模型58
Hugging Face 发布适配 pi 编码智能体的 Qwen3.8-27B-pi-adapted
原标题:Introducing Qwen3.8-27B-pi-adapted 🤗
Hugging Face 的 clem 发布 Qwen3.8-27B-pi-adapted,用强化学习和 LoRA 适配器把 Qwen 模型专门适配到 pi 编码智能体上。
中文译文尚未完成,先为你展示原文。
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: http://huggingface.co/harness-hub/Qwen3.8-27B-pi-adapted
Methodology: https://huggingface.co/blog/harness-hub/harness-adapters
