Huawei open-sources openPangu-2.0 pretraining, SFT and RL code
华为开源盘古 openPangu-2.0 的预训练、SFT 代码和后训练 RL 代码正式开源上线
The release exposes full training pipelines tuned for Ascend hardware, making it a rare reference for teams that want to reproduce or fine-tune large models outside the NVIDIA ecosystem. Developers running Ascend clusters or evaluating Chinese domestic chips can use the repos as working baselines for pretraining and RL post-training. It also gives a concrete counterpoint to Meta's Llama-style open release playbook.
On 28 Sep, Huawei released the pretraining, SFT and post-training RL code for openPangu-2.
0 as open source.openPangu is Huawei's open-source AI model brand focused on Ascend-native training and inference practices.
The released components are hosted on GitCode under the ascend-tribe organisation, with model-related components rolling out to the open-source platform progressively.
Repositories include openPangu-2.0-Training and openPangu-2.
0-RL.
华为开源盘古 openPangu-2.0 的预训练、SFT 代码和后训练 RL 代码正式开源上线
IT之家 9 月 28 日消息，华为今日宣布， 开源盘古 openPangu-2.0 的预训练、 SFT 代码和后训练 RL 代码正式开源上线 。 开源盘古 openPangu 是华为开源 AI 模型品牌，致力于通过昇腾原生训练与推理技术，为业界用好昇腾提供最佳实践参考。 openPangu-2.0 模型相关组件已陆续上线开源平台。IT之家附开源地址如下： https://gitcode.com/ascend-tribe/openPangu-2.0-Training https://gitcode.com/ascend-tribe/openPangu-2.0-RL
This report is categorized under AITOP's "Models" desk, focusing on China's AI industry and domestic foundation model ecosystem. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include openPangu, Huawei, open-source models, fine-tuning.
Source attribution: curated from IT之家. Cross-source corroboration: 5 independent sources have covered this development (including pandaily, AIGCLINK, 量子位), confirming industry-wide signal strength.
