{"slug": "huawei-open-sources-openpangu-2-0-pretraining-sft-and-rl-code", "title": "Huawei open-sources openPangu-2.0 pretraining, SFT and RL code", "summary": "Huawei's Ascend Tribe released the pretraining, supervised fine-tuning and post-training reinforcement-learning code for its openPangu-2.0 model family. The release includes openPangu-2.0-Training, which supports pretraining and SFT, and openPangu-2.0-RL, which focuses on reinforcement-learning post-training, both designed for Huawei's Ascend-based training ecosystem.", "body_md": "Huawei’s Ascend Tribe has released the pretraining, supervised fine-tuning and post-training reinforcement-learning code for its openPangu-2.0 model family.\n\nThe code is designed for Huawei’s Ascend-based training ecosystem. The newly available projects include openPangu-2.0-Training, which supports pretraining and SFT, and openPangu-2.0-RL, which focuses on reinforcement-learning post-training. [[Ascend Tribe](https://gitcode.com/ascend-tribe), in Chinese]", "url": "https://wpnews.pro/news/huawei-open-sources-openpangu-2-0-pretraining-sft-and-rl-code", "canonical_source": "https://technode.com/2026/09/28/huawei-open-sources-openpangu-2-0-pretraining-sft-and-rl-code/", "published_at": "2026-09-28 07:25:45+00:00", "updated_at": "2026-09-28 07:48:00.381218+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-research", "developer-tools", "ai-infrastructure"], "entities": ["Huawei", "Ascend Tribe", "openPangu-2.0", "openPangu-2.0-Training", "openPangu-2.0-RL", "Ascend"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/huawei-open-sources-openpangu-2-0-pretraining-sft-and-rl-code", "markdown": "https://wpnews.pro/news/huawei-open-sources-openpangu-2-0-pretraining-sft-and-rl-code.md", "text": "https://wpnews.pro/news/huawei-open-sources-openpangu-2-0-pretraining-sft-and-rl-code.txt", "jsonld": "https://wpnews.pro/news/huawei-open-sources-openpangu-2-0-pretraining-sft-and-rl-code.jsonld"}}