百度发布开源模型 ERNIE 5.5 Flash Base，采用 280B 参数的 MoE 架构，激活参数 14B，预训练使用 33.5T tokens，支持最长 1M 上下文。该模型在推理、编码和长上下文基准上表现较强，后训练已在进行中。百度官方账号转发该发布内容并表示后续还有更多进展。
同一件事，精选收录的是《百度开源文心5.5 Flash Base，多基准测试刷新同尺寸模型 SOTA》
Stay tuned for more!
【引用 @tianxiangsun】Excited to introduce ERNIE 5.5 Flash Base, my first release since joining @Baidu_Inc !
An open-sourced 280B MoE model with just 14B active parameters, pretrained on 33.5T tokens. It delivers strong performance across reasoning, coding, and long-context benchmarks, with support for up to 1M context.
Huge respect and thanks to the incredible team behind this — outstanding work!
Post-training is already underway, and I can't wait to bring it to you soon.
And this is just the beginning — more exciting technical developments are on the way. Stay tuned!
Excited to introduce ERNIE 5.5 Flash Base, my first release since joining @Baidu_Inc ! An open-sourced 280B MoE model with just 14B active parameters, pretrained on 33.5T tokens. It delivers strong performance across reasoning, coding, and long-context benchmarks, with support for up to 1M context. Huge respect and thanks to the incredible team behind this — outstanding work! Post-training is already underway, and I can't wait to bring it to you soon. And this is just the beginning — more exciting technical developments are on the way. Stay tuned! https://ernie.baidu.com/release/ernie-5-5-flash-base/在 X 查看被引用的帖子
来源：Baidu Inc. · x.com