5 stories
Supervised fine-tuning (SFT) remains a widely used approach for post-training large language models, because fixed demonstrations can directly introduce desired reasoning strategies and behavioral patterns.
Supervised fine-tuning (SFT) equips large language models (LLMs) with specialized capabilities, but often comes at the cost of forgetting the general capabilities of their parent models (i.e., the pretrained models before fine-tuning).
Why does supervised fine-tuning (SFT) lead to more forgetting than reinforcement fine-tuning (RFT), even when all teacher demonstrations are semantically correct?
On September 28, 2026 Huawei open-sourced openPangu-2.0 pretrain, SFT and post-training RL code for its Ascend-native MoE stack, complementing earlier Pro (505B) and Flash (92B) weight releases.
Huawei’s Ascend Tribe has released the pretraining, supervised fine-tuning and post-training reinforcement-learning code for its openPangu-2.0 model family. The code is designed for Huawei’s Ascend-based training ecosystem.
Showing 5 of 5 stories
You're all caught up.
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts
