LLMBox - Documentations Training Tutorial: Training Utilization CLI Usage: Utilization Reproduction: test.sh Benchmarking LLaMA-3 Full test scripts: benchmarking_llama3.sh. Trouble Shooting: Debug an evaluation run Datasets Supported datasets How to load datasets with subsets How to load datasets from HuggingFace How to load dataset GPQA Example: run_gpt_eval.py How to customize dataset Example: customize_dataset.py Models How to customize model How to use chat template Example: Customize HuggingFace model Trouble Shooting vLLM no module name packaging