PandailyAsia
Huawei Open-Sources openPangu-2.0 Pretrain, SFT and RL Training Code on Ascend

Huawei open-sourced the pretraining, supervised fine-tuning (SFT) and post-training reinforcement-learning (RL) code for openPangu-2.0 on September 28, 2026, according to TMT Post and related…
Read at Pandaily ↗Related

AsiaStepFun Step 5 Preview: ~600B MoE Long-Horizon Agent; Open Weights Due Oct 15 Pandaily

AsiaNaiveAI Open-Weights Naive-N0.5-Flash: 309B MoE, Hybrid SWA–DSA 1M Context, MIT Pandaily

AsiaHuawei open-sources openPangu-2.0 pretraining, SFT and RL code TechNode

AsiaAs China mulls how to make open-weight AI less dangerous, report proposes 6-stage process SCMP Tech

Tens of thousands of security probes show OpenAI's Hugging Face incident was just the beginning The Decoder
