YouTube
Hugging Face Journal Club: Scaling Laws for Pre-training & RL
Hugging Face
Описание
The Hugging Face research team discusses the paper "Understanding Reasoning from Pretraining to Post-Training" which discovers a joint scaling law for pre-training and reinforcement learning. Paper link: https://huggingface.co/papers/2607.16097
…
AI-помощник по материалу
Сгенерируйте квиз или краткое резюме по этому материалу.
#video#education#open-source-ai