Supervised Fine-Tuning (SFT)

10 posts · 6 sources

LangChainYouTube12h

Why Nobody Has Solved Continual Learning

Scale AIBlog1d

How a Global Insurance Company and Scale Are Building a Real-Time Copilot

Hugging FaceBlog2w

Open-sourcing AstaBrief, the fast report-generation model in Asta

GoogleBlog11 Sept

Autonomous LLM post-training with Tunix on TPUs- Google Developers Blog

DecagonBlog4 Sept

Audio-native semantic speaker-change detection

BasetenBlog22 Jul

GLM 5.2 with vision

GoogleBlog28 May

How the community trained Gemma to "Think" with Tunix and TPUs- Google Developers Blog

GoogleBlog16 Apr

MaxText Expands Post-Training Capabilities: Introducing SFT and RL on Single-Host TPUs- Google Developers Blog

DecagonBlog25 Mar

Why off-policy training isn't enough: SFT, RL, and the limits of imitation

DecagonBlog21 Nov

Engineering fast, performant AI agents through fine-tuning