Update README.md

README.md

@@ -5,17 +5,35 @@ language:
 ---
 
 # CarbonVillain
+This model is an experimental version created using (mergekit)[https://github.com/cg123/mergekit].  
 
-## Model description
+- merge models
+  - Weyaxi/SauerkrautLM-UNA-SOLAR-Instruct
+  - https://huggingface.co/VAGOsolutions/SauerkrautLM-SOLAR-Instruct
+- method: slerp
 
-More information needed
+This model is the same as CarbonVillain-en-13B-v1 and was registered twice due to my mistake.  
 
-## Intended uses & limitations
+# Prompt Template(s)
 
-More information needed
+```
+### User:
+{user}
 
-## Training and evaluation data
+### Assistant:
+{asistant}
+```
 
-More information needed
 
-## Training procedure
+# Evaluation
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_jeonsworld__CarbonVillain-en-10.7B-v1)
+
+| Metric                | Value                     |
+|-----------------------|---------------------------|
+| Avg.                  | 74.27   |
+| ARC (25-shot)         | 71.24      |
+| HellaSwag (10-shot)   | 88.45    |
+| MMLU (5-shot)         | 66.42      |
+| TruthfulQA (0-shot)   | 71.97  |
+| Winogrande (5-shot)   | 83.26  |
+| GSM8K (5-shot)        | 64.29     |