Nvidia details LLM family NVLM 1.0, which can handle vision and language tasks while enhancing text-only capabilities and is led by the 72B-parameter NVLM-D-72B
Nvidia has released a powerful open-source artificial intelligence model that competes with proprietary systems from industry leaders like OpenAI and Google.
Nvidia releases NVLM-1.0-D-72B frontier-class multimodal LLM with decoder-only architecture SOTA results on vision-language and text-only tasks [image]
🔥Super excited to release NVLM-1.0-D-72B, the frontier-class multimodal LLM with decoder-only architecture 🚀SOTA results on vision-language and text-only tasks 🤗Ckpt and inference scripts in HF https://huggingface.co/... 📢Stay tuned for training code, NVLM-1.0-X, and NVLM-1.0-H