Linear Thinking: Simple Nets Tackle Language and Math
·42 words·1 min
Blog
Phi-1: The Tiny Model Outsmarting Giants
·255 words·2 mins
Reasoning AWOL? Paper Claims Only ICL Emerged
·50 words·1 min
Weight Averaging: Have Your Cake and Save Your Model
·44 words·1 min
Phi-nomenal Code Gen: Phi-1-Base Beats August Models
·172 words·1 min
Weaving Longer Contexts: Yarn Scaling for LLMs
·25 words·1 min
Tensor Shape-Shifting: See Shapes Before Values
·33 words·1 min
AI Watches YouTube, Masters Minecraft—Harder Than AlphaGo?
·50 words·1 min
Tiny Weights, Mighty Models: The Mystery of Weight Decay
·308 words·2 mins
Conquering FP16 Frustrations: One-Liner to FP8 Gold on H100s
·54 words·1 min