Update README.md

README.md

@@ -7,23 +7,42 @@ library_name: transformers
 tags:
 - mergekit
 - merge
-
 ---
 ### OpenCrystal-12B-L3
-
 This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
 
-## Merge Details
-### Merge Method
+![Rohma]()
+
+
+### Instruct Template
+Default llama3 instruct and context preset.
+
+### Samplers
+```
+Temp : 1.23
+Min P : 0.05
+Repetition Penalty : 1.05
 
-This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [Darkknight6742/llama-3-12b-Instruct](https://huggingface.co/Darkknight6742/llama-3-12b-Instruct) as a base.
+[And everything else neutral]
+```
+
+### Features
 
-### Models Merged
+- Can speak as other npc automatically.
+- Creative (Alot)
+- Coherent
+- Output feels like you're using Character.ai
+- (can maybe have v2 if needed)
+- Follows prompt better
+- can summarize and generate image propmts well [Tested 100%] (Due to llama 3 as base)
 
-The following models were included in the merge:
-* [Darkknight6742/L3-12B-Niitama-v1](https://huggingface.co/Darkknight6742/L3-12B-Niitama-v1)
-* [Darkknight6742/L3-12B-Celeste-V1.2](https://huggingface.co/Darkknight6742/L3-12B-Celeste-V1.2)
 
+### Instruct Prompt
+```
+You're {{char}}, follow {{char}} personality and plot of the story, Don't impersonate as {{user}}, Speak as others NPC except {{user}} when needed. Be Creative, Create various interesting events and situations during the story.
+```
+
+## Merge Details
 ### Configuration
 
 The following YAML configuration was used to produce this model:
@@ -40,11 +59,11 @@ models:
       density: 0.9
       weight: 0.9
 merge_method: ties
-base_model: Darkknight6742/llama-3-12b-Instruct # For Base Coherence
+base_model: Darkknight6742/llama-3-12b-Instruct # For Base Coherence and prompting
 parameters:
   int8_mask: true
   rescale: true
   normalize: false
 dtype: bfloat16
 
-```
+```