reproducible AI Agent Skills

nemo-evaluator-sdk

21.8k

davila7

Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.

Hermetic Test Patterns

71

PramodDutta

Building hermetic tests that are fully isolated from external dependencies using fakes, containers, and deterministic time/random sources.