Skip to content
Read the original: QbitAI
Published
60/100

Baidu open-sources ERNIE 5.5 Flash Base, a 280B MoE base model

AIBaidu says it has open-sourced ERNIE 5.5 Flash Base, a MoE base model with 280B total parameters and 14B active per token. The model was pretrained on 33.5 trillion tokens with a 128K context length, extendable to 1M tokens during fine-tuning and inference.
Read the original qbitai.com

Loading source posts…

Source details

QbitAI · 量子位的朋友们 · qbitai.comPublished · added here

Original title: 百度开源文心5.5 Flash Base,多基准测试刷新同尺寸模型 SOTA