Update README.md

README.md

@@ -11,11 +11,11 @@ library_name: transformers
 
 <h3 align="center">
   <b>
-    <span>━━━━━━━━━━━━━━━━━━━━━━━━━</span>
+    <span>━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━</span>
     <br/>
     Unlocking the Reasoning Potential of Language Model<br/>From Pretraining to Posttraining
     <br/>
-    <span>━━━━━━━━━━━━━━━━━━━━━━━━━</span>
+    <span>━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━</span>
     <br/>
   </b>
 </h3>
@@ -35,7 +35,41 @@ library_name: transformers
 
 <br/>
 
-> This model repository is licensed under the MIT License.
+---
+
+## Updates
+
+[2025.05.30] We scaled the SFT dataset from approximately 500K to 6M instances and continuously expanding the RL training window size from 32K to 48K, the performance of [MiMo-7B-RL-0530](https://huggingface.co/XiaomiMiMo/MiMo-7B-RL-0530) on AIME24 can be continuously improved and eventually surpass that of DeepSeek R1 (79.8).
+
+<table>
+  <thead>
+    <tr>
+      <th>Benchmark</th>
+      <th>MiMo-7B-RL</th>
+      <th>MiMo-7B-RL-0530</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <td colspan="3"><strong>Mathematics</strong></td>
+      <p align="center">
+        <td rowspan="11"><img width="80%" src="https://github.com/XiaomiMiMo/MiMo/raw/main/figures/length.jpg?raw=true"></td>
+      </p>
+    </tr>
+    <tr><td>MATH500<br/>(Pass@1)</td><td>95.8</td><td>97.2</td></tr>
+    <tr><td>AIME 2024<br/>(Pass@1)</td><td>68.2</td><td>80.1</td></tr>
+    <tr><td>AIME 2025<br/>(Pass@1)</td><td>55.4</td><td>70.2</td></tr>
+    <tr><td colspan="3"><strong>Code</strong></td></tr>
+    <tr><td>LiveCodeBench v5<br/>(Pass@1)</td><td>57.8</td><td>60.9</td></tr>
+    <tr><td>LiveCodeBench v6<br/>(Pass@1)</td><td>49.3</td><td>52.2</td></tr>
+    <tr><td colspan="3"><strong>STEM</strong></td></tr>
+    <tr><td>GPQA-Diamond<br/>(Pass@1)</td><td>54.4</td><td>60.6</td></tr>
+    <tr><td colspan="3"><strong>General</strong></td></tr>
+    <tr><td>Alignbench1.1<br/>(Evaluated by GPT4.1)</td><td>6.9</td><td>7.4</td></tr>
+  </tbody>
+</table>
+
+---
 
 ## I. Introduction
 
@@ -122,7 +156,7 @@ MiMo-7B series
 
 ### SGLang Inference
 
-Thanks to the [contribution](https://github.com/sgl-project/sglang/pull/5921) from the SGLang team, we supported MiMo in SGLang mainstream within 24h with MTP coming soon.
+Thanks to the [MiMo model support](https://github.com/sgl-project/sglang/pull/5921) and [MTP](https://github.com/sgl-project/sglang/pull/6059) from the SGLang team, we supported MiMo in SGLang mainstream.
 
 Example Script
 
@@ -132,9 +166,14 @@ python3 -m uv pip install "sglang[all] @ git+https://github.com/sgl-project/sgla
 
 # Launch SGLang Server
 python3 -m sglang.launch_server --model-path XiaomiMiMo/MiMo-7B-Base --host 0.0.0.0 --trust-remote-code
+
+# Launch MTP Server
+python3 -m sglang.launch_server --model-path XiaomiMiMo/MiMo-7B-Base --trust-remote-code \
+--speculative-algorithm EAGLE --speculative-num-steps 1 --speculative-eagle-topk 1 \
+--speculative-num-draft-tokens 2  --mem-fraction 0.5
 ```
 
-Detailed usage can be found in [SGLang documents](https://docs.sglang.ai/backend/send_request.html). MTP will also be supported in 24h.
+Detailed usage can be found in [SGLang documents](https://docs.sglang.ai/backend/send_request.html).
 
 ### vLLM inference
 
@@ -223,7 +262,7 @@ print(tokenizer.decode(output.tolist()[0]))
 ```bibtex
 @misc{coreteam2025mimounlockingreasoningpotential,
       title={MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining}, 
-      author={{Xiaomi LLM-Core Team}},
+      author={LLM-Core-Team Xiaomi},
       year={2025},
       eprint={2505.07608},
       archivePrefix={arXiv},