# Example configuration for the evaluation script model: "meta-llama/llama-3.3-70b-instruct" provider: "Hyperbolic" output_dir: "results" max_concurrent: 10 default_size: 20 # Default size for all datasets default_seed: 42 # Default seed for all datasets categories: - category: "algebra" datasets: - dataset: "complex_arithmetic" params: min_real: -10 max_real: 10 min_imag: -10 max_imag: 10 - category: "arithmetic" datasets: - dataset: "products" size: 10 seed: 43 params: min_digits: 2 allow_negation: true - dataset: "chain_sum" size: 12 seed: 43 params: min_digits: 2 allow_negation: true