L$^2$M: Mutual Information Scaling Law for Long-Context Language Modeling
"缩放定律" 相关文章
Relative-Based Scaling Law for Neural Language Models
喝点VC｜YC对谈Anthropic预训练负责人：预训练团队也要考虑推理问题，如何平衡预训练和后训练仍在早期探索阶段
喝点VC｜YC对谈Anthropic预训练负责人：预训练团队也要考虑推理问题，如何平衡预训练和后训练仍在早期探索阶段
AI的“物理学”：揭秘GPT-3背后改变一切的“缩放定律”
Investigating Neural Scaling Laws Emerging from Deep Data Structure
Scaling Laws and Spectra of Shallow Neural Networks in the Feature Learning Regime
Towards a Comprehensive Scaling Law of Mixture-of-Experts
Scaling Laws for Optimal Data Mixtures
How to build AI scaling laws for efficient LLM training and budget maximization
How to build AI scaling laws for efficient LLM training and budget maximization
How to build AI scaling laws for efficient LLM training and budget maximization
Gemstones: A Model Suite for Multi-Faceted Scaling Laws
How to build AI scaling laws for efficient LLM training and budget maximization
Anthropic's cofounder says 'dumb questions' are the key to unlocking breakthroughs in AI
EvoSLD: Automated Neural Scaling Law Discovery With Large Language Models
LLM 系列（五）：模型训练篇
社区供稿 | 3700 次预训练总结超参规律，开源海量实验，告别盲猜
社区供稿 | 3700 次预训练总结超参规律，开源海量实验，告别盲猜
Grok 3也「跳票」了？馬斯克的「10萬台GPU最強算力」也搞不定「新一代AI大模型」？
