{ "tokens_per_source": { "oasst2": 16013383, "mbpp": 28619, "gsm8k": 1377570, "glaive": 20915137 }, "distinct_tokens_seen": 163430, "n_special": 33, "vocab": 248077, "hot_32k": { "n": 32768, "weighted_coverage_of_corpus": 0.97266 }, "hot_64k": { "n": 65536, "weighted_coverage_of_corpus": 0.99124 } }