E
Microsoft’s small math AI model does math better than the big boys.
Microsoft found that small language models can exceed the performance of much larger ones when trained to specialize in a single area. Researchers fine-tuned the Mistral 7B model to create Orca-Math, an SLM that solved grade school math problems better, at 86.8 percent, than models like Llama 2, GPT-3.5, and Gemini Pro — even though it ingests significantly less data.
The company was rumored to build a team entirely focused on creating SLMs (AI models that use less computing power), which would be suited for phones and laptops.
Follow topics and authors from this story to see more like this in your personalized homepage feed and to receive email updates.
Loading comments
Getting the conversation ready...
Most Popular
Most Popular
- Our long national sunscreen nightmare is almost over
- Kaleidescape’s movie player blows streaming, and your wallet, away
- Barret Zoph is out at OpenAI again after just five months
- Midjourney goes from generating cat images to full-body ultrasound scans
- Hue’s wired wall modules bring non-smart lights into its ecosystem
