Update README.md

README.md

@@ -18,7 +18,7 @@ base_model:
 
 ## Introduction
 
-Ring-lite is a fully open-source MoE LLM provided by InclusionAI, which has 16.8B parameters with 2.75B activated parameters. Ring-lite builds upon the publicly available [Ling-lite-1.5](https://huggingface.co/inclusionAI/Ling-lite-1.5) model, which contains 16.8 billion total parameters with 2.75 billion activated parameters. We use joint training pipeline combining knowledge distillation with reinforcement learning. Our model achieves performance comparable to state-of-the-art (SOTA) small-size reasoning models on challenging benchmarks (AIME, LiveCodeBench, and GPQA-Diamond) while activating only one-third of their parameters.
+Ring-lite is a fully open-source MoE LLM provided by InclusionAI, which has 16.8B parameters with 2.75B activated parameters. It builds upon the publicly available [Ling-lite-1.5](https://huggingface.co/inclusionAI/Ling-lite-1.5) model We use joint training pipeline combining knowledge distillation with reinforcement learning. Our model achieves performance comparable to state-of-the-art (SOTA) small-size reasoning models on challenging benchmarks (AIME, LiveCodeBench, and GPQA-Diamond) while activating only one-third of their parameters.
 
 
 
@@ -33,7 +33,7 @@ Ring-lite is a fully open-source MoE LLM provided by InclusionAI, which has 16.8
 </div>
 
 ## Evaluation
-For a comprehensive evaluation of the quality of our reasoning models, we implemented automatic benchmarks to assess their performance, including math, code and science.
+For a comprehensive evaluation of the quality of our reasoning models, we implemented automatic benchmarks to assess their performance including math, code and science.
 
 <p align="center">
     <img src="https://huggingface.co/inclusionAI/Ring-lite/resolve/main/performance.png" width="1000"/>