29 Jan 2025
6m

2025.01.29 | RL泛化优,SFT稳定输出;FP4量化降成本,精度保持。

Podcast cover

HuggingFace 每日AI论文速递

Open in Podwise to generate AI notes

Sign in to process this episode and unlock summaries, transcripts, highlights and translations.

Open in Podwise

Shownotes are not generated by Podwise.

2025.01.29 | RL泛化优,SFT稳定输出;FP4量化降成本,精度保持。