Update README.md

README.md

@@ -4,32 +4,62 @@ base_model:
 - EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1
 - LatitudeGames/Wayfarer-Large-70B-Llama-3.3
 - crestf411/L3.1-nemotron-sunfall-v0.7.0
+- tokyotech-llm/Llama-3.1-Swallow-70B-Instruct-v0.3
+- SicariusSicariiStuff/Negative_LLAMA_70B
+- nbeerbower/llama3.1-kartoffeldes-70B
+- deepseek-ai/DeepSeek-R1-Distill-Llama-70B
 library_name: transformers
 tags:
 - mergekit
 - merge
-
 ---
-# merge_v7b_full
+# Genetic Lemonade Unleashed
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/65b19c6c638328850e12d38c/P8HgQAzAjEWE67u9sSKJz.png)
+
+This model is the final result of a few dozen different merges during my process of learning how to merge. I think it's pretty good.
+
+Designed for primarily for RP.
 
 This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
 
+## SillyTavern Settings
+
+### Sampler Settings
+- Temp: 1
+- MinP: 0.02-0.05
+- Dry: 0.8, 1.75, 4
+
+### Instruct
+
+[Llam@ception](https://huggingface.co/Konnect1221/The-Inception-Presets-Methception-LLamaception-Qwenception/tree/main/Llam%40ception)
+
+Any system prompt will work, but their Context / Instruct template I recommend.
+
+Alternatively you can use Llama-3-Instruct-Names but you will need to uncheck "System same as user".
+
 ## Merge Details
 ### Merge Method
 
 This model was merged using the [SCE](https://arxiv.org/abs/2408.07990) merge method using ./merge_v6_base_E as a base.
 
-### Models Merged
-
-The following models were included in the merge:
-* [Sao10K/L3.1-70B-Hanami-x1](https://huggingface.co/Sao10K/L3.1-70B-Hanami-x1)
-* [EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1](https://huggingface.co/EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1)
-* [LatitudeGames/Wayfarer-Large-70B-Llama-3.3](https://huggingface.co/LatitudeGames/Wayfarer-Large-70B-Llama-3.3)
-* [crestf411/L3.1-nemotron-sunfall-v0.7.0](https://huggingface.co/crestf411/L3.1-nemotron-sunfall-v0.7.0)
-
-### Configuration
+### merge_v6_base_E
+```yaml
+models:
+  - model: deepseek-ai/DeepSeek-R1-Distill-Llama-70B
+  - model: nbeerbower/llama3.1-kartoffeldes-70B
+  - model: tokyotech-llm/Llama-3.1-Swallow-70B-Instruct-v0.3
+  - model: SicariusSicariiStuff/Negative_LLAMA_70B
+select_topk: .15
+merge_method: sce
+base_model: meta-llama/Llama-3.3-70B-Instruct
+out_dtype: bfloat16
+dype: float32
+tokenizer:
+  source: base
+```
 
-The following YAML configuration was used to produce this model:
+### Genetic Lemonade Unleashed
 
 ```yaml
 models:
@@ -44,4 +74,4 @@ out_dtype: bfloat16
 dype: float32
 tokenizer:
   source: union
-```
+```