Running 269 The ultimate guide to multi-harness RL 🔀 269 Train open models with RL inside real agent harnesses
JetBrains/Mellum2.1-12B-A2.5B-Thinking-GGUF Text Generation • 12B • Updated about 16 hours ago • 178k • 138
view article Article Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries +7 aminediroHF, qgallouedec, kashif, lewtun, edbeeching, albertvillanova, nouamanetazi, lvwerra, sergiopaniego • Mar 10 • 195
view article Article Continuous batching from first principles +1 ror, ArthurZ, mcpotato • Nov 25, 2025 • 455
Running on CPU Upgrade Featured 3.34k The Smol Training Playbook 📚 3.34k The secrets to building world-class LLMs
Running 4.09k The Ultra-Scale Playbook 🌌 4.09k The ultimate guide to training LLM on large GPU Clusters
ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration Paper • 2511.21689 • Published Nov 26, 2025 • 129