AI 精选动态
智能评分 60
Ornith-1.0 开源编码模型发布
AI 推荐理由
差异点在于其联合优化脚手架和解决方案的自改进训练策略，是开源编码模型中的新方法。核心解读
Ornith 团队发布 Ornith-1.0 开源模型家族，参数规模包括 9B Dense、31B Dense、35B MoE 和 397B MoE，在多个编码基准上达到同尺寸开源模型 SOTA，如 SWE-Bench verified 82.4、Terminal-Bench 2.1 77.5。模型基于 gemma4 和 qwen3.5 后训练，采用新型自改进训练策略，联合优化任务脚手架和解决方案，MIT 许可证。
全文
AK (@_akhaliq) 转发了 Ornith (@ornith_) 的帖子：
🫡Thanks to @_akhaliq for the help!
Now you can try🐦Ornith-1.0-9B on Hugging Face Spaces.
🔗 https://t.co/X2PJmhJi7K
> **引用原帖 Ornith (@ornith_):**
> Aloha! 🌺 Meet Ornith-1.0, a family of open-source LLMs specialized for agentic coding.
> Ornith-1.0 spans the full parameter sizes including 9B Dense, 31B Dense, 35B MoE, and 397B MoE. It achieves state-of-the-art performance among open-source models of comparable size on coding benchmarks including:
> ✅Terminal-Bench 2.1(77.5)
> ✅SWE-Bench(82.4 on verified, 62.2 on pro, 78.9 on Multilingual)
> ✅NL2Repo(48.2)
> ✅SWE Atlas(41.2 on QnA, 42.6 RF, 39.1 TW)
> ✅ClawEval(77.1)
> Post-trained on top of gemma4 and qwen3.5, Ornith-1.0 employs a novel self-improving training strategy in which reinforcement learning is used to generate not only solution rollouts, but also the task-specific scaffolds that drive those rollouts. By jointly optimizing the scaffold and the resulting solution, the model generate higher-quality solutions in agentic coding.😎
> All models are released under the MIT license, enabling full commercial and research use.
> 📖Tech Blog: https://t.co/qT9N2HYWFn
> 🤗Huggingface: https://t.co/PRrwqjeBtM
> https://x.com/ornith_/status/2070148887067963854