Results for “minimap2”
3 skills
lord1egypt simpo-training
Trains LLMs with SimPO, a reference-free preference optimization method that outperforms DPO, using configurable hyperparameters and workflows for various models and tasks.
2
qhjqhj00 umap-learn
Reduce high-dimensional data with UMAP for visualization, clustering preprocessing, and supervised or semi-supervised learning, including parameter tuning guidance.
3 · bundle
orchestra-research simpo-training
Train language models with SimPO, a reference-free preference optimization method that outperforms DPO without needing a reference model.
10.4k · bundle