百度开源 2800 亿参数 ERNIE 5.5 Flash Base 基础模型
原标题：Baidu releases ERNIE 5.5 Flash Base with 280 billion parameters as an open-source foundation model
AI 摘要
百度发布开源基础模型 ERNIE-5.5-Flash-Base，采用混合专家架构，总参数 2800 亿、每输入激活 140 亿，预训练使用 33.5 万亿 token，训练上下文最高 128K，微调与推理时可支持最高 100 万 token 上下文。该模型刻意不做微调或后训练，由开发者自行决定后续方向，后训练版本后续推出。百度称其在推理、代码和长上下文基准上与 DeepSeek V4 Flash、MiMo V2.5 等同规模开源基础模型竞争，权重已在 Hugging Face 以 FP8 和 BF16 格式提供。
正文节选
Baidu releases ERNIE 5.5 Flash Base with 280 billion parameters as an open-source foundation model Baidu's AI development is still alive, but most of the work is on you. The Chinese company has released ERNIE-5.5-Flash-Base, an open foundation model that ships deliberately without fine-tuning or post-training. Developers are expected to decide for themselves where to take the model. A post-trained version is supposed to follow. ERNIE 5.5 uses a mixture-of-experts architecture with 280 billion pa