#多模态
AI at Meta@AIatMetaAI 评分4040
Andrej Karpathy@karpathyAI 评分4242
Mira Murati@miramurati精选AI 评分7878引用Thinking Machines@thinkymachinesToday, we are releasing Inkling-Small. Inkling-Small achieves comparable performance to Inkling at a quarter of its size. It features 276B total parameters, 12B active. We are making the full weights available. https://thinkingmachines.ai/news/inkling-small/ Fine-tune it on Tinker today, or chat with it in text, image, and audio on Tinker Playground.
推荐理由:Inkling-Small 以四分之一体量达到与 Inkling 相当的性能,并开放完整权重,读者可据此判断小模型的部署与微调空间。
Mira Murati@miramurati精选AI 评分7878引用Thinking Machines@thinkymachinesToday, we are introducing Inkling. Inkling reasons efficiently across text, image, and audio modalities. We are making the full weights available. https://thinkingmachines.ai/news/introducing-inkling/ Available today for fine-tuning on Tinker. Play with it in the Inkling Playground. 🧵
推荐理由:Thinking Machines 首款模型从零训练并开放权重,读者可据此了解其多模态推理定位与微调入口。
Mira Murati@miramuratiAI 评分6262Mira Murati 表示团队正在分享其在交互模型上的工作,这是一类从零训练、原生处理实时交互的新模型,而非在回合制模型上外挂交互能力。推文附有一段视频链接。
Andrej Karpathy@karpathyAI 评分3838引用Thariq@trq212http://x.com/i/article/2052796100608974848