Content
@
0 reply
0 recast
0 reaction
𝚐𝔪𝟾𝚡𝚡𝟾
@gm8xx8
NVLM-1.0-D-72B is a multimodal LLM with a decoder-only architecture, delivering SOTA results in both vision-language and text tasks. Checkpoints and inference scripts are available on Hugging Face. https://huggingface.co/nvidia/NVLM-D-72B
0 reply
0 recast
5 reactions
Hess 互关
@missjess91
GM,
0 reply
0 recast
0 reaction
