{"type":"link","version":"1.0","title":"MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers","author_name":"AI Archs","author_url":"https://ai-arch.pages.dev","provider_name":"AI Archs","provider_url":"https://ai-arch.pages.dev","url":"https://ai-arch.pages.dev/n/arxiv2002.10957","thumbnail_url":"https://ai-arch.pages.dev/og/arxiv2002.10957.png","thumbnail_width":1200,"thumbnail_height":630}