We are a Turkish Hugging Face organization that builds AI models that are small and push above their weight.
Our main proposition for our language models is that they're small, but they do one thing — or multiple things, if we are crazy — right, and do it well.
Expİvme is our series of models made mainly for experimentation. They lack codenames, and they're not part of the main family roster. Expİvme models are mostly not expected to perform well in benchmarks — instead they try to see how different architectures or training styles work on small models. When an Expİvme family develops well enough, it can be promoted to the normal İvme family, marking it as ready for production.
We will try to bring models on time, but we can't really verify they'll come as soon as we say they are coming. We hit budget problems and noisy hosts — even backing up İvme-Conversate-v1-Base's training data was hard after our host refused to boot. But don't worry, we will try our best as long as our host doesn't fail and our budget doesn't hit its limit.
İvmeLabs
