- i wonder if language models like phi-1 with quality training data could be used to train better language models by using it's emergent properties alone https://the-decoder.com/microsofts-tiny-phi-1-language-model-shows-the-importance-of-data-quality-in-ai-training/ 2 comments artificial
Linking pages
- Microsoft CTO Kevin Scott on Bing’s quest to beat Google and the future of AI art - The Verge https://www.theverge.com/23900198/microsoft-kevin-scott-ai-art-bing-google-nvidia-decoder-interview 5 comments
- AI models might need to scale down to scale up again https://the-decoder.com/ai-models-might-need-to-scale-down-to-scale-up-again/ 0 comments
Linked pages
Related searches:
Search whole site: site:the-decoder.com
Search title: Microsoft's tiny Phi-1 language model shows how important data quality is for AI training
See how to search.