Your laptop (VS Code) Azure Static Web Apps ─────────────────── ───────────────────── 1. Prep data python scripts/data_prep.py 2. Run eval python run_eval.py --agent1 data.xlsx 3.
We provide a multi-step flow to run lm-evaluation-harness metrics offline for ONNX models. Offline mode is used to evaluate models generations on specific hardware (i.e., NPUs). The offline mode is ...