ByteBrief
We're a portrait publication through and through. Turn your phone back and your briefing picks up right where you left it.
(We tried widescreen once. It wasn't us.)
Baidu releases ERNIE 5.5 Flash Base, a 280B parameter model activating 14B parameters per token. The checkpoint supports 128K training context and 1M for fine-tuning. Teams can use it to compare fine-tuning, instruction tuning or RL methods on multi-GPU servers.
Tap to vote and see what everyone thinks.
Summary by ByteBrief