Update README.md

README.md

@@ -18,7 +18,9 @@ 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. It was derived from [Ling-lite-1.5](https://huggingface.co/inclusionAI/Ling-lite-1.5) through a training process involving reasoning SFT, reasoning RL and general SFT. This model delivers performance comparable to [Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on reasoning benchmarks, 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. 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. 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. We use joint training pipeline combining knowledge distillation with RL
+
+
 
 ## Model Downloads