Update README.md

README.md

@@ -9,58 +9,26 @@ library_name: transformers
 tags:
 - mergekit
 - merge
-
+- roleplay
+- creative
+- storytelling
+- dark
+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 is a merge of pre-trained language models. 
 
-This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [OddTheGreat/Badman_12B](https://huggingface.co/OddTheGreat/Badman_12B) as a base.
+I had idea for this merge, but it took many attempts to make my idea real.
 
-### Models Merged
+Basically, it is upgraded Badman, more "smart", better in storytelling, and most important, way better in ERP.
 
-The following models were included in the merge:
-* [bamec66557/VICIOUS_MESH-12B-OMEGA](https://huggingface.co/bamec66557/VICIOUS_MESH-12B-OMEGA)
-* [PocketDoc/Dans-SakuraKaze-V1.0.0-12b](https://huggingface.co/PocketDoc/Dans-SakuraKaze-V1.0.0-12b)
-* [PocketDoc/Dans-DangerousWinds-V1.1.0-12b](https://huggingface.co/PocketDoc/Dans-DangerousWinds-V1.1.0-12b)
-* [anthracite-org/magnum-v4-12b](https://huggingface.co/anthracite-org/magnum-v4-12b)
+Model capable to write cruel and even unsettling things, be aware. 
 
-### Configuration
+Russian capabilities preserved, on full ru cards model works slightly better than its predecessor, on partly translated cards can lose language, but rarely (1 answer from 10)
 
-The following YAML configuration was used to produce this model:
+Can write for user and generate some cliche, but it fixes easily by prompt and samplers. I like how it responds on t1.01 /t1.1, top p 0.95, min p 0.05, with XTC 0.1 0.1 (or 0.1 0.3) 
 
-```yaml
-models:
-  - model: bamec66557/VICIOUS_MESH-12B-OMEGA
-    parameters:
-      density: 0.5
-      weight: 0.5
-  - model: PocketDoc/Dans-DangerousWinds-V1.1.0-12b
-    parameters:
-      density: 0.3
-      weight: 0.3
-  - model: OddTheGreat/Badman_12B
-    parameters:
-      density: 0.5
-      weight: 0.5
-  - model: anthracite-org/magnum-v4-12b
-    parameters:
-      density: 0.3
-      weight: 0.3
-  - model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
-    parameters:
-      density: 0.2
-      weight: 0.2
-      
-merge_method: ties
-base_model: OddTheGreat/Badman_12B
-parameters:
-  normalize: false
-  int8_mask: true
-dtype: float16
-tokenizer: 
- source: union
-```
+Tested on various character cards and some adventures. Total responses ~600, Used ChatML format. Mistral format is supported, model's replies completely differently, i recommend give a try to both and compare what you like more.