Pipe Network (@pipenetwork) / X

Pinned

Run @thinkymachines Inkling on Apple Silicon with ease. Introducing MLX quants for different ram sizes and full recipes: github.com/PipeNetwork/in… 👇

Thinking Machines

@thinkymachines

Jul 15

Today, we are introducing Inkling. Inkling reasons efficiently across text, image, and audio modalities. We are making the full weights available. thinkingmachines.ai/news/introduci… Available today for fine-tuning on Tinker. Play with it in the Inkling Playground. 🧵

Pipe Network reposted

🤖DR 🇺🇸

@AISystemGuy

2h

REAP versions included too: drops the lowest-saliency routed experts per MoE layer, where saliency = mean over active tokens of router_gate × ‖expert_output‖₂. The router renormalizes over survivors; the 2 shared experts, attention, and embeddings are untouched.