Qwen3.8 Adapted Model Rises to No. 5 on Hub Trending
Qwen3.8-27B-pi-adapted has reached No. 5 on the Hub trending chart. The quoted post says the model was adapted specifically for the pi coding agent using reinforcement learning and a LoRA adapter.
View original postIntroducing Qwen3.8-27B-pi-adapted 🤗 We adapted Qwen's model specifically for the pi coding agent using reinforcement learning and a LoRA adapter. The results, measured as pass@1: 🚀 SWE-bench Pro (Hard 51): 29.4% → 62.7% 💻 Terminal-Bench 2.1: 39.5% → 55.8% ⚡ 55–62% fewer tool calls per task This is the power of open models: you can adapt them to YOUR tools and YOUR use cases. Let’s build! 💛 Open weights: https://t.co/aH4cl2qnED Methodology: https://t.co/avSfF93K4V
View original
Introducing Qwen3.8-27B-pi-adapted 🤗 We adapted Qwen's model specifically for the pi coding agent using reinforcement learning and a LoRA adapter. The results, measured as pass@1: 🚀 SWE-bench Pro (Hard 51): 29.4% → 62.7% 💻 Terminal-Bench 2.1: 39.5% → 55.8% ⚡ 55–62% fewer tool calls per task This is the power of open models: you can adapt them to YOUR tools and YOUR use cases. Let’s build! 💛 Open weights: https://t.co/aH4cl2qnED Methodology: https://t.co/avSfF93K4V
Body
Number 5 trending on the hub!
https://t.co/j7DKgnPzPh https://t.co/XZ7HH9LeW0
AI Trends