How test-time scaling unlocks hidden reasoning skills in small language fashions (and permits them to outperform LLMs)
Very small language fashions (SLMs) can outperform main giant language fashions (LLMs)…
Microsoft’s new rStar-Math approach upgrades small fashions to outperform OpenAI’s o1-preview at math issues
Microsoft is doubling down on the potential of small language fashions (SLMs)…
