view article Article MOPD: how frontier labs merge RL experts into one model and how to do it using TRL sergiopaniego • 5 days ago • 24
view post Post 4,027 How do I test an LLM for my unique needs?If you work in finance, law, or medicine, generic benchmarks are not enough.This blog post uses Argilla, Distilllabel and 🌤️Lighteval to generate evaluation dataset and evaluate models.https://github.com/argilla-io/argilla-cookbook/blob/main/domain-eval/README.md 1 reply · 👀 6 6 + Reply
Encoder comparison after equivalent retrieval fine-tuning Collection ModernBERT, Ettin and UltraBERT: 54 retrieval models, frozen data and results. Validation-selected models first. Matched training, one seed. • 59 items • Updated 25 days ago • 4