{ "n_in": 172700, "train": 164101, "val": 8589, "removed_test_overlap": 0, "n_lang": 133, "by_source": { "aya": 86901, "wildchat": 75821, "oasst2": 9968 }, "task_dist": { "open_qa": 83253, "text_generation": 33543, "other": 13062, "rewrite": 9481, "closed_qa": 8538, "code_generation": 8194, "chatbot": 5740, "brainstorming": 5639, "extraction": 2367, "classification": 1515, "summarization": 1358 }, "dim_means": { "creativity": 0.29, "reasoning": 0.209, "contextual_knowledge": 0.401, "domain_knowledge": 0.333, "constraints": 0.097, "complexity": 0.202 } }