提问 HN:关于本地化专业 LLM/VLM 的反馈

1作者: BlackForest_ai7 个月前
我们推出了 causa™,这是一款可在苹果设备上完全离线编排和运行 LLM 的应用程序(即将支持 VLM)。 我们正在收集社区的反馈,了解大家认为哪些专业或微调模型最适合在设备端进行推理。我们已经支持主流的通用模型系列(GPT-OSS、Llama、Mistral 等),现在正专注于为特定任务微调的领域特定模型。 例如: * JetBrains 的 Mellum 系列——专为软件工程优化 * gpt-oss-safeguard——专为策略推理和 AI 安全设计 如果您知道其他高质量的专业模型(最好是开放权重),并且可以从移动端部署中受益,我们非常欢迎您的建议。
查看原文
We’ve launched causa™, our application that orchestrates and runs LLMs fully offline across Apple devices (VLM support coming soon). We’re collecting feedback on which specialized or fine-tuned models the community would find most valuable for on-device inference. We already support the main general-purpose families (GPT-OSS, Llama, Mistral, etc.) and are now focusing on domain-specific models fine-tuned for targeted tasks.<p>Examples: • Mellum series by JetBrains — optimized for software engineering • gpt-oss-safeguard — tailored for policy reasoning and AI safety<p>If you know of other high-quality specialized models (preferably with open weights) that could benefit from mobile deployment, we’d love your input.