🧀 BigCheese.ai

Social

Nvidia releases NVLM 1.0 72B open weight model

🧀

NVLM 1.0, the cutting-edge multimodal large language model from NVIDIA, surpasses prominent proprietary and open-access models in vision-language tasks with its open-source NVLM-1.0-D-72B decoder model, along with shared code for community use, outperforming its text-only capabilities post multimodal training.

  • Model named NVLM 1.0
  • Debuted September 17, 2024
  • 72B parameters
  • Decoder-only architecture
  • Also excels in text-only tasks