精选模型70

Meta 发布最小模型 Muse Ember,面向推理执行与智能体任务

原标题:Today we're introducing Muse Ember, our smallest and most efficient model, built for complex reasoning execution and everyday agent work.

AI at Meta@AIatMeta发布时间 (北京时间)

Meta 发布 Muse Ember,称其为自家最小、最高效的模型,面向复杂推理执行和日常智能体工作。该模型可跨应用承接工作流、按顺序调用工具、运行测试并做针对性代码修复,具备 1M-token 上下文窗口,原生理解文本、图像、音频和视频,可处理大规模文档集与多种输入。

推荐理由Meta 公布最小最省模型 Muse Ember 的定位与能力,可据此判断轻量模型在智能体工作流中的适用边界。

Today we're introducing Muse Ember, our smallest and most efficient model, built for complex reasoning execution and everyday agent work.

Muse Ember can carry workflows across apps, call tools in sequence, run tests and make targeted code fixes. With a 1M-token context window and native understanding of text, images, audio and video, it can also work across large document sets and varied inputs.

Meta / LlamaAgent 智能体多模态模型发布#模型发布#Agent#多模态#Meta