AI Dynamics

Global AI News Aggregator

About

NeuralDaredevil-8B Model Improvement Through DPO Training

There's still room for improvement: GSM8K suffered because it's underrepresented in my DPO dataset. More epochs would definitely help too. I find it super exciting and I'm curious to see how people will use it. NeuralDaredevil-8B:

→ View original post on X — @maximelabonne