Update README.md

README.md

@@ -142,6 +142,8 @@ This combination optimizes Anvita for superior reasoning, dynamic conversations,
 Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/sethuiyer__Qwen2.5-7B-Anvita-details).
 Personal Benchmarks - check [PERSONAL_BENCHMARK.md](./PERSONAL_BENCHMARK.md)
 
+For optimal reasoning performance, it is recommended to use **BF16** precision and the [Entropic Chain of Thought](https://huggingface.co/sethuiyer/Qwen2.5-7B-Anvita/blob/main/entropic_cot.py) decoding method. This experimental decoder combines entropy and CoT decoding to enhance output quality.
+
 ## Features
 
 - **Enhanced Reasoning:** Optimized for multi-step reasoning across various domains.
@@ -157,8 +159,6 @@ To get started with Anvita, ensure you have the necessary dependencies installed
 pip install transformers rich
 ```
 
-For optimal reasoning performance, it is recommended to use **BF16** precision and the [Entropic Chain of Thought](https://huggingface.co/sethuiyer/Qwen2.5-7B-Anvita/blob/main/entropic_cot.py) decoding method. This experimental decoder combines entropy and CoT decoding to enhance output quality.
-
 ## Quick Start
 
 Here's a simple example to demonstrate how to use Anvita for generating responses with enhanced reasoning capabilities.