In the world of NLP, new models pop up almost every day, making it hard to keep track of them all. Our development team needed a way to summarize and organize key details about these models, so we decided to do some research.
We started by analyzing all the models listed on Hugging Face, gathering key information such as the base model, architecture, library, use cases, and URLs. Since this might be useful to others as well, we’re sharing our findings here. Hope it helps!
The full table is quite large, so check out the detailed list via the link below:
- Text Type Models: https://wiki.wikisecurity.net/faq:nlp-models
- Vision Type Models: https://wiki.wikisecurity.net/faq:nlp-models-vision
- Audio Type Models: https://wiki.wikisecurity.net/faq:nlp-models-audio
- Video Type Models: https://wiki.wikisecurity.net/faq:nlp-models-video
){kind=link}