the-crypt-keeper

Import model evaluation results into ReasonScape r12 or tables300 dataset. Use when importing new models, quantization variants, or adding evaluation data. Keywords - model, import, evaluate, dataset, results, eval, hf, huggingface.

Create context-limited versions of evaluations. Use when you need to simulate lower context windows or compare model performance at different context limits. Keywords - context, clip, truncate, window, limit, simulate, 8k, 12k, 16k.