Ollama's new engine for multimodal models

Their example "understanding and translating vertical Chinese spring couplets to English" has a lot of mistakes in it. I'm guessing the person writing the blog post to show off that example doesn't actually know Chinese.

What is actually written: Top: 家和国盛 Left: 和谐生活人人舒畅迎新春 Right: 平安社会家家欢乐辞旧岁

What Ollama saw: Top: 盛和家国 (correct characters but wrong order) Left: It reads "新春" (new spring) as 舒畅 (comfortable) Right: 家家欢欢乐乐辞旧岁 (duplicates characters and omits the first four)

I'm one of the maintainers who ran that example. I am Chinese.

The English translation, I thought was pretty spot on. We don't hide the mistakes of the models or fake the demos.

Overtime, of course I hope the models to improve much more