Comment on Local AI is one step closer through Mistral-NeMo 12B
i_like_water@feddit.org 3 months agoFrom the top of my head: the context size is way higher. 128k tokens vs 8k usually.
Comment on Local AI is one step closer through Mistral-NeMo 12B
i_like_water@feddit.org 3 months agoFrom the top of my head: the context size is way higher. 128k tokens vs 8k usually.
bamboo@lemm.ee 3 months ago
Oh wow. Yeah a large context size is a significant improvement, doesn’t seem like the article included that detail.