Results for “workflow-optimization”

3 skills

Trains LLMs with SimPO, a reference-free preference optimization method that outperforms DPO, using configurable hyperparameters and workflows for various models and tasks.

More results

Guides machine learning development with experiment tracking, hyperparameter optimization, model registry, and MLOps pipeline integration.

Optimizes Dify workflows and plugins by restructuring graphs, reducing LLM token usage, tuning worker pools, and improving parallel processing.