microsoft/unilm

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

228 best points · 105 comments · 6 Hacker News posts · 22,240 GitHub stars · View on GitHub

Hacker News discussions

• Microsoft Kosmos-1: A Multimodal Large Language Model (228 points, 104 comments, by solarist, 2023-03-01)
• Large-Scale Self-Supervised Pre-Training Across Tasks, Languages, and Modalities (3 points, 0 comments, by axiomdata316, 2021-12-25)
• The Era of 1-Bit LLMs: Training Tips, Code and FAQ (2 points, 1 comments, by rkwasny, 2024-03-20)
• The Era of 1 Bit LLMs – Training, Tips, Code [pdf] (2 points, 0 comments, by netsec_burn, 2024-03-20)
• The Era of 1-Bit LLMs: Training Tips, Code And FAQ [pdf] (2 points, 0 comments, by histories, 2024-03-21)
• Kosmos-2.5: A Multimodal Literate Model (1 points, 0 comments, by hubraumhugo, 2024-06-03)