Update README.md

README.md

@@ -10,16 +10,23 @@ base_model:
 pipeline_tag: text-generation
 ---
 
-
-<div align="center">
-  <span style="font-family: default; font-size: 2em; display:block; margin-bottom:0.1em;">DeepSWE-Preview</span>
-  <a href="https://github.com/agentica-project/rllm"
-     style="display:inline-flex;align-items:center;gap:8px;height:36px;padding:0 18px;background:linear-gradient(155deg,#2c3e50 0%,#34516a 100%);color:#fff;font:600 14px/1 -apple-system,BlinkMacSystemFont,'Segoe UI',sans-serif;line-height:1;border-radius:9999px;text-decoration:none;box-shadow:0 0 10px rgba(90,180,255,.55),0 3px 9px rgba(0,0,0,.18);white-space:nowrap;vertical-align:middle;">
-    <img src="https://hebbkx1anhila5yf.public.blob.vercel-storage.com/IMG_3783-N75vmFhDaJtJkLR4d8pdBymos68DPo.png" alt="rLLM logo" style="width:18px;height:18px">
-    Built&nbsp;with&nbsp;rLLM
-  </a>
-  <span style="font-family: default; font-size: 1em; display:block; margin-top:0.6em; margin-bottom:0.6em;">🚀 Democratizing Reinforcement Learning for LLM Agents (RLLM) 🌟</span>
+<!-- Header Section -->
+<div align="center" style="background: linear-gradient(135deg, #1c1c1e 0%, #2c2c2e 100%); backdrop-filter: blur(1.25em); border-radius: 1.25em; padding: 1.5em 1.5em; box-shadow: 0 0.5em 2em rgba(0,0,0,0.3); margin-bottom: 1em; border: 1px solid #3a3a3c;">
+
+  <!-- Logo and Title -->
+  <div style="display: flex; align-items: center; justify-content: center; gap: 1em; margin-bottom: 1em;">
+    <div style="width: 3.5em; height: 3.5em; border-radius: 1em; display: flex; align-items: center; justify-content: center;">
+      <img src="https://hebbkx1anhila5yf.public.blob.vercel-storage.com/IMG_3783-N75vmFhDaJtJkLR4d8pdBymos68DPo.png" alt="DeepSWE logo" style="width: 2.5em; height: 2.5em;">
+    </div>
+    <h1 style="font-size: 3em; font-weight: 150; color: #ffffff; margin: 0; font-family: -apple-system, BlinkMacSystemFont, 'SF Pro Display', sans-serif; letter-spacing: -0.02em;">DeepSWE-Preview</h1>
+  </div>
+
+  <!-- Subtitle -->
+  <p style="font-size: 1.2em; color: #a1a1aa; margin: 0 0 0 0; font-family: -apple-system, BlinkMacSystemFont, 'SF Pro Text', sans-serif; line-height: 1.5; font-weight: 400;">
+    Democratizing Reinforcement Learning for LLM Agents
+  </p>
 </div>
+
 <div align="center" style="line-height: 1;">
   <a href="https://github.com/agentica-project/rllm" style="margin: 2px;">
     <img alt="Code" src="https://img.shields.io/badge/rLLM-000000?style=for-the-badge&logo=github&logoColor=000&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
@@ -40,6 +47,7 @@ pipeline_tag: text-generation
 </div>
 </div>
 
+
 ## DeepSWE Overview
 DeepSWE-Preview is a fully open-sourced, state-of-the-art coding agent trained with only reinforcement learning (RL) to excel at software engineering (SWE) tasks. DeepSWE-Preview demonstrates strong reasoning capabilities in navigating complex codebases and viewing/editing multiple files, and it serves as a foundational model for future coding agents. The model achieves an impressive **59.0%** on SWE-Bench-Verified, which is currently #1 in the open-weights category.