inclusionAI
/

Ring-mini-linear-2.0

@@ -23,20 +23,46 @@ We are excited to announce the official open-source release of Ring-mini-linear-
 Building on the success of our Ling 2.0 series, this model continues to leverage a powerful hybrid architecture of linear and standard attention, perfectly balancing high performance with superior efficiency. By integrating our proven MoE design with optimizations like a 1/32 expert activation ratio and MTP layers, Ring-mini-linear achieves the performance of a massive 8 B dense model while activating only 1.4 B parameters.  This model was converted from Ling-mini-base-2.0, further trained on an additional xx B tokens.
 When it comes to benchmarks, Ring-mini-linear-2.0 not only holds its own against standard attention models (like ring-mini-2) but also outperforms other open-source MoE and Dense models in its class on several demanding tasks. Plus, with native support for a 128k long context, it's faster and more precise than ever, especially when handling long-form inputs and outputs.
-<p align="center">
-  <img src="https://cdn-uploads.huggingface.co/production/uploads/68d20104a6f8ea66da0cb447/v3t1CFN2MSZznYFej2Oc6.webp" width="800">
-</p>
 ## Evaluation
-<p align="center">
-      <img src="https://cdn-uploads.huggingface.co/production/uploads/68d20104a6f8ea66da0cb447/_tjjgBEBlankfrWUY0N9i.png" width="1000">
-</p>
 ## Linear Attention, Highly Sparse，High-Speed Generation
 Thanks to its hybrid attention mechanism and highly sparse MoE architecture, Ring-mini-linear-2.0 achieves near-linear time complexity and constant space complexity, resulting in outstanding inference efficiency. To fully demonstrate this advantage, we conducted a head-to-head comparison between our model and top-tier competitors of similar size or performance.
 The results are remarkable. In the prefill stage, Ring-mini-linear-2.0's performance is exceptional; when the context length exceeds 256k, its throughput is over 12 times higher than that of Qwen3-8B. Furthermore, in the high-concurrency decode stage, its capabilities are even more pronounced. For generation lengths exceeding 32k, its throughput easily surpasses 12 times that of Qwen3-8B.
 ## Model Downloads
 <div align="center">

 Building on the success of our Ling 2.0 series, this model continues to leverage a powerful hybrid architecture of linear and standard attention, perfectly balancing high performance with superior efficiency. By integrating our proven MoE design with optimizations like a 1/32 expert activation ratio and MTP layers, Ring-mini-linear achieves the performance of a massive 8 B dense model while activating only 1.4 B parameters.  This model was converted from Ling-mini-base-2.0, further trained on an additional xx B tokens.
 When it comes to benchmarks, Ring-mini-linear-2.0 not only holds its own against standard attention models (like ring-mini-2) but also outperforms other open-source MoE and Dense models in its class on several demanding tasks. Plus, with native support for a 128k long context, it's faster and more precise than ever, especially when handling long-form inputs and outputs.
+<div style="display: flex; justify-content: center;">
+  <div style="text-align: center;">
+    <img src="https://cdn-uploads.huggingface.co/production/uploads/68d20104a6f8ea66da0cb447/v3t1CFN2MSZznYFej2Oc6.webp" width="800">
+    <p style="margin-top: 8px; font-size: 14px;"><strong>Figure xx:</strong> demo</p>
+  </div>
+</div>
 ## Evaluation
+<!-- <p align="center">
+      <!-- <img src="https://cdn-uploads.huggingface.co/production/uploads/68d20104a6f8ea66da0cb447/_tjjgBEBlankfrWUY0N9i.png" width="1000"> -->
+</p> -->
+<div style="display: flex; justify-content: center;">
+  <div style="text-align: center;">
+    <img src="https://cdn-uploads.huggingface.co/production/uploads/68d20104a6f8ea66da0cb447/OyvwJdc0qRIJiHM1VJgwO.gif" width="1000">
+    <p style="margin-top: 8px; font-size: 14px;"><strong>Figure xx:</strong> Hybrid Linear Model Architecture</p>
+  </div>
+</div>
 ## Linear Attention, Highly Sparse，High-Speed Generation
 Thanks to its hybrid attention mechanism and highly sparse MoE architecture, Ring-mini-linear-2.0 achieves near-linear time complexity and constant space complexity, resulting in outstanding inference efficiency. To fully demonstrate this advantage, we conducted a head-to-head comparison between our model and top-tier competitors of similar size or performance.
 The results are remarkable. In the prefill stage, Ring-mini-linear-2.0's performance is exceptional; when the context length exceeds 256k, its throughput is over 12 times higher than that of Qwen3-8B. Furthermore, in the high-concurrency decode stage, its capabilities are even more pronounced. For generation lengths exceeding 32k, its throughput easily surpasses 12 times that of Qwen3-8B.
+<div style="display: flex; justify-content: center; align-items: flex-start; gap: 20px;">
+  <div style="text-align: center;">
+    <img src="https://cdn-uploads.huggingface.co/production/uploads/68d20104a6f8ea66da0cb447/O9gHLIOCdpWvBbPC6bMM5.webp" width="500">
+    <p style="margin-top: 8px; font-size: 14px;"><strong>Figure xx:</strong> Ring-mini-linear-2.0 prefill throughput</p>
+  </div>
+  <div style="text-align: center;">
+    <p align="center">
+      <img src="https://cdn-uploads.huggingface.co/production/uploads/68d20104a6f8ea66da0cb447/AvMTStWFX-Frzv-vOzyr6.webp" width="500">
+    </p>
+    <p style="margin-top: 8px; font-size: 14px;"><strong>Figure xx:</strong> Ring-mini-linear-2.0 decode throughput</p>
+  </div>
+</div>
 ## Model Downloads
 <div align="center">