Researchers find why larger language models pick up skills that small ones miss(the-decoder.com)
the-decoder.com
Researchers find why larger language models pick up skills that small ones miss
https://the-decoder.com/researchers-pinpoint-why-larger-language-models-pick-up-skills-that-small-ones-miss/
1 コメント
I for one can’t wait to see a 1.2b, 2b, or 3b model use skills. It would democratize the agentic AI landscape. My 4b model is to slow on my M1Pro. Need quicker access to standardized skills and tool usage.