Ramp Labs 开源 PorTAL 框架，支持跨模型 LoRA 适配

精选理由

如果你做 LoRA 微调或想用一个框架搞定 Gemma、Mistral 和 Inkling 多个模型的适配，可以看看 Ramp 开源的 PorTAL。

AI 摘要

Ramp Labs 开源了 PorTAL 框架，用于共享任务表示和跨模型 LoRA 适配。该框架目前支持 Gemma 4 E2B、Mistral 7B 和 Thinky Machines 的 Inkling 模型，覆盖混合注意力模型和多模态系统。代码已在 ramp-public/portallib 仓库中公开，模型托管于 Hugging Face 的 RampPublic 组织。

原文 · Jerry Liu

If I only went off X posts, I'd think Ramp was an AI lab

If I only went off X posts, I'd think Ramp was an AI lab Ramp Labs @RampLabs We’re open-sourcing PorTAL, our framework for shared task representations and cross model LoRA adaptation. It now spans from hybrid attention models to multimodal systems including Gemma 4 E2B, Mistral 7B & @thinkymachines ' Inkling. Code: ramp-public/portallib Models: @huggingface /RampPublic Your browser does not support the video tag. 🔗 View on Twitter 🔗 View Quoted Tweet 💬 1 🔄 0 ❤️ 5 👀 1047 📊 2 ⚡

查看原推