Update README.md

README.md

@@ -15,7 +15,8 @@ base_model:
 <p align="center">🤗 <a href="https://huggingface.co/inclusionAI">Hugging Face</a>&nbsp&nbsp | &nbsp&nbsp🤖 <a href="https://modelscope.cn/organization/inclusionAI">ModelScope</a></p>
 
 Today, we officially release Ring-mini-2.0 — a high-performance inference-oriented MoE model deeply optimized based on the Ling 2.0 architecture. With only 16B total parameters and 1.4B activated parameters, it achieves comprehensive reasoning capabilities comparable to dense models below the 10B scale. It excels particularly in logical reasoning, code generation, and mathematical tasks, while supporting 128K long-context processing and 300+ tokens/s high-speed generation.
-Enhanced Reasoning: Joint Training with SFT + RLVR + RLHF
+
+## Enhanced Reasoning: Joint Training with SFT + RLVR + RLHF
 Built upon Ling-mini-2.0-base, Ring-mini-2.0 undergoes further training with Long-CoT SFT, more stable and continuous RLVR, and RLHF joint optimization, significantly improving the stability and generalization of complex reasoning. On multiple challenging benchmarks (LiveCodeBench, AIME 2025, GPQA, ARC-AGI-v1, etc.), it outperforms dense models below 10B and even rivals larger MoE models (e.g., gpt-oss-20B-medium) with comparable output lengths, particularly excelling in logical reasoning.
 For a comprehensive evaluation of the quality of our reasoning models, we implemented automatic benchmarks to assess their performance including math, code and science. The results indicate **Ring-mini-2.0** achieves comparable performace with **Ring-lite-2507** while  activating only half parameters.
 
@@ -23,6 +24,13 @@ For a comprehensive evaluation of the quality of our reasoning models, we implem
     <img src="https://mdn.alipayobjects.com/huamei_d2byvp/afts/img/OQWDT7e6BVwAAAAATGAAAAgADod9AQFr/original" width="1000"/>
 <p>
 
+## High Sparsity, High-Speed Generation
+Inheriting the efficient MoE design of the Ling 2.0 series, Ring-mini-2.0 activates only 1.4B parameters and achieves performance equivalent to 7–8B dense models through architectural optimizations such as 1/32 expert activation ratio and MTP layers. Thanks to its low activation and high sparsity design, Ring-mini-2.0 delivers a throughput of 300+ tokens/s when deployed on H20. With Expert Dual Streaming inference optimization, this can be further boosted to 500+ tokens/s, significantly reducing inference costs for high-concurrency scenarios involving thinking models. Additionally, with YaRN extrapolation, it supports 128K long-context processing, achieving a relative speedup of up to 7x in long-output scenarios.
+<p align="center">
+    <img src="https://mdn.alipayobjects.com/huamei_d2byvp/afts/img/gjJKSpFVphEAAAAAgdAAAAgADod9AQFr/original" width="1000"/>
+<p>
+
+
 ## Model Downloads
 
 <div align="center">