Update README.md

README.md

@@ -126,29 +126,6 @@ pipeline_tag: text-generation
   <img src="https://huggingface.co/sethuiyer/CodeCalc-Mistral-7B/resolve/main/codecalc.webp" height="128px" alt="CodeCalc">
 </p>
 
-This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
-
-## Usage
-
-Alpaca Instruction Format and [Divine Intellect](https://raw.githubusercontent.com/oobabooga/text-generation-webui/ae8cd449ae3e0236ecb3775892bb1eea23f9ed68/presets/Divine%20Intellect.yaml) preset.
-
-```
-You are an intelligent programming assistant.
-
-### Instruction:
-Implement a linked list in C++
-
-### Response:
-```
-
-Preset:
-
-```text
-temperature: 1.31
-top_p: 0.14
-repetition_penalty: 1.17
-top_k: 49
-```
 
 ### Configuration
 
@@ -170,6 +147,7 @@ parameters:
 
 ```
 
+
 ### Evaluation
 
 | T  | Model                                       | Average | ARC  | HellaSwag | MMLU  | TruthfulQA | Winogrande | GSM8K |
@@ -178,3 +156,27 @@ parameters:
 | 📉  | uukuguy/speechless-code-mistral-7b-v1.0     | 63.6    | 61.18| 83.77     | 63.4  | 47.9       | 78.37      | 47.01 |
 
 The merge appears to be successful, especially considering the substantial improvement in the GSM8K benchmark while maintaining comparable performance on other metrics.
+
+
+## Usage
+
+Alpaca Instruction Format and [Divine Intellect](https://raw.githubusercontent.com/oobabooga/text-generation-webui/ae8cd449ae3e0236ecb3775892bb1eea23f9ed68/presets/Divine%20Intellect.yaml) preset.
+
+```
+You are an intelligent programming assistant.
+
+### Instruction:
+Implement a linked list in C++
+
+### Response:
+```
+
+Preset:
+
+```text
+temperature: 1.31
+top_p: 0.14
+repetition_penalty: 1.17
+top_k: 49
+```
+