User announces the release of Aurora1.0-150M, a 150M parameter model trained on 7B tokens using an RTX Pro 6000 Blackwell. No inference engine, quantization, context length, or throughput figures are reported. Benchmarks cited: PIQA 62.24%, Hellaswag 32.20%, Arc-Easy 44.91%, Arc-Challenge 25.00%, Arithmark 3.0 33.90%, CapitalBench 36.55%.
Aurora1.0
1 report
Aurora1.0 VRAM requirements by size and quant →Thin page (1 of 3 reports needed for indexing). Add yours.