Mistral recently released, and being slightly better than it predecessor, i wanted to update Apparatus.
 
-This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+Also, i tested new pantheon, and i like how it mimic human expressions and mannerisms, so idea of new merge was born.
 
-## Merge Details
-### Merge Method
+Goal of this merge is transfer Apparatus to new Mistral 3.1, and enhance it dialogue capabilities while preserving it stability and ru performance.
 
-This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [mrfakename/mistral-small-3.1-24b-instruct-2503-hf](https://huggingface.co/mrfakename/mistral-small-3.1-24b-instruct-2503-hf) as a base.
+It seems that i succeed. Model is smart enough, instruction-following, decently creative and stable. 
 
-### Models Merged
+tested on 250 answers, narration is really good, dialogues too, swipes make difference. 
 
-The following models were included in the merge:
-* [Gryphe/Pantheon-RP-1.8-24b-Small-3.1](https://huggingface.co/Gryphe/Pantheon-RP-1.8-24b-Small-3.1)
-* [OddTheGreat/Apparatus_24B](https://huggingface.co/OddTheGreat/Apparatus_24B)
+Russian performance still here, no problems with full ru cards and partly translatd ones.  
 
-### Configuration
+Qvink Memory seems to break something. With it on, replies becomes much shorter.
 
-The following YAML configuration was used to produce this model:
+Better use prebuilt V7 format in ST, but chatML also work fine. T1.01 XTC 0.1 0.1
 
-```yaml
-models:
-  - model: Gryphe/Pantheon-RP-1.8-24b-Small-3.1
-    parameters:
-      density: 0.1
-      weight: 0.1
-  - model: OddTheGreat/Apparatus_24B
-    parameters:
-      density: 1
-      weight: 1
+Is it better than Apparatus? i cannot tell, so your feedback is apperciated.
 
-merge_method: ties
-base_model: mrfakename/mistral-small-3.1-24b-instruct-2503-hf
-parameters:
-  normalize: false
-  int8_mask: true
-dtype: float16
-```
+P.S this model not include vision, but as soon i figure how to merge it in, i will update it.