THUDM/CogVLM
a state-of-the-art-level open visual language model | 多模态预训练模型
4 best points · 1 comments · 3 Hacker News posts · 6,747 GitHub stars · View on GitHub
Hacker News discussions
- CogAgent-18B – visual-based GUI Agent capabilities (4 points, 1 comments, by stevenhuang, 2023-12-17)
- CogVLM – a state-of-the-art-level open visual language model (2 points, 0 comments, by eunos, 2023-10-16)
- CogVLM: Visual Expert for Pretrained Language Models (2 points, 0 comments, by ilaksh, 2023-11-07)